DESC:PRIORITY STATEMENT
[001] The present application hereby claims priority from Indian patent application with the application number 202241070408, filed on 06 December 2022, the entire contents of which are incorporated herein by reference.
FIELD OF TECHNOLOGY
[002] The present disclosure generally relates to data analytics and machine learning and more particularly to a machine learning (ML) based learning system for determining competency of a user, while completing a task presented to the user and a method thereof.
BACKGROUND
[003] In classrooms, tuition centers and similar such institutes, student assessments are conducted regularly, and the results of these assessments are then used to rank students. This ranking of students may be traumatic for the students causing stress. The ranking mechanisms does not help in determining the student’s concept-wise understanding of a subject.
[004] Also, several online learning platforms are available today, where the students can learn at their own pace from anywhere. The downside of such available online learning platform is the lack of tutor supervision. Most online learning platforms have simple data and statistics-based feedback to the students and teachers that include number of hours spent on the learning platform, number of instructional videos viewed, Multiple Choice Questions attempted, and number of assignments (problems) attempted, in the form of tables and charts. This type of student feedback does not address the root cause of the student’s inability in problem solving.
[005] The traditional learning models are trainer centric model, where the trainer leads the learning plan, and the learning objectives are set by the trainer which may not be suitable for all the students, and it lacks individual attention to a student. Also, it is difficult to find in which specific concept the user or student lacks. Further, the traditional learning models work on uniform methodology and learning path which is same for all students. Hence, lacks in providing personalized study plan based on individual competency level.
[006] Further, in the traditional learning system the level of understanding of the student is assessed by assignments, tests, quizzes at the end of the course. The traditional learning system lacks in topic wise assessment during the course period, to enhance the performance of student. Also, the assessments are provided at the end of the course period which is uniform to all students with same content and same format.
[007] The assessment tools in the traditional learning system is configured for analysing the student based on the grades obtained in the final exam of a learning course. In a scenario where a student fails to attain the required grade the whole learning course is repeated instead of re-learning the specific content where the student needs clarity. Also, if a student lacks in previous year’s concept the traditional learning system is ignorant in teaching those concepts.
[008] The existing systems uses statistical analysis as a tool to analyse the student’s competency and performance based on grades obtained by them in the final assessment of a learning course. While using statistical analysis on a large dataset such as a student’s performance in a year, it may be a tedious process and the obtained results may not accurate. Also, the classical statistical analysis is a time-consuming mechanism when it comes to a large dataset. These methods focus only on student’s performance but lacks in finding the student’s understanding in concepts involved in a learning course.
[009] Baker John Allan, Cepuran Kenneth James, et al. tiltle: “Systems and Methods for Analyzing Learner’s Roles and Performances and for Intelligently Adapting the Delivery of Education” Patent No: US-20220230554-A1, dated 20.07.2022, provides a system and method to further a student’s understanding of a subject matter through analyzing data captured. The system and method generate reports based on the correlation data and develops statistical models that highlight learning and behavioural trends. However, the classical statistical model mechanism cannot help in identifying the level of competency of students when the data sets are large and highly non-linear.
[0010] Therefore, in view of the problems mentioned above, it is advantageous to provide a system and a method that can overcome one or more of the problems and limitations as mentioned above.
SUMMARY
[0011] This summary is provided to introduce a selection of concepts in simple manners that are further described in the detailed description of the disclosure. This summary is not intended to identify key or essential inventive concepts of the subject matter nor is it intended to determine the scope of the disclosure.
[0012] To overcome at least some of the above mentioned problems, a system and a method for determining competency of the user based on a task presented to the user is disclosed. A system and method are needed for classifying the user into predefined learning stage based on the determined competency.
[0013] Briefly, according to an exemplary embodiment, a system for determining competency of at least one user and for classifying the at least one user into a predefined learning stage is disclosed. The system includes a user device configured for collecting a first data based on an interaction of the at least one user with the user device while completing the task presented to the at least one user on the user device. The system includes a data communication device of the user device configured for transmitting the first data to a server for analysing the first data based on a first set of parameters and a second set of parameters. The system includes a server configured for receiving the first data and a second data. The system includes a model which is trained iteratively, using a second data. The second data being the data based on each interaction of each user of a plurality of users while completing each task of a plurality of tasks, associated with an academic subject, presented to each of the plurality of users. The model is trained for determining the competency of the at least one user using a scoring mechanism based on analysis of the first data and classifying the at least one user into the predefined learning stage, based on determined competency of the at least one user.
[0014] Briefly, according to an exemplary embodiment, a method for determining competency of at least one user, for classifying the at least one user into a learning stage is disclosed. The method includes collecting a first data from a user device, based on an interaction of the at least one user with the user device while completing the task presented to the at least one user on the user device. The method includes transmitting the first data to a server using a data communication device of the user device for analysing the first data based on a first set of parameters and a second set of parameters. The method includes receiving the first data and a second data from the server for training a model iteratively, using a second data, the second data being the data based on each interaction of each user of a plurality of users while completing each task of a plurality of tasks, associated with an academic subject, presented to each of the plurality of users. The model is trained for determining the competency of the at least one user using a scoring mechanism based on analysis of the first data and classifying the at least one user into a predefined learning stage, based on determined competency of the at least one user.
[0015] The summary above is illustrative only and is not intended to be limiting in any way. In addition to the illustrative aspects, exemplary embodiments, and features described above, further aspects, exemplary embodiments, and features will become apparent by reference to the drawings and the following detailed description.
