WO2015047424A1

WO2015047424A1 - Personalized learning system and method thereof

Info

Publication number: WO2015047424A1
Application number: PCT/US2013/062777
Authority: WO
Inventors: Elliott Paul LEVINE; Sara Rebecca AGARWAL; Kyle Curtis MCBRIDE; Vere Chambers CHAPPELL; Thomas William GREAVES
Original assignee: Hewlett-Packard Development Company, L.P.
Priority date: 2013-09-30
Filing date: 2013-09-30
Publication date: 2015-04-02

Abstract

Implementations of the present disclosure disclose a system and method for providing personalized learning. According to one implementation, a personalized learning interface for facilitating interaction with an operating user is displayed on a client device. A plurality of relevant remediation resources are ranked based on a profile information and assessment data associated with the operating user. Upon detecting a learning assistance event, an ordered list of the ranked remediation resources is displayed on the personalized learning interface for selection by the operating user.

Description

PERSONALIZED LEARNING SYSTEM AND METHOD THEREOF

BACKGROUND

[0001] Today, emerging technologies are now making the promise of alternative forms of education possible. For example, adaptive learning, or e- Learning, which can be defined broadly as the use of electronic technology to facilitate learning including computer-assisted learning and network-enabled technologies, has garnered significant market attention in recent years. Generally, e-Learning aims to capitalize on a growing need within the education market - one that goes beyond the digital classroom to a personalized learning experience for students - giving parents, teachers and school administrators the ability to foster and manage a highly interactive and collaborative learning environment.

BRIEF DESCRIPTION OF THE DRAWINGS

[0002] The features and advantages of the present disclosure as well as additional features and advantages thereof will be more clearly understood hereinafter as a result of a detailed description of implementations when taken in conjunction with the following drawings in which:

[0003] FIG. 1 illustrates a simplified block diagram of a personalized learning system according to an example implementation.

[0004] FIG. 2 illustrates a more detailed block diagram of the personalized learning system according to an example implementation.

[0005] FIG. 3 illustrates a sample screen shot of a personalized learning dashboard interface according to an example implementation.

[0006] FSG. 4 illustrates a sequence diagram for implementing the personalized learning system according to an example implementation.

[0007] FIG. 5 illustrates a simplified flow chart of the processing steps of a method for personalized learning in accordance with an example implementation.

[0008] FIG. 8 illustrates a simplified flow chart of the processing steps for ranking remediation resources in the personalized learning system in accordance with an example implementation. [0009] FSG, 7 illustrates a system flow chart for Implementing a personalized learning system in accordance with an example implementation.

DETAILED DESCRIPTION OF THE INVENTION

[00010] The following discussion is directed to various examples. Although one or more of these examples may be discussed in detail, the implementations disclosed should not be interpreted, or otherwise used, as limiting the scope of the disclosure, including the claims. In addition, one skilled in the art will understand that the following description has broad application, and the discussion of any implementations is meant only to be an example of one implementation, and not intended to intimate that the scope of the disclosure, including the claims, is limited to that implementation. Furthermore, as used herein, the designators "A", "B" and "N" particularly with respect to the reference numerals in the drawings, indicate that a number of the particular feature so designated can be included with examples of the present disclosure. The designators can represent the same or different numbers of the particular features.

[00011 ] The figures herein follow a numbering convention in which the first digit or digits correspond to the drawing figure number and the remaining digits identify an element or component in the drawing. Similar elements or components between different figures may be identified by the user of similar digits. For example, 143 may reference element "43" in Figure 1 , and a similar element may be referenced as 243 in Figure 2. Elements shown in the various figures herein can be added, exchanged, and/or eliminated so as to provide a number of additional examples of the present disclosure. In addition, the proportion and the relative scale of the elements provided in the figures are intended to illustrate the examples of the present disclosure, and should not be taken in a limiting sense.

[00012] Typically, a student proceeds through a course of study, such as an online course or textbook. When the student reaches a point where they are having difficulty, there are very few options to resolve their personal learning issue. Teachers, commercial online courses and individual end-of-course tutorials are some of the more common prior solutions to the personalized learning challenge.

[00013] Teachers are highly desirable in the classroom as a highly-trained teacher is invaluable for aiding students through a course. Even the best teachers, however, suffer from limited time (on a per-student basis) in addition to limited familiarity with potentially thousands of available resources for a specific curriculum standard. Furthermore, teachers often have no way of recognizing which available resource will be most effective for a specific student and their specific set of personalization requirements. Also, for a variety of reasons, some students in need of remediation may not wish to ask the teacher for assistance.

