Glean Technologies, Inc. (20240256582). Search with Generative Artificial Intelligence simplified abstract

Search with Generative Artificial Intelligence

Organization Name

Glean Technologies, Inc.

Inventor(s)

Arvind Jain of Los Altos CA (US)

Calvin Qi of San Francisco CA (US)

Chau Hai Tran of New York NY (US)

Eddie Zhou of Redwood City CA (US)

Megha Jhunjhunwala of Redwood City CA (US)

Mrinal Mohit of San Francisco CA (US)

Pancham Yadav of San Francisco CA (US)

Philip Ophus of Redwood City CA (US)

Shivaal Roy of Palo Alto CA (US)

Vivek Choksi of Los Altos Hills CA (US)

Search with Generative Artificial Intelligence - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240256582 titled 'Search with Generative Artificial Intelligence

The patent application describes methods and apparatuses for utilizing generative artificial intelligence (AI) techniques to automatically generate and display summaries of search results.

• A search and knowledge management system generates a set of search results for a given query and provides them as input to a generative AI model.
• The generative AI model, such as a Generative Pre-trained Transformer (GPT) model, generates a summary response in natural language text.
• The set of search results may include electronic documents and messages, which the AI model summarizes for easy understanding.

Potential Applications:

• Enhancing search engine capabilities by providing concise summaries of search results.
• Improving knowledge management systems by automatically generating summaries of relevant information.
• Streamlining information retrieval processes for users by presenting summarized content.

Problems Solved:

• Reducing the time and effort required to sift through search results.
• Enhancing the accessibility and comprehension of search results for users.
• Automating the summarization process to increase efficiency in information retrieval.

Benefits:

• Increased efficiency in processing and understanding search results.
• Improved user experience by providing concise and relevant summaries.
• Enhanced productivity by automating the summarization of large amounts of information.

Commercial Applications:

• Search engine optimization tools for businesses looking to improve their online visibility.
• Knowledge management software for organizations seeking to streamline information retrieval processes.
• Content curation platforms for aggregating and summarizing relevant information for users.

Questions about the technology: 1. How does the generative AI model determine which information to include in the summary response? 2. What are the potential limitations of using AI to generate summaries of search results?

Original Abstract Submitted

methods and apparatuses for utilizing generative artificial intelligence (ai) techniques to automatically generate and display summaries of search results are described. a search and knowledge management system may generate a set of search results for a given search query and provide the set of search results (e.g., a set of verified documents that are the most relevant verified documents for the search query) as part of an input prompt to guide a generative ai model in generating a summary response of the set of search results. the generative ai model may comprise a generative pre-trained transformer (gpt) model. the summary response may comprise a natural language text response and the set of search results may comprise electronic documents and messages and/or portions thereof.