BRIEF DESCRIPTION OF THE FIGURES
[0016] These and other features, aspects, and advantages of the exemplary embodiments may be better understood when the following detailed description is read with reference to the accompanying drawings in which like characters represent like parts throughout the drawings, wherein:
[0017] Figure 1 illustrates a high-level block diagram of a machine learning (ML) based system configured for ‘determining user competency’ while completing a task in a specific subject matter, according to an embodiment of the present disclosure;
[0018] Figure 2 illustrates a detailed view of the system 100 of Figure 1 for determining user competency and further classifying the at least one user into a predefined learning stage while completing the task presented to at least one user, according to an embodiment of the present disclosure;
[0019] Figure 3 illustrates an example flow chart depicting a method for determining user competency and classifying at least one user into a predefined learning stage, based on at least one user’s as well as all cumulative user’s data of interaction, according to an embodiment of the present disclosure;
[0020] Figure 4(A) illustrates a flowchart depicting a method for determining competency of the at least one user and classifying the user into a predefined learning stage, according to an embodiment of the present disclosure;
[0021] Figure 4(B) illustrates a flowchart depicting the method performed by a ML based competency processor in the server, according to an embodiment of the present disclosure;
[0022] Figure 5 illustrates a pictorial representation showing a classification of predefined learning stages to classify the at least one user based on determined competency of the at least one user, according to an embodiment of the present disclosure;
[0023] Figure 6 illustrates an example task with concepts provided to at least one user for completing the task, according to an embodiment of the present disclosure; and
[0024] Figure 7 is a block diagram of a computing device utilized for implementing the system (100) of Figure 1, according to an embodiment of the present disclosure;
[0025] Further, skilled artisans will appreciate that elements in the figures are illustrated for simplicity and may not have necessarily been drawn to scale. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the figures by conventional symbols, and the figures may show only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the figures with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein.
DETAILED DESCRIPTION
[0026] For the purpose of promoting an understanding of the principles of the invention, reference will now be made to the embodiments illustrated in the figures and specific language will be used to describe the same. It will nevertheless be understood that no limitation of the scope of the invention is thereby intended, such alterations and further modifications in the illustrated system, and such further applications of the principles of the invention as illustrated therein being contemplated as would normally occur to one skilled in the art to which the invention relates.
[0027] It will be understood by those skilled in the art that the foregoing general description and the following detailed description are exemplary and explanatory of the invention and are not intended to be restrictive thereof.
[0028] The terms "comprise", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion such that a process or method that comprises a list of steps does not comprise only those steps but may comprise other steps not expressly listed or inherent to such a process or a method. Similarly, one or more devices or sub-systems or elements or structures or components proceeded by "comprises... a" does not, without more constraints, preclude the existence of other devices or other sub-systems or other elements or other structures or other components or additional devices or additional sub-systems or additional elements or additional structures or additional components. Appearances of the phrase “in an embodiment”, “in another embodiment” and similar language throughout this specification may, but do not necessarily, all refer to the same embodiment.
[0029] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The system, methods, and examples provided herein are illustrative only and not intended to be limiting.
[0030] In addition to the illustrative aspects, exemplary embodiments, and features described above, further aspects, exemplary embodiments of the present disclosure will become apparent by reference to the drawings and the following detailed description.
[0031] In some embodiments, the word ‘user’, ‘learner’, ‘student’ and ‘individual’ used in the description may reflect the same meaning and may be used interchangeably. In some embodiments, the word ‘problems’, ‘series of questions’, ‘task’ and ‘one or more questions’ used in the description may reflect the same meaning and may be used interchangeably. In some embodiments, the word ‘learning stage’, ‘learning level’, used in the description may reflect the same meaning and may be used interchangeably.
[0032] It is to be noted that in some embodiments disclosed herein, completing a task may mean solving a problem, answering a question, doing an assignment, answering a multiple choice question, which may itself require solving a mathematical problem, a problem in physics that requires both a knowledge of concepts in physics and solving a mathematical problem using the concepts, using knowledge of a subject and using logic to arrive at the solution and so on. It is to be noted that, the scope of the term ‘solving a problem’ is not limited to only mathematics and physics as stated above, but the same concepts of mathematics and physics may be implemented for computer programming or any other subject matter. It may not only include the physical sciences but also natural sciences, economics, social sciences, and so on. The disclosed system and method can also be implemented for any academic subject. The tasks related to computer programming may be assigned to the user by just changing the content and the corresponding concepts of any other subject matter.
[0033] The term ‘competency’ and the ‘learning stages’ as referred to herein is explained as follows. As known in the state of the art, the term ‘competency’ is a series of knowledge, abilities, skills, experiences, and behaviors, which leads to effective performance in an individual's activities. Competency is measurable and can be developed through training. It is to be noted that, the term ‘competency’ in regard to the present disclosure, as used herein may be defined as the score obtained by evaluating the completed task presented to the user, based on various factors such as correct response for a task, time taken for a task, concepts referred for a task, and combinations thereof.
[0034] The term ‘learning stage’ in regard to the present disclosure, as used herein may be defined as the learning level that is gradually built by the user by using, attempting to solve, or solving a series of curated problems provided to the user by the disclosed system. The system as disclosed herein classifies the user into a predefined learning stage based on the user competency in completing the task.
[0035] Embodiments of the present disclosure will be described below in detail with reference to the accompanying figures.
[0036] Figure 1 illustrates a high-level block diagram of a machine learning (ML) based system 100 configured for ‘determining user competency’ while completing a task presented to the user. Figure 1 depicts a high-level block diagram of the system 100, where a plurality of users are interacting using the user devices 101-B-N with the system 100 along with a number of tutors (for example a tutor using a user device 101-A) who are also using the system 100 to interact with students using user devices 101-B-N.
[0037] The system 100 as disclosed herein includes modules to record and analyse the interaction of the user with disclosed system 100, while completing the task given by the system 100 using the data capture device or any user device (101). The students and tutors’ interaction with the user devices 101-A, 101-B-N is communicated to web applications 103 using one or more data communication methods. The frontend system 104 communicates this information to the backend system 105 where a server (not shown) is configured for analysing the data associated with interaction. In one embodiment the data associated with interaction of the user with the system 100, is referred to as a first data and is explained in detail below. This students and tutors’ interaction with the user devices 101-A to 101-N is stored in a database 106 and used for determining a second data. The use of second data is explained in detail below with reference to Figure 2. The second data is the data collected in advance or collected historically, based on each interaction of student’s and tutors’ while completing each task of a plurality of tasks, associated with an academic subject, presented to each of the students and tutors. The second data may be defined as the data of interaction of universal set of users interacting with the system 100 for all tasks cumulatively.