[00014] Another prior solution is personal customization within an online or digital course. The disadvantage here is that no single course can include all of the materials required to effectively personalize a response for each specific student. The ability of an online course to do so is often precluded by course design strategies, licensing issues, testing issues, and the practical limit on the size of a learning unit. As a result, curriculum publishers tend to publish materials that hopefully reach the largest potential sub-audience. The result is a product that might be a decent fit for every student, but is far from a perfect fit for any one student.

[00015] Still other solutions involve providing personalization at the end of a course or unit, or after a test is given. The primary disadvantage here is cycle time. The student is not offered a personalized remediation option until, on average, three to four days after a learning failure occurs. Sn some cases, the remediation happens a year later when the student must retake the course because they failed it the first time. Moreover, research indicates that remediation is most effective when administered closer to the time of need. Another disadvantage here is the lack of an available remediation unit that is tailored specifically to the personalization profile of the student in need. Since there is insufficient data to guide the teacher or other educational tool (e.g., online course), there is a low probability that the proffered remediation will be effective for the specific student requesting learning assistance. [00016] In short, the prior attempts fail to fully personalize a curriculum unit to account for ail potential personalization factors, which may be quite numerous. These factors run the gamut from differences in language, reading level, learning style, location and size of gaps in required prerequisite knowledge, visual acuity, vocabulary and many others. Thus, there is a need in the art for a personalized course of instruction that provides more immediate intervention to students when needed.

[00017] Implementations of the present invention provide a system and method for personalized learning. According to some examples, the system and method provides a personalized activity plan and intervention loop outside the closed course. The intervention loop is designed to be accessed at the moment the student is in need, not necessarily at the end of the lesson or after a test. Moreover, the intervention is multi-faceted and may include web resources chosen through sophisticated statistical analytics and an on-demand question/answer system, which aids in identifying those resources found to be most effective for specific, similarly-situated students.

[00018] Referring now in more detail to the drawings in which like numerals identify corresponding parts throughout the views, FIG. 1 illustrates a simplified block diagram of a personalized learning system according to an example implementation. As shown in the present example, the personalized learning system 100 includes a network service provider 1 10 and client devices 105a and 105b operated, for example, by a student 101 and an educator 103.

[00019] Service provider 1 10 may represent a cloud computing architecture having at least one computer system or host server, which is operational with numerous other general purpose or special purpose computing system environments or configurations and may include, but is not limited to, personal computer systems, server computer systems, mainframe computer systems, laptop devices, multiprocessor systems, microprocessor-based systems, network personal computers, and distributed cloud computing environments that include any of the above systems or devices, and the like. Moreover, the host server provider system 1 10 may be described in the general context of computer system-executable instructions stored on a computer readable storage, such as program modules, being executed by a computer system. The host server or service provider 1 10 further includes a processing unit 107 and personalized learning engine (PLE) comprising of the recommendation and analysis module 1 14a and the student and resource database 1 14b.

[00020] Processor 107 may be, at least one central processing unit (CPU), at least one semiconductor-based microprocessor, at least one graphics processing unit (GPU), other hardware devices suitable for retrieval and execution of instructions stored in machine-readable storage medium 109, or combinations thereof. For example, the processor 107 may include multiple cores on a chip, include multiple cores across multiple chips, multiple cores across multiple devices, or combinations thereof. Processor 107 may fetch, decode, and execute instructions to implement the approaches of the personalized learning system. As an alternative or in addition to retrieving and executing instructions, processor 107 may include at least one integrated circuit (IC), other control logic, other electronic circuits, or combinations thereof that include a number of electronic components for performing the requisite functionality.

[00021 ] Machine-readable storage medium 109 may be any electronic, magnetic, optical, or other physical storage device that contains or stores executable instructions. Thus, machine-readable storage medium may be, for example, Random Access Memory (RAM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), a storage drive, a Compact Disc Read Only Memory (CD-ROM), and the like. As such, the machine-readable storage medium can be non-transitory. As described in detail herein, machine- readable storage medium 109 may be encoded with a series of executable instructions for providing the personalized learning system.

