Abstract

Some search engines may be less efficient at answering comparative queries that require filtering based on specific user-defined constraints, sometimes returning less relevant results. A disclosed method describes an approach for this scenario by constructing and refining a virtual table of options. The system can take an input query, a list of informational needs, and a list of filtering criteria. It can then discover an initial set of potential options and iteratively perform targeted web searches for each one to gather the required information and verify compliance with each criterion. This process allows for the elimination of unsuitable candidates and can provide for retry mechanisms, which may result in a structured output of filtered options that correspond to complex, multi-faceted user queries.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.

Share

COinS