[0038] The backend system 105 also has bidirectional communication with two sets of databases. The first database 106 stores one or more of tasks comprising multiple choice questions (MCQs), videos, and assignments. The second database 115 stores the students’ details and parameters. The system 100 as disclosed herein includes the user device (101) comprising a data capture device to record the interaction between the system 100 and the students using the user device 101-A to 101-N, while the students are completing a task. A series of problem-solving interactions of the user are captured and the same is disclosed described in detail in Indian patent application numbered 202241042572 titled “A System for estimating a deficit in knowledge required and method thereof” having priority date of: 25 July 2022., the complete content of which is incorporated herein by reference.
[0039] After a series of interactions of the user, with this disclosed system 100 the output of the system 100 is configured for determining the competency of the user.
[0040] The term ‘determining user competency’ may be defined and explained as follows. The system 100 gives one or more tasks to the user, in other words, one or more questions to be answered. In this process, the system 100 determines the competency level, using a scoring mechanism, and this competency level helps in classifying the user into a predefined learning stage, in each sub-topic and topic, and group of concepts pertaining to each task. There are finite number of concepts pertaining to each sub-topic of the subject matter. The entire process of determining user competency required for classifying the user into a predefined learning stage based on completing the task presented to at least one user is explained further below.
[0041] The system 100 includes modules configured for determining the user’s competency and classifying him into a predefined learning stage for a group of tasks pertaining to a subtopic, topic or a group of topics using a custom designed Machine Learning model with input parameters such as number of attempts, number of time solved time taken, number of times concepts referred, etc. A mentor trained in this subject matter can then take corrective action such as remedial classes, revision classes so that the user’s learning stage can improve to next levels 4 and 5, described later with reference to Figure 5. In a classroom based scenario, either online or actual classroom, the mentor will get to know the learning stages of each student individually for each complexity of tasks.
[0042] The system 100 also includes modules to holistically determine the user’s precise subject matter competency as well as his/her learning levels based on concepts or combination of concepts involved, allowing him to rapidly master the complete topic. The present system 100, based on his competency, and his conceptual level of understanding for solving the problems associated with the topic, classify the user learning stage, thereby enabling the user to achieve mastery with the topic. The disclosed learning system 100 is based on machine learning and has a mechanism of improving its performance in assisting users to learn better with every interaction of all users interacting with the present system.
[0043] A manner in which the system 100 is configured for determining competency while completing a task presented to at least one user and further configured for classifying the at least one user into a learning stage, based on at least one user’s as well as all cumulative user’s data of interaction is described in detail further below. Figure 2 illustrates a detailed view of the system 100 of Figure 1 for determining user competency and further classifying the at least one user into a learning stage while completing the task presented to at least one user, according to an embodiment of the present disclosure.
[0044] Figure 2 illustrates a system 200 for determining user competency and further classifying the at least one user into a learning stage while completing the task presented to at least one user, according to an embodiment of the present disclosure.
[0045] It is to be noted that the system 200 as shown herein may be explained with respect to a single user, however, it should be noted that the present disclosure may be similarly applied to multiple users. Further, the user using the user device 201 may communicate with the system 200 using one or more user devices (exemplary user device 201) through a network (not shown) using a data communication device. Examples of the user device 201 include, but not limited to, a mobile phone, a computer, a tablet, a laptop, a palmtop, a handheld device, a telecommunication device, a personal digital assistant (PDA), and the like. Examples of the network include, but not limited to, a mobile communication network, a Local Area Network (LAN), a Wireless Local Area Network (WLAN), a Wide Area Network (WAN), internet, a Small Area Network (SAN), and the like.
[0046] In one aspect of the embodiment, the system 200 is configured for determining user competency of the user, while completing a task presented to the user using user device 201. In another aspect of the embodiment, the system 200 is configured for determining user competency using scoring module 230 and further classifying the user into a predefined learning stage. Both aspects of the mentioned embodiments are explained in detail below.
[0047] The system 200 includes the user device 201 configured for collecting a first data based on an interaction of the at least one user with the user device 201 while completing the task presented to the at least one user on the user device 201. In one example, the task may include one or more problems to be solved or attempted by at least one user, presented on the user device 201. The first data is defined as the data of the user created by the system 200 while the user is submitting the completed tasks given to them (The term ‘them’ here is the gender-neutral singular in place of her or them and may be used throughout this disclosure in that sense) by the system 200.
[0048] The system 200 is configured to maximize the user’s learning for the specific subject matter with the help of a user device 201 by displaying one or more problems, collecting the user interaction from the data capture device 202 in the user device 201, and transmitting this captured data to the application servers 206. Using the data communication device 210, the user interactions (the first data) are collected by the application server 206 and stored in the database. The data communication device 210 of the user device 201 is configured for transmitting the first data to the server 206 for analysing the first data based on a first set of parameters and a second set of parameters.
[0049] The first set of parameters includes data associated with a submission of each completed task by the at least one user, wherein the data is related to a combination of concepts present in the task, level of difficulty in completing the task, time given to complete the task, time taken by the user to complete the task, number of concepts referred to or used by the user to complete the task, number of attempts by the user to complete the task, result associated with task solved. In one example, the level of difficulty in completing the task or time given to complete the task to the user may be based on decision or opinion of a subject matter expert in the specific academic subject or a consensus opinion of a group of experts and so on. For example, the expert may take into consideration the total number of concepts needed to solve a problem or completing a task as a measure of difficulty.
