2021 | Health | India | Promising | SDG3
CovAid – Twist

1. General


SDG 3: Good Health and Well-being



2. Project Details

Company or Institution

Team Kriegers


CovAid – Twist

General description of the AI solution

Our project (CovAid) focuses on aiding people who are affected by the pandemic by helping them to get leads for Oxygen Cylinders, Plasmas and Hospital beds through twitter. For developing this solution we have used UiPath, an RPA platform for automation.

First bot retrieves all the tweets that has requests for Oxygen, Plasma and Hospital beds from twitter and uploads them to orchestrator queue. It also has a mechanism to avoid the same tweet and also the re-tweeted tweets from being pushed to queue so as to ensure that there is no redundant data processed.

The second bot picks up tweets from the queue asynchronously since it’s a long running process, classifies them using ML Skill developed in UiPath’s AI Centre, extracts the location from the tweet using Google NLP and Maps API, retrieves the requested information from the data service, post them back as a reply to the respective tweet.

RPA + AI make it more interesting by doing wonders.





3. Aspects

Excellence and Scientific Quality: Please detail the improvements made by the nominee or the nominees’ team or yourself if your applying for the award, and why they have been a success.

The ML Skill build uses Text based classification ML Model where the custom dataset that’s in accordance with our solution is being trained using recurring pipeline runs and a feedback to the ML Model is also sent so as it make it more stable and reliable.

The Google NLP ML Skill that’s being called via API identifies the entities from the twitter text from which the location entity is found.

Since there is a feedback that’s going back to the ML Model, older the ML Model gets, more will become its stability and reliability making the percentage of success grow exponentially.

The ML Model was trained by using live data and processed more records on live by giving leads to people who suffer, thus making it ready for deployment.

Scaling of impact to SDGs: Please detail how many citizens/communities and/or researchers/businesses this has had or can have a positive impact on, including particular groups where applicable and to what extent.

Our solution has created a remarkable impact among people in Twitter who has requested for oxygen cylinders, plasma’s and hospital beds along with the NGOs who are trying to help people out there by connecting each other.

This solution has been built as a prototype that proves that it can be scaled across domains and platforms where there are any needs or a request that’s been put forward so as to take in help or to get a work done for them and our solution will sustain as far as people need something.
To incorporate our solution an end user need not have to change what’s been done by them in general and when implemented could earn the confidence of people as they get benefited. This could eventually pull not only the company’s but also a common man towards AI and showcases what not it can do to make life simple.

Since our solution is built around the existing platforms that people use, especially social media platforms where there are lot of requests moving around looking for support, we don’t have any closed community as such that implements our solution rather it focuses every human out there making it stand alone and independent.

Our project has already helped 8 NGOs across India to connect with people in need.

Scaling of AI solution: Please detail what proof of concept or implementations can you show now in terms of its efficacy and how the solution can be scaled to provide a global impact ad how realistic that scaling is.

Our solution is not only restricted to healthcare domain and concentrates on COVID but also can be implement for other domains and pandemics as described below.

Disaster/Crisis – where people suffer by not getting basic supplementary to lead their life like food, groceries etc during flood, tsunami etc.

Feedback/Review analysis – where depending on the feedback people expect a reply or an organization reporting their performance .

Blood/Organ donation – where people request for blood or organs for their loved ones

Service Request – where an employee or a common man log a request for getting their requirements.

Education – where a student asks a question

Ethical aspect: Please detail the way the solution addresses any of the main ethical aspects, including trustworthiness, bias, gender issues, etc.

While building our solution we have ensured that AI is being used in an ethical way. Consent has been taken from NGOs for storing their records, also end user to whom the bot replies are also notified by the post through disclaimers.


International Research Centre
on Artificial Intelligence (IRCAI)
under the auspices of UNESCO 

Jožef Stefan Institute
Jamova cesta 39
SI-1000 Ljubljana



The designations employed and the presentation of material throughout this website do not imply the expression of any opinion whatsoever on the part of UNESCO concerning the legal status of any country, territory, city or area of its authorities, or concerning the delimitation of its frontiers or boundaries.

Design by Ana Fabjan