System and method for determining the outcome of an assessment of a candidate

Abstract

A system (200) and a method (400) for determining the outcome of an assessment of a candidate (102(1)) are disclosed. The method (400) includes accessing assessment data (220) associated with the candidate (102(1)) enrolled in a study program from a database (204) associated with the system (200). The method (400) further includes determining a study plan for the candidate (102(1)) by mapping at least one study material with at least one learning outcome of the study program associated with the candidate 102(1). The prediction model (222) is further configured to update the study plan based on at least one behavior of the candidate (102(1)). The prediction model (222) is further configured to determine an outcome of an assessment of the candidate (102(1)) based on the at least one behavior of the candidate (102(1)) using the study plan.

Description

SYSTEM AND METHOD FOR DETERMINING THE OUTCOME OF AN ASSESSMENT OF A CANDIDATETECHNICAL FIELD

[0001] The present disclosure relates to a candidate assessment and, more particularly, to computer-implemented systems and methods for determining the outcome of an assessment of the candidate.BACKGROUND

[0002] Traditional methods for preparing the candidates (e.g., students) for assessment (e.g., competitive examination, qualifying exams (like International English Language Testing System (IELTS), Graduate Record Examinations (GRE), etc.) heavily rely on general study techniques, such as designing special study materials for each assessment for all the candidates enrolled for that particular assessment. As the study materials are not specific to the candidate, the outcome (i.e., the result) of the assessment may not be effective.

[0003] The existing assessment results do not provide the study materials specific to candidates based on the candidate's capacity or the previous candidate assessment results. The existing systems further fail to analyze the current performance of the candidate and provide appropriate action plans to the candidate. For example, if the candidate is performing moderately well and requires motivation, better study plans and materials need to be provided to the candidate to improve the current status and achieve the desired results. In some instances, it is essential to inform the candidate about the alternative actions, such as opting for an alternative course or study plan, in case the existing study course is not suitable for the candidate. Further, the conventional methods often fail to break down examination requirements into actionable data elements, leading to inefficient preparation and lower success rates.

[0004] Based on the above, there exists a technological need for an improved computer-implemented system and method for analyzing and predicting examination success using Artificial Intelligence (Al).SUMMARY

[0005] To solve the foregoing problem and to provide other advantages, one aspect of the present disclosure is to provide computer-implemented systems and methods for determining the outcome of an assessment of the candidate.

[0006] In an aspect, a method for determining the outcome of an assessment of the candidate is disclosed. The method includes accessing assessment data associated with the candidate of a plurality of candidates from a database associated with the system. The assessment data includes at least one study material of a study program, at least one learning outcome of the study program, and at least one behavior schema associated with the candidate. The method further includes determining, by a prediction model associated with the system, a study plan for the candidate by mapping the at least one study material with the at least one learning outcome of the study program associated with the candidate. The method further includes determining, by the prediction model, at least one behavior of the candidate, based on the at least one behavior schema, wherein the at least one behavior schema is pre-set to the study program and associated with the study plan. The method further includes updating, by the prediction model, the study plan based on the at least one behavior of the candidate. The method further includes determining, by the prediction model, an outcome of the assessment of the candidate based on the performance of the candidate using the study plan, wherein the outcome of the assessment includes an inference of at least one of success or failure of the assessment.

[0007] An advantage of some embodiments is that the method provides a personalized and adaptive study plan using Al by analyzing candidate-specific data, including behavior and performance. This enables dynamic updates and accurate prediction of assessment outcomes. It offers a technical advancement over generic systems by tailoring learning strategies in real-time, thereby improving exam success rates.

[0008] In an aspect, the method further includes identifying at least one assessment schema corresponding to the study program enrolled by the candidate from a set of historical assessment schemas. The assessment data comprises the set of historical assessment schemas. The method further includes generating at least one knowledge organization schema associated with the study program, based on the at least one identified assessment schema. The method further includes determining the at least one study material and one or more topics associated with thestudy program enrolled by the candidate using the at least one knowledge organization schema. The method further includes generating at least one learning outcomes schema associated with the study program, based on the at least one identified assessment schema, wherein the at least one learning outcomes schema comprises at least one learning outcome associated with the study program. The method further includes determining the at least one learning outcome parameter associated with the study program enrolled by the candidate using the at least one learning outcomes schema. The method further includes generating, by the prediction model, the study plan, by mapping the determined at least one study material and one or more topics, and the at least one learning outcome associated with the study program. The method further includes generating, by the prediction model, at least one success prediction schema associated with the study program, based on the generated study plan. The method further includes determining, by the system, the at least one success prediction parameter associated with the study plan enrolled by the candidate using the at least one success prediction schema.

[0009] An advantage of some embodiments is that the method provides a technical solution by using Artificial Intelligence (Al) to intelligently process and analyze historical assessment data. It begins by identifying at least one assessment schema related to the candidate’s enrolled study program from a set of historical assessment schemas. This is an advancement over traditional systems, as it allows the system to learn from past assessment structures. Based on this, the system generates a knowledge organization schema, which helps in identifying relevant study material and one or more topics for the candidate. The method also generates a learning outcomes schema from the same assessment schema, which includes one or more learning outcomes linked to the study program. Using this, the system determines learning outcome parameters to track candidate progress. These elements are mapped by the prediction model to generate a personalized study plan. Further, the model creates a success prediction schema based on the study plan and determines success prediction parameters specific to the candidate. This layered and structured approach allows the system to provide highly accurate, personalized, and dynamic study plans, making the preparation process more data-driven and increasing the chances of assessment success.

[0010] In an aspect, the method further includes determining, by the prediction model, at least one behavior of the candidate, based on at least one value taken by the at least onebehavioral parameter during the course of the study plan. The method further includes updating, by the prediction model, the study plan based on the at least one behavior of the candidate.

[0011] An advantage of some embodiments is that the method further enhances personalization by determining, through the prediction model, at least one behavior of the candidate based on the value taken by at least one behavioral parameter during the course of the study plan. This provides a technical solution for real-time monitoring of the candidate’s engagement and learning patterns. Based on the identified behavior, the prediction model updates the study plan accordingly. This is a key advancement over static learning systems, as it allows dynamic adjustment of the study plan in response to how the candidate is actually performing. The advantage of this approach is that it keeps the learning process aligned with the candidate’s needs and progress, leading to more effective preparation and a higher chance of success.

[0012] In an aspect, the method further includes determining, by the prediction model, at least one value taken the at least one success prediction parameter during the course of the study plan, wherein the at least one value corresponds to the performance of the candidate using the study plan. The method further includes determining, by the prediction model, at least one assessment score, based on the at least one value taken by the at least one success prediction parameter. The at least one assessment score indicates the outcome of the assessment. The method further includes comparing, by the prediction model, the at least one assessment score with a predetermined assessment score. The method further includes updating the study plan based on the at least one value taken by the at least one success prediction parameter. The method further includes, upon determining the at least one assessment score is less than the predetermined assessment score, determining, by the prediction model, at least one alternative study program for the candidate.

[0013] An advantage of some embodiments is that the method provides a further technical solution by enabling continuous performance tracking and intelligent decision-making during the study plan. The prediction model determines at least one value taken by at least one success prediction parameter, which reflects the candidate's performance while following the study plan. Based on this value, the prediction model calculates at least one assessment score that indicates the likely outcome of the candidate's assessment. This score is then compared with apredetermined assessment score. If the calculated assessment score is lower than the expected score, the method includes updating the study plan based on the success prediction parameter value. Additionally, the system determines at least one alternative study program for the candidate. This is a major advancement over conventional methods, as it allows the system to take corrective action before the actual assessment by identifying learning gaps early. The advantage is that it helps candidates redirect their efforts through a more suitable or effective study program, thereby increasing the chances of achieving better results.

[0014] In an aspect, the method of determining at least one behavior of the candidate includes receiving at least one behavioral data associated with the candidate based on at least one interaction of the candidate with the study plan. The method further includes identifying at least one key feature associated with the performance of the candidate from the at least one behavioral data based on the at least one value of the at least one behavioral parameter set in the at least in behavioral schema. The method further includes predicting at least one behavior of the candidate based on the identified the at least in key features.

[0015] An advantage of some embodiments is that the method offers a technical solution for behavior-based learning adaptation by analyzing how the candidate interacts with the study plan. It begins by receiving at least one behavioral data point based on the candidate’s interaction with the study plan. From this behavioral data, the system identifies at least one key feature related to the candidate’s performance, using the value of at least one behavioral parameter set in the behavioral schema. Based on these key features, the system predicts at least one behavior of the candidate. This is an advancement over traditional learning systems, which do not account for real-time learner interaction data. The advantage of this approach is that it enables a more accurate understanding of the candidate’s learning patterns, allowing for better customization of the study plan and improved learning outcomes.

[0016] In an aspect, a server system is disclosed. The server system includes a communication interface, a memory that includes executable instructions, and a processor communicably coupled to the communication interface and the memory. The processor is configured to cause the server system to access assessment data associated with a candidate of a plurality of candidates from a database associated with the system. The assessment data includesat least one study material of a study program, at least one learning outcome of the study program, and at least one behavior schema associated with the candidate. The processor is further configured to cause the server system to determine, using a prediction model associated with the server system, a study plan for the candidate by mapping the at least one study material with the at least one learning outcome of the study program associated with the candidate. The processor is further configured to cause the server system to determine, using the prediction model, at least one behavior of the candidate, based on the at least one behavior schema, wherein the at least one behavior schema is pre-set to the study program and associated with the study plan. The processor is further configured to cause the server system to update using the prediction model, the study plan based on the at least one behavior of the candidate. The processor is further configured to cause the server system to determine, using the prediction model, an outcome of the assessment of the candidate based on the performance of the candidate using the study plan. The outcome of the assessment includes an inference of at least one of success or failure of the assessment.

[0017] An advantage of some embodiments is that the server system enables centralized, automated, and intelligent management of personalized study plans using Al-based predictions. This improves scalability, ensures consistent performance analysis across multiple candidates, and enhances the accuracy of assessment outcome predictions.

[0018] In an aspect, the processor is further configured to cause the server system to identify at least one assessment schema corresponding to the study program enrolled by the candidate from a set of historical assessment schemas. The assessment data comprises the set of historical assessment schemas. The processor is further configured to cause the server system to generate at least one knowledge organization schema associated with the study program, based on the at least one identified assessment schema. The processor is further configured to cause the server system to determine the at least one study material and one or more topics associated with the study program enrolled by the candidate using the at least one knowledge organization schema. The processor is further configured to cause the server system to generate at least one learning outcomes schema associated with the study program, based on the at least one identified assessment schema. The at least one learning outcomes schema comprises at least one learning outcome associated with the study program. The processor is further configured to cause the server system to determine the at least one learning outcome parameter associated with the study programenrolled by the candidate using the at least one learning outcomes schema. The processor is further configured to cause the server system using the prediction model, to generate the study plan, by mapping the determined at least one study material and one or more topics, and the at least one learning outcome associated with the study program. The processor is further configured to cause the server system to generate, using the prediction model, at least one success prediction schema associated with the study program, based on the generated study plan. The processor is further configured to cause the server system to determine the at least one success prediction parameter associated with the study plan enrolled by the candidate using the at least one success prediction schema.