[0050] The users’ parameters 215 which are the second set of parameters are also collected and sent to a data preprocessor 207. The second set of parameters are determined based on the data associated with each interaction of each user of a plurality of users while completing each task of the plurality of tasks, associated with the academic subject, presented to the each of the plurality of users. For example, the second set of parameters 215 are determined, based on all users’ cumulative data of interaction of those who have interacted with the learning system 200.
[0051] The modules of the system 200 collects, collates, and pre-processes the following first set of parameters associated with the submission of answers to each problem by the user such as problem ID, one or more concepts required to solve each problem, level of difficulty of each problem, time given to solve the problem, time taken by the user to solve the problem, number of concepts referred to by the user to solve this problem, level of help taken, number of attempts by the user to solve this problem, solution to the problem, and whether the problem was solved or not.
[0052] This pre-processed data is then fed to a Machine Learning Engine – ML based competency module 225, in communication with the application server 206 which provides computation of the user’s competence, and accordingly determines the competency score using the scoring module 230 and classifies the user into a predefined learning stage, which is then sent to the user’s feedback device 203. The ML based competency module 225 is implemented with a combination of AI/ML technologies, designed to minimize the ‘Cognitive load’ for the user when learning and solving problems of a subject matter associated with an academic subject.
[0053] To train the Machine Learning model, the second data, which is the totality of all the users’ all interactions with the system are taken. Since this is a pattern (concepts) based approach, all the patterns required for each interaction of all users are captured from the server (206). All patterns in totality are first tokenized so that a Machine Learning engine can comprehend this data. Then each set of patterns required for each interaction with the system are sequenced. Each set of sequenced, tokenized patterns required are then vectorized using embeddings. Similarly, all numerical parameters of the second data are normalized and scaled based on the relative merit of the parameters. This combined data is fed to the specifically designed Machine Learning model for training. The output of this model corresponds to the classification into five learning Stages from level 1 to 5 (as explained with reference to Figure 5).
[0054] The second data is the data collected in advance or collected historically, based on each interaction of each user of a plurality of users while completing each task of a plurality of tasks, associated with an academic subject, presented to each of the plurality of users. The second data may be defined as the data of interaction of universal set of users interacting with the system for all tasks cumulatively. This second data is used for training the ML based competency module 225 iteratively, whereas the first data, pertaining to a specific user using the user device 201 is used for determining competency of at least one user, for classifying the at least one user into a learning stage. This second data as well as the current user’s live data are directed to the application server 206 from where it goes to the data preprocessing 207 where the data is cleaned, correlated, the categorical data is encoded.
[0055] In another embodiment, the model in the ML based competency module 225 is trained for determining a competency for the at least one user indicative of competency of the user with the academic subject based on the analysis of the first data and a learning history of the user. The model is trained for classifying the at least one user into a predefined learning stage based on the determined competency. The term ‘learning history’ may be explained with an example. Let us consider the term ‘learning history’ from the context of a chapter in mathematics such as Trigonometry. The user may be briefed with simple concepts such as basic trigonometric identities. The user may be assigned a simple task (questions) to be solved based on basic trigonometric identities. The various parameters, such as first set of parameters (as explained above, for example, level of difficulty in completing the task, time given to complete the task, time taken by the user to complete the task, number of concepts referred to or used by the user to complete the task) of this user will be recorded by the system as the first data. The ML based competency module 225 of the system 200 is configured to determine the competency of the user based on these initial interactions. Subsequently, more complex problems will be given to this user which may be a combination of basic trigonometric identities, factorizations concepts, simultaneous equations, or triangles. The other topics may belong to concepts of earlier chapters of the same year or any of the earlier classes or years. The ML based competency module 225, is then configured to derive the user's learning history based on the data collected while completing the assigned tasks.
[0056] In one embodiment, the model in the ML based competency module 225 is trained iteratively with second data containing totality of all user’s data with the system such as user interactions, time taken by users, concepts referred by users, and so on. The model works based on concept-based approach in determining the competency of the user. This iterative training of the model is done in a batch, for example, on weekly basis to ensure that the results are accurate.
[0057] Once the ML model is trained in a batch process with a weekly periodicity, it is ready to be used for predicting the Learning Stage of a specific user’s specific interaction with the system by using the first data. This first data has to go through the pre-processing steps described above in Figure 1 and is then fed to the trained ML model which predicts the Learning Stage for this specific user for this particular interaction with the system.
[0058] However, while using the scoring mechanism for determining the competency of the user using the user device 201, the competency is computed based on the first data. The trained data is used for classifying the at least one user into a predefined learning stage for completing a task presented to the at least one user, using the output of the model and the analysed first data. The output of the model is user classified into a predefined learning stage. The model classifies the predefined learning stage based on ‘Blooms Taxonomy’ which classifies learning into five stages (as explained with reference to Figure 5).
[0059] The scoring mechanism is explained in detail herein. The determination of competency is performed using scoring module 230 which analysis the first data which is the user interaction while completing the task and the data pertaining to learning history of a particular user. By using a scoring module 230 with scoring mechanisms, a user’s competency score is calculated by the model. The input to this model is concepts retrieved from the server for the task given to the user. The concepts retrieved are analysed and tokenized to comprehend the data. The concepts are grouped into set as required for computing the score for the first data that is the user interaction while completing the task. It is this model which computes the score of the user for the given task.
[0060] The steps for scoring mechanisms includes retrieving a plurality of concepts associated with the first data each time the at least one user interacts with the user device (201) while completing the task presented to the at least one user on the user device (201). For example, the user may be presented with Task- A in a topic trigonometry, the system 200 retrieves the concepts related to trigonometry for the given task.
[0061] Further the scoring module 230 is configured for analysing each group of concepts of the plurality of concepts associated with the first data each time the at least one user interacts with the user device while completing the task presented to the at least one user on the user device. For example, the user may be presented with the Task-A involving trigonometry which is vast topic. The concepts of this topic are grouped into sets required by the presented task to the user. If a trigonometry equation is presented to the user as task, solving the equation requires concepts such as trigonometry identities, factorization and the trigonometric values. These set of concepts are grouped with the task to track the user competency.
