Explaining what a “Symbolic Artificial Intelligence Expert System” is in a way that is easy to understand for the average Joe or Mary with limited IT knowledge can be a challenge. I’ve recently stepped up to the challenge and thought I’d frame my obsession with symbolic AI expert systems in the context of another obsession of mine, food. Let me break this down in 5 steps I’ll call ‘DarkLight Food Delivery’.
The first item we want to talk about is the ‘ingredients’ (data feeds and data sources). Different restaurants (organizations) will have different ingredients based on their cuisine (industry). DarkLight would create knowledge models (ontologies) of the different ingredients along with metadata about those ingredients such as handling, storage, use, nutritional attributes, where they came from, etc.
The second item we want to talk about is the ‘recipes’ (department, organization, industry knowledge) that each restaurant has based on the ingredients they use. Some recipes might be well known in the industry and some might be carefully guarded restaurant secrets handed down over time. This is the restaurant’s knowledge that allows them to get the most value out of the ingredients used. DarkLight would capture the restaurant’s recipes in integrated knowledge models (ontologies)
The third item we want to talk about is the ‘Chef skills’ (the domain expert’s experience and know how) in working with the ingredients and the restaurant’s recipes to create meals that customer’s will not only enjoy but keep coming back for more. DarkLight would capture the Chef skills in cognitive (thinking) playbooks that encode the skills of the Chef in working with ingredients and recipes to create the different meals. The reproducibility of the meal is possible through the sharing of the knowledge models (ontologies) for the ingredients, recipes, and the cognitive playbooks with the encoded chef skills.
The fourth item we want to talk about is the ‘meals’ (this is the result/output) that are created by the Chef who creates the meals from the ingredients using the recipes of the restaurant needed for each customer order. Each meal created in DarkLight is a knowledge graph and thanks to the ingredient and recipe knowledge models (ontologies) DarkLight can explain what the meal is, what ingredients are in it, nutrition values, allergies warnings, etc. since that metadata is in the integrated knowledge models.
The fifth and final item we want to talk about is ‘food delivery’ of the meals to both internal and external customers. In DarkLight this aligns to automated command and control to tell wait staff (OpenC2 – orchestrators) what action to take with the meals or to hand the meals off to the delivery service (STIX – Threat Intel or CASE – Cyber Investigation) for delivery of the meals to remote customers.
Written by Shawn Riley
Shawn Riley serves as the Chief Visionary Officer and Technical Advisor to the CEO for DarkLight.ai. Shawn also volunteers as the Executive Vice President, Strategic Cyberspace Science and Board of Directors member at the non-profit Centre for Strategic Cyberspace + Security Science in London, England, UK. Shawn is an industry thought leader in the NSA's Science of Security virtual organization with a focus on applied cybersecurity science and AI-driven science in security operations.