Using Watson Content Hub as a central repository and tag generator

Want to learn how to integrate Watson into your applications? Well, it’s as easy as clicking on this link and getting started. From image recognition to financial services API’s there is an entire catalog of Watson API’s right at your finger tips. I personally have been playing with the Watson Content Hub API’s and they are very cool. A project I worked on used the Watson Content Hub(WCH) API’s with WebSphere Commerce where we used WCH as not only a central repository but also extracted the tags Watson generated for product images and pushed them into the product record in WebSphere Commerce. This enhanced the searching for products by a customer greatly. Watson generated key words we didn’t think of at first, making search and type-ahead much better.

Here is a quick video where we used a City Cool product called Minimals Moped. We pushed the images to WCH, Watson generated new tags, then we used those tags in the products keyword field. The search indexer did the rest and viola, the search experience was greatly enhanced to have a broader set of key words per product.

Watson drives IBM Digital Experience

If you missed it, at the IBM Connect conference, Chris and Rob demonstrated how to build a page using Watson to assist in suggesting the content for the page with a single click.  Very impressive and as Chris said “that is awesome”.  Totally agree!

In the video below (which is much longer than the snippet I provide here), Rob shows the Cognitive Assist feature to help in constructing a new landing page for their campaign.

Cognitive Assistant

Take a look at the video to see how cool this new feature is.

The future of Marketing with Watson


If you missed the demonstration at Amplify with Watson and the IBM Marketing platform then you missed a really impressive demonstration.

Using Watson Translation service in an Eclipse SWT application Part 2

The next follow-up to the last article is the code I used to communicate with the Watson Translation service. But first I want to show the flow of the data:

So basically the SWT client sends a JSON string to the server in the body of the message. You can do this as long as you specify application/json as the Content-Type. For JSON, I use the JSON library for Java over at and its been perfect. I have even begun using this library for all of my in memory objects because then I can easily serialize it out for storage or over the network.

Below you will see the primary code to send this message:

JSONObject payload = new JSONObject();
payload.put("toLang", obj.get("to"));
payload.put("text", obj.get("text"));
URL url = new URL(pet_bluemix_translation_service);
URLConnection connection = url.openConnection();
connection.setRequestProperty("Content-Type", "application/json");
OutputStreamWriter out = new OutputStreamWriter(connection.getOutputStream());
//Now get the response
BufferedReader in = new BufferedReader(new InputStreamReader(connection.getInputStream()));
String n = in.readLine();
StringBuffer sbValue = new StringBuffer();
while(n != null){
	n = in.readLine();
final String value = sbValue.toString();

Using Watson Translation service in an Eclipse SWT application

Image (3) flow-680x156.png for post 5379

In this video I show how I used Watson Translation services in IBM Bluemix to translate an entire catalog of products and categories. I used a simple Node-Red flow to achieve this with little programming on the server-side.

The most impressive demonstration at NRF 2014

Screen Shot 2014-01-17 at 12.54.27 PMI will admit that I did not see every demonstration or product at NRF and while the Intel booth had some great technology, I think the Watson + Fluid + Northface demonstration was the best.  It was the best for a couple of primary reasons. One, it showed a natural way for a person to shop and two, the responses from Watson were similar to that of a human (in context) but of course in digital format. If you Google (Watson Fluid Northface) you will see all kinds of coverage on this technology and implementation.

You can also watch Ginni Rometty showing a demo at NRF14 of the Expert Personal Shopper (EPS) on the Northface web site. This demo was also given at the IBM booth. The video is 54 minutes long but the The Northface + Fluid + Watson demo is between 20:00-23:30, yes, only about 3 minutes.

Here is a snippet of the conversation:

Ginni – “I am gearing up for a 14 day back packing trip. What equipment do I need?”

EPS – Responds with Expedition Tents, Cold Weather Sleeping Bags, Technical Packs, Expeditions in Patagonia

Ginni – “What technical pack is needed for an expedition to Fitz Roy Patagonian in the winter?”

EPS – Responds with “These are the packs suited for winter expeditions” and lists a set of North Face packs and even recommends a specific pack – the Prophet 65 pack and mentions ABS technology.

Ginni – “Can you tell me about ABS technology?”

EPS – responds with a technical article about the Avalanche AirBag System

Ginni then continues the discussion by asking how the back pack is rated.  This to me is the evolution of product search and education. Imagine going to your favorite online store and was able to ask these kinds of questions for the product you are interested in.