DESC:FORM 2

THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENT RULES, 2003

COMPLETE SPECIFICATION
(See Section 10 and Rule 13)

Title of invention:
MACHINE FIRST QA TRIAGING SYSTEM AND METHOD

Applicant:
Tata Consultancy Services Limited
A company Incorporated in India under the Companies Act, 1956
Having address:
Nirmal Building, 9th Floor,
Nariman Point, Mumbai 400021,
Maharashtra, India

The following specification particularly describes the invention and the manner in which it is to be performed.
CROSS-REFERENCE TO RELATED APPLICATIONS AND PRIORITY
[001] The present application claims priority from Indian provisional patent application no. 201821035006, filed on September 17, 2018. The entire contents of the aforementioned application are incorporated herein by reference.

TECHNICAL FIELD
[002] The disclosure herein generally relates to machine learning and analytics, and, more particularly, to Machine First Quality Assurance (QA) Triaging system for automated triaging of log files for Root Cause analysis and prescriptive analytics by providing recommendation.

BACKGROUND
[003] In software product organization, there are multi-module systems, where logs are heterogeneous which is distributed across multiple server, debugging an issue by manually searching and querying among million line of log files is a very tedious and time consuming process. Whenever any issue occurs in following business scenario such as (a) Production environment, (b) Quality assurance (QA) engineering, (c) Sustenance Scenario, (d) Product analytics; QA engineer or L3/L4 support engineer has to manually analyze multiples log files containing lots of noise to identify a few error strings that can be helpful in identifying the error and its root cause. Even if QA engineer and L3/L4 support engineers are able to identify the root cause of error but the accuracy of identified error is always questionable.
[004] Further, currently if any issue occurs in Production / Sustenance scenario client raise L0 ticket and it goes through escalation process to L3/L4 support engineer for root cause analysis. L3/ L4 support engineer has to perform below mentioned task manually for root causal analysis. (a) Manually collect all log data files from distributed servers and keep it up at a centralized location; (b) Manually Analyze each and every log file to identify error, its root cause and check if there is any error in the system. Similarly in QA engineering scenario after every test case (Functional, non-functional, regression etc.) execution QA engineer has to analyze multiple log files that contains lot of noise, to identify root cause. Manual analysis of log file having lots of noise is a very time consuming and tedious process. Accordingly, there exists business challenges such as Time, Quality, Knowledge retention, Environment Setup, Client Environment access, Cost, Effort, Business loss.

SUMMARY
[005] Embodiments of the present disclosure present technological improvements as solutions to one or more of the above-mentioned technical problems recognized by the inventors in conventional systems. For example, in one embodiment, a method for automated triaging of plurality of log files to perform root cause analysis and prescriptive analytics is provided. The processor implemented method includes receiving, via one or more hardware processors, a plurality of subject matter expert (SME) knowledge associated with a plurality of errors; generating, via the one or more hardware processors, a knowledge repository based on the plurality of SME knowledge; analyzing, via the one or more hardware processors, the plurality of error strings of the knowledge repository to identify a plurality of hidden patterns; generating, via the one or more hardware processors, an ordered rule dataset with label based on the a plurality of hidden patterns to form a decision tree of the plurality of errors; analyzing, via the one or more hardware processors, at least one error from the plurality of log files to convert an unstructured data to a structured data; and classifying, via the one or more hardware processors, the at least one error by comparing the structured data with the ordered rule dataset. In an embodiment, the knowledge repository includes (i) plurality of error strings associated with an error, (ii) error type, and (iii) root cause. In an embodiment, the ordered rule dataset include a plurality of rules.

