![]() The Watson Explorer Engine admin interface IBM Watson Explorer Results Module To leverage 360 degree views engine must be combined with IBM Watson Explorer Application Builder. For enterprise search applications engine comes with its own search interface. The web based admin interface allows IT users a simple way to manage this powerful application. Engine can be configured to be distributed among many servers to meet big data needs and scale quickly. During the crawling process, XSLT can be utilized to modify the data of the document before storing it to the index. The documents are stored as XML documents. Engine basically acts as an enterprise search engine that can be leveraged to crawl and indexed large amounts of data both structured and unstructured. The foundational components come from IBM’s acquisition of a startup called Vivisimo based out of Pittsburgh, PA. The Watson Explorer Engine component is the key backend component of the foundational components. ![]() IBM Watson Explorer Content Analytics Studio.IBM Watson Explorer Content Analytics Search.IBM Watson Explorer Content Analytics Miner.IBM Watson Explorer Content Analytics Admin Console.IBM Watson Explorer Analytical Components.IBM Watson Explorer Application Builder.IBM Watson Explorer Foundational Components.IBM Watson Explorer ships with several different modules: This data can be integrated into a single, 360-degree view, application on the front-end. The product can also utilize Query Routing to route queries to websites and return the results within its own interface. Using its own proprietary indexing technology, Watson Explorer can leverage natural language processing to deliver relevant query results to end-users. Out of the box Watson Explorer ships with many popular connectors for enterprise data systems. ![]() The tool allows you to consume and index data from various data sources. It allows you to explore vast amounts of enterprise data. IBM Watson Explorer is a data discovery tool. I’m going to write a few posts to explain what exactly it’s like working for the IBM Watson Group and what applications I work with. Since this is my personal site I don’t usually focus on what I do at my 9-5. A few people have contacted me about what I do at my day job as a Watson Explorer Consultant. ![]() I’m going to talk a little bit about IBM Watson Explorer (WEX). I strongly suggest that you do your own research before deciding to make any investment. I do hold a portfolio of crypto assets and may hold some of the assets discussed in this post. I’m simply sharing my thoughts on the state of the crypto market. This is pretty complicated, too, so I'll leave you with a relevant paper: Twitter-Network Topic Model: A Full Bayesian Treatment for Social Network and Text Modeling.This post is not financial advice. The textual content, such as it is, won't play nice with these embedding algorithms, but you have hashtags and strong social signals mentions, retweets, and follows. The idea is to attach a number (or rather, a vector) to everything from a word to a document. If all that sounds Chinese to you, start by reading about "named entity recognition", and "word embeddings". If the graph is too dense, thin out the weaker edges. Once you have the embeddings, and the edges (thanks to NER), use a graph layout algorithm like force direction. If I had to do this I would use a named entity recognition (NER) and document embeddings (doc2vec, etc.). There are a lot of things going on here, but k-means is not one of them. They've created a graph from the news articles, topics, and named entities (locations, persons, companies, organizations).
0 Comments
Leave a Reply. |