connect with us

tell me more

case study

Ed Tech

request call backsubmit
*Required Field
**We would love to subscribe to our newsletter via email. Please rest assured we’ll treat your information with the greatest care and will never sell it to other companies for marketing purposes. See full Privacy Policy.

Thank you.

Your message has been sent and a member of our team will be in touch shortly.
CLOSE
Oops! Something went wrong while submitting the form. Please try again.
X
download Pdf version
The World has changed - AI Proof of Value Service. Discover more

case study 

Ed Tech

How Fountech is Creating the AI for a Hyper-Personalized self-learning TutorBot

sector 

Education

 / 

the client

Fountech Solutions have been working on an AI driven EdTech platform for a corporate Learning & Development organisation, as they may wish to extend their existing B2B solution to home tutoring, schools and the wider B2C Educational Technology market.

The organisation comprises of educational specialists, psychologists, data scientists and other appropriate professionals, who share a vision that traditional teaching methods are redundant.

They wish to disrupt and completely change the way that learners access and digest learning resources, whoever and wherever they might be. Achieving such a huge task means harnessing the power of AI. Such a brand new, accessible, international, affordable platform, allowing every learner in the world to unlock their full potential, would be impossible with non-AI computing methods.

the problem

Our client recognises that many learners are way behind their capabilities as a result of the antiquated ‘one-voice, many-ears’ fixed message style of teaching that still exists today, even with available technology, which remains largely unexploited.

No method of group teaching can ever be 100% efficient. Classroom or lecture-hall delivery, workplace training, web-based distance learning courses & lessons, each is burdened with the same problem in varying degrees, and it’s a simple set of barriers: Each and every learner needs to be taught at a different pace, with differing appropriate materials and media. This is because every person has their own optimum ‘learning style’. Even 1:1 human tutors only have limited time and resources at their disposal and they tend to be expensive. People wanting only a few hours’ extra tuition per week face bills in the hundreds of Dollars or Euros per month.

That’s why an AI-driven platform is required, which assesses every single individual user’s optimum learning style, then adjusts the content, medium, pace and presentation of learning resources. In this way, every learner fully understands every lesson to the very best of their own ability. And our client wishes it to be free to access for at least the basic elements of the service.

No items found.

We Consult. We Imagine. We Disrupt.

the solution

In order for this visionary concept to be successful, the single most important factor is hyper-personalization. The key is for each and every individual learner to have access to a variety of subject resource and content, with delivery at the exact optimum pace, method and through appropriate media. In order to achieve this, the AI must be able to assess each person’s engagement level and understanding of the presented material. This is achieved by three minute ‘micro-lessons’ that involve engagement analysis and ‘teach-back’ strategies. After each lesson, the AI autonomously self-learns its success level of the learner’s understanding, against the learner’s dynamically assigned learning style, thus the AI verifies its success, stores the learner’s preferences and adjusts subsequent micro-lesson delivery accordingly.

The platform uses an interactive 1:1 avatar TutorBot, which delivers microlessons and listens to its learners via voice, then replies and ‘teaches back’ in both audio and text; like a home ‘smart speaker’ that can also transcript the output textually on a screen, if required.

Human 1:1 tutors will also use the platform. They will offer payable and sometimes free services as a resource. As part of their interaction with learners, the platform’s analysis tools can be used to assist them, drawing upon a vast library of resources; from video to voice, graphics to grammar. The TutorBot avatar will assess the learner’s needs and present the most appropriate material at optimum pace. The engagement analysis, the pace of answers, the request for repeats, all contribute to the AI’s understanding of how each person learns in their own best way.

Interactive Resource Material

There’s way too much science to dive in deep here, but one of the most useful tools in the platform's virtual box will be the ability to have textual resources interact with learners. Such resources can either be sourced from e-books or by scanning and parsing printed textbooks.

To do so, first, the AI must ‘learn about’ the resource, using algorithms. Here is an overview of how they work:

SUBJECT CLASSIFICATION

Categorising chapters, for example, into one of many categories.Classification can also assign type and genre (e.g: fiction, horror).