[006] In an embodiment, the plurality of hidden patterns may be identified by analyzing the knowledge repository to perform at least one of: (a) perform regular expression based extraction of useful structured data from the plurality of log files, and (b) create the ordered rule dataset with the label. In an embodiment, the plurality of rules may form a decision tree like structure. In an embodiment, each node represent a pattern in the rule dataset and leaf node represent type of error, root cause and recommendation. In an embodiment, the structured data may include a file name, timestamp, and error strings. In an embodiment, the ordered rule dataset may include a set of rules that collectively comprise a classification model.
[007] In another aspect, a system for automated triaging of plurality of log files to perform root cause analysis and prescriptive analytics is provided. The system comprises a memory storing instructions; one or more communication interfaces; and one or more hardware processors coupled to the memory via the one or more communication interfaces, wherein the one or more hardware processors are configured by the instructions to: receive, a plurality of subject matter expert (SME) knowledge associated with a plurality of errors; generate, a knowledge repository based on the plurality of SME knowledge; analyze, the plurality of error strings of the knowledge repository to identify a plurality of hidden patterns; generate, an ordered rule dataset with label based on the a plurality of hidden patterns to form a decision tree of the plurality of errors; analyze, at least one error from the plurality of log files to convert an unstructured data to a structured data; and classify, the at least one error by comparing the structured data with the ordered rule dataset. In an embodiment, the knowledge repository includes (i) plurality of error strings associated with an error, (ii) error type, and (iii) root cause. In an embodiment, the ordered rule dataset include a plurality of rules.
[008] In an embodiment, the plurality of hidden patterns may be identified by analyzing the knowledge repository to perform at least one of: (a) perform regular expression based extraction of useful structured data from the plurality of log files, and (b) create the ordered rule dataset with the label. In an embodiment, the plurality of rules may form a decision tree like structure. In an embodiment, each node represent a pattern in the rule dataset and leaf node represent type of error, root cause and recommendation. In an embodiment, the structured data may include a file name, timestamp, and error strings. In an embodiment, the ordered rule dataset may include a set of rules that collectively comprise a classification model.
[009] In yet another aspect, there are provided one or more non-transitory machine readable information storage mediums comprising one or more instructions which when executed by one or more hardware processors causes at least one of: receiving, via one or more hardware processors, a plurality of subject matter expert (SME) knowledge associated with a plurality of errors; generating, via the one or more hardware processors, a knowledge repository based on the plurality of SME knowledge; analyzing, via the one or more hardware processors, the plurality of error strings of the knowledge repository to identify a plurality of hidden patterns; generating, via the one or more hardware processors, an ordered rule dataset with label based on the a plurality of hidden patterns to form a decision tree of the plurality of errors; analyzing, via the one or more hardware processors, at least one error from the plurality of log files to convert an unstructured data to a structured data; and classifying, via the one or more hardware processors, the at least one error by comparing the structured data with the ordered rule dataset. In an embodiment, the knowledge repository includes (i) plurality of error strings associated with an error, (ii) error type, and (iii) root cause. In an embodiment, the ordered rule dataset include a plurality of rules.
[010] In an embodiment, the plurality of hidden patterns may be identified by analyzing the knowledge repository to perform at least one of: (a) perform regular expression based extraction of useful structured data from the plurality of log files, and (b) create the ordered rule dataset with the label. In an embodiment, the plurality of rules may form a decision tree like structure. In an embodiment, each node represent a pattern in the rule dataset and leaf node represent type of error, root cause and recommendation. In an embodiment, the structured data may include a file name, timestamp, and error strings. In an embodiment, the ordered rule dataset may include a set of rules that collectively comprise a classification model.
[011] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.

BRIEF DESCRIPTION OF THE DRAWINGS
[012] The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, serve to explain the disclosed principles:
[013] FIG. 1A illustrates a system for automated triaging of log files to perform root cause analysis and prescriptive analytics, according to some embodiments of the present disclosure.
[014] FIG. 1B illustrates an exemplary Machine First Quality assurance (QA) Triaging system for automated triaging of log files for root cause analysis and prescriptive analytics, according to some embodiments of the present disclosure.
[015] FIG. 2 illustrate an exemplary input template to capture a subject matter expert (SME) knowledge for one or more errors according to some embodiments of the present disclosure.
[016] FIG. 3 is an exemplary view illustrates a decision tree of an error classification in the Machine First QA Triaging system according to some embodiments of the present disclosure.
[017] FIG. 4 is an exemplary view of ordered rule dataset with label for one or more errors according to some embodiments of the present disclosure.
[018] FIG. 5 is an exemplary view of output obtained after running the Machine First QA Triaging system on a syslog of Linux server according to some embodiments of the present disclosure.
[019] FIG. 6 is a table view illustrates an exemplary case study associated with the Machine First QA Triaging system according to some embodiments of the present disclosure.
[020] FIG. 7 is a flow diagram illustrating a method for automated triaging of log files for root cause analysis and prescriptive analytics, according to some embodiments of the present disclosure.