[0062] Further the scoring module 230 is configured for scoring the analysed group of concepts for encoding and embedding into a memory coupled to a competency module 225 of the server for determining a competency score of the at least one user. As known in the state of the art, the Word2vec is a method used for creating word embeddings and is used to obtain embedded group of concepts and the same has been used herein. Word embeddings is a combination of word tokenization and embeddings processes, since ML mathematical models can only process numbers and cannot process words. There are multiple algorithms for embeddings such as for example, Word2Vec, Glove, Embedding, and similar such algorithms known in the state of art. Embedding has two uses. The first one is dimensionality reduction, which translates into reduction in computations. In one example, the knowledge may be a combination of 500 concepts. Downstream in the ML model, it will require computations which are an exponential order of this number. By embedding this to say 50 for example, the computations are reduced by an order of magnitude. The second purpose of the embedding of concepts is to cluster the group of concepts for further processing. Embeddings make it easier to do machine learning on large inputs such as sparse vectors representing words.
[0063] In an exemplary embodiment, the user is presented with Task- A which relates to solving for ‘x’ in a trigonometry equation and the example question is given below:
-2 sin2 x – 3 cos x + 3= 0
[0064] The above task involves understanding of one or more concepts to be applied for completing it. The task involves the concept of trigonometric identities to be applied first and secondly, factorization to applied and finally trigonometric values. These concepts must be applied to the task in the same sequence to complete the task with right solution. Hence, the user is required to complete the task with the understanding of concepts involved in the same sequence to answer the task right.
[0065] In another exemplary embodiment, the user is presented with Task-B, Task-C, where the task involves understanding of different and plurality of concepts in different sequence of applying to correctly answer the task and complete it. Each task presented to the user may involve understanding different concepts which are applied to complete the task in different sequence.
[0066] The ML based competency module 225 then outputs the determined user’s competence in completing a task. Consequently, it also predicts user’s learning stage by classifying the user into a predefined learning stage or stage of learning based on the competency determined for the task completed. The system 200 enables the user to know his competency and learning stage for the completed task so as to improve his learning stage and get mastered in the subject.
[0067] The steps for classifying the user into predefined learning stage involves receiving the competency score for the user for each of the sub-topic for each of the chapter for the subject matter. For example, the chapter polynomials may have sub-topics types of polynomials such as linear polynomial, quadratic polynomial, cubic polynomial. For each of the sub-topic a competency score is determined.
[0068] Further, by calculating the average of each of the sub-topic of a chapter the learning stage of the user is determined. The Learning Stage for a sub-topic for this specific user will be computed by averaging the Learning Stages for all latest interactions within this sub-topic, for this specific user. The Learning Stage (1 to 5) for a Chapter (Topic) for the subject matter will be computed by averaging the Learning Stages of all sub-topics (step 3 above) within this Chapter, for a specific student.
[0069] For example, the chapter polynomial having subtopics linear polynomial, quadratic polynomial and cubic polynomial, where each one has competency score and to classify the learning stage for the chapter polynomial, the average competency score of the sub-topics are taken. Using the average competency score of the sub-topics of the chapter, the learning stage of the user for the chapter is determined by mapping the average score with the pre-defined learning stage.
[0070] Thus, the system 100 and 200 as disclosed includes modules and a ML based model trained and configured to enable the user to achieve mastery in a particular subject matter in the best possible manner. The system 100 and 200 as disclosed in Figure 1 includes modules for providing the user, a series of assignments to solve, records the user’s interaction with this analytics system, such as problems solved, problems attempted but not solved, how many times attempted/solved, levels of problems, concepts, combination of concepts involved, etc. These specific items analysed by the system 100 and 200 go beyond the specific class or grade or chapter of the subject matter for the user, thereby ensuring that the fundamental concepts and knowledge which is lacking or if the student is weak in a particular subject matter, such topics associated with the subject matter are exhaustively covered. In one embodiment, the application server 206 and the modules present in the server 206 captures the different journeys taken by different users with their unique capabilities, competency to ensure their mastery of the subject matter in an efficient way.
[0071] The disclosed system 100 and 200 is a self-optimizing system which makes users learn a subject matter faster and in a better way by analysing the user interaction with the system by identifying the competency score based on the task completed and classifying the user into a predefined learning stage. The disclosed system 100 and 200 consolidates his mastery in a subject matter.
[0072] Figure 3 illustrates an example flow chart depicting a method 300 for determining user competency and classifying at least one user into a predefined learning stage, based on at least one user’s as well as all cumulative user’s data of interaction. Figure 3 may be described from the perspective of a processor 225 that is configured to execute computer-readable instructions to carry out the functions of the modules (described shown in Figure 2) of the system 200. In particular, the steps as described in Figure 3 may be executed for determining user competency and classifying at least one user into a predefined learning stage. Each step is described in detail below.
[0073] At step 342, the user is presented with a task for completion. In one example, the task may include a video, a reading material of subject matter for him to understand the various topics and sub-topics in a chapter of a subject matter. At step 344, the user is then presented with a series of MCQs (Multiple Choice Questions) so that his level of understanding of the sub-topic is tested and captured. Subsequently, at step 348(a) MCQ registry records the number of attempts taken by the user to complete the task. Here, the distinction must be emphasized that the user has learned the concepts, and he may not have competency to complete the task. According to the method 300, the user will now be presented, at step 346, with simple task related to the sub-topics only. The user interaction on completing the task is recorded along with the level of complexity of the task. At step 348(b), the assignment registry records the number of times attempts, number of times solved, concepts referred by user, concepts learned by the user, time taken to solve, time given to solve the task. These user interaction data is passed on to the ML based competency module 225, at step 350 which determines the user competency and classifies the user into a predefined learning stage. The ML based competency module 225 provides the analysed results, at step 352 to the user through the feedback device 203 of the user device 201. Once all topics, chapters are covered the user is presented with complex task at step 354. The task presented to the user consist of different levels of complexity on a particular sub-topic, topic, and chapter to make the user achieve mastery in predefined learning stage.
