| 1 |
Data collection form for NGOs
- Form built in Microsoft forms or manual
- Server on azure to handle incoming form data and store in database 1
|
MUST |
Completed preliminary form layouts |
Mark, Rachel |
| 2 |
Database 1 (for collecting form data)
- Fields to contain information via the submitted form
|
MUST |
Database created and designed database in Azure |
Mark |
| 3 |
PDF data extraction tool
- Extract relevant information from report PDFs from NGOs
- Such Information may include but is not limited to: financial information, project details, location, staff records
- Using Azure's Cognitive Services
|
MUST |
"Phase one" of development progress |
Yansong, Rachel, Mark |
| 4 |
Database 2 (UN "Knowledge-base")
- Fields to store information from PDF extraction tool
|
MUST |
Todo |
- |
| 5 |
Front end access to database 1
- Through web-app
- Hosted on Azure
|
SHOULD |
Todo |
- |
| 6 |
Front end access to database 2
- Through web-app
- Hosted on Azure
|
SHOULD |
Todo |
- |
| 7 |
Server unit to contain PDF extractor
- Mechanism to upload new PDF documents
- Accessible from web-app
- Mechanism to send extracted data to database
|
SHOULD |
Todo |
- |
| 8 |
Statistical analysis tool
- First-stage analysis of data we collect
- Could be used as part of, or be superseded by, the Machine Learning based recommendation algorithm.
|
COULD |
Todo |
- |
| 9 |
Build generative adversarial network (GAN)
- Utilises both database structures to create lots of similar data
- Allows modelling of the data to be undertaken
|
COULD |
Todo |
- |
| 10 |
Machine Learning based recommendation algorithm
- Can generate synthesised UN reports
- Provides recommendations to the UN, particularly around which NGOs should receive more or less funding
|
COULD
| Todo |
- |
| 11 |
Link database 1 & 2 into a single coherent structure |
COULD |
Todo |
- |
| 12 |
Build app in order for individuals in and outside of the ANCSSC to access and review our data
- Includes graphs and other visual media to explain different SDGs
|
WOULD LIKE |
Todo |
- |