[0019] An advantage of some embodiments is that the server system intelligently organizes and maps historical assessment data to generate structured study plans and predict outcomes using defined schemas. This ensures personalized learning paths, improves accuracy in success prediction, and enhances the efficiency of exam preparation.

[0020] In an aspect, the processor is further configured to cause the server system to determine, using the prediction model, at least one behavior of the candidate, based on at least one value taken by the at least one behavioral parameter during the course of the study plan. The processor is further configured to cause the server system to update using the prediction model, the study plan based on the at least one behavior of the candidate.

[0021] An advantage of some embodiments is that the server system dynamically adapts the study plan by analyzing candidate behavior in real-time using behavioral parameters. This leads to more responsive and personalized learning, improving engagement and overall performance outcomes.

[0022] In an aspect, the processor is configured to cause the server system to determine, using the prediction model, at least one value taken the at least one success prediction parameter during the course of the study plan. The at least one value corresponds to the performance of the candidate using the study plan. The processor is further configured to cause the server system to determine, by the prediction model, at least one assessment score, based on the at least one value taken by the at least one success prediction parameter. The at least one assessment score indicates the outcome of the assessment. The processor is further configured tocause the server system to compare, using the prediction model, the at least one assessment score with a predetermined assessment score. The processor is further configured to cause the server system to update the study plan based on the at least one value taken by the at least one success prediction parameter. Upon determining the at least one assessment score is less than the predetermined assessment score, the processor is further configured to cause the server system to, determine, using the prediction model, at least one alternative study program for the candidate.

[0023] An advantage of some embodiments is that the server system enables continuous performance evaluation and comparison with expected outcomes using success prediction parameters. This allows early identification of gaps and automatic suggestion of alternative study programs, improving the chances of candidate success.

[0024] In an aspect, the processor is further configured to cause the server system to determine, at least one behavior of the candidate includes receiving at least one behavioral data associated with the candidate based on at least one interaction of the candidate with the study plan. The processor is further configured to cause the server system to identify at least one key feature associated with the performance of the candidate from the at least one behavioral data based on the at least one value of the at least one behavioral parameter set in the at least in behavioral schema. The processor is further configured to cause the server system to predict at least one behavior of the candidate based on the identified the at least in key features.

[0025] An advantage of some embodiments is that the server system uses real-time behavioral data from candidate interactions to identify key performance features and predict behavior. This enables accurate and personalized adjustments to the learning path, enhancing learning outcomes and engagement.BRIEF DESCRIPTION OF THE FIGURES

[0026] The following detailed description of illustrative embodiments is better understood when read in conjunction with the appended drawings. To illustrate the present disclosure, exemplary constructions of the disclosure are shown in the drawings. However, the present disclosure is not limited to a specific device, or a tool and instrumentalities disclosed herein. Moreover, those in the art will understand that the drawings are not to scale.

[0027] FIG. 1 illustrates an example representation of an environment related to at least some embodiments of the present disclosure;

[0028] FIG. 2 is a simplified block diagram of a server system for determining the outcome of an assessment of the candidate, in accordance with an embodiment of the present disclosure;

[0029] FIG. 3 is a schematic diagram of a prediction model used for determining the outcome of the assessment of the candidate, in accordance with an embodiment of the present disclosure; and

[0030] FIG. 4 illustrates a flow chart of a method for determining the outcome of the assessment of the candidate, in accordance with another embodiment of the present disclosure.

[0031] The drawings referred to in this description are not to be understood as being drawn to scale, except if specifically noted, and such drawings are only exemplary in nature.DETAILED DESCRIPTION

[0032] In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure. It will be apparent, however, to one skilled in the art that the present disclosure can be practiced without these specific details. Descriptions of well-known components and processing techniques are omitted to not unnecessarily obscuring the embodiments herein. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein may be practiced and to further enable those of skill in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.

[0033] Reference in this specification to “one embodiment” or “an embodiment” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. The appearances of the phrase “in an embodiment” in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusiveof other embodiments. Moreover, various features are described which may be exhibited by some embodiments and not by others. Similarly, various requirements are described, which may be requirements for some embodiments but not for other embodiments.

[0034] Moreover, although the following description contains many specifics for the purposes of illustration, anyone skilled in the art will appreciate that many variations and / or alterations to said details are within the scope of the present disclosure. Similarly, although many of the features of the present disclosure are described in terms of each other, or in conjunction with each other, one skilled in the art will appreciate that many of these features can be provided independently of other features. Accordingly, this description of the present disclosure is set forth without any loss of generality to, and without imposing limitations upon, the present disclosure.

[0035] Various examples of the present disclosure provide computer-implemented systems and methods for determining the outcome of an assessment of the candidate. The system uses a structured approach for mastering and understanding the assessment (e.g., competitive exams, qualifying exams (like International English Language Testing System (IELTS), Graduate Record Examinations (GRE)) and the use of technology in education, focusing on a data-driven Artificial Intelligence (Al) based system for predicting outcomes (e.g., success and failure) of a candidate (e.g., student) in the assessment using a prediction model.

[0036] The term “study program” refers to a course that a candidate enrolls in the system (i.e., server system) of the present invention. Some examples of the study program include, but are not limited to Union Public Service Commission (UPSC), Public Service Commission (PSC), National Eligibility cum Entrance Test (NEET), Joint Entrance Examination (JEE), Graduate Aptitude Test in Engineering (GATE), Common Law Admission Test (CLAT), Common Admission Test (CAT) and so on. The study program is preset in the system (i.e., server system) and can be selected by the candidate at the time of enrolment in a program. The administrator of the system (i.e., server system) can also generate a study program and store it in the database, which can be displayed to the candidate at the time of enrolment.

[0037] The term “study material” includes at least one of the study notes, the study reference, the frequently asked questions, the important points, and so on, associated with the study program. The study material can be in the form of at least one or more of a digital copy, a hardcopy, an audio form, a video form, and so on. Such data is considered raw data and supplied to the system by at least an instructor (e.g., 104(1)) or the content providers 106.

[0038] A schema refers to a structured framework that defines how data or information is organized, categorized, and related. It helps in systematically storing, retrieving, and managing data in various fields. For example, in databases, a schema defines tables, columns, various parameters, their values, and relationships between various parameters. For example, in knowledge organization, a schema helps classify study materials in a repository based on subjects and categories.

[0039] The historical assessment schema refers to a structure that defines a type of assessment (i.e., written, multiple-choice questions) corresponding to the study program enrolled by the candidate. The assessment schema also includes details related to analysis of the assessment, indicating the information related to past question papers, question trends, frequently asked questions, weightage given to each topic in previous questions, and so on. For example, the historical assessment will have a set of historical assessment parameters related to the assessment of the study program. The set of historical assessment parameters (also referred to as historical assessment parameters) is used to understand how topics were treated in the past, identify important areas of focus, and help candidates and instructors to plan better for assessments. The historical assessment parameters may take one or more values depending on the parameter value defined in the historical assessment schema. The knowledge organization schema refers to a structure that defines how the study materials need to be organized in the database. A knowledge organization schema arranges materials in a structured way to help classify, index, and find information easily. Materials can be organized in a hierarchical structure, where broad categories come first, followed by specific subcategories. The study materials in a study program are organized using different parameters to make learning easy and structured. The knowledge organization schema will have a set of knowledge organization parameters related to the study materials of the study program. The knowledge organization schema also provides the relationship between each knowledge organization parameter. The knowledge organization parameters may take one or more values depending on the parameter value defined in the knowledge organization schema. The knowledge organization schema may also have at least one reference value for each knowledge organization parameter, which can be used to evaluate the assessment of the candidate.

[0040] The learning outcome refers to a set of targets specific to the study program that the candidate needs to achieve after completing the study program. The learning outcome ensures a comprehensive understanding and readiness for the assessment. The learning outcome parameters are set based on the learning outcome requirement schema. The structure of the learning outcome requirement schema defines how the learning outcome requirements need to be stored in the database. For example, the learning outcome requirement schema will have a set of learning outcome parameters related to the learning outcome requirements of the study program. The learning outcome requirement schema also provides the relationship between each learning outcome parameter. The learning outcome parameters may take one or more values depending on the parameter value defined in the learning outcome requirement schema. The learning outcome requirement schema may also have at least one reference value for each learning outcome requirement parameter, which can be used to evaluate the assessment of the candidate.

[0041] The behavior schema refers to a structure that defines how the behavior of the candidates needs to be stored in the database. For example, the behavior schema will have a set of behavioral parameters related to the behavior of the candidate. The behavior schema also provides the relationship between each behavioral parameter. The behavioral parameters may take one or more values depending on the parameter value defined in the behavior schema. The behavior schema may also have at least one reference value for each behavioral parameter that can be used to evaluate the assessment of the candidate.

[0042] The success prediction schema refers to a structured framework that helps to analyse and predict a candidate’s chances of success based on specific factors. The success prediction schema includes success parameters such as exam scores, study time, and cognitive abilities, which influence performance. The success parameters mainly depend on how the candidate follows the study plan. Additionally, the success prediction schema uses indicators like engagement with study materials and consistent improvement in test scores to assess the likelihood of success.

[0043] Various embodiments of the present invention are described hereinafter with reference to FIG. 1 to FIG. 4.

[0044] FIG. 1 illustrates an example representation of an environment 100 related toat least some embodiments of the present disclosure Although the environment 100 is presented in one arrangement, other embodiments may include the parts of the environment 100 (or other parts) arranged otherwise depending on, for example, for determining the outcome of an assessment of the candidate.

[0045] The environment 100 generally includes a plurality of entities (i.e., users), for example, a plurality of candidates 102, a plurality of instructors 104, and a plurality of content providers 106. The plurality of candidates 102(1), 102(2),..., 102(N) (collectively, referred to as the ‘plurality of candidates 102 or simply candidates 102) where ‘N’ is a Natural number. Each candidate of the candidates 102 is associated with a respective candidate device (e.g., 108(1) of a plurality of candidate devices 108. The plurality of candidate devices 108(1), 108(2),..., 108(N) (collectively, referred to as the ‘plurality of candidate devices 108 or simply candidate devices 108) where ‘N’ is a Natural number. The plurality of candidates includes students preparing for various competitive exams, qualifying exams, officers preparing for departmental promotions, and so on.

[0046] The plurality of instructors 104(1), 104(2),..., 104(N) (collectively, referred to as the ‘plurality of instructors 104 or simply instructors 104) where ‘N’ is a Natural number. Each instructor (e.g., 104(1)) of the plurality of instructors 104 is associated with a respective instructor device (e.g., 110(1)) of a plurality of instructor devices 110. The plurality of instructor devices 110(1), 110(2),..., 110(N) (collectively, referred to as the ‘plurality of instructor devices 110 or simply instructor devices 110) where ‘N’ is a Natural number. The plurality of instructors 104 includes tutors assisting in various competitive exams, qualifying exams, teachers having knowledge of the in various competitive exams, and so on.