[0074] Each task presented to the user may require understanding and application of one or more concepts for completing the task. The number of concepts required for each of the task may vary according to the level of complexity of the task. The concepts required for completing a problem may be from the user’s current progressive class or grade, the previous classes or grades. The terms ‘task’ is interchangeable with ‘assignment’, ‘problem’ in the disclosure.
[0075] Once the user (200) has successfully navigated through the complex problems, with the help of the ML based competency module 225, which spans it may also contain concepts from different chapters, and also may contain concepts from previous classes, the User/Mentor can take corrective actions based on feedback given to the user device. The ML based competency module 225 provides insightful feedback to user with unique learning content such as exercises, homework based on the determined competency and the classified learning stage of the user. Similarly, the ML based competency module 225 provides feedback to the mentor with a holistic view of conceptual understanding among users to take corrective action such as revision class, remedial class, extra class on the topic of a particular subject where the user needs attention.
[0076] Figure 4(a) illustrates an overall flowchart depicting method 400 for determining competency of a user and classifying the user into a predefined learning stage. Figure 4(a) may be described from the perspective of a processor 225 that is configured to execute computer-readable instructions to carry out the functions of the modules (described shown in Figure 2) of the system 200. In particular, the steps as described in Figure 4(a) may be executed for determining user competency and classifying at least one user into a predefined learning stage. Each step is described in detail below. The order in which the method steps are described below is not intended to be construed as a limitation, and any number of the described method steps can be combined in any appropriate order to execute the method or an alternative method. Additionally, individual steps may be deleted from the method, without departing from the spirit and scope of the subject matter described herein.
[0077] At step 412, the method 400A includes collecting a first data based on an interaction of the at least one user with the user device 201. A user device (201) is configured for collecting a first data based on an interaction of the at least one user with the user device (201) while completing the task presented to the at least one user on the user device (201). For example, this step 412 of the method 400 captures user interaction with system 200 towards solving topic-wise problems.
[0078] At step 414, the method 400A includes transmitting the first data to a server (206). A data communication device (210) configured for transmitting the first data to a server (206) for analysing the first data based on first set and second set of parameters. For example, this step 414 of the method 400A processes the inputs from the user as well as another user cumulatively.
[0079] Furthermore, at step 416, the method 400A includes training the model iteratively with the second data received from the server 206. The second data includes the data based on each interaction of each user of a plurality of users while completing each task of a plurality of tasks, associated with an academic subject, presented to each of the plurality of users. For example, this step 416 of the method 400A includes iteratively training the model in a batch process with a weekly periodicity with all user interaction data of all the users for determining and predicting the results accurately.
[0080] Lastly, at step 418, the method 400A includes determining competency of a user using scoring mechanism and classifying the user into a predefined learning stage based on competency. For example, this step 418 of the method 400A analyses the user competency at that instant in real time and classifies the learning stage of the user based on the competency of the presented task.
[0081] The method for determining the competency of the user includes an implementation of a scoring mechanism. The input for the scoring mechanism is concepts retrieved from the server for the task given to the user. The concepts retrieved are analysed and tokenized to comprehend the data. The concepts are grouped into set as required for computing the score for the first data that is the user interaction while completing the task. It is this model which computes the score of the user for the given task.
[0082] The learning stage of the user is determined by calculating the average competency calculating an average competency score based on the determined competency score, for each group of concepts associated with each of the plurality of task presented to the at least one user; and using the calculated average competency score for mapping with the predefined learning stage for classifying the learning stage of the at least one user.
[0083] Further, based on the determined competency and learning stage the user through his feedback device is communicated with the feedback generated by the ML based competency module for taking corrective action at the earliest.
[0084] Figure 4 (b) illustrates the flowchart 400B depicting the logic flow in the application server, the ML based competency module, and the user system, according to the embodiments of the present disclosure. The flowchart shows the process for determining the competency of the user and classifying the user into predefined learning stage. The flowchart 400 also shows that this system 200 determines the competency of the user at any instance. Figure 4(b) may be described from the perspective of a processor 225 that is configured to execute computer-readable instructions to carry out the functions of the modules (described shown in Figure 2) of the system 200. In particular, the steps as described in Figure 4(b) may be executed for determining user competency and classifying at least one user into a predefined learning stage. Each step is described in detail below. The order in which the method steps are described below is not intended to be construed as a limitation, and any number of the described method steps can be combined in any appropriate order to execute the method or an alternative method. Additionally, individual steps may be deleted from the method, without departing from the spirit and scope of the subject matter described herein. The method 400B enables the user to become competent to complete any task presented to him on a particular subject matter and gain mastery in the subject matter at all the levels in learning stage, so that user may face any task without any fear.
[0085] The method (400B) includes the step 472 where the user interacts with the system 200 for completing the task comprising an assignment or problem presented to the user on the user device. At step 474, the first data based on the user interaction is collected and transmitted to the application server. The first data is defined as the data of the user created by the system 200 while the user is submitting the completed tasks given to them by the system 200. The server is configured to process (at step 476) the inputs (the first data) from the user and the second data. The application server is configured for receiving the first data for training a model iteratively, using a second data. The second data is the data collected in advance or collected historically, based on each interaction of each user of a plurality of users while completing each task of a plurality of tasks, associated with an academic subject, presented to each of the plurality of users. The second data may be defined as the data of interaction of universal set of users interacting with the system for all tasks cumulatively. This second data is used for training the model, whereas the first data, pertaining to a specific user using the user device is used for determining their competency. This second data as well as the current user’s live data are directed to the application server from where it goes to the data preprocessing where the data is cleaned, correlated, the categorical data is encoded. At step 478, the user’s competency is analysed at the current instance. The user’s competency is determined using scoring module 230 for the user, based on analysis of the first data. The model is trained for determining competency of at least one user using scoring module 230 based on the first data and classify the at least one user into a predefined learning stage, based on determined competency of the at least one user.
