Companies are working hard to keep on top of an ever-increasing compliance burden. Since the policies are constantly changing, it's always challenging to keep up and ensure that every process complies.
With SQUARE, our goal is to help the officials at these companies by arming them with a wealth of knowledge in a smarter, more efficient, and much more organized way.
Companies across sectors – gaming, gambling, human resources, or legal – need to comply with the policies and rules regulating their industries. One common activity across industries is SEARCHING for the correct information by the auditor or the person implementing or utilizing the policies and verifying if they're right.
Before we get into the details of using SQUARE for compliance, let me explain what SQUARE is.
SQUARE is Cognistx's scalable and production-ready intelligence search system that takes user queries and provides granular results across millions of documents in just a few seconds.
Below I will explain how we applied SQUARE in compliance for two domains.
SQUARE enables users to ask questions and get accurate, granular responses from compliance documents and websites across multiple states in the United States. In addition, SQUARE stays up to date by periodically updating its knowledge base.
The steps below were performed to build a Google-like search engine for a gaming regulations domain.
Step 1: CRAWL data from trusted state gaming regulation websites across the U.S.
Step 2: CLEAN and INDEX the crawled data set to create the knowledge base.
Step 3: PREDICT answers for user queries in real-time at SCALE using SQUARE.
SQUARE base models were used to develop a platform that helped automate the manual process of verifying vendors' security questionnaire forms. This made the data from third-party security and risk documents like SOC and ISO reports searchable by predicting answers to user queries in real-time.
The steps below were performed to automate the manual verification procedure of the vendors' security questionnaire form.
Step 1: EXTRACT text from vendors' third-party security and risk documents like SOC and ISO reports.
Step 2: COLLECT queries/keywords across domains like risk assessment, access control, privacy policies, etc. and process them.
Step 3: PREDICT answers for user queries in real-time at SCALE using SQUARE Engine.
We have seen clients using SQUARE in two ways.
1. Open Search, in which we create a central database using documents that would have otherwise been looked at manually. A user can instantly look for the correct information from this repository by asking questions. SQUARE responses will also have a confidence score and a link to the respective document highlighting the segment from where the answer was extracted.
2. Constrained Search, in which we might parse new data to answer a specific question set every time. The model will be initiated every time a new searchable document is uploaded to the system.
In this method, the user can generate reports or find answers from a predefined set of questions for a dataset of their liking.
If you're interested in SQUARE, contact me at jagriti@cognistx.com. I can demo the product and tell you more about SQUARE and how it can be applied to your business and industry.