[00022] The student and resource database 1 14b includes profile information relating to individual students and various groups of students, in addition to educational resource content for providing specific and ranked intervention tools (e.g., web resources, database, tutors) to a requesting user (i.e., student). For example, resources and educational content may include a formative assessment test item database of standards for various states, Knovation® netTrekker ® correlated resources, the National Repository of Online Courses (NROC), and similar online or other educational resources.

[00023] More particularly, implementations described herein represent an external feedback loop rather than an internal loop within a particular product as in the prior solutions. Thus, the proposed system may essentially have an unlimited set of interventions, of ail types, that addresses ail personalization factors of the student user irrespective of a particular course curriculum (i.e., student is the main focus). That is, personalization may be accomplished in any curriculum, or any database or resource. Furthermore, the remediation or intervention resources may include multiple independent sets of learning tools such as external web resources, curriculum products, search engine results, tutors, and/or peers for example. And for each remediation resource above, the system ranks and provides an order list of the ranked resources for the student to select for the desired assistance as will be described in further detail below.

[00024] In certain examples, computing devices 105a and 105b represent a personal computing device operated by a student 100 and teacher 103 respectively. The computing devices 105a and 105 may be, for example, a notebook computer, a tablet computing device, a portable reading device, a wireless e-reading device, a mobile phone, a server, a workstation, a special purpose machine, or any other personal computing device configured with network access. The computing devices 105a and 105b are configured to run a web browser 125a and 125b for hosting a web-based user interface (e.g., personalized learning dashboard). In one example implementation, the personalized user interface 127a and 127b will display different items for the student user 101 and the educator user 103 as will be further described in the example scenarios below.

[00025] In one example scenario, a student 101 launches content and subject modules on their electronic device 105a. Since the PLE stores student profile information in the student data and resource database 1 15, all personal preferences (e.g., style, speed, font, colors, etc.) are loaded onto the dashboard interface 127a upon log-on. Before the first instructional unit, the PLE may ask the student if they are comfortable with basic terminology ~ words that should be known from previous lessons -- thai will be important for success in the lesson. If the student 101 indicates a lack of knowledge with respect to the basic terminology, then the PLE may direct the student 101 to a glossary or other material until the user feels more comfortable in proceeding. The PLE may do this, for instance, when it knows student did not score well on the previous lesson when these topics were initially introduced. The student 101 interacts with material on the dashboard 127a and portable device 105a and views the videos and graphics as available. The student 101 may also have the option to read transcripts of the videos for easier comprehension of accents, styles, etc. At the end of the material, the student 101 is presented with questions that evaluate his comprehension of the material. The student 101 may also be given the opportunity to rate the material (where permitted and applicable) so that the PLE may take this data, which is added to the database and then utilized by the algorithms for other similar student profiles, and refresh the ratings and resource rankings in real-time.

[00026] Still further, through the PLE, a student 101 may enter a request for teacher assistance for a concept that they are presently struggling with. Secondary remediation options may also be presented and include texting a friend, picking a different source of content that is rated highly by others, watching a video, chatting with a study group that has scored well in this topic already and the like. Since the student 101 chose to ask a question directly to the educator 103, the educator 103 may immediately receive a notification on her dashboard 127b and proceed to work with the student 101 on a one-on-one basis. After a brief conversation, the educator 103 may suggest reviewing the topic from a different source. Thereafter, the student 101 may discover a highly- rated intervention resource on the dashboard interface 127a with more interesting or comprehensible content. After reviewing this material, student 101 may again load the mini quiz and discover a completely different set of questions. However, since the student now has better grasp on the underlying concepts, the student is able to answer the questions and easily passes the minimum requirement exam.

[00027] in another example scenario, educator 103 may be notified of new content available for their class via her dashboard 127b. In the event the content is open-sourced and not mandated by the state as core curriculum, educator 103 may need to view the material and make a recommendation as to whether or not it should be incorporated into the student curriculum. Educator 103 views the material, assessment questions and/or any metadata or other assessment content might in order to make a qualified decision. The educator may also review the PLE's recommendation for what kind of students could use this material, their characteristics, demographics and other personalization criteria as per the PLE specifications. Upon review and approval by the educator 103, the content may be made available in the content queue for the appropriate grade and subject along with the relevant metadata about the content.