[0047] The plurality of content providers 106(1), 106(2),..., 106(N) (collectively, referred to as the ‘plurality of content providers 106 or simply content providers 106) where ‘N’ is a Natural number. Each content provider (e.g., 106(1)) of the plurality of content providers 106 is associated with a respective content provider device (e.g., 112(1)) of a plurality content provider devices 112. The plurality of content provider devices 112(1), 112(2),..., 112(N) (collectively, referred to as the ‘plurality of content provider devices 112 or simply content provider devices 112) where ‘N’ is a Natural number. The plurality of content providers 106 includes tutors assistingin various competitive exams, teachers knowing the various competitive exams, and staff appointed for gathering content (e.g., a syllabus (i.e., study program), previous question papers, input outcomes of the syllabus, etc.), and so on.

[0048] The environment 100 further includes a server system 114, a third-party application server 128, and a database 118. The candidate devices 108, the instructor devices 110, the content provider devices 112, the server system 114, the third-party application server 128, and the database 118 are coupled to, and in communication with (and / or with access to) a network 120. The network 120 may include, without limitation, a Light Fidelity (Li-Fi) network, a Local Area Network (LAN), a Wide Area Network (WAN), a metropolitan area network (MAN), a satellite network, the Internet, a fiber-optic network, a coaxial cable network, an Infrared (IR) network, a Radio Frequency (RF) network, a virtual network, and / or another suitable public and / or private network capable of supporting communication among the entities illustrated in FIG. 1, or any combination thereof.

[0049] Various entities (i.e., users) in the environment 100 may connect to the network 120 in accordance with various wired and wireless communication protocols, such as Transmission Control Protocol and Internet Protocol (TCP / IP), User Datagram Protocol (UDP), 2nd Generation (2G), 3rd Generation (3G), 4th Generation (4G), 5th Generation (5G) communication protocols, Long Term Evolution (LIE) communication protocols, or any combination thereof. For example, the network 120 may include multiple different networks, such as a private network made accessible by the candidate devices 108, the instructor devices 110, the content provider devices 112, the server system 114, and the database 118 separately, and a public network (e.g., Internet) through which the by the candidate devices 108, the instructor devices 110, the content provider devices 112, the server system 114, and the database 118 may communicate.

[0050] Some examples of the candidate devices 108, the instructor devices 110, and the content provider devices 112 may include, but are not limited to, laptops, smartphones, desktops, tablets, workstation terminals, an Ultra-Mobile Personal Computer (UMPC), a phablet computer, a handheld personal computer, and the like.

[0051] In an embodiment, to effectively track candidate behavior using electronic devices (e.g., candidate devices 108), different types of electronic devices can be used. Eachelectronic device helps in its way to understand how candidates behave during exams or study sessions. The Visual Monitoring Candidate Devices, like Closed-Circuit Television (CCTV ) and webcams, are often used to watch candidates during exams. These cameras can track facial expressions, eye movements, and signs of distraction. Electroencephalogram (EEG ) headsets are special candidate devices that can read brain activity to understand focus and stress levels. In some embodiments, the wearable candidate devices are useful for tracking body signals. For example, smartwatches and fitness bands can measure heart rate, stress levels, and movement patterns. The electroencephalograph (EEG) headsets can also track brain waves to understand how candidates are thinking or feeling. Global Positioning System (GPS ) candidate devices can track movement, while smart glasses can show where a candidate is looking.

[0052] The candidate devices 108 can be audio-based candidate devices, such as microphones and noise sensors help to track sounds. The devices can catch signs of stress in a candidate’s voice or detect noises that might disturb their focus. The candidate devices 108 can be motion and gesture candidate devices that can track body movements, hand gestures, and posture. Candidate devices called Inertial Measurement Units (IMUs), which include accelerometers and gyroscopes, can also track movement patterns. In some embodiments, the candidate devices 108 can be environmental monitoring candidate devices, such as Infrared (IR) sensors and LDR (Light Dependent Resistors) check the room’s temperature, lighting, and noise levels to ensure a comfortable environment for learning.

[0053] The candidate devices 108 can be input tracking candidate devices used to study how candidates’ type, click, or move their mouse. Tools like Universal Serial Bus (USB) keyloggers can track typing speed, pauses, and corrections. Radio Frequency Identification (RFID) candidate devices can track movement in areas like classrooms or libraries. The candidate devices 108 can be specialized proctoring candidate devices that are used in online exams to monitor candidates. These tools use Artificial Intelligence (Al) to track behavior, identify distractions, and spot unusual activities. In an embodiment, the candidate devices 108 can use Optical Character Recognition (OCR) technology to read handwritten text during exams. By using these candidate devices together, exam authorities can better understand candidate behavior, improve testing environments, and provide extra help to candidates who may need it.

[0054] It should be noted that the number of the candidate devices 108, the instructor devices 110, and the content provider devices 112, described herein, are only used for exemplary purposes and do not limit the scope of the invention. The main objective of the invention is to provide the environment 100 for determining the outcome of an assessment of the candidate.

[0055] Each of the candidate devices 108, the instructor devices 110, and the content provider device 112 has at least one assessment application 126 and a third-party application server 128. In at least one embodiment, the assessment application 126 may be accessed through the third-party application server 128 hosted and managed by the third-party application server 128 via the network 120. Typically, the third-party application server 128 creates a contractual agreement with the assessment application 126 to comply with the privacy and security requirements of the assessment application 126. Based on the contractual agreement, the server system 114, including the assessment application 126, may provide access to the assessment services for the third-party application server 128 through integrated Application Programming Interface (API) services. In other words, the assessment application 126 may be a plugin for the third-party application server 128 associated with the third-party application server 128. In some embodiments, the assessment application 126 can be implemented as operating system extensions, modules, plugins, and the like. Further, the assessment application 126 may be operative in cloud infrastructure, or the assessment application 126 may be executed within or as a Virtual Machine (VM) or virtual server that may be managed in the cloud infrastructure.

[0056] The server system 114 is embodied in at least one computing device in communication with the network 120. In an embodiment, the database 118 may be a separate entity (or an external database) that is in communication with the server system 114 via the network 120. Without limitation, the database 118 may be configured to store information related to assessment data 122 and a prediction model 124. The assessment data 122 includes at least one study material, at least one learning outcome of a study program, and at least one schema associated with the candidate (e.g., candidate 102(1)) and the study program. In one embodiment, the assessment data 122 refers to the data used by the prediction model 124 for determining the outcome of an assessment of the candidate (e.g., 102(1)). In an embodiment, the assessment data 122 refers to the parameters defined in the various schemas, including the behavioural schema, outcome schema, and knowledge organization schema, which are specific to each candidate. The assessment data122 also includes values taken by the parameters during the study program.

[0057] In an embodiment, the server system 114 is configured to access the assessment data 122 associated with the candidate (e.g., candidate 102(1)) of the plurality of candidates 102 from the database 118 associated with the server system 114. The manner of collecting study materials, deciding the learning outcome and defining the at least one schema are explained with respect to FIG.2. The prediction model 124 associated with the server system 114 is configured to determine a study plan for the candidate (e.g., candidate 102(1)) by mapping the at least one study material with the at least one learning outcome of the study program associated with the candidate (e.g., candidate 102(1)). The prediction model 124 is further configured to determine at least one behavior of the candidate (e.g., candidate 102(1)), based on the at least one behavior schema. In an embodiment, the at least one behavior schema is pre-set to the study program and associated with the study plan. The prediction model 124 is further configured to update the study plan based on the at least one behavior of the candidate (e.g., candidate 102(1)). The prediction model 124 is further configured to determine an outcome of an assessment of the candidate (e.g., candidate 102(1)) based on the at least one behavior of the candidate (e.g., candidate 102(1)) using the study plan. The outcome of the assessment includes an inference of at least one of success and failure of the assessment. In an embodiment, the server system 114 may be deployed as a standalone server or can be implemented in the cloud as Software as a Service (SaaS). The assessment application 126 associated with the server system 114 provides or hosts the assessment application 126 for facilitating the integration of detailed analysis of the assessment, understanding of learning outcomes, organized knowledge management, and learner behavior analysis to predict and enhance the probability of outcome (i.e., success) using data analysis, machine learning, and the prediction model 124 to provide a personalized approach, enhancing the likelihood of success of the candidate. In some embodiments, the server system 114 may provide the assessment application 126 as a web service accessible through a website. In such a scenario, the assessment application 126 may be accessed through the website over the network 120 using a web browser application (e.g., Google Chrome®, Safari®, Mozilla Firefox™, Opera™, Microsoft Edge®, etc.) installed in the candidate devices 108, the instructor devices 110, and the content provider devices 112.

[0058] The server system 114 is configured to receive a service request for performingthe assessment of the candidate 102 in the environment 100. The service request includes but is not limited to, creating new user accounts (e.g., candidate 102(1), instructor 104(1), and content provider 106(1)) are collectively referred to as users), managing various candidate accounts, receiving data from various candidates 102, delivering content to the candidates 102, providing support to candidates 102, receiving study material from the content providers 106, receiving feedback from the instructors 104, and so on.

[0059] The number and arrangement of systems, devices, and / or networks shown in FIG. 1 are provided as an example. There may be additional systems, devices, and / or networks; fewer systems, devices, and / or networks; different systems, devices, and / or networks; and / or differently arranged systems, devices, and / or networks than those shown in FIG. 1. Furthermore, two or more systems or devices shown in FIG. 1 may be implemented within a single system or device, or a single system or device is shown in FIG. 1 may be implemented as multiple, distributed systems or devices. Additionally, or alternatively, a set of systems (e.g., one or more systems) or a set of devices (e.g., one or more devices) of the environment 100 may perform one or more functions described as being performed by another set of systems or another set of devices of the environment 100.

[0060] The technical problem with existing assessment systems is that traditional exam preparation methods offer uniform study materials to all candidates, without considering individual differences such as strengths, weaknesses, prior performance, or current learning progress. These systems lack the ability to monitor a candidate’s ongoing performance and do not provide tailored study plans or timely interventions. As a result, candidates who may be underperforming, demotivated, or mismatched with the course content receive little to no guidance for course correction. Additionally, conventional systems fail to break down examination goals into actionable steps, leading to inefficient preparation and reduced success rates.

[0061] The claimed method addresses these challenges by employing an Artificial Intelligence (Al) based approach to analyze each candidate’s assessment data 122, including past results, learning outcomes, and behavioral patterns. The system generates a personalized study plan by aligning study materials with specific learning objectives and continuously monitors the candidate’s behavior to dynamically update the plan. This ensures that the preparation process isadaptive and responsive to the candidate’s current status. Moreover, the method predicts the likely outcome of the assessment, that is, either success or failure, enabling early interventions and informed decision-making. This intelligent, customized system enhances the effectiveness of exam preparation and improves the chances of candidate success.

