Search Retrieval

An enterprise app builder approached us to enhance their sales person-oriented app with a critical feature centered around retrieving the latest news about professionals and organizations they work for.

How we did it

Intelligent Algorithms

Identifying and crawling relevant sites to return immediate results

Clustering

Identifying and segregating news items with similar content

NLP

Mining relevant multi-lingual news items and translating for consumption

“One of the coolest things is that we are able to get highly relevant results that prioritizes the importance of the news clipping as well as the sentiment, which was the missing piece in our app. We could never have done this without the (MindWave) technology.”

Challenge

A real-time API was required by the client to integrate with their app, which would obtain relevant news results for any professional’s name, with or without additional information such as their role or organization name. They wanted the news results to be summarized, ranked by importance and given an overall sentiment score.

  • Identify which external service to leverage to obtain latest news stories from everywhere
  • Ignore irrelevant results
  • Remove exact or near duplicate news stories
  • Determine relevance and sentiment of each news story
  • Handle large volumes
  • Ensure quick results
  • Data security and privacy

Solution

Using MindWave, we created the appropriate set of queries to search for the appropriate external service given any specific input from the app. Powerful intelligent algorithms filter out irrelevant results and removes exact or near duplicate news stories. Each news story was analyzed to determine its relevance and sentiment – both overall and for important topics within the news story. 

The solution was setup to ensure scalability with the expectation of a large volume of query. The entire setup was made in the cloud fully controlled by the client.

  • Distributed, scalable architecture
  • Core natural language understanding engine
  • Clustering of news stories based on their content
  • Analysis of trends in the news to help recognize, classify and disambiguate input query terms as needed
  • Client cloud control

Result

The real-time API allowed the app to obtain relevant news results for any professional’s name it provides with or without additional information such as their role or the organization at which they work. The filtered set of results matched with a very high likelihood the person or organization specified in the call from their app to the API.

Each news result is ranked by importance and with an associated overall sentiment score. Main topics in each of the news results together and corresponding sentiment score is also returned. The real-time API returned results almost immediately creating an elevated user experience and increasing the apps stickiness.

The success of using MindWave AI led to deeper engagement on a number of fronts with the client.

Other Stories

AI powered Consumer Profiling for Banking

Given very limited customer data that included the name, e-mail address and location, MindWave produced a variety of individual consumer insights for more personalised targeting

Search Retrieval of News with sentiment related to corporates

A real-time API was required by the client to integrate with their app which would obtain relevant news results for any professional’s name it provides with or without additional information such as their role or organization name.

Automated Student Assessment

The use of MindWave AI made it possible for automated assessment and adaptive testing. Which means assessing the difficulty of each question, and then score the student responses.