[00028] FIG. 2 illustrates a more detailed block diagram of the personalized learning system according to an example implementation. As shown here, the personalized learning system includes content providers 215, users 205, network 230, service provider 210, and a user dashboard interface 227. The service provider server 210 includes several modules including a dashboard interface and associated API 227, social networking and communications tools 213, personalized learning engine 214, assessment tools 216, a learning management system 217, transactional business module 218, and content creation and management tools 219.

[00029] The Social Networking and Communications (SNC) Tools and Applications module 213 may include software and instructions that enables students to collaborate during study and assignment preparation, remote mentoring, and/or virtual classroom environments. The SNC tools may also include social networking, email, text chat, audio and video chat, or messaging/notifications for facilitating communication between students.

[00030] In one example, the personalized learning engine (PLE) 214 represents software that drives the personalized learning system of the present implementations. More particularly, the PLE drives the full personalization of the student's classroom experience and enables the move from teacher-centric to student-centric learning. The PLE 214 will be able to make recommendations to the students, teachers, and parents based on a broad range of system inputs. For instance, teacher or school inputs may include state and local standards, district curriculum, individual teacher course plans, teacher identified course content, teacher evaluations/reviews, and/or scheduling. The student input parameters may include an individual student's learning speed, comprehension rating, quiz and test results, homework, attendance, special learning needs, query analysis, performance levels, speed of learning, third party "partner" input, text and rich media content, content indexes, assessment tools results, classroom management data, and the like. Still further, and as described above, the recommendation and analysis module of the RLE 214 interacts with the student and resource datastore for updating rankings of the resources and maintaining student profile and grouping information.

[00031 ] Assessment tools 216 are designed to measure progress of a student user against learning standards. The assessment tools 216 may help in determining whether a student has mastered a particular subject, is an average student compared to others in his grouping profile, below state standards for example, or lacks the requisite knowledge to complete a particular course. The Learning Management System (LMS) module 217 may include class enrollment, schedules, attendance, calendar, grading, course assignments, and the like, while allowing for the implementation of a third-party LMS utilizing the RLE application programming interface as will be discussed in further detail below. The Transactional Business Engine 218 represents an integrated business engine for tracking content use, ad hoc purchase or licensing of content, micro- transactions for content use, and the like. Content Creation and Management (CC ) module 219 may include text and presentation authoring tools (e.g., LibreOffice, OpenOffice™, Microsoft Office™), media creation and editing tools, and the like. The CCM 219 may further include infrastructure tools to manage educational content that is stored or referenced by the system including management of student and/or teacher-created content.

[00032] Furthermore, the user dashboard interface 227 includes an application programming interface (API) that enables third-party applications, developers, and third-party content providers 215 to efficiently and efficiently link to the personalized learning system in order to create an expansive, extended set of services accessible through a single user interface or portal. By supporting this type of standardized interface, the present implementations will be able to aggregate data and feedback derived from third-party sources (e.g., content providers 215, libraries, streaming services, etc.). Once linked in this fashion, data generated by those services and applications combined with the data in the database can be analyzed by the PLE 214 and presented in a unified fashion. According to one example, the system may be constructed to allow for a less- dedicated level of interaction with the overall framework via XML-based data import for instance. Moreover, many academic institutions are using standalone third-party applications and/or services. Implementations of the present system will not interfere with the continued, independent use of those; however, by using the API to integrate with the PLS, the overall effectiveness of both systems can be increased. The API may further enable schools to continue to utilize favored, in-place applications and/or incorporate new applications as desired in order to meet the specific requirements of the administrators, teachers, and students.

[00033] FSG. 3 illustrates a sample screen shot of a personalized learning dashboard interface according to an example implementation. The dashboard interface 327 includes a plurality of remediation resources for selection by a student operating the personalized learning system via a client device. For instance, lesson selection element 324 identifies the current lesson selected and being operated on by the student user. That is, selection element 324 may be utilized to trigger which resources are displayed to the user. In accordance with one implementation, the dashboard interface 327 is pre-popuiated by the PLE when the student enters the dashboard interface 327 such that changing the focus of the course selection element 324 will in turn change the resultant display. Additionally, the online resources section 315 may include a subset of online resources 315' selected from the database of tagged online resources. As will be explained in further detail below, the resource list is continually updated and ranked by the recommendation and analysis module of the PLE. The ranking of resources may be based on the current context (e.g., current course or topic area of trouble), a grouping profile associated with the student user (e.g., visual learner with high aptitude), student user's profile information (e.g., attributes of the user), and the assessment data associated with the student (e.g., current master level of topic, past performance, etc.).