[0062] In the context of the present invention, the term “candidate” broadly refers to any individual or entity being evaluated. This may include students preparing for competitive examinations such as Union Public Service Commission (UPSC), Joint Entrance Examination (JEE), National Eligibility cum Entrance Test (NEET), or qualifying examinations like International English Language Testing System (IELTS), Graduate Record Examinations (GRE), and Test of English as a Foreign Language (TOEFL); employees undergoing workplace skill evaluations, periodic performance reviews, or competency assessments for promotions; job applicants participating in pre-employment aptitude tests, coding challenges, or psychometric profiling; vocational trainees in government or private skill development programs assessed through practical demonstrations and theory tests; healthcare professionals undergoing mandatory recertification examinations or compliance checks for medical protocols; financial, legal, or regulatory professionals appearing for licensing or compliance tests; sports players or athletes being assessed for training progress and match readiness; and language learners improving their proficiency through standardized tests or platform-based challenges.

[0063] The term “assessment” refers to any structured evaluation or performance measurement, such as standardized academic examinations, online adaptive quizzes, certification examinations, skill-based practical evaluations, workplace Key Performance Indicator (KPI) assessments, compliance and regulatory testing, or simulation-based evaluations like flight simulators for pilots and Virtual Reality (VR)-based safety training for factory workers. The term “study material” covers all types of learning or training content, including text-based notes, electronic books (eBooks), academic modules, video lectures, webinars, recorded sessions, interactive simulations, gamified learning modules, practice question banks, mock examinations, case studies, and workplace Standard Operating Procedures (SOPs). The term “learning outcome” represents measurable skills or knowledge the candidate is expected to acquire, such as passing an examination, mastering a set of technical skills, achieving certification, meeting compliance clearance, or reaching a defined proficiency level. The “behavior schema” includes candidate-specific behavioral data influencing performance, such as time taken to complete modules, number of attempts, accuracy levels, error trends, engagement frequency, level of focus, attention span, and learning preferences. The “outcome” refers to the predicted or final result after following the adapted study plan, which may be success or failure in an evaluation, achievement of certification, improvement in workplace productivity, reduction in error rates, or upgrading to a higher performance category.

[0064] For example, a student preparing for International English Language Testing System (IELTS) with low reading scores but high listening scores may receive a study plan focused on reading comprehension modules; an employee excelling in lead generation but underperforming in closing sales deals may be guided to targeted negotiation training; a job applicant failing coding challenges may be given algorithm practice tasks along with alternative career suggestions; a factory technician with slow safety drill responses may be assigned VR-based safety simulations; and a language learner with strong speaking but weak grammar skills may be given grammar-focused exercises before the assessment date. These examples illustrate that the invention can be applied across academic, professional, vocational, and compliance-oriented domains, ensuring that the adaptive study plan generation process is not restricted to a single field.

[0065] FIG. 2 is a simplified block diagram of a server system 200 (also referred to as system 200) for facilitating the assessment of the candidates 102, in accordance with an embodiment of the present disclosure. The server system 200 is an example of the server system 114 of FIG. 1. In some embodiments, the server system 200 is embodied as a cloud-based and / or SaaS-based (Software as a Service) architecture. Typically, the server system 200 may use pipeline architectures for determining the outcome of an assessment of the candidate. The server system 200 includes a computer system 202 and a database 204. The computer system 202 includes at least one processor 206 (hereinafter referred to as processor 206) for executing instructions, a memory 208, a communication interface 210, a storage interface 214, and a User Interface (UI) 216 that communicate with each other via a centralized bus 212.

[0066] In some embodiments, the database 204 is integrated into the computer system 202. For example, the computer system 202 may include one or more hard disk drives as the database 204. In one embodiment, the database 204 is integrated within the computer system 202and configured to store an instance of the assessment application 126. The storage interface 214 is any component capable of providing the processor 206 with access to the database 204. The storage interface 214 may include, for example, an Advanced Technology Attachment (ATA) adapter, a Serial ATA (SATA) adapter, a Small Computer System Interface (SCSI) adapter, a Redundant Array of Inexpensive Disks (RAID) controller, a Storage Area Network (SAN) adapter, a network adapter, and / or any component providing the processor 206 with access to the database 204. The UI 216 is in communication with the database 204. The UI 216 is configured to present one or more UIs to the candidate devices 108, the instructor devices 110, and the content provider devices 112 for determining the outcome of an assessment of the candidate (e.g., 102(1)). The database 204 is an example of the database 118 of FIG. 1. The assessment data 122 and the prediction model 124 of FIG. 1 are depicted as the assessment data 220 and the prediction model 222 of FIG. 2.

[0067] The processor 206 includes suitable logic, circuitry, and / or interfaces to execute computer-readable instructions for performing one or more operations to determine the outcome of an assessment of the candidate. Examples of the processor 206 include, but are not limited to, an Application-Specific Integrated Circuit (ASIC) processor, a Reduced Instruction Set Computing (RISC) processor, a Complex Instruction Set Computing (CISC) processor, a Field- Programmable Gate Array (FPGA), and the like. The memory 208 includes suitable logic, circuitry, and / or interfaces to store a set of computer-readable instructions for performing operations. Examples of the memory 208 include a Random- Access Memory (RAM), a Read-Only Memory (ROM), a removable storage drive, a Hard Disk Drive (HDD), and the like. It will be apparent to a person skilled in the art that the scope of the disclosure is not limited to realizing the memory 208 in the server system 200, as described herein. In another embodiment, the memory 208 may be realized in the form of a database server or cloud storage working in conjunction with the server system 200, without departing from the scope of the present disclosure.

[0068] The processor 206 is operatively coupled to the communication interface 210 such that the processor 206 is capable of communicating with a remote device 218 such as, the candidate devices 108, the instructor devices 110, the content provider devices 112, and the third- party application server 128 or communicate with any entity connected to the network 120 (as shown in FIG. 1). It is noted that the server system 200, as illustrated and hereinafter described, is merely illustrative of an apparatus that could benefit from embodiments of the present disclosureand, therefore, should not be taken to limit the scope of the present disclosure. It is noted that the server system 200 may include fewer or more components than those depicted in FIG. 2.

[0069] In one embodiment, the processor 206 includes a data pre-processing module 224 and a data processing module 226. The data pre-processing module 224 and the data processing module 226 include a suitable logic, circuitry, and / or interfaces to execute computer- readable instructions for performing pre-processing of raw data. In an embodiment, the raw data includes data received from the candidate (e.g., candidate 102(1)). Such data includes, candidate name, Date of Birth (BOD) of the candidate (e.g., candidate 102(1)), program details of the candidate 102(1), reminder data set by the candidate (e.g., candidate 102(1)), notes data entered or stored by the candidate (e.g., candidate 102(1)) while undergoing the study plan, and so on. In another embodiment, the raw data includes data received from the instructors 104, including data related to the course, study material, feedback to candidates 102, grading of assignments, and so on. In another embodiment, the raw data includes data received from the content providers 106, including data related to study materials, in the form of audio, video, three-dimensional content, structured study content, text materials, books, references, links to outside content, latest news, and so on. In an embodiment, the instructors 104 and / or the content providers 106 may provide information related to a set of rules to be used by the data processing module 226 for defining the various schemas. In another embodiment, one or more trained Artificial Intelligence (Al) models to define the set of rules for generating the various schemas. The Al model can be trained using a set of training data for generating the various schemas in the present disclosure.

[0070] The data pre-processing module 224 is configured to receive data (i.e., raw data) from one or more entities (such as candidates 102, instructors 104, data providers 106, etc.) of the environment 100. The data pre-processing is done before storing the data in the database 204, so that the raw data can be later used efficiently by the prediction model 222 and the data processing module 226. In preferred embodiment, the data pre-processing module 224 is configured to receive raw data from the instructors 104 and the content providers 106 for a study program. The process starts with data cleaning, where errors, duplicate entries, and missing values are fixed or removed to ensure accuracy. Then, the data is structured properly by converting text into numerical values, encoding categories, and scaling numbers to maintain consistency. Important features are selected or created, while unnecessary details are removed to reduce storagesize and improve efficiency. During pre-processing, the data is analyzed to determine its format, types, and required transformations. The data pre-processing module 224 is further configured to remove incorrect, duplicate, incomplete, or inconsistent data.

[0071] The data processing module 226 includes a suitable logic, circuitry, and / or interfaces to execute computer-readable instructions for performing one or more operations to generate one or more schemas based on the set of assessment rules. The data processing module 226 is configured to generate at least the historical assessment schemas, the learning outcome requirement schema, the knowledge organization schema, the behavior schema, the success prediction schema, and the assessment schema. The historical assessment schemas refer to the preset schemas (i.e., core subjects, question pattern, etc.) of a competitive exam that the candidate (e.g., candidate 102(1)) has enrolled for. In some embodiments, the server system 200 may receive one or more historical assessment schemas from the instructors 104 and / or the content providers 106. In some embodiments, based on the input received from the instructors 104 and / or the content providers 106, the data processing module 226 can generate a new schema. The historical assessment schema also defines assessment types, such as Multiple-Choice Questions (MCQs), essay writing, and interviews, each linked to a passing score, like 50% for prelims and 60% for mains. Each parameter also has at least one reference value, a standard score used to measure a candidate’s performance.

[0072] The data processing module 226 is configured to analyze the assessment data 220 and generate at least one schema based on a set of assessment rules predefined in the database 204. In an embodiment, the set of assessment rules is pre-defined based on each type of the schema. The set of assessment rules includes but is not limited to identifying data types of parameters (that are specific to the schema) to assign the correct format, such as text, numbers, or dates. The set of assessment rules defines the uniqueness and primary keys of each parameter to ensure that records like candidate Identities (IDs) or test IDs remain unique. Foreign key relationships are established to connect related data, such as linking candidate details with their test results. Data validation rules are set to maintain correct formats, such as ensuring dates follow a standard pattern or numeric values stay within a valid range.

[0073] The set of historical assessment parameters includes academic performancehistory considers past grades, scores, and trends to analyze strengths and weaknesses. The set of historical assessment parameters includes parameters related to the type of assessment (e.g., MCQ, written test, and so on) corresponding to the study program (e.g., NEET, JEE, and so on) enrolled by the candidate (e.g., 102(1)). The historical assessment schemas (also referred to as the set of historical assessment schemas) refer to different ways students have been tested over time. In the past, many exams used descriptive or essay-type questions, where students had to write long answers to explain their understanding. One common method is MCQ-based tests, where students choose the correct answer from multiple options, like in the National Eligibility cum Entrance Test (NEET), which is used for medical admissions. Some exams, like the Common Admission Test (CAT), focus on aptitude-based testing, checking logical thinking and problem-solving skills instead of specific subjects. Other assessments included interviews, where students had to answer questions face-to-face to show their knowledge and communication skills. In practical fields like medicine and engineering, students also take practical or skill-based tests to show hands-on abilities. Over time, these testing methods have changed to make exams fairer, faster, and more accurate in judging students’ abilities. The assessment schema specific for the candidate enrolled in the study program is selected by the data processing module 226 from the set of historical assessment schemas.

