Difference between revisions of "Artificial Intelligence/Robotoff/Roadmap"

From Open Food Facts wiki
Jump to navigation Jump to search
(Created page with "2021 Roadmap draft === “More themes for detections, more efficient detections, with more techniques, more broadly automatically applied, and more broadly distributed and va...")
 
Line 45: Line 45:
 
**** Secondary goal: OCR-based category prediction
 
**** Secondary goal: OCR-based category prediction
  
 
+
==== Categories and ingredients ====
* Improve on the existing
 
 
 
 
 
 
* Categories
 
* Categories
 
** [https://github.com/openfoodfacts/openfoodfacts-ai/issues/6 Generate new categories by automatically clustering similar products]
 
** [https://github.com/openfoodfacts/openfoodfacts-ai/issues/6 Generate new categories by automatically clustering similar products]
 
* Ingredients
 
* Ingredients
 
** [https://github.com/openfoodfacts/robotoff/issues/155 Check if the ingredient list matches the Google OCR result] 
 
** [https://github.com/openfoodfacts/robotoff/issues/155 Check if the ingredient list matches the Google OCR result] 
 +
 
==== Support quality ====
 
==== Support quality ====
 
(Probably doable in Q2, after the Wild School prototype completes)
 
(Probably doable in Q2, after the Wild School prototype completes)

Revision as of 19:27, 1 February 2021

2021 Roadmap draft

“More themes for detections, more efficient detections, with more techniques, more broadly automatically applied, and more broadly distributed and validated by contributors”

Developper experience

  • Document installation better including simulating a Product Opener sending and receiving to and from Robotoff
  • Make it easy to assess impact of Regex on existing OCRs (or the need for it could be replaced by the self service regex system)

Solve current performance issues

Put an initial version of nutrition table extraction in production

Integrate spellcheck into Product Opener

  • Integrate the spellcheck into Product Opener (already available in the Robotoff API)

Add more detections

There are a lot of things to detect on a packaging. While we can add many individual detections (and that's very fine, there are some good and impactful examples in this project), we should aim to build general purpose systems that will scale across languages and kinds of detection (eg a system able to detect any kind of recurring text pattern)


Speculative projects

  • Being able to auto-extract recurring patterns of text, and create rules to populate fields from them (or create insights) (Le Wagon project)

Increase insight validation

Increase insight validation, either by

  • increasing distribution (though apps, 3rd party apps, games…)
  • increasing ability to validate them automatically
    • More aggressive application of many insights
      • EMLyon project
        • apply top level categories for the Nutri-Score
        • Secondary goal: OCR-based category prediction

Categories and ingredients

Support quality

(Probably doable in Q2, after the Wild School prototype completes)

  • Leverage the historization databases to:

Support the Eco-Score

Extract the various variable of the Eco-Score:

Hunger Games

  • Bring the logos and labels games to the next level
  • Bind the nutrition game to the nutrition prediction
  • Add a nudge to login to Open Food Facts
  • Add a mission page (could be a link to a wiki page)

Next-gen Robotoff and high impact tooling

  • Secondary insights
  • Composite insights - "IF & IF THEN" insights
  • Add a self-service Elastic Search interface to let power users create new Regex rules (search within all the OCRs for a keyword or pattern, to help find the potential volumetry and refine the REGEX, and then add a Rule-building interface that saves the detection in a new BDD table that will then be used by Robotoff)