DETAILED DESCRIPTION OF EMBODIMENTS
[021] Exemplary embodiments are described with reference to the accompanying drawings. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. Wherever convenient, the same reference numbers are used throughout the drawings to refer to the same or like parts. While examples and features of disclosed principles are described herein, modifications, adaptations, and other implementations are possible without departing from the scope of the disclosed embodiments. It is intended that the following detailed description be considered as exemplary only, with the true scope being indicated by the following claims.
[022] Referring now to the drawings, and more particularly to FIGS. 1 through 7, where similar reference characters denote corresponding features consistently throughout the figures, there are shown preferred embodiments and these embodiments are described in the context of the following exemplary system and/or method.
[023] FIG. 1A illustrates a system for automated triaging of log files to perform root cause analysis and prescriptive analytics, according to some embodiments of the present disclosure. The system 100 includes or is otherwise in communication with one or more hardware processors such as a processor 106, an I/O interface 104, at least one memory such as a memory 102. In an embodiment, a Machine First Quality assurance (QA) Triaging tool can be implemented as a standalone unit in the system 100. In another embodiment, the Machine First Quality assurance (QA) Triaging tool can be implemented as a module in the memory 102. The processor 106, the I/O interface 104, and the memory 102, may be coupled by a system bus.
[024] The I/O interface 104 may include a variety of software and hardware interfaces, for example, a web interface, a graphical user interface, and the like. The interfaces 104 may include a variety of software and hardware interfaces, for example, interfaces for peripheral device(s), such as a keyboard, a mouse, an external memory, a camera device, and a printer. The I/O interfaces 104 can facilitate multiple communications within a wide variety of networks and protocol types, including wired networks, for example, local area network (LAN), cable, etc., and wireless networks, such as Wireless LAN (WLAN), cellular, or satellite. For the purpose, the interfaces 104 may include one or more ports for connecting a number of computing systems with one another or to another server computer. The I/O interface 104 may include one or more ports for connecting a number of devices to one another or to another server.
[025] The hardware processor 106 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions. Among other capabilities, the hardware processor 106 is configured to fetch and execute computer-readable instructions stored in the memory 102.
[026] The memory 102 may include any computer-readable medium known in the art including, for example, volatile memory, such as static random access memory (SRAM) and dynamic random access memory (DRAM), and/or non-volatile memory, such as read only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and magnetic tapes. In an embodiment, the memory 102 includes a plurality of modules and a repository for storing data processed, received, and generated by the plurality of modules. The plurality of modules may include routines, programs, objects, components, data structures, and so on, which perform particular tasks or implement particular abstract data types.
[027] The repository, amongst other things, includes a system database and other data. The other data may include data generated as a result of the execution of one or more modules in the plurality of modules.
[028] FIG. 1B illustrates an exemplary Machine First QA Triaging system for automated triaging of plurality of log files to perform root cause analysis and prescriptive analytics, according to some embodiments of the present disclosure. The Machine First QA Triaging system is configured for automated triaging of the plurality of log files for automated collection of log files from a distributed environment tool (e.g., remote server) to centralized location. In an embodiment, the plurality of log files collected may be in unstructured format. The Machine First QA Triaging system is further configured to convert obtained unstructured data to structured data. In an embodiment, a machine learning model of the Machine First QA Triaging system identifies one or more errors and perform associated root Cause analysis and provides recommendation for resolution of the one or more errors.
[029] In an embodiment, information is analyzed to determine one or more common keywords occurs in any failure log files. Based on the common keywords a pattern is created. In an embodiment, the one or more rules forms a tree like structure, wherein each node represent a pattern in rule engine and leaf node represent type of error, root cause and recommendation.
[030] In an embodiment, a log shipper is configured to ship one or more logs from a distributed environment to a centralized server. For example, a user (e.g., L3/L4 or QA engineer) may execute the tool on log directory / files which is present across one or more servers then the log shipper is configured to ship one or more relevant files from the distributed environment to the centralized server.
[031] A log parser is configured to compare a log data pattern. The log parser further convert an unstructured data to a structured format (e.g., a structured data) by extracting information which is incorporated in the log parser. In an embodiment, the structured data includes a file name, timestamp, and error string. In an embodiment, the structured data can be in any format such as CSV file, JavaScript Object Notation (JSON) etc.
[032] In an embodiment, the structured data and one or more rules defined in the ordered rule dataset is inputted to a machine-learning model. In an embodiment, the one or more logs following the one or more rules based decision tree which classify an error type and associated root cause and provide recommendation.