[0074] The historical assessment schema also provides the relationship between each historical assessment parameter. The set of historical assessment parameters may take one or more values depending on the parameter value defined in the historical assessment schema. The historical assessment schema may also have at least one reference value for each historical assessment parameter, which can be used to evaluate the assessment of the candidate. The assessment schema refers to a schema selected from the historical assessment schema based on the study program selected by the candidate during the program enrollment process. In case the historical assessment schema corresponding to the study program to be enrolled is not available, the system generates a new schema based on the input received from the instructors 104 and the content providers 106.

[0075] In an embodiment, the historical assessment schemas are generated by the data processing module 226, by analyzing past question papers, materials, and resources. This schema follows rules that map past questions to different assessment parameters, like topics, subtopics,question type, formats, difficulty level, trend pattern and so on. The mappings are validated before being analyzed.

[0076] In an embodiment, the historical assessment schemas are generated based on the assessment analysis and question paper analysis. In an example, the historical assessment schemas may include historical assessment parameters. The assessment parameters include, without limitation, assessment analysis parameters that involve defining the criteria and metrics used to evaluate the study program and question papers. The assessment analysis parameters help in creating a structured and systematic approach to assessment analysis. The assessment analysis parameters include, but are not limited to, difficulty level, question type, question format, question nature, frequency analysis, weightage distribution, trend analysis, and so on. The assessment analysis parameters vary with respect to assessments. By establishing clear assessment analysis parameters, the server system 200 can gain a deeper understanding of the assessment structure. This information is crucial for developing an effective study plan that targets the most important and frequently tested areas.

[0077] Analyzing past assessment question papers is crucial for understanding the assessment pattern, types of questions, different parameters for analysis, and the distribution of questions across various topics. This analysis helps in identifying key areas to focus on during preparation. In cases of new assessments or where previous question papers are not available, the assessment or expected outcome that has the closest relation, in terms of specific parameters, to the target assessment is considered in this step. The data processing module 226 is configured to identify key areas and the nature of questions frequently asked in the assessment. The data processing module 226 is further configured to provide insights into the nature of questions that are likely to appear in the assessment. Thus, the historical assessment schemas include a set of parameters related to assessment, assessment analysis, and past assessment question papers corresponding to the study program.

[0078] The data processing module 226 is configured to generate the learning outcome requirement schema based on the assessment rules and the outcome requirement (i.e., raw data) supplied by the instructors 104 and the content providers 106. The learning outcome requirement schema is a way to organize learning goals in the study program. The data pre-processing module224 receives the raw data from the instructors 104 and content providers 106 regarding what are the outcomes of each program. After pre-processing, the data is stored in the database 204. The data processing module 226 may access the data and generate a learning outcome requirement schema. The learning outcome requirement schema defines chapter-wise, sub-topic-wise, and topic-wise details of a specific study program. Such material includes different learning outcome parameters, which are the key things candidates need to leam, such as knowledge, skills, and assessments. The schema also shows how these learning goals are connected. For example, some learning outcomes must be completed before moving on to the next, or some skills depend on understanding certain topics first. This structure helps educators plan courses, track student progress, and make sure learning outcomes match academic or job requirements.

[0079] In an embodiment, the data processing module 226 is generated based on curriculum goals and expected competency with regard to the exam demand. The schema also ensures sequential learning flow using topic dependencies. Validations are done in accordance with assessment objectives.

[0080] In an embodiment, the data processing module 226 is also configured to generate the knowledge organization schema based on the assessment rules and the study materials (i.e., raw data) supplied by the instructors 104 and the content providers 106. The knowledge organization schema is a way to arrange and store information so that it is easy to find and use. It helps in organizing knowledge by grouping similar topics together, linking related ideas, and adding labels or keywords to make searching easier. For example, in a library, books are classified by subject, like science or history, so people can find them quickly. In digital systems, topics are connected, like linking "cells" in biology to "Deoxyribonucleic Acid (DNA)" and "mitochondria." It also follows a structure, starting from broad subjects and narrowing down to specific details, such as science to physics, physics to mechanics Newton’s Laws. This kind of organization is used in education, libraries, and online databases to help people easily access the information they need.

[0081] In an embodiment, the knowledge organization schema is generated by the data processing module 226, by categorizing study materials based on subjects, chapters, topics, and subtopics, using hierarchical syllabus convention. Classification has defined classification logic.

[0082] The knowledge organization schema structures the content repository, ensuring that all study materials are organized logically and are easily accessible. The knowledge organization schema supports efficient knowledge management and retrieval. The data processing module 226 is configured to generate the knowledge organization schema that organizes study materials for efficient learning. The knowledge organization schema is used to categorize study materials based on subjects, chapters, and topics. The content repository ensures that all materials are relevant and updated from time to time. For example, a knowledge organization schema for a civil service exam study program in organizing study materials, test methods, and evaluation rules in a structured way. It includes different knowledge parameters that define subjects, their connections, and reference values for assessment. For example, the knowledge organization schema may include parameters like subjects, study material type, difficulty level, and assessment type. Each subject, such as history, polity, economy, science, and technology, can have smaller topics like modern Indian history, constitution basics, national income, and space research. Study materials may include National Council of Educational Research and Training (NCERT) books, reference books, online courses, and mock tests, with each resource marked as easy, medium, or hard based on difficulty level. For example, a candidate’s mock test score can be compared with a standard score to check if they are ready for the actual exam. This structured method helps students prepare better by focusing on important topics, using the right study materials, and tracking their progress effectively. It should be noted that each type of schema, including historical assessment schemas, knowledge organization schema, and learning outcome requirement schema, is connected to the study program chosen by the candidate.

[0083] For example, in case the candidate is enrolled for the NEET examination, the data processing module 226 checks the corresponding assessment schema to be used for NEET from the historical assessment schema. For the NEET examination, the questions are Multiple Choice Questions (MCQ), hence, the data pre-processing module 224 selects one (i.e., MCQ) of the historical assessment schemas. The historical assessment schemas also provide a set of topics (e.g., Physics, Biology, and Chemistry) that are covered in the study program, that is, the NEET. It should be noted that each set of topics (e.g., physics) may have a set of sub-topics (e.g., light, motion). Based on the set of topics to be covered, the data pre-processing module 224 is configured to determine the one or more topics (e.g., Physics, Biology, and Chemistry) from the at least one study material. Then, the data processing module 226 is configured to determine the one or morestudy parameters (e.g., understanding of concept, application, use, calculation) to be used for evaluating the candidate based on the one or more topics of the at least one study material. In an embodiment, for the enrolled study program, the knowledge organization schema is already preset in the database 204. The data processing module 226 retrieves the knowledge organization schema corresponding to the enrolled study program. In another embodiment, for the enrolled study program, the learning schema is already pre-set in the database 204. The data processing module 226 retrieves the learning schema corresponding to the enrolled study program.

[0084] The data processing module 226 is further configured to generate the success prediction schema based on the data supplied by the instructors 104 and the content providers 106. From the data, a set of success parameters is defined and set by the data processing module 226. The set of success parameters includes exam scores, study time, achieved learning outcomes, and thinking ability. The success prediction schema provides the relationship between each success prediction parameter. The success prediction parameters may take one or more values depending on the parameter value defined in the learning outcome requirement schema. The success prediction schema may also have at least one reference value for each success prediction parameter, which can be used to evaluate the assessment of the candidate. In an embodiment, for an existing study program, the knowledge organization schema is already pre-set in the database 204. The data processing module 226 retrieves the knowledge organization schema corresponding to the existing study program. In another embodiment, for the existing study program, the success prediction schema is already pre-set in the database 204. The data processing module 226 retrieves the success prediction schema corresponding to the enrolled study program.

[0085] The success prediction schema is generated by the data processing module 226 by correlating outcome indicators like test scores, study time, consistency of learning, focus time and other behavioural traits using rules derived from historical data. Each parameter is assigned weights and reference threshold to predict likelihood of success.

[0086] Once all the schemas are generated, the processed data is stored in the database 204 based on the respective schema. In a preferred embodiment, the data processing module 226 is configured to determine the at least one study material associated with the study program enrolled by the candidate from the database 204. More specifically, once all the schemas are readyand available, the data processing module 226 is configured to identify an assessment schema corresponding to the study program enrolled by the candidate from the set of historical assessment schemas. The data processing module 226 is further configured to identify the learning outcome schema, and the knowledge organization schema based on the identified assessment schema.

[0087] In an embodiment, the prediction model 222 is configured to determine a study plan for the candidate using the learning outcome schema and the knowledge organization schema. The study plan is determined by mapping the at least one study material with the at least one learning outcome associated with the study program enrolled by the candidate. The term “study plan” refers to a plan that is delivered to the candidate enrolled in the study program. The study plan includes a well-organized study material specific to the candidate based on the enrolled study program. The study plan includes at least sequential, structured, or real-time data specific to the candidate enrolled in the study program.

[0088] The prediction model 222 is configured to use the various schemas, its parameters, and values associated with the candidate enrolled in the study program, while undergoing the study plan. In an embodiment, the data processing module 226 analyses values of the parameters and makes predictions using the prediction model 222. The prediction model 222 improves over time by learning from new data. As more candidates take tests, the server system 200 records their answers, accuracy, and speed.

[0089] The prediction model 222 is configured to determine at least one behavior of the candidate, based on the at least one behavior schema. The at least one behavior schema is preset to the study program and associated with the study plan. In some embodiments of the invention, without limitation, the data processing module 22 can generate the at least one behavior schema, and / or update the existing at least one behavior schema, based on the values taken by various parameters used in various schemas of the present disclosure. In an embodiment, the at least one behavior schema is generated based on the rules. The rules are used to track user actions across the learning journey. Parameters are based on exam demand and assessed against behavioural indicators

[0090] Determining at least one behavior of the candidate helps the server system 200 to understand how a candidate approaches learning, such as their study habits, time spent on different topics, and response patterns in tests. By analysing these behaviours, the server system 200 can provide personalized recommendations to improve performance. For example, if a candidate (candidate 102(1)) frequently skips difficult questions or takes too much time on certain topics, the server system 200 can suggest better strategies to manage time and focus on weaker areas. This way, the prediction model 222 helps to create a more effective and customized study plan for each candidate 102(1). The behavior schema tracks and analyzes the actions and events related to candidate learning. The behavior schema helps in understanding how candidates interact with the study plan and identify areas for improvement, monitoring learner events, actions, and physical aspects provides insights into their study habits, learning behavior, engagement levels, and areas where they might be struggling. The behavior schema is to monitor and analyze candidate behavior. The data processing module 226 is configured to track candidate interactions with study materials. The data processing module 226 is further configured to analyze engagement patterns and study habits. The data processing module 226 is further configured to identify and address learning challenges. Understanding learner behavior helps in customizing the study plan to fit individual needs. It allows for timely interventions and support to keep candidates on track.