[00034] The PLE dashboard may also include an "ask a question" area 328 as part of the user interface. Here, the operating student can enter a free form question. In one example, the PLE seeds the advanced search parameters with information describing the problem the signaling student is facing, and also other personalization information from the Random Forest groups and the student personalization database. The user's question may be sent to a predetermined search engine (e.g., Google) via an API which adds context and filtering parameters such as the reading level of student, in an attempt to ensure that the most relevant answers for the specific requestor (i.e., student) are returned by the search engine.

[00035] The course progress area 328 may indicate a student's progress through the current course. Each block may represent a state standard or mastery indicator for a particular subject or course. For example, a green color may indicate mastery, while red and yellow block colors indicate non-mastery and partial mastery respectively. In one implementation, the operating student may select a block to initiate a mastery quiz in an attempt to update the color block indicator in the course progress area 328.

[00036] In addition, a number of secondary remediation resources 329 may be provided to the student operating the dashboard. For example, a "Topic Search" section may provide links to information sources categorized by major categories. The "Friends" subsection may provide the user with links to contact a friend for help with an assignment. According to one implementation, the listed friends may be randomly selected based on certain criterion - such as mastery of the topic in question, similar profile grouping, and the availability of said friends. Still further, the "Tutors" subsection may include the name of an appropriate tutor given the subject matter and mastery level of the student. In one example, upon clicking the "Tutors" subsection, the dashboard automatically connects the student to an online tutoring service in which the student can communicate with the designated tutor via an electronic whiteboard. The system may also use peer tutors as a remediation resource. Rather than an unguided selection by the studeni, the PLE system may identify which peer students have already mastered the specific topic identified as troublesome for the operating user, The determination of a suitable peer tutor may be established via the assessment tools of the PLE system. In one example, the system may use the Random Forest groupings to identify a student that learns similar to the signaling student, and has mastered the material, thereby resulting in a much improved peer tutoring experience.

[00037] Moreover, the dashboard may also incorporate a computational knowledge search engine for enabling students to obtain answers to equations for a variety of topics. Lastly, the "Teachers" subsection is configured to provide a local teacher or teachers associated with presently-displayed course. According to example implementation, students can select a listed teacher in which the system will create an email form for the student that automatically populates the topic in question and transmits to the teacher.

[00038] FSG. 4 illustrates a sequence diagram for implementing the personalized learning system according to an example implementation. Initially, in segment 450, a teacher or student logs into the personalized learning system via a web browser running on the client device 405. Next, in segment 452 the personalized learning service provider 410 confirms the user as a registered user based on the profile data (e.g., username and password) stored in the database. Thereafter, in segment 454 the personalized learning dashboard is launched on the client device 405 for facilitating user interaction therewith. As the student interacts with the dashboard in segment 458, the recommendation and analysis module continually tracks the student interaction and course performance and provides personalized content based on the student profile information and interaction in segment 457. The PLE may detect a learning intervention event such as assistance requested by the operating student in segment 458a (e.g., user clicks help button), or when the PLE automatically determines that the user requires learning assistance based on recent performance activities in segment 458b (e.g., fails quiz or misses multiple consecutive questions via interface).

[00039] Associated student data (performance and assessment data) is analyzed in segment 460 in order to determine a proper grouping profile to associate with the requesting student (e.g., visual iearner, kinesthetic learner, auditory iearner, etc.). In segment 462, the educational resources are identified for relevance and ranked based on for example, the current course or subject, the nature of the question, and/or the grouping profile associated with the requestor. Furthermore, the ranking of remediation resources and grouping profile assignment for the user may be made prior to detection of the learning intervention or assistance event in order to reduce the processing time necessary to calculate and rank the relevant resources, thus providing more immediate feedback to the user. Lastly, in segment 484, an ordered list of the ranked educational resources (i.e., highest rank to lowest rank) is then presented and available for selection by the operating user via the dashboard and host service provider.

