{"id":1897,"date":"2018-07-26T13:47:23","date_gmt":"2018-07-26T13:47:23","guid":{"rendered":"http:\/\/capture.ccio.us\/?p=1897"},"modified":"2018-08-07T17:48:21","modified_gmt":"2018-08-07T17:48:21","slug":"predictive-research-engine-architecture","status":"publish","type":"post","link":"https:\/\/capture.club\/portal\/2018\/07\/26\/predictive-research-engine-architecture\/","title":{"rendered":"Capture Club Predictive Research Engine Architecture"},"content":{"rendered":"

<\/p>We are NOT a Search Engine.\u00a0 We are a Research Engine<\/strong>.\n

Over the years, we have developed a fast, robust, resource-friendly, distributed framework for handling near-real-time Machine Learning and Predictive Analytics.<\/p>\n

From a high-level, our architecture looks like this:<\/p>\n

\"Capture
This is our architecture for the Predictive Research Engine.<\/figcaption><\/figure>\n

External datasources (E.g. websites, documents, file systems, etc) are ingested using our proprietary Indexing Engine, and either persisted into Solr<\/a> or used for real-time Machine Learning<\/a> by EMPATHS<\/a>. Once an inverted index is constructed form the ingested data, HAIDIE<\/a> goes to work building out dynamic classifiers<\/a>. These classifiers are essentially nano-applications that have a topic, and a set of associations that are constantly re-evaluated for relevancy and priority.\u00a0 When a query or query profile is entered into the system, HAIDIE goes to work and provides near-real-time Machine Learning, responding to the ZEN<\/a> interface via the TAME<\/a> protocol.\u00a0 \u00a0This allows for an on-going conversation, and allows the system to learn from the user.<\/p>\n

Some of the most innovative aspects of our research engine are:<\/p>\n