[033] The Machine First QA Triaging system includes a learning module. The learning module is configured to capture a subject matter expert (SME) knowledge (e.g., Heuristic information) in a structured template (e.g., a JavaScript Object Notation (JSON) file, CSV file, an excel file).
[034] FIG. 2 illustrate an exemplary input template to capture the SME knowledge for one or more errors according to some embodiments of the present disclosure. In an embodiment, a known error repository is created which include one or more error string which an SME identify to find root cause of the one or more errors, in a same order as appear in the log files along with error, error type, root cause and recommendation for resolution to the error.
[035] FIG. 3 is an exemplary view illustrates a decision tree of an error classification in the Machine First QA Triaging system according to some embodiments of the present disclosure. In an embodiment, for each error corresponding the known error repository is analyzed to identify hidden patterns. In an embodiment, the hidden patterns form a decision tree like structure where each node represent the path which the SME follows and leaf node represent associated error, error type , root cause and recommendation. In an embodiment, the one or more hidden patterns are utilized to (a) perform regular expression based extraction of useful structured data from the log files, (b) create an ordered rule dataset with label which dynamically evolve with time. In an embodiment, a regular expression based pattern is updated in a log parser. In an embodiment, the process is a periodic activity which initially can be performed monthly and gradually in a regular interval can be increased or when required (major architecture / feature change).
[036] FIG. 4 is an exemplary view of the ordered rule dataset with label for one or more errors according to some embodiments of the present disclosure. In an embodiment, the ordered rule dataset for each known error is created. In an embodiment, the ordered rule dataset includes a set of rules that collectively comprise a classification model. In an embodiment, the structured data captured from the log parser is compared against a rule dataset. In an embodiment, if one or more conditions are met then classifier is configured to classify one or more errors and provide associated root cause.
[037] In an embodiment, type of learning system can be a supervised and an unsupervised learning. For example, output of the machine learning model can be saved in any form like a CSV, a web page, a graph, and a dashboard.
[038] Experimental results:
[039] FIG. 5 is an exemplary view of output obtained after running the Machine First QA Triaging system on a syslog of Linux server according to some embodiments of the present disclosure. In an exemplary embodiment, the solution is implemented on syslog of Linux environment, and in Linux there are multiple types of error like: (a) Login error, (b) Memory error, (c) Mail error, (d) Kernel error …etc. In an embodiment, the error is divided in two part (a) Known error, (b) Unknown error.
[040] Knowledge repository:
[041] For known error, a knowledge repository having one or more string for identifying the one or more errors, in a same order as appear in one or more log files are created. In the knowledge repository, based on the knowledge of the SME, error type, root cause and recommendation is added.
[042] After analyzing the knowledge repository, one or more hidden pattern is identified, and for each error the one or more hidden pattern form a decision tree like structure where each node represent the error string and root node represent associated error type, root cause, and recommendation for resolution. In an embodiment, an ordered rule dataset with label is created which includes root cause, error, error type, and recommendation.
[043] Convert unstructured data to structured format
[044] In an embodiment, the identified pattern are incorporated in a regular expression based pattern in the log parser. The Log parser read each and every log files present on a specified path and based on the regular expression based pattern which converts the unstructured data to the structured format and extract one or more attributes and save all the structured data in a JSON, CSV file format.
[045] In an embodiment, the structured data become input to our model, the supervised machine learning model may traverse the decision tree arrives at the leaf node having error type and recommendation.
[046] FIG. 6 is a table view illustrates an exemplary case study associated with the Machine First QA Triaging system according to some embodiments of the present disclosure.
[047] FIG. 7 is a flow diagram illustrating a method for automated triaging of log files for root cause analysis and prescriptive analytics, according to some embodiments of the present disclosure. The method includes one or more following steps i.e., at step 702, the plurality of SME knowledge associated with a plurality of errors is received. At step 704, a knowledge repository is generated based on the plurality of SME knowledge. In an embodiment, the knowledge repository comprises (i) plurality of error strings associated with an error, (ii) error type, and (iii) root cause. At step 706, the plurality of error strings of the knowledge repository is analyzed to identify a plurality of hidden patterns. At step 708, an ordered rule dataset with label is generated based on the plurality of hidden patterns to form a decision tree of the plurality of errors. In an embodiment, the ordered rule dataset include a plurality of rules. At step 710, at least one error from the plurality of log files is analyzed to convert an unstructured data to a structured data. At step 712, the at least one error is classified by comparing the structured data with the ordered rule dataset. In an embodiment, the knowledge repository includes (i) plurality of error strings associated with an error, (ii) error type, and (iii) root cause. In an embodiment, the ordered rule dataset include a plurality of rules.