[0086] At step 482, the learning stage of the user is classified based on the average competency of each of the task presented to the user. The average competency score is calculated based on the determined competency score for each of group concept of the task presented to the user. At step 484, the method includes communicating the feedback to the user in terms of learning stage of the user.
[0087] Figure 5 illustrates a pictorial representation 500 showing a classification of predefined learning stages to classify the at least one user based on determined competency of the at least one user, according to an embodiment of the present disclosure. Figure 5 shows the learning stages based on competency which is a structure classified based on bloom's taxonomy. This learning stages classification is highly non-linear due to parameters such as number of times various problems are attempted/solved, etc. and is based on ML based competency module. The aim of this disclosed system is to ensure rapid elevation of a user from learning stage, for example, from, Stage 1 to Stage 5.
[0088] The reference numeral 501 depicts the learning stage of the user classified as “Stage 1- Learning stage - Remember stage”. This stage is an initial stage in the learning stage classification. Based on the ML based competency module, if a user is classified into “Learning stage” 501, the user may have ability to solve basic problems with minimal concepts. The level of complexity of task presented to the user at this stage are very basic with primary principle involved in a particular sub-topic of a subject matter. There is no time limit set at this stage and user can refer to concepts for completing the task. The number of attempts taken by the user is also taken into consideration for progressing in learning.
[0089] Each task presented to the user may have a primary concept and secondary concept. A primary concept is a current curriculum related concept and secondary concept may belong to previous class curriculum which may be required to complete the task.
[0090] If the user is successful in stage 501, he may traverse to the next level (502) that is “Stage 2- Competency stage 1 - Apply stage”. The user may be classified into this stage if he completes a similar basic level task as given in stage 501, but the user does not refer to the concept related to the task. The user remembers the concept from Stage 501 and applies it in Stage 502 task. Also, the Stage 502 tasks is presented to the user with time limit i.e., the user needs to complete the task within the given time.
[0091] The successful user in Stage 502, progresses to the next stage 503. The next stage 503 is Competency stage i.e., Analysis stage”. The user is classified into this stage if the user completes task with medium complexity i.e., level 2, level 3 tasks. These levels of problems may contain two or more primary concepts in correct sequence to be solved and classified as medium and high in complexity. Also, the user can refer to concepts of related to task presented and there is no time limit set, but the number of attempts taken by the user is taken into consideration.
[0092] The next stage 504 is Competency stage i.e., Analysis stage. The user is subject to similar kind of task as presented in previous stage and user can refer to the concepts related to the task for completing the task but here the task is presented to the user along with the time.
[0093] The last stage 505 of classification of learning stage is Competency stage, i.e., the Synthesis stage. The user is classified into this stage if the user completes the task in correct sequence from various concepts in sub-topic, topic, chapter in the given time without referring the concepts related to the task.
[0094] The classification of the user’s learning stage is a non-linear process since the user navigates through the five stages having various criteria at each stage and involving a large set of data to be recorded and computed. A user with high calibre may navigate the learning stage and may be different from a user with average grade. This nature of the user would affect factors such as the number of problems attempted/solved, number of times a specific problem was attempted/solved, time taken to solve a specific problem, etc., while determining competency and classifying user into a predefined learning stage. With the assistance of the ML based competency module, the system will help to accurately determine and classify the learning stage to achieve mastery for the user in the subject matter.
[0095] Thus, the system 200 as disclosed herein with reference to Figure 2 is configured for classifying the user into a predefined learning stage (Figure 5) based on the determined competency. The learning stages in are scaled from 1 to 5 levels, the levels being determined in Figure 5. The learning stages is also referred in this document as ‘learning levels. This classification of learning levels is highly nonlinear in nature, and the embodiment of the present disclosure discloses a customized Machine Learning model for the same. As an example, if a student reads through a chapter in math’s, for example trigonometry of class X, including solved examples, most likely his ‘learning stage’ for many problems may be of ‘level 2’, as against to levels 4 and 5 required to ace any tests.
[0096] Figure 6 illustrates an example task presented to the user on the user device. The task includes a problem statement, and the user may need an understanding of one or more concept for completing the task. The concepts involved to complete the presented task may be associated with concepts of present class of the user and from previous class of the user. The embodiment of the present disclosure determines the competency of the user using scoring module 230 and classify the user into the predefined learning stage. Based on the determined competency and learning stage the system may recommend corrective action to the user or mentor. The user is provided with unique learning content such as homework, exercises, assignments to overcome the shortcomings in various levels. Similarly, the mentor is recommended with revision class, remedial class, extra class on particular subject matter based on the holistic view of user’s competency.
[0097] Figure 7 is a block diagram of a computing device utilized for implementing the system 200 of Figure 2. The modules of the system 200 described herein are implemented in the computing devices. The computing device 700 comprises one or more processor 702, one or more computer-readable RAMs 704 and one or more computer-readable ROMs 706, all being interconnected to one or more buses 708. Further, the computing device 700 includes a storage device 710 that may be used to execute operating systems 720 and modules existing in the system 100. The various modules of the system 200 may be stored in a storage device 710. Both the operating system and the modules existing in the system 100 and server 110 are executed by processor 802 via one or more respective RAMs 804 which typically include cache memory.
