Building Expert Systems Without a Single Software Developer

The article, How Expert Systems & Legal Document Automation Can Help Law Firms & Freelancers Stay Competitive, makes what could be considered a provocative statement but a statement that I believe is very true.  Also, take that article and change the term “Law Firm” to “Accounting Firm” and “lawyer” to “accountant”; the ideas apply equally as well to both areas of knowledge.


That statement should be unpacked a bit.  How could you POSSIBLY automate things without developers???  That is impossible.  Well, so actually, it is not.  This is what the article is really saying.  You build what I might call a "platform" and then use that platform to build the powerful expert system.  The article says there are two things necessary to build an expert system; but I say there are three:
  • First you need to build a knowledge base of declarative, machine-readable rules.  And I say that the knowledge base should be created using some global standard such as XBRL so that those rules can be used by others, not just by the creator.  Basically, this enables the machine-readable rules to be shared for free or for a fee.
  • Second, you need to build an inference engine (a.k.a. reasoner, rules engine, semantic reasoner, logic engine, insights engine) that processes those rules and basically runs the expert system.
  • Third, you also need a business professional user interface that enables business professionals to interact with the expert system.
This graphic below summarizes the components of such an expert system or people are now calling these knowledge based systems:

Something in that article is particularly interesting.  The article, which is targeted at law firms and lawyers uses an accounting example of such an expert system: TurboTax.

So a software engineer and I are creating an expert system for creating financial reports.  The software engineer, Fuad Begic, has been programming since he was 12 years old and his father was also a programmer. You can think of this as the THIRD BULLET in the list above. The software application is currently called Luca and is part of the Auditchain Suite.

We are leveraging an inference engine, the SECOND BULLET, that another software engineer and I created called Pacioli.  That software engineer, Miguel Calejo, has 30 years of logic programming expertise and happened to have learned from Bob Kowalski, the original designer of PROLOG. The Pacioli logic engine was one of four finalists for the Alain Colmerauer Prolog Heritage Prize.

My work with Miguel and Fuad is built on other work with Hamed Mousavi, another software engineer who worked with me to create Pesseract which helped us figure out and prove the logical model of a financial report and led to the creation of the Seattle Method.  Pesseract is a desktop tool for viewing XBRL-based digital financial reports.

Yet another software engineer, Yury Volkovich, built a cloud-based application, another version called General Luca currently, that specialized in creating reports using the Seattle Method.


The author of that first article I referenced started a company called Gavel that provides legal document automation.  What is interesting is that they have a position that they call an "automator".  Those automators are the ones that build the automation and their background is legal, not software engineering.

Financial accounting, reporting, auditing, and analysis is also going to need automators.

Resources:

Comments

Post a Comment

Popular posts from this blog

Relational Knowledge Graph System (RKGS)

Image
Relational Knowledge Graph System (RKGS) is an interesting idea that combines the relational paradigm and the knowledge graph paradigm.  This documentation, Why RKGS , explains the idea. This gets even more interesting with the notion of "relational AI".  RelationalAI is described as follows by the company of the same name, Relational.ai : “RelationalAI is a cloud-based relational knowledge graph management system, with state of the art probabilistic processing and declarative reasoning at scale to make developing Data Applications a superpower for your business.” This notion of knowledge graphs represented in relational databases fits into my belief that knowledge graphs have two aspects: the expression SYNTAX and the logic of what is expressed or SEMANTICS. While the LOGIC of a knowledge graph is always the same regardless of technical syntax used to express that logic; there are many, many different technical syntaxes that can be used to represent a knowledge graph. There
Read more

Graph Hairball

Image
Knowledge graph system logic, the "things" and "relations between things" that  graph theory calls "vertices" (a.k.a. nodes, points, entities, things) and "edges" (a.k.a.  links, lines, relations, associations), looks like a big graph hairball as some people call it an example of which you can see here: Why?  This common view of a graph is because there has to be some "general view" of the information provided by the graph.  This is just like a general view of the information within a relational database is a table ; a set of ROWS and COLUMNS for exactly one table at a time. So what is interesting is that with a graph database the default view is everything in the graph of knowledge.  Whereas the default view of everything in a relational database is one table at a time. Further, it does not really matter whether the information that populates your knowledge graph comes from, say, CSV files, Excel, JSON, XBRL, RDF, PROLOG or whateve
Read more

PLATINUM Business Use Cases, Test Cases, Conformance Suite

Image
A brick wall is made of exactly two things: bricks, mortar. But a brick wall created by a master craftsman, or mason, and a brick wall created by a “weekend warrior” with no knowledge of masonry will be very different. Master craftsmen are created and that process takes time and effort. This blog post is a first prototype that brings several things together into one useful resource for business professionals.  It pulls together the human readable information of the Showcase of Reports   and the machine readable information of the Conformance Suite of XBRL-based Financial Reports Prepared using the Seattle Method .  Then, I want to incorporate the information found in these PLATINUM XBRL-based Financial Report Examples . The three resources can be useful and used independently; but they are even more useful when used together.  Business professionals really could not care a less about the technical details of getting some result that they want.  But technical professionals need to under
Read more