[0091] In an embodiment, the prediction model 222 receives at least one behavioral data associated with the candidate 102(1) based on at least one interaction of the candidate 102(1) with the study plan. Then, the prediction model 222 is configured to identify at least one key feature associated with the performance of the candidate 102(1) from the at least one behavioral data based on at least one value taken by the at least one behavioral parameter in the at least in behavioral schema. The at least one key feature represents a measurable aspect of the candidate’s behavior that has a significant impact on predicting the candidate’s performance, such as, without limitation, time taken to complete a task or module, number of attempts required to achieve a correct answer, accuracy levels, recurring error patterns, engagement frequency, focus consistency, attention span, learning pace, or responsiveness to feedback. The identification of the at least one key feature is performed based on at least one value taken by the at least one behavioral parameter in the behavioral schema, which captures structured data relating to the candidate’s learning patterns and work habits. The prediction model 222 is further configured to predict at least one behavior or outcome of the candidate 102(1) based on the identified key features, wherethe outcome may include success or failure in an assessment, attainment of certification, measurable improvement in skill proficiency, reduction in operational errors, or advancement to a higher performance category, thereby enabling adaptive modification of the study plan in real time.

[0092] The prediction model 222 is also designed to update the study plan based on the candidate’s behaviour. The study plan is created using different parameters linked to various schemas, including the behavioural schema, outcome schema, and knowledge organization schema, which are specific to each candidate (e.g., candidate 102(1)). These parameters help the server system 200 to understand the candidate’s learning style, strengths, and weaknesses. The study plan includes different types of assessments, such as chapter-wise assessments, sub-topic- wise assessments, topic-wise assessments, and overall study plan assessments. These assessments help to evaluate the candidate’s progress and understanding of different subjects. Based on the results, the server system 200 can adjust the study plan by recommending additional practice, revising certain topics, or suggesting better time management techniques. This ensures that the study plan remains personalized and helps the candidate (e.g., candidate 102(1)) improve effectively throughout the study program.

[0093] In an embodiment, the server system 200 can suggest ways for candidates 102 to improve based on their progress. For example, if a candidate (e.g., candidate 102(1)) struggles with a subject, the prediction model 222 of the server system 200 may recommend extra practice, study materials, or better time management. The server system 200 tracks improvements of the candidates 102 and adjusts the advice accordingly. In this way, the server system 200 provides accurate predictions and helpful feedback to help candidates 102 perform better in examinations. This will help the candidates 102 achieve the learning outcome and assessment goals. This will directly increase the success rate of getting through in the enrolled study program.

[0094] The prediction model 222 is configured to predict future outcomes and adjust study plans to improve the learning of the candidate (e.g., candidate 102(1)). Several factors influence success prediction, including academic performance, engagement level, study habits, problem-solving skills, and behavioral insights. The prediction model 222 also considers past performance trends, personal challenges, and access to learning resources. These factors are stored in the database 204 and linked to each candidate’s data, helping the prediction model 222 makemore accurate predictions. The success prediction schema includes one or more parameters that are specific factors or variables, such as examination scores, time spent studying, and cognitive abilities, that are used to analyze and predict success. The success prediction schema also includes indicators that are measurable signs to show whether a candidate (e.g., candidate 102(1)) is likely to succeed, such as high engagement in study materials or consistent improvement in test scores. The prediction model 222 can create personalized study plans and adjust the learning program to meet the candidate’s needs, ensuring better outcomes. Using the success prediction schema, the prediction model 222 can generate personalized study plans and adjust learning programs to match a candidate’s needs. This ensures better outcomes by focusing on areas that require improvement and optimizing the learning process.

[0095] The success prediction schema identifies key indicators that correlate with candidate success. These predictions are used to assess the likelihood of achieving the desired learning outcomes. In an embodiment, a candidate's chances of success in the assessment can be based on factors specific to the study program. The success prediction schema includes a scoring logic that will be normalized and compared to a reference value that is set for the study program. For example, if the comparison result is greater than 80 is a high chance of success in the study program. In another example, if the comparison result is less than 40, it shows failure in the study program. The success prediction schema is used to predict candidate success based on key indicators. The schema generation module 226 is configured to identify success prediction from past data. The prediction model 222 is configured to assess current candidate performance. The prediction model 222 is further configured to use predictors to guide and adjust study plans. Success prediction provides valuable insights into what contributes to candidate success. By understanding these factors, the server system 200 can tailor the whole program to help candidates achieve their goals.

[0096] The prediction model 222 is further configured to determine an outcome of an assessment of the candidate (e.g., candidate 102(1)) based on at least one value taken by the success prediction parameters in the success prediction schema. The outcome of the assessment includes an inference of at least one of success and failure of the assessment. The working of the prediction model 222 is explained using FIG.3. In an embodiment, the study plan is updated based at least on the at least one value taken by the success prediction parameters and the at least onebehavioral parameter of the candidate (e.g., candidate 102(1)).

[0097] It should be noted that the prediction model 222 is configured to determine whether the defined learning outcomes for the study program are met by the candidates 102. The data processing module 226 is configured to define the parameters in the respective schema to measure and track candidate progress. For example, the data processing module 226 develops metrics for each learning outcome, including but not limited to metrics for regular assessments, to evaluate the understanding of the candidate (e.g., candidate 102(1)). The data processing module 226 is further configured to define feedback metrics. The prediction model 222 adjusts the study plans based on the values of the feedback metrics. Thus, the measurement parameters provide a way to quantify progress and identify areas that need improvement. Regular assessments ensure that candidates stay on track and make consistent progress toward their goals. It should be noted that the parameters generated by the data processing module 226 are not limited to the analysis parameters, measurement parameters, parameters in each schema, and so on, and may include other parameters used for determining the outcome of an assessment of the candidate (e.g., candidate 102(1)).

[0098] Analysing past question papers to identify patterns and frequently asked topics is essential for predicting likely questions in upcoming exams. The assessment schema includes information related to the assessment analysis and past question papers corresponding to the study program. The prediction model 222 is configured to predict potential questions and provide targeted practice using the assessment schema. To predict likely questions for upcoming assessments based on past patterns, the prediction model 222 identifies recurring patterns in past question papers. Use the prediction model 222 (i.e., machine learning algorithms) to predict probability. The server system 200 provides candidates with practice questions based on predictions. The question prediction technique helps candidates focus on the most relevant topics and types of questions, increasing their chances of success.

[0099] The course delivery involves the mapping of the organized study material to the learning outcomes and the creation of a structured course delivery plan. This component ensures that the study plan aligns with the learning goals and assessment requirements. The prediction model 222 is configured to deliver a structured and effective study plan by mapping thestudy material to learning outcomes. The prediction model 222 is configured to develop a timeline for course delivery. The prediction model 222 is configured to implement interactive and engaging learning methods. A well-structured course delivery plan ensures that candidates receive the right study material at the right time. Interactive methods keep candidates engaged and enhance their understanding of the material.

[0100] More specifically, the prediction model 222 integrates all the collected data (i.e., assessment data 220) and predicts the probability of a candidate (e.g., candidate 102(1)) succeeding in the assessment. The algorithm in the prediction model 222 considers various factors such as study program coverage, learning outcomes, behavior patterns, and success predictors. The prediction model 222 is configured to determine the probability of assessment success and provide alternative assessment suggestions if the success grade is not met. Thus, the prediction model 222 integrates the input data from the knowledge organization, learner behavior, and success predictors, and applies integrated data for analysis. After analysis by the prediction model 222, an outcome (also referred to as probability scores) is generated for each candidate (e.g., candidate 102(1)).

[0101] If the success grade is not achieved in the outcome, the prediction model 222 is configured to analyze the candidate’s performance data to suggest alternative assessments better suited to their strength and knowledge areas. The prediction model 222 provides a data-driven determination of a candidate's likelihood of success and suggests alternative assessments if necessary. This information can be used to provide targeted support and increase the chances of assessment success, and offer viable options for the candidate’s career path. It should be noted that the various modules, such as the data pre-processing module 224, and data processing module 226, described herein, can be configured in a variety of ways, including electronic circuitries, digital arithmetic, and logic blocks, and memory systems in combination with software, firmware, and embedded technologies.

[0102] The prediction model 222 is initially trained using, without limitation, historical datasets containing study materials, mapped learning outcomes, candidate behavior schemas, and recorded assessment results. Each record in the dataset includes indicators such as time spent on activities, number of attempts, accuracy rates, behavioural aspects like level of focus,attention span, consistency, and the final performance outcome. During training, the model applies machine learning techniques, such as gradient descent for neural networks, entropy-based splitting for decision trees, margin maximization for support vector machines, or iterative policy updates for reinforcement learning models, to identify patterns and correlations between inputs and outcomes. The parameters or weights of the prediction model 222 are iteratively adjusted to minimize prediction errors, and the trained model is validated against separate test data to ensure accuracy and generalization. Once trained, the prediction model 222 can process new candidate data to dynamically map study materials, adapt study plans, and accurately predict likely assessment outcomes in real time.

[0103] The prediction model 222 employed in the present invention is implemented as a technical system including a machine learning-based architecture, such as a neural network or decision tree algorithm, executed on the server system 200 with defined data flow between modules. For instance, a decision tree model may be used to guide how a system chooses learning content based on student performance, such as directing a student with lower quiz scores to remedial material. A neural network could be employed to analyze complex learning behavior by processing various inputs like time taken, level of focus, attention span, consistency, and so on, thereby predicting future performance or customizing study paths. Similarly, a Support Vector Machine (SVM) might classify learners into different categories like “weak,” “average,” or “strong” based on historical usage patterns. A Bayesian model could calculate the probability of a student's success based on the assessment and adjust the study plan accordingly. A reinforcement learning model allows the system to adjust over time by learning from student interactions, for example, increasing the use of video content if students perform better with it. Lastly, a K-means clustering algorithm can be used to group users with similar learning styles and offer group-specific content. Including such detailed examples in the specification shows that the invention is not merely an abstract idea or mental act but provides a concrete technical solution using specific computational models and algorithms.

[0104] The prediction model 222 operates on structured learning outcome data and candidate-specific behavior schemas to dynamically map and adapt study plans in real-time. Unlike simple rule-based systems, the model uses weighted inputs, behavioral feedback loops, and an adaptive logic layer to improve prediction accuracy and personalize assessments over time,thereby solving a technical problem of efficient individualized learning plan generation on digital platforms.

[0105] The prediction model 222 is a self-hosted transformer-based Large Language Model (LLM) with a decoder-only architecture, fine-tuned from the Large Language Model Meta Al (LLaMA) and enhanced through proprietary schema-driven training to align outputs with the claimed objectives. The prediction model 222 consists of 32 transformer decoder blocks, each with approximately 6,144 hidden units, employing Switched Gated Linear Units (SwiGLU) activation in feed-forward layers for improved schema-mapped learning representations and Softmax for output logits. The model uses pre-trained LLaMA weights, with additional domain-specific layers initialized via Xavier uniform, and is implemented in Python Torch (PyTorch) with Hugging Face Transformers.