[0098] Examples of storage devices 710 include semiconductor storage devices such as ROM 706, EPROM, flash memory, or any other computer-readable tangible storage device 710 that can store a computer program and digital information. Computing device also includes R/W drive or interface 714 to read from and write to one or more portable computer-readable tangible storage devices 728 such as a CD-ROM, DVD, and memory stick or semiconductor storage device. Further, network adapters or interfaces 712 such as a TCP/IP adapter cards, wireless WI-FI interface cards, or 3G or 4G wireless interface cards or other wired or wireless communication links are also included in computing device 700. In one embodiment, the modules existing in the system 100 may be downloaded from an external computer via a network for example, the Internet, a local area network or other, wide area network and network adapter or interface 712. Computing device 700 further includes device drivers 718 to interface with input and output devices. The input and output devices can include a computer display monitor 718, a keyboard 724, a keypad, a touch screen, a computer mouse 726, and/or some other suitable input device.
[0099] While specific language has been used to describe the disclosure, any limitations arising on account of the same are not intended. As would be apparent to a person skilled in the art, various working modifications may be made to the method in order to implement the inventive concept as taught herein.
[00100] The figures and the foregoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, orders of processes described herein may be changed and are not limited to the manner described herein. Moreover, the actions of any flow diagram need not be implemented in the order shown; nor do all of the acts necessarily need to be performed. Also, those acts that are not dependent on other acts may be performed in parallel with the other acts. The scope of embodiments is by no means limited by these specific examples. Numerous variations, whether explicitly given in the specification or not, such as differences in structure, dimension, and use of material, are possible. The scope of embodiments is at least as broad as given by the following claims. ,CLAIMS:WE CLAIM:

1. A system (200) for determining competency of at least one user, for classifying the at least one user into a predefined learning stage, the system (200) comprising:
a user device (201) configured for collecting a first data based on an interaction of the at least one user with the user device (201) while completing the task presented to the at least one user on the user device (201);
a data communication device (210) of the user device (201) configured for transmitting the first data to a server (206) for analysing the first data based on a first set of parameters and a second set of parameters; and
a server (206) configured for receiving the first data and a second data for: training a model iteratively, using a second data, the second data being the data based on each interaction of each user of a plurality of users while completing each task of a plurality of tasks, associated with an academic subject, presented to each of the plurality of users;
wherein the model is trained for:
determining the competency of the at least one user using a scoring mechanism, wherein the scoring mechanism is based on analysis of the first data, and
classifying the at least one user into the predefined learning stage, based on determined competency of the at least one user.

2. The system (200) as claimed in claim 1, the wherein the scoring mechanism is based on analysis of the first data and steps for scoring mechanism comprises:
retrieving a plurality of concepts associated with the first data each time the at least one user interacts with the user device (201) while completing the task presented to the at least one user on the user device (201);
analyzing each group of concepts of the plurality of concepts associated with the first data each time the at least one user interacts with the user device (201) while completing the task presented to the at least one user on the user device (201); and
scoring the analysed group of concepts for encoding and embedding into a memory coupled to a competency module 225 of the server 206 for determining a competency score of the at least one user.

3. The system (200) as claimed in claim 2, the steps for classifying the user into predefined learning stage comprises:
receiving the determined competency score for the at least one user;
calculating an average competency score based on the determined competency score, for each o group of concepts associated with each of the plurality of task presented to the at least one user; and
using the calculated average competency score for mapping with the predefined learning stage for classifying the learning stage of the at least one user.

4. The system (200) as claimed in claim 1, wherein the first set of parameters includes data associated with a submission of each completed task by the at least one user; wherein the data is related to a combination of concepts present in the task, level of difficulty in completing the task, time given to complete the task, time taken by the user to complete the task, number of concepts used by the user to complete the task, number of attempts by the user to complete the task, result associated with task solved.

5. The system (200) as claimed in claim 1, wherein the second set of parameters are determined based on the data associated with each interaction of each user of a plurality of users while completing each task of the plurality of tasks, associated with the academic subject, presented to the each of the plurality of users.

6. The system (200) as claimed in claim 1, wherein training the model iteratively for generating a feedback:
to the at least one user for learning and completing the task presented to at least one user; and
to a mentor of the at least one user for providing a holistic view of understanding of a concept of the at least one user to take corrective action.

7. The system (200) as claimed in claim 1, wherein the feedback comprises recommending corrective actions for learning, specific learning contents comprising exercises, homework based on the classified predefined learning stage of the at least one user.

8. A method (400) for determining competency of at least one user, for classifying the at least one user into a learning stage, the method (400) comprising:
collecting a first data from a user device (201), based on an interaction of the at least one user with the user device (201) while completing the task presented to the at least one user on the user device (201);
transmitting the first data to a server (206) using a data communication device (210) of the user device (201) for analysing the first data based on a first set of parameters and a second set of parameters; and
receiving the first data and a second data from the server (206) for: training a model iteratively, using a second data, the second data being the data based on each interaction of each user of a plurality of users while completing each task of a plurality of tasks, associated with an academic subject, presented to each of the plurality of users;
wherein the model is trained for:
determining the competency of the at least one user using a scoring mechanism, wherein the scoring mechanism is based on analysis of the first data, and
classifying the at least one user into a predefined learning stage, based on determined competency of the at least one user.

9. The method as claimed in claim 8, wherein the steps for scoring mechanism based on the first data for determining the competency and classifying the user into predefined learning stage, comprises:
retrieving a plurality of concepts associated with the first data each time the at least one user interacts with the user device (201) while completing the task presented to the at least one user on the user device (201);
analyzing each group of concepts of the plurality of concepts associated with the first data each time the at least one user interacts with the user device (201) while completing the task presented to the at least one user on the user device (201); and
scoring the analysed group of concepts for encoding and embedding into a memory coupled to a competency module 225 of the server for determining a competency score of the at least one user.

10. The method as claimed in claim 8, wherein the steps for classifying the user into predefined learning stage comprises:
classifying the at least one user into a predefined learning stage based on the determined competency score for the at least one user;
calculating an average competency score of each of the group of concepts associated with each of the plurality of task presented to the at least one user; and
using the calculated average competency score for mapping with a predefined learning stage for classifying the learning stage of the at least one user.