[048] In an embodiment, the plurality of hidden patterns are identified by analyzing the knowledge repository to perform at least one of: (a) perform regular expression based extraction of useful structured data from the plurality of log files, and (b) create the ordered rule dataset with the label. In an embodiment, the plurality of rules forms a decision tree like structure. In an embodiment, each node represent a pattern in the rule dataset and leaf node represent type of error, root cause and recommendation. In an embodiment, the structured data include a file name, timestamp, and error strings. In an embodiment, the ordered rule dataset include a set of rules that collectively comprise a classification model.
[049] The Machine First QA Triaging system provides a solution for entire L3/L4 Support and QA engineering by confident triage, explore and perform root causal analysis. The Machine First QA Triaging system provides following benefits such as: (a) Knowledge retention: Intelligence inbuilt into the tool, (b) Faster Time to market: Reduce time in analysis of large amount of test data and fault identification, (c) Quality: high accuracy (d) Environment Setup: No need to setup test environment, (e) Reduce Cost, (f) Effort: Reduce manual dependency Improve stability, (g) Reduce Downtime with faster error resolution.
[050] In an exemplary embodiment, for unknown error, where error type and its root cause is not known, unsupervised machine learning like clustering, association can be implemented where it create clusters of different types of error type and assign probability to those error. The tool is integrated where save learnings gained by the SME knowledge and output obtained after running machine learning model. Integrate dashboard to display the output through different visualizations.
[051] The written description describes the subject matter herein to enable any person skilled in the art to make and use the embodiments. The scope of the subject matter embodiments is defined by the claims and may include other modifications that occur to those skilled in the art. Such other modifications are intended to be within the scope of the claims if they have similar elements that do not differ from the literal language of the claims or if they include equivalent elements with insubstantial differences from the literal language of the claims.
[052] It is to be understood that the scope of the protection is extended to such a program and in addition to a computer-readable means having a message therein; such computer-readable storage means contain program-code means for implementation of one or more steps of the method, when the program runs on a server or mobile device or any suitable programmable device. The hardware device can be any kind of device which can be programmed including e.g. any kind of computer like a server or a personal computer, or the like, or any combination thereof. The device may also include means which could be e.g. hardware means like e.g. an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a combination of hardware and software means, e.g. an ASIC and an FPGA, or at least one microprocessor and at least one memory with software processing components located therein. Thus, the means can include both hardware means and software means. The method embodiments described herein could be implemented in hardware and software. The device may also include software means. Alternatively, the embodiments may be implemented on different hardware devices, e.g. using a plurality of CPUs.
[053] The embodiments herein can comprise hardware and software elements. The embodiments that are implemented in software include but are not limited to, firmware, resident software, microcode, etc. The functions performed by various components described herein may be implemented in other components or combinations of other components. For the purposes of this description, a computer-usable or computer readable medium can be any apparatus that can comprise, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
[054] The illustrated steps are set out to explain the exemplary embodiments shown, and it should be anticipated that ongoing technological development will change the manner in which particular functions are performed. These examples are presented herein for purposes of illustration, and not limitation. Further, the boundaries of the functional building blocks have been arbitrarily defined herein for the convenience of the description. Alternative boundaries can be defined so long as the specified functions and relationships thereof are appropriately performed. Alternatives (including equivalents, extensions, variations, deviations, etc., of those described herein) will be apparent to persons skilled in the relevant art(s) based on the teachings contained herein. Such alternatives fall within the scope of the disclosed embodiments. Also, the words “comprising,” “having,” “containing,” and “including,” and other similar forms are intended to be equivalent in meaning and be open ended in that an item or items following any one of these words is not meant to be an exhaustive listing of such item or items, or meant to be limited to only the listed item or items. It must also be noted that as used herein and in the appended claims, the singular forms “a,” “an,” and “the” include plural references unless the context clearly dictates otherwise.
[055] Furthermore, one or more computer-readable storage media may be utilized in implementing embodiments consistent with the present disclosure. A computer-readable storage medium refers to any type of physical memory on which information or data readable by a processor may be stored. Thus, a computer-readable storage medium may store instructions for execution by one or more processors, including instructions for causing the processor(s) to perform steps or stages consistent with the embodiments described herein. The term “computer-readable medium” should be understood to include tangible items and exclude carrier waves and transient signals, i.e., be non-transitory. Examples include random access memory (RAM), read-only memory (ROM), volatile memory, nonvolatile memory, hard drives, CD ROMs, DVDs, flash drives, disks, and any other known physical storage media.
[056] It is intended that the disclosure and examples be considered as exemplary only, with a true scope of disclosed embodiments being indicated by the following claims.
,CLAIMS:

