Grants4Companies: Applying Declarative Methods for Recommending and Reasoning About Business Grants in the Austrian Public Administration (System Description)

TL;DR

The methods and technologies underlying the application Grants4Companies, which uses a logic-based expert system to display a list of business grants suitable for the logged-in business, and a Proof of Concept implementation of reasoning over the formalised grant conditions are described.

Abstract

We describe the methods and technologies underlying the application Grants4Companies. The application uses a logic-based expert system to display a list of business grants suitable for the logged-in business. To evaluate suitability of the grants, formal representations of their conditions are evaluated against properties of the business, taken from the registers of the Austrian public administration. The logical language for the representations of the grant conditions is based on S-expressions. We further describe a Proof of Concept implementation of reasoning over the formalised grant conditions. The proof of concept is implemented in Common Lisp and interfaces with a reasoning engine implemented in Scryer Prolog. The application has recently gone live and is provided as part of the Business Service Portal by the Austrian Federal Ministry of Finance.

Figures (11)

• Figure 1: Examples of atomic formulae and their intended semantics
• Figure 2: The definition of the concept gv.at:natürliche-oder-juristische-Person. The formula captures the condition that the applicant is a natural person, i.e., the legal form of the company is that of a sole trader (:Einzelunternehmen), or a legal person (captured by the defined formula gv.at:Ist-Juristische-Person).
• Figure 3: Example grant, TP-Nr.1052703. The grant provides funding for increasing energy efficiency. It is applicable to natural and legal persons (GV.AT:natürliche-oder-juristische-Person) in the city of Villach (the Unternehmenssitz or a Betriebsstandort has to be in the municipal identification number 20201). Some other conditions cannot be checked automatically based on the data about the company available within public administration and hence are not formalised (e.g., that the request for funding has to be submitted at most 8 months after implementing the measures for increasing energy efficiency).
• Figure 4: Example grant in Prolog syntax, TPPNr#1052703. For the original formulation of this particular grant, see Fig. \ref{['fig:ex-grant']}
• Figure 5: The truth tables for 3-valued strong Kleene logic $K_3$. The truth values false, unknown, true are represented by $\bot$, $u$ and $\top$, respectively.