Back to results
US 2025/0219969 A1Published application
Systems and methods for enhancing vector searches for question-and-answer platforms
AssigneeIntuit Inc.
InventorsSumangal MANDAL, Vaishali GUPTA
Life of this patent
Estimating the term…
Abstract
Systems and methods are provided for enhancing vector searches for question-and-answer platforms.
Claims20
A computing system comprising:
- a processor;
- and
- a non-transitory computer-readable storage device storing computer-executable instructions, the instructions operable to cause the processor to perform operations comprising:
- obtaining a plurality of question and answer (QnA) posts provided by at least one user on a social media QnA platform;
- feeding at least one of the obtained QnA posts as an input to a generative large language model (LLM);
- generating a plurality of QnA pairs via the generative LLM by analyzing the at least one of the obtained QnA posts;
- embedding the plurality of QnA posts and the generated plurality of QnA pairs to a vector space;
- receiving a query from a user device;
- embedding the query to the vector space;
- executing a vector search of the embedded user query on the embedded plurality of QnA posts and the generated plurality of QnA pairs to determine a response to the user query;
- and
- transmitting the response to the user device.
9 more elements
A computer-implemented method, performed by at least one processor, comprising:
- obtaining a plurality of question and answer (QnA) provided by at least one user on a social media QnA platform;
- feeding at least one of the obtained QnA posts as an input to a generative large language model (LLM);
- generating a plurality of QnA pairs via the LLM by analyzing the at least one of the obtained QnA posts;
- embedding the plurality of QnA posts and the generated plurality of QnA pairs to a vector space;
- receiving a query from a user device;
- embedding the query to the vector space;
- executing a vector search of the embedded user query on the embedded plurality of QnA posts and the generated plurality of QnA pairs to determine a response to the user query;
- and
- transmitting the response to the user device.
6 more elements
A computing system comprising:
- a processor;
- a vector store comprising a plurality of embedded question and answer (QnA) posts provided by at least one user on a social media QnA platform and a plurality of embedded QnA pairs generated via being fed as an input to a generative large language model (LLM) and the generative LLM analyzing the QnA posts;
- a non-transitory computer-readable storage device storing computer-executable instructions, the instructions operable to cause the processor to perform operations comprising:
- receiving a query from a user device;
- embedding the query to a vector space;
- executing a vector search of the embedded user query on the vector store to determine a response to the user query;
- and
- transmitting the response to the user device for display.
5 more elements
Dependencies are inferred from the claim text.