[00040] FIG. 5 illustrates a simplified flow chart of the processing steps of a method for personalized learning in accordance with an example implementation. In block 502, the PLE dashboard is launched on client device operated by the user. As described above, the user may comprise of a student or educator, with each user being provided with specific and personalized content. In block 504, the student user interacts with the PLE dashboard interface. The input from the student may include an online quiz, test, essay, or other assessment information provided by the PLE service provider via the dashboard. The student interaction (i.e., activity and performance) is then analyzed by the PLE in block 508. Based on the analysis of the student's profile and interaction with the dashboard, in block 508, the PLE service provider presents personalized activities and resources based on the relatedness of the student profile with a grouping profile of statistically-similar students. The student profile may contain several attributes related to their preferred style of learning, past history of academic strengths and weaknesses, and other attributes. In one implementation, the learning style, physical features of the student, interaction level with the dashboard, and/or environmental factors may be analyzed to match the student user with statistically similar students.

[00041 ] For example, if a student's attention appears to drift often, the PLE may determine that moving the student around can aid the student to refocus on learning and so the dashboard may display activities that require the student to physically move, or the dashboard may prompt the user to listen to calming background music on headphones while working in order to refocus the student. The dashboard and PLE may determine that the user is an auditory learner and therefore provide more audio recordings than text, or vice versa if the student is analyzed and determined that a quiet environment is preferred to maximize student effectiveness. For kinesthetic or tactile learning styles, the dashboard and PLE may direct student users to hands-on activities at certain intervals. Similarly, creative learners may be directed to creative activities, while visual learners are directed to visually-stimulating activities, but may have difficulty listening to an explanation of an answer. Students with developmental or neurological disorders may be provided with larger on-screen targets and fewer answer choices, while a quadriplegic or other disabled student may be provided with audio prompts and/or audio spelling during the course instruction. In the event the user's English skills are limited, the dashboard and PLE may prompt the user in their primary language.

[00042] WVhen the PLE receives a request for assistance from the operating user (or via automatically learning intervention), the PLE may also determine the associated learning context. For example, the PLE system understands that not only that the student is having trouble in Algebra, it also knows that the student is working on non-linear equations with fractional exponents. This information may then be added to the assessment information related to the student user to tune the PLE and recommendation module. In the future, this assessment data may be used in the Random Forest group selection process, allowing for a student to be grouped differently based on the subject, or the actual topic being addressed.

[00043] In block 510, remediation resources are ranked and presented to the user based on the grouping profile best-suited for the student, performance of the student, and/or metatag data associated with the educational resources. More particularly, intervention web resources may be assigned a certain relevance score based on the subject of interest, the number of words in the metatag data matching or closely associated with the course subject matter, and/or the number of times the resource was selected by a student grouping profile matching the requesting student's profile. Those resources having a higher relevance score may be assigned a higher priority ranking for that particular student than those resources having a lower relevance score. For instance, a web source that was viewed by numerous high school students and comprises of metafag data such as <meta name- American Civil War" content- 'graphical timeline of American independence" /> may be assigned a high relevance score and high rank for a student grouped as a visual learner and presently studying a 9^!h grade course in "U.S. History". Next, in block 512, the ranked list of intervention resources is presented to the user via the dashboard interface. For example, the top five highest ranked remediation resources may be presented on the client device and dashboard interface.

[00044] FIG. 6 illustrates a simplified flow chart of the processing steps for ranking remediation resources in the personalized learning system in accordance with an example implementation. The PLE serves the function of presenting to students educational resources based on the meta-tagged resources. The PLE process may begin with the creation of a SQL fable with entries for each student and each tagged resource. From a student's perspective, the process may start with a series of course survey tests that are administered via the interface and received by the PLE service provider in block 802. The surveys are used to gather data on learning styles, math interest and aptitude, individual personalization parameters, and the like. Once the surveys are administered and the data is made available in the database, a set of algorithms are used to identify groupings of similar students in block 604. According to one implementation, a Random Forest algorithm is utilized to identify like groups of students based on a large number of potentially seemingly unrelated data points. That is, a Random Forest algorithm and survey data are initially used by the PLE to prime its engine.

[00045] In block 606, the PLE service provider continually monitors and tracks the student's interactions with the dashboard including preferred content, material reviewed, time spent on lessons, and the like. When a learning intervention or assistance event is detected in block 608, a group of relevant educational resources are ranked (or may be pre-ranked and refined based on latest activity) in order for the particular student seeking help on their specific problem in block 610. The learning intervention event may be detected based on a user physical selecting a designated "help" or similar button on the dashboard interface, or the intervention may be determined automatically based on the user's interaction with the dashboard interface. For example, the PLE may automatically determine that assistance is needed when the user incorrectly answers a consecutive number of activity questions (e.g., 4 consecutive wrong answers), or if the student user fails (or receives a below average score) a quiz or other examination administered via the dashboard interface. The educational intervention resources are ranked based on lesson context or topic/course the student is presently struggling with, along with the grouping profile (e.g., auditory learner), assessment data (e.g., mastery level, recent performance) and attributes (e.g., grade level, age, aptitude) associated with the operating user.