1. A processor implemented method for automated triaging of plurality of log files to perform root cause analysis and prescriptive analytics, comprising:
receiving, via one or more hardware processors, a plurality of subject matter expert (SME) knowledge associated with a plurality of errors;
generating, via the one or more hardware processors, a knowledge repository based on the plurality of SME knowledge, wherein the knowledge repository comprises (i) plurality of error strings associated with an error, (ii) error type, and (iii) root cause;
analyzing, via the one or more hardware processors, the plurality of error strings of the knowledge repository to identify a plurality of hidden patterns;
generating, via the one or more hardware processors, an ordered rule dataset with label based on the plurality of hidden patterns to form a decision tree of the plurality of errors, wherein the ordered rule dataset comprises a plurality of rules;
analyzing, via the one or more hardware processors, at least one error from the plurality of log files to convert an unstructured data to a structured data; and
classifying, via the one or more hardware processors, the at least one error by comparing the structured data with the ordered rule dataset.

2. The processor implemented method of claim 1, wherein the plurality of hidden patterns are identified by analyzing the knowledge repository to perform at least one of: (a) perform regular expression based extraction of useful structured data from the plurality of log files, and (b) create the ordered rule dataset with the label.

3. The processor implemented method of claim 1, wherein the plurality of rules forms a decision tree like structure, wherein each node represent a pattern in the rule dataset and leaf node represent type of error, root cause and recommendation.

4. The processor implemented method of claim 1, wherein the structured data includes a file name, timestamp, and error strings.

5. The processor implemented method of claim 1, wherein the ordered rule dataset includes a set of rules that collectively comprise a classification model.

6. A system (100) for automated triaging of plurality of log files to perform root cause analysis and prescriptive analytics, comprising:
a memory (102) storing instructions;
one or more communication interfaces (106); and
one or more hardware processors (104) coupled to the memory (102) via the one or more communication interfaces (106), wherein the one or more hardware processors (104) are configured by the instructions to:
receive, a plurality of subject matter expert (SME) knowledge associated with a plurality of errors;
generate, a knowledge repository based on the plurality of SME knowledge, wherein the knowledge repository comprises (i) plurality of error strings associated with an error, (ii) error type, and (iii) root cause;
analyze, the plurality of error strings of the knowledge repository to identify a plurality of hidden patterns;
generate, an ordered rule dataset with label based on the plurality of hidden patterns to form a decision tree of the plurality of errors, wherein the ordered rule dataset comprises a plurality of rules;
analyze, at least one error from the plurality of log files to convert an unstructured data to a structured data; and
classify, the at least one error by comparing the structured data with the ordered rule dataset.

7. The system of claim 6, wherein the plurality of hidden patterns are identified by analyzing the knowledge repository to perform at least one of: (a) perform regular expression based extraction of useful structured data from the plurality of log files, and (b) create the ordered rule dataset with the label.

8. The system of claim 6, wherein the plurality of rules forms a decision tree like structure, wherein each node represent a pattern in the rule dataset and leaf node represent type of error, root cause and recommendation.

9. The system of claim 6, wherein the structured data includes a file name, timestamp, and error strings.

10. The system of claim 6, wherein the ordered rule dataset includes a set of rules that collectively comprise a classification model.