Walmart Apollo, LLC

Hrushikesh Mohapatra

Tabassum Parveen

Siddhanth Jain

Sreenivasa Prasad Sista

Rahul D Sharnagat

Abhishek Kalai Raghavendra

An approach is disclosed for mapping an intent of a query. The approach receives query data for one or more queries. The approach determines product type data of the one or more queries. The approach determines attribute data for the determined product type data. The attribute data includes sequence attribute data and sequence value data. The approach retrieves catalog data for one or more items that include product type data that matches the determined product type data. The catalog data includes catalog attribute data and catalog value data. The approach determines engagement data for the one or more received queries. The engagement data includes a number of times customers interacted with a retrieved item for a respective query. The approach determines cumulative engagement data based on the retrieved catalog data and the determined engagement data. The approach generates a probability and an evaluation score based on the cumulative engagement data.

Query intent mapping

A system and method for analyzing reviews is disclosed herein. User-generated content (UGC) such as on-line reviews of products can be broken up in to different features of the products being reviewed. The UGC is analyzed to find each mention of each feature. Then each mention is analyzed to determine a polarity of each mention. The polarities are aggregated into an overall feature score that tallies the polarity across all reviews. Such a feature score can be calculated for each feature. Thereafter, the feature scores for each feature can be displayed to the user, along with the actual UGC used to determine the feature scores. The display can be in text form or graphical. Other embodiments are also disclosed herein.

System and method for annotating reviews

A system and method for analyzing reviews is disclosed herein. User-generated content (UGC) such as on-line reviews of products can be broken up in to different features of the products being reviewed. The UGC is analyzed to find each mention of each feature. Then a tag cloud or other visual indicia of the features is created. The tag cloud or other visual indicia displays a certain subset of the features, with an indication of how often certain features are discussed. The indication of how often features are discussed can be the font size of the tag cloud or other visual indicia. Other embodiments are also disclosed.

Growing community of inventors

Bengaluru, India

Hrushikesh Mohapatra