[00046] Consequently, a number of ranked and relevant educational resources are then displayed and presented as one of several remediation options for the student's choosing in block 612. The ranked listing of resources may be presented on a new page or on a sub-portion of the display so that the student may continue working on their current lesson. As explained above, the ranked set of educational or intervention resources may include ranked online web resources or educational databases, curriculum products for exploration, and/or qualified peer tutors (e.g., masterly level designation). Once a resource is selected by the user in block 614, the ranking of the resources are updated by the PLE based on the grouping profile of the selecting user in block 616. That is, as students actually use recommended resources from the dashboard, and as students pass or fail the various tests and mastery quizzes, the Random Forest algorithms and resource rankings are updated accordingly. For example, the PLE may be configured to run the Random Forest algorithm in real-time based on user activity, or on a nightly or hourly basis so as to recalculate the personalization data for each student and for each available learning resource.

[00047] FSG. 7 illustrates a system flow chart of implementing a personalized learning system in accordance with an example implementation. In block 702, a user enters their log-in information into a web-based interface, for example, to request access to the personalized learning service provider. Upon identification of a registered user of the PLE system, in block 704 the host service provider launches the content specific to the identified user (e.g., student, teacher, administrator, etc.) in addition to a selected course (e.g., Algebra). The host server processing unit then monitors student input in block 708, and in accordance with one example, provides a desired topic or subject in block 708, or launches a quiz interface for completion by the student user. The user may select a particular lesson plan from those available for selection in block 716, or the PLE is updated with the results of the quiz in block 718. In both instances, the recommendation module and grouping profiles are updated to account for the user's lesson selection and/or quiz results in block 722. In addition, the user may elect to launch the personalized learning engine dashboard in block 710. As described above, based on the grouping profile associated with the operating student, a list of ranked remediation resources are displayed on the PLE dashboard for review and selection by the user in block 720 when requested. Once a resource is selected by the user, the PLE and recommendation and analysis module is again updated based on the student users profile and the selected remediation resource in block 722.

[00048] Implementations of the present disclosure provide a system and method for personalized learning. Moreover, many advantages are afforded by the implementations of the present examples. For instance, students are able to move at their own pace with focus on content mastery as the basis for advancement to a new topic rather than time spent on specific content. The personalized learning system described herein provides academic institutions with an integrated tool kit that is presented as web services accessible both within the school facilities as well as by authorized users in remote locations via secure access through the internet.

[00049] Furthermore, implementations described herein provide personalization outside the primary core curriculum offering, which adds an element of personalization and flexibility that is difficult or sometimes impossible to obtain when personalization occurs within a specific vendors core curriculum product. Additionally, the student-centric approach, coupled with the array of speciaiized remediation options, results in assistance that is timely and more effective and personalized for each student. Students are able to spend more time on task-learning and less time spent off task, thereby improving academic achievement. Consequently, more students pass courses and governments spend less money on remediation and re-teaching courses.

[00050] Furthermore, while the disclosure has been described with respect to particular examples, one skilled in the art will recognize that numerous modifications are possible. For instance, although examples described herein depict a notebook computer as the portable electronic device, the disclosure is not limited thereto. For exampie, the portable electronic device may be a netbook, a tablet personal computer, a ceil phone, or any other electronic device capable of communicating with the personal learning host server.

[00051 ] Moreover, not all components, features, structures, characteristics, etc. described and illustrated herein need be included in a particular example or implementation. If the specification states a component, feature, structure, or characteristic "may", "might", "can" or "could" be included, for example, that particular component, feature, structure, or characteristic is not required to be included. If the specification or claim refers to "a" or "an" element, that does not mean there is only one of the element. If the specification or claims refer to "an additional" element, that does not preclude there being more than one of the additional element. It is to be noted that, although some examples have been described in reference to particular impiementations, other impiementations are possible according to some examples. Additionally, the arrangement o order of elements or other features illustrated in the drawings or described herein need not be arranged in the particular way illustrated and described. Many other arrangements are possible according to some examples.