[0106] The proprietary training dataset includes approximately 350 million to 650 million tokens, measured post-de-duplication and quality filtering using the LLaMA tokenizer. The proprietary training dataset is constructed from structured and diverse sources, including historical question papers, syllabus maps, behavioral tracking logs, learning outcome records, and success prediction schema parameters. The dataset encompasses a mix of question-answer pairs, syllabus-aligned content, reference materials, and detailed student interaction data, such as performance metrics and behavioral logs. Coverage spans competitive examinations, qualifying tests, and skill-based programs in multiple formats, with diversity ensured across defined schema parameters for robust generalization. Annotation and labelling are performed via a human-in-the- loop (HITL) process by domain experts, involving the initial mapping of each data point to four key schema structures, behavioral schema, learning outcome schema, knowledge organization schema, and success prediction schema, ensuring high-quality, structured model training.

[0107] The pre-processing module 224 includes multiple data preparation stages: duplicate removal, spell correction, irrelevant content filtering, and schema-linked consistency checks. Numerical features such as scores and timings are scaled via Min-Max normalization, while categorical features (e.g., subject / topic, behavioral parameters) are encoded into embeddings. Additional feature engineering creates derived metrics such as learning difficulty scores and engagement indices, directly mapped to schema-defined behavioral and successprediction parameters. Temporal alignment ensures synchronization between behavioral logs, learning milestones, and study plan updates in accordance with the behavioral schema requirements.

[0108] Pre-processing plays a critical role in enhancing model accuracy. Schema- aware pre-processing aligns input data with standardized parameter formats, resulting in a measured 7.5% improvement in prediction accuracy. Low-confidence or inconsistent entries are filtered to maintain dataset integrity, and feature engineering guided by schema definitions further enhances model performance, increasing the success prediction Fl -score from 72% to 79%.

[0109] Training is carried out using cross-entropy loss with label smoothing and the Adaptive Moment Estimation with Weight Decay (AdamW) optimizer (learning rate 2+105, weight decay 0.01), over five epochs with a batch size of 128. Regularization includes dropout at 0.1 and gradient clipping. An 80 / 10 / 10 stratified validation split ensures balanced coverage across all schema-linked parameters, and training is performed on eight NVIDIA Al 00 graphics processing units (GPUs).

[0110] Performance evaluation spans multiple metrics, such as accuracy, precision, recall, and Fl -score, tailored to specific tasks: question generation (accuracy), content generation (Bilingual Evaluation Understudy (BLEU) & Recall-Oriented Understudy for Gisting Evaluation (ROUGE)), study plan recommendations (Recall@K), and success prediction (Fl-score). Receiver Operating Characteristic - Area Under the Curve (ROC-AUC) is used for binary success / failure classification. The test set includes over 70,000 questions, 1,000+ reference materials, and real behavioral logs, with performance variance across programs limited to ±3%, and schema-specific evaluations confirming consistent application of knowledge and outcome parameters.

[0111] In the pre-trained model configuration, the schema-linked dataset structure directly addresses the underlying technical problem by enabling the generation of personalized and adaptive study plans linked to behavioral, knowledge, and outcome parameters. The dataset’s diversity across schema parameters ensures broad coverage, reducing bias and improving the reliability of predictions across competitive, qualifying, and skill-based programs. Empirical evaluation demonstrates predictable and repeatable outcomes, with five independent test runs producing consistent results and a metric variance of less than 1%, attributable to deterministicschema mappings that standardize study plan generation.

[0112] FIG. 3 is a schematic diagram showing the process 300 for determining the outcome of the assessment of the candidate 102(1), in accordance with an embodiment of the present disclosure. The data processing module 226 of FIG. 2 is used to generate, without limitation, the behavior schema 302, the learning outcome schema 304, the knowledge organization schema 306, and the success prediction schema 308. The learning outcome parameter 314 in the learning outcome schema 304 takes one or more values while undergoing the study plan delivered to the candidate 102(1). Similarly, the knowledge organization parameter 316 in the knowledge organization schema 306 takes one or more values while undergoing the study plan delivered to the candidate 102(1). It should be noted that the parameter values can be initially preset. In an embodiment, the parameter values can be assigned during the duration of the study program in real time, depending on the performance of the study plan by the candidate 102(1).

[0113] The raw data received from the candidate devices 108(1) are pre-processed by the pre-processing module 224 and stored in the database 204. Such data can be accessed by the behaviour determination module 322 of the prediction model 222 to analyze various patterns of the candidates 102 to identify behavioral traits (i.e., behavior of the candidate) like focus, confidence, or hesitation. The various patterns include, but are not limited to, time spent on each question or module, mouse movements and clicks, keyboard inputs, switching between tabs or windows, idle time or inactivity, repeated attempts, or changes in answers, and use of shortcuts or specific patterns of navigation.

[0114] The behavioral parameters 312 in the behavior schema 302 take the values based on the determined or identified behavior of the candidate 102(1) while undergoing the study plan. The prediction model 222 includes a study plan module 324 configured to determine the study plan by integrating the various parameter values, such as the values from the learning outcome parameters 314, knowledge organization parameters 316, and behavioral parameters 312 of the candidate 102(1). The study plan module 324 is configured to map the learning outcome with the organized study plan and the learning behavior data. Based on the mapped information, the success prediction schema 308 is used to identify the key indicators that correlate with the candidate's outcome (i.e., success or failure in assessment). The prediction model 222 is used topredict the outcome based on the key indicators. Such a study plan is designed specifically for the candidate 102(1), and it is updated based on the candidate's behavior. The candidate's behavior is proportional to the values taken by the behavioral parameters 312 in the behavior schema 302 while undergoing the study plan. In an embodiment, the study plan is updated based on the values taken by the success prediction parameters 318 of the success prediction schema 308. It should be noted that the prediction model 222 is capable of updating the study plan that includes the assessment questions that are likely to be asked in the real-time assessment of the study program. More specifically, the prediction model 222 is capable of generating the study plan, tweaking the study materials and practice questions based on the performance of the candidate 102(1) and the candidate's behavior while undergoing the study plan. This helps the candidates 102 focus on areas needing improvement and better prepare for the final evaluation.

[0115] Once the study plan is delivered to the candidate 102(1), after the final assessment (that is, after completing the study plan), the outcome determination module 326 of the prediction model 222 uses the success prediction parameters 318 of the success prediction schema 308. The outcome determination module 326 is configured to determine the outcome of an assessment (see, outcome of assessment 328) of the candidate 102(1) based on the performance of the candidate 102(1) using the study plan. The at least one value of the success prediction parameters 318 corresponds to the performance of the candidate 102(1) using the study plan. It should be noted that the study plan includes the final assessment also. The outcome of the assessment includes an inference of at least one of success and failure of the assessment. Upon determining the at least one assessment score is less than the predetermined assessment score, the prediction model 222 determines at least one alternative study program 330 for the candidate 102(1). For example, if the candidate 102(1) first enrolls for the NEET examination, the prediction model 222 analyzes the performance and behavior of the candidate 102(1) during the study plan and assessment. Based on the outcome of an assessment (see, outcome of assessment 328), it is determined that, the candidate 102(1) may not secure an MBBS seat. Thus, the prediction model 222 suggests alternative programs like Biotechnology, Biochemistry, or Microbiology to the candidate 102(1).

[0116] FIG. 4 illustrates a flow chart of a method 400 for determining the outcome of the assessment of the candidate 102(1), in accordance with another embodiment of the presentdisclosure. The method 400 depicted in the flow diagram may be executed by, for example, the server system 200. Operations of the method 400, and combinations of operation in the method 400, may be implemented by, for example, hardware, firmware, a processor, circuitry, and / or a different device associated with the execution of software that includes one or more computer program instructions. The operations of the method 400 are described herein may be performed by an application interface that is hosted and managed with the help of the server system 200. The method starts at Step 402.

[0117] At step 402, the server system (e.g., the server system 200) is configured to access the assessment data 220 associated with the candidate (e.g., candidate 102(1)) of the plurality of candidates 102 from the database 204 associated with the server system 200. The assessment data 220 includes at least one study material of a study program, at least one learning outcome of the study program, and at least one behavior schema associated with the candidate (e.g., candidate 102(1)).

[0118] At step 404, the prediction model (e.g., prediction model 222) associated with the server system (e.g., the server system 200) is configured to determine a study plan for the candidate (e.g., candidate 102(1)) by mapping the at least one study material with the at least one learning outcome of the study program associated with the candidate (e.g., candidate 102(1)).

[0119] At step 406, the prediction model 222 is further configured to determine at least one behavior of the candidate (e.g., candidate 102(1)), based on the at least one behavior schema. The at least one behavior schema is pre-set to the study program and associated with the study plan.

[0120] At step 408, the prediction model 222 is further configured to update the study plan based on the at least one behavior of the candidate (e.g., candidate 102(1)).

[0121] At step 410, the prediction model 222 is further configured to determine an outcome of an assessment of the candidate (e.g., candidate 102(1)) based on the at least one behavior of the candidate (e.g., candidate 102(1)) using the study plan, wherein the outcome of the assessment includes an inference of at least one of success and failure of the assessment. It should be noted that the study plan corresponding to the study program enrolled by the candidate is firstdelivered to the candidate. Then, the at least one behavior of the candidate undergoing the study plan is analyzed. Based on the analysis, the study plan can be adjusted. The outcome of the assessment of the candidate is determined at any stage of the study plan by the prediction model.

[0122] The disclosed method and system offer a significant advancement in assessment preparation by leveraging Artificial Intelligence to create personalized, adaptive study plans for each candidate. Unlike traditional methods that rely on uniform materials, the system analyzes historical assessment schemas, learning outcomes, and behavioural data to generate a structured and targeted learning path. It continuously monitors the candidate's interaction with the study plan, identifies key behavioural patterns, and updates the plan accordingly to align with the candidate’s current performance and learning needs.

[0123] Additionally, the system predicts assessment outcomes by evaluating success prediction parameters in real-time. If the expected performance falls below a predefined threshold, the system intelligently suggests alternative study programs, allowing timely course correction. This not only improves the candidate's chances of success but also ensures efficient use of resources and effort. The result is a smart, scalable solution that supports better learning outcomes, personalized support, and data-driven decision-making in educational and competitive exam environments.

[0124] The disclosed method with reference to FIG. 4, or one or more operations of the server system 200 may be implemented using software including computer-executable instructions stored on one or more computer-readable media (e.g., non-transitory computer- readable media, such as one or more optical media discs, volatile memory components (e.g., DRAM or SRAM), or nonvolatile memory or storage components (e.g., hard drives or solid-state nonvolatile memory components, such as Flash memory components) and executed on a computer (e.g., any suitable computer, such as a laptop computer, netbook, Web book, tablet computing device, smartphone, or other mobile computing devices). Such software may be executed, for example, on a single local computer or in a network environment (e.g., via the Internet, a wide- area network, a local-area network, a remote web-based server, a client-server network (such as a cloud computing network), or other such networks) using one or more network computers. Additionally, any of the intermediate or final data created and used during the implementation ofthe disclosed methods or systems may also be stored on one or more computer-readable media (e.g., non-transitory computer-readable media) and are considered to be within the scope of the disclosed technology. Furthermore, any of the software-based embodiments may be uploaded, downloaded, or remotely accessed through a suitable communication means. Such suitable communication means includes, for example, the Internet, the World Wide Web, an intranet, software applications, cable (including fiber optic cable), magnetic communications, electromagnetic communications (including RF, microwave, and infrared communications), electronic communications, or other such communication means.

