Systems and methods for graph-based dynamic information retrieval and synthesis

US12282504B1 · kind B1 · utility

Assignee

• HARMAN CONNECTED SERVICES, INC. · US

Inventors

• Jai Ganesh · Savanuru, IN
• Somdev Goswami · Bengaluru, IN
• Ashutosh Vyas · Gothan, IN
• Priyesha Chetan Kapadia · Ashti, IN
• Vaishnavi Shiwankar · Ashti, IN
• Adusumilli Sai Kiran · Vemula, IN
• Sahana H S · Bengaluru, IN
• Dodla Mounya · Vemula, IN
• Aakash Tatoba Walavalkar · Ashti, IN

Key dates

• Filing date: Apr 30, 2024
• Grant date: Apr 22, 2025
• Expiry date: Apr 30, 2044

Classification

• Technology area (CPC G): Physics
• CPC primary: G06F16/9024
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Disclosed herein are systems and methods for graph-based dynamic information retrieval and synthesis, particularly for enhancing the response generation of chatbot applications using large language models (LLMs). The methods involve receiving a user query, generating a query embedding, and accessing a knowledge graph comprising nodes representing documents with associated document embeddings. A set of documents is retrieved based on similarity scores, and a distance matrix is constructed to calculate shortest-path distances between nodes. Documents are clustered to identify a largest cluster from which content is retrieved to formulate a response. The disclosed embodiments improve upon retrieval augmented generation (RAG) by leveraging the hierarchical relationships of a knowledge graph and node interconnectedness to provide contextually coherent information and mitigate the inclusion of information from irrelevant or superficially related documents in LLM responses.