[00052] The techniques are not restricted to the particular details listed herein. Indeed, those skilled in the art having the benefit of this disclosure will appreciate that many other variations from the foregoing description and drawings may be made within the scope of the present techniques. Accordingly, it is the following claims including any amendments thereto that define the scope of the techniques.

Claims

WHAT IS CLAIMED SS:

1 1 . A computer-implemented method for personalized learning

2 comprising:

3 displaying, on a client device, a learning interface for facilitating interaction with an operating user;

5 ranking, via a learning engine, a plurality of relevant remediation resources

6 based on profile information and assessment data associated with the operating

7 user;

8 detecting a learning assistance event based on interaction of the user with

9 the learning interface; and

0 displaying, in response to said learning assistance event, an ordered list of1 the ranked remediation resources on the personalized learning interface for selection by the operating user. j 2. The method of claim 1 , further comprising:

receiving, via the learning interface, a selection of a remediation resource

3 from the operating user; and

updating, via the learning engine, the ranking of the plurality of educational

5 resources based on the selection of the user and the grouping profile of the

6 operating user.

1 3. The method of claim 1 , further comprising:

receiving, via the learning interface, survey data from a plurality of users;

3 and

identifying, via the learning engine, similar user grouping profiles based on

5 the survey data of the plurality of users.

1 4. The method of claim 3, wherein the relevant remediation resources

2 are ranked based on lesson context, the grouping profile associated with the

3 operating user, and assessment data and attributes associated with the operating

4 user.

1 5. The method of claim 4, wherein the plurality of relevant remediation resources includes web resources, curriculum products, search engine results,

3 and/or peer tutors.

1 6. The method of claim 1 , further comprising:

receiving, via the learning interface, identification information from the

3 operating user;

identifying, via the learning engine, the operating user as a registered

5 user;

6 displaying personalized educational content on the personalized learning

7 interface based on the identified user.

1 7. The method of claim 6, wherein the remediation resources are displayed on the learning interface automatically based on recent performance

3 activity of the user operating the learning interface.

1 8. A personalized learning system comprising:

a client device operated by a student user;

3 a host service provider for identifying a registered student user;

a learning interface for facilitating interaction with the operating user; and

5 a learning engine configured to analyze and rank a piurality of relevant

6 intervention resources based on profile information and assessment data

7 associated with the student user;

8 wherein upon detecting a learning assistance event, an ordered list of the

9 ranked plurality of intervention resources is displayed to the user based upon a0 grouping profile associated with the user. j 9. The system of claim 8, further comprising:

a database for storing user information and intervention resource date;

3 wherein upon selection of a resource, the ranking of relevant intervention resources are updated in the database based upon the grouping profile of the

5 user and the intervention resource selected by the user.

10. The system of claim 9, wherein grouping profiles are based on similarities of survey data associated with the plurality of users.

1 1 . The system of claim 10, wherein the relevant intervention resources are ranked based on lesson context, the grouping profile associated with the operating user, and assessment data and attributes associated with the operating user.

12. The system of claim 1 1 , wherein the plurality of relevant intervention resources include web resources, curriculum products, search engine results, and/or peer tutors.

13. The system of claim 8, wherein personalized educational content is displayed on the learning interface based on the identification of a registered user, and

wherein the personalized educational content is based on statistically similar profile of the operating user with other users.

14. A non-transitory computer readable medium for personalized learning having programmed instructions stored thereon for causing a processor to:

provide for display, on a client device, a personalized learning interface for facilitating interaction with a student;

receive survey data from a plurality of students interacting with the personalized learning interface; and

determine a plurality of relevant educational resources based profile information associated with the student;

rank the plurality of relevant educational resources based lesson context, the grouping profile associated with the operating user, and assessment data and attributes associated with the student;

provide for display of an ordered list of the ranked educational resources on the personalized learning interface for selection by the requesting student in response to a detected learning assistance event; and update, upon receiving selection of an educational resource by the student, the ranking of the plurality of relevant educational resources based on the selection of the requesting student and the grouping profile of the requesting student.

15. The non-transitory computer readable medium of claim 14, wherein the programmed instructions stored thereon further cause the processor to:

identify, upon receiving identification information from a student operating the personalized interface, the operating student as a registered user based; and provide for display of personalized educational content on the personalized learning interface based on the identified student, wherein the personalized educational content is based on statistically similar profiles of the operating student with other students.