|Project Description: ||It is a recognized fact that humans usually tend to compare one thing with the other unless they get satisfied. During this process of expecting for the alternatives, they are noticing very much difficult to cipher out what they want. They typically look for the best one with more features, functionalities, good quality and at the same time something that is cheaper or affordable. Though the existing methods achieve high precision, they nonetheless suffer from low recall and performance issues.
The proposed system overcomes these drawbacks and improves the efficiency of mining entities. Therefore, in order to assure high precision and high recall, we prepare a novel approach that combines the Bootstrapping and relation keyword query questioning process for text search techniques in SQL. The primary goal of this project is to identify whether the question is comparable or not and then we pull out the required entities from the query by making use of an extensive online question record . Initially, the user presents a query as an input; later the system will identify whether the passed question is comparable or not. Once the system verifies that the query given by the user is equivalent, the required entities are extracted, and the output is presented to the user with the possible options. This approach provides better results compared to the existing approach.