CREATING CONNECTIONS BETWEEN SUBCOMPONENTS

Previously processed segments can refer to similar content or expand upon previous content. The AI algorithms can create connections between segments and create / suggest learning sets within there sources.

CONVERTING KNOWLEDGE TO RETRIEVABLE INFORMATION

The contents and meta-data are stored in a graph-based knowledge-representation system, which is used to easily retrieve interrelated data.

ENTITY RECOGNITION & INFORMATION ENRICHMENT

Some specific names, professions, physical locations etc etc are extracted from text. These can be used to conduct a broader search, external to the book itself. For example, a particular chapter of a history book might refer to an historic character, in which case, the reader could click on that character's name or ask by voice to learn more about them.

The Resource as a Teacher

CONTENT SUMMARIES

Long documents and other content is summarized to a synopsis of chosen length, say 400 words per instance, and each can be categorised by themes. Moreover, interrelated information can be asked of the system e.g. "Can you tell me about the period of Stalin’s rule over Russia?"

CONVENTIONAL & SEMANTIC TEXT SEARCH

Literal searches and 'similar meaning searches' would mean that a search of“despotic dictatorships”, “autocratic government” or “Stalinist regime” should bring the same result.

CHARACTERISTIC(S) SEARCH

Entities can be defined (in part) by their characteristics, e.g.: “Boyle’s law”. If readers search “Boyle”, results will include all entities containing “Boyle” but also “Boyle’s Law” and an entry concerning the Physicist Robert Boyle.

‘TEACHING AND TESTING’ THE USER ABOUT CONTENT

The system can ask the learner to ‘teach back’ any material or create questions to test their understanding of the salient points of the lesson. The system will assess factual understanding and relate that to the level of engagement of the user during the learning process.

EXPANDING ON CONTENT

The 'reader' can ask for more information about anything, and online connectivity enables the system to bring up other relevant media related to the query, e.g. "Tell me more about JosephStalin..."

ENGAGEMENT ANALYSIS

An analysis of the learner’s responses during lesson delivery and assessment can help the system understand the extent to which they were engaged. This assessment is based on a combination of factual understanding and biometric responses ( in the cases where the system is allowed to monitor visual and auditory responses of the learner). If the system detects low levels of engagement, the platform can adapt the presented material using different wording or even between different media (visual vs audio vs combination of both etc), thus encouraging the learner to-engage with the content.

TRANSLATION INTO OTHER LANGUAGES

Readers may be bilingual but may still feel more comfortable having material presented in their native language. This can help with their understanding and engagement analysis efforts, not least if they are using the resource to learn a new language!

the outcome

The platform continues to develop, with Fountech Solution’s AI at its heart. The level of investment and interest clearly shows that positive results are demonstrating the utility of this exciting interactive platform. Our client have since been approached by several Ed Tech sector corporations. Fountech Solutions aren’t just responding to the EdTech market’s requirements, nor are they merely predicting the future, they are creating it.

request Pdf version

features

The vCAIO will conduct a situational assessment to identify the needs of, and opportunities for, the organisation.  They will provide a report outlining a gap analysis and the baseline from where to start defining the AI strategy going forward

Create a vision of where the organisation should be going

Set standards for strategy implementation through establishing the correct management structures and considering ethical issues

Make things happen by operating at the right level, knowing what to outsource and what to achieve in-house for optimum delivery

Build capacity in the organisation by recruiting the right talent and identifying appropriate vendors or consultants to solve key problems

Become the public face of the new technology, both internally and externally

discover

Understanding your needs and identifying opportunity to exploit

analysis

Evaluate your data

report

Knowledge Gaps   |   Costs v Benefits   |   Your Competitors

external

Latest Industry Tech and how we can enhance it just for you

Synopsis

Our key recommendations and suggested next steps

download pdf version

tell me more

case study

Ed Tech

submit
*Required Field
**We would love to subscribe to our newsletter via email. Please rest assured we’ll treat your information with the greatest care and will never sell it to other companies for marketing purposes. See full Privacy Policy.
download pdf version
Oops! Something went wrong while submitting the form. Please try again.