[0125] Although the invention has been described with reference to specific exemplary embodiments, it is noted that various modifications and changes may be made to these embodiments without departing from the broad scope of the invention. For example, the various operations, blocks, etc., described herein may be enabled and operated using hardware circuitry (for example, complementary metal oxide semiconductor (CMOS) based logic circuitry), firmware, software, and / or any combination of hardware, firmware, and / or software (for example, embodied in a machine-readable medium). For example, the apparatuses and methods may be embodied using transistors, logic gates, and electrical circuits (for example, application-specific integrated circuit (ASIC) circuitry and / or in Digital Signal Processor (DSP) circuitry).

[0126] Particularly, the server system 200 and its various components may be enabled using software and / or using transistors, logic gates, and electrical circuits (for example, integrated circuit circuitry such as ASIC circuitry). Various embodiments of the invention may include one or more computer programs stored or otherwise embodied on a computer-readable medium, wherein the computer programs are configured to cause a processor or the computer to perform one or more operations. A computer- readable medium storing, embodying, or encoded with a computer program, or similar language, may be embodied as a tangible data storage device storing one or more software programs that are configured to cause a processor or computer to perform one or more operations. Such operations may be, for example, any of the steps or operations described herein. In some embodiments, the computer programs may be stored and provided to a computer using any type of non-transitory computer-readable media. Non-transitory computer- readable media include any type of tangible storage media. Examples of non-transitory computer- readable media include magnetic storage media (such as floppy disks, magnetic tapes, hard diskdrives, etc.), optical magnetic storage media (e.g., magneto-optical disks), Compact Disc Read- Only Memory (CD-ROM), Compact Disc Recordable CD-R, Compact Disc Rewritable CD-R / W), Digital Versatile Disc (DVD), BLU-RAY® Disc (BD), and semiconductor memories (such as mask ROM, programmable ROM (PROM), Erasable PROM (EPROM), flash memory, Random Access Memory (RAM), etc.). Additionally, a tangible data storage device may be embodied as one or more volatile memory devices, one or more non-volatile memory devices, and / or a combination of one or more volatile memory devices and non-volatile memory devices. In some embodiments, the computer programs may be provided to a computer using any type of transitory computer-readable media. Examples of transitory computer-readable media include electric signals, optical signals, and electromagnetic waves. Transitory computer-readable media can provide the program to a computer via a wired communication line (e.g., electric wires, and optical fibers) or a wireless communication line.

[0127] Various embodiments of the invention, as discussed above, may be practiced with steps and / or operations in a different order, and / or with hardware elements in configurations, that are different from those that, are disclosed. Therefore, although the invention has been described based on these exemplary embodiments, it is noted that certain modifications, variations, and alternative constructions may be apparent and well within the scope of the invention.

[0128] Although various exemplary embodiments of the invention are described herein in a language specific to structural features and / or methodological acts, the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as exemplary forms of implementing the claims.

Claims

ClaimsI / We Claim:

1. A method (400) for determining the outcome of an assessment of the candidate (102(1)), the method (400) comprising: accessing (402), by a server system (200), assessment data (220) associated with the candidate (102(1)) of a plurality of candidates (102) from a database (204) associated with the server system (200), wherein the assessment data (220) comprises at least one study material of a study program, at least one learning outcome of the study program, and at least one behavior schema associated with the candidate (102(1)); determining (404), by a prediction model (222) associated with the server system (200), a study plan for the candidate (102(1)) by mapping the at least one study material with the at least one learning outcome of the study program associated with the candidate (102(1)); determining (406), by the prediction model (222), at least one behavior of the candidate (102(1)), based on the at least one behavior schema, wherein the at least one behavior schema is pre-set to the study program and associated with the study plan; updating (408), by the prediction model (222), the study plan based on the at least one behavior of the candidate (102(1)); and determining (410), by the prediction model (222), an outcome of the assessment of the candidate (102(1)) based on performance of the candidate (102(1)) using the study plan, wherein the outcome of the assessment includes an inference of at least one of success and failure of the assessment.

2. The method (400) as claimed in claim 1 , further comprising: identifying, by the server system (200), at least one assessment schema corresponding to the study program enrolled by the candidate (102(1)) from a set of historical assessment schemas, wherein the assessment data (220) comprises the set of historical assessment schemas; generating, by the server system (200), at least one knowledge organization schema associated with the study program, based on the at least one identified assessment schema;determining, by the server system (200), the at least one study material and one or more topics associated with the study program enrolled by the candidate (102(1)) using the at least one knowledge organization schema; generating, by the server system (200), at least one learning outcomes schema associated with the study program, based on the at least one identified assessment schema, wherein the at least one learning outcomes schema comprises at least one learning outcome associated with the study program; determining, by the server system (200), the at least one learning outcome parameter associated with the study program enrolled by the candidate (102(1)) using the at least one learning outcomes schema; generating, by the prediction model (222), the study plan, by mapping the determined at least one study material and one or more topics, and the at least one learning outcome associated with the study program; generating, by the prediction model (222), at least one success prediction schema associated with the study program, based on the generated study plan; and determining, by the server system (200), the at least one success prediction parameter associated with the study plan enrolled by the candidate (102(1)) using the at least one success prediction schema.

3. The method (400) as claimed in claim 2, further comprising: determining, by the prediction model (222), at least one behavior of the candidate (102(1)), based on at least one value taken by the at least one behavioral parameter during the course of the study plan; and updating, by the prediction model (222), the study plan based on the at least one behavior of the candidate (102(1)).

4. The method (400) as claimed in claim 3, further comprising: determining, by the prediction model (222), at least one value taken by the at least one success prediction parameter during the course of the study plan, wherein the at least one value corresponds to the performance of the candidate (102(1)) using the study plan;determining, by the prediction model (222), at least one assessment score, based on the at least one value taken by the at least one success prediction parameter, wherein the at least one assessment score indicates the outcome of the assessment; and comparing, by the prediction model (222), the at least one assessment score with a predetermined assessment score.

5. The method (400) as claimed in claim 4, wherein the study plan is updated based on the at least one value taken by the at least one success prediction parameter.

6. The method (400) as claimed in claim 4, further comprising: upon determining the at least one assessment score is less than the predetermined assessment score, determining, by the prediction model (222), at least one alternative study program for the candidate (102(1)).

7. The method (400) as claimed in claim 4, wherein determining at least one behavior of the candidate (102(1)) comprises: receiving at least one behavioral data associated with the candidate (102(1)) based on at least one interaction of the candidate (102(1)) with the study plan; identifying at least one key feature associated with the performance of the candidate (102(1)) from the at least one behavioral data based on the at least one value of the at least one behavioral parameter set in the at least one behavioral schema; and predicting at least one behavior of the candidate (102(1)) based on the identified the at least in key feature.

8. A server system (200), comprising: a communication interface (210); a memory (208) comprising executable instructions; and a processor (206) communi cably coupled to the communication interface (210) and the memory (208), the processor (206) configured to cause the server system (200) to at least: access assessment data (220) associated with the candidate (102(1)) of a plurality of candidates (102) from a database (204) associated with the server system (200), whereinthe assessment data (220) comprises at least one study material of a study program, at least one learning outcome of the study program, and at least one behavior schema associated with the candidate (102(1)); determine using a prediction model (222) associated with the server system (200), a study plan for the candidate (102(1)) by mapping the at least one study material with the at least one learning outcome of the study program associated with the candidate (102(1)); determine using the prediction model (222), at least one behavior of the candidate (102(1)), based on the at least one behavior schema, wherein the at least one behavior schema is pre-set to the study program and associated with the study plan; update using the prediction model (222), the study plan based on the at least one behavior of the candidate (102(1)); and determine using the prediction model (222), an outcome of the assessment of the candidate (102(1)) based on performance of the candidate (102(1)) using the study plan, wherein the outcome of the assessment includes an inference of at least one of success and failure of the assessment.

9. The server system (200) as claimed in claim 8, wherein the server system (200) is further caused to identify at least one assessment schema corresponding to the study program enrolled by the candidate (102(1)) from a set of historical assessment schemas, wherein the assessment data (220) comprises the set of historical assessment schemas; generate at least one knowledge organization schema associated with the study program, based on the at least one identified assessment schema; determine the at least one study material and one or more topics associated with the study program enrolled by the candidate (102(1)) using the at least one knowledge organization schema; generate at least one learning outcomes schema associated with the study program, based on the at least one identified assessment schema, wherein the at least one learning outcomes schema comprises at least one learning outcome associated with the study program;determine the at least one learning outcome parameter associated with the study program enrolled by the candidate (102(1)) using the at least one learning outcomes schema; generate using the prediction model (222), the study plan, by mapping the determined at least one study material and one or more topics, and the at least one learning outcome associated with the study program; generate using the prediction model (222), at least one success prediction schema associated with the study program, based on the generated study plan; and determine the at least one success prediction parameter associated with the study plan enrolled by the candidate (102(1)) using the at least one success prediction schema.

10. The server system (200) as claimed in claim 9, wherein the server system (200) is further caused to: determining, by the prediction model (222), at least one behavior of the candidate (102(1)), based on at least one value taken by the at least one behavioral parameter during the course of the study plan; and updating, by the prediction model (222), the study plan based on the at least one behavior of the candidate (102(1)).

11. The server system (200) as claimed in claim 9, wherein the server system (200) is further caused to: determine, by the prediction model (222), at least one value taken by the at least one success prediction parameter during the course of the study plan, wherein the at least one value corresponds to the performance of the candidate (102(1)) using the study plan; determine, by the prediction model (222), at least one assessment score, based on the at least one value taken by the at least one success prediction parameter, wherein the at least one assessment score indicates the outcome of the assessment; and compare, by the prediction model (222), the at least one assessment score with a predetermined assessment score.

12. The server system (200) as claimed in claim 11, wherein the study plan is updated based on the at least one value taken by the at least one success prediction parameter.

13. The server system (200) as claimed in claim 11, wherein the server system (200) is further caused to: upon determining the at least one assessment score is less than the predetermined assessment score, determining, by the prediction model (222), at least one alternative study program for the candidate (102(1))14. The server system (200) as claimed in claim 11, wherein determining at least one behavior of the candidate (102(1)) comprises: receiving at least one behavioral data associated with the candidate (102(1)) based on at least one interaction of the candidate (102(1)) with the study plan; identifying at least one key feature associated with the performance of the candidate (102(1)) from the at least one behavioral data based on the at least one value of the at least one behavioral parameter set in the at least one behavioral schema; and predicting at least one behavior of the candidate (102(1)) based on the identified the at least in key feature.

Images