View source for Oracle international corporation (20240126795). CONVERSATIONAL DOCUMENT QUESTION ANSWERING simplified abstract

=CONVERSATIONAL DOCUMENT QUESTION ANSWERING=


==Organization Name==

[[:Category:oracle international corporation|oracle international corporation]]


[[Category:oracle international corporation]]

==Inventor(s)==

[[:Category:Xu Zhong of Melbourne (AU)|Xu Zhong of Melbourne (AU)]][[Category:Xu Zhong of Melbourne (AU)]]

[[:Category:Thanh Long Duong of Seabrook (AU)|Thanh Long Duong of Seabrook (AU)]][[Category:Thanh Long Duong of Seabrook (AU)]]

[[:Category:Mark Edward Johnson of Sydney (AU)|Mark Edward Johnson of Sydney (AU)]][[Category:Mark Edward Johnson of Sydney (AU)]]

[[:Category:Charles Woodrow Dickstein of New York NY (US)|Charles Woodrow Dickstein of New York NY (US)]][[Category:Charles Woodrow Dickstein of New York NY (US)]]

[[:Category:King-Hwa Lee of Bellevue WA (US)|King-Hwa Lee of Bellevue WA (US)]][[Category:King-Hwa Lee of Bellevue WA (US)]]

[[:Category:Xin Xu of San Jose CA (US)|Xin Xu of San Jose CA (US)]][[Category:Xin Xu of San Jose CA (US)]]

[[:Category:Srinivasa Phani Kumar Gadde of Fremont CA (US)|Srinivasa Phani Kumar Gadde of Fremont CA (US)]][[Category:Srinivasa Phani Kumar Gadde of Fremont CA (US)]]

[[:Category:Vishal Vishnoi of Redwood City CA (US)|Vishal Vishnoi of Redwood City CA (US)]][[Category:Vishal Vishnoi of Redwood City CA (US)]]

[[:Category:Christopher Kennewick of Kirkland WA (US)|Christopher Kennewick of Kirkland WA (US)]][[Category:Christopher Kennewick of Kirkland WA (US)]]

[[:Category:Balakota Srinivas Vinnakota of Sunnyvale CA (US)|Balakota Srinivas Vinnakota of Sunnyvale CA (US)]][[Category:Balakota Srinivas Vinnakota of Sunnyvale CA (US)]]

[[:Category:Raefer Christopher Gabriel of San Jose CA (US)|Raefer Christopher Gabriel of San Jose CA (US)]][[Category:Raefer Christopher Gabriel of San Jose CA (US)]]

==CONVERSATIONAL DOCUMENT QUESTION ANSWERING - A simplified explanation of the abstract==


This abstract first appeared for US patent application 20240126795 titled 'CONVERSATIONAL DOCUMENT QUESTION ANSWERING

==Simplified Explanation==

The patent application describes techniques for integrating document question answering in an artificial intelligence-based platform, such as a chatbot system. 

* Receiving a query from a user
* Rewriting the query to include specific descriptors
* Computing an embedding vector for the rewritten query
* Retrieving textual passages from a document store using the embedding vector
* Determining answers within the retrieved passages
* Returning the answers to the user

== Potential Applications ==
This technology could be applied in customer service chatbots, virtual assistants, and search engines to provide accurate and relevant answers to user queries.

== Problems Solved ==
This technology solves the problem of efficiently retrieving information from large document stores and providing precise answers to user queries in real-time.

== Benefits ==
The benefits of this technology include improved user experience, increased efficiency in information retrieval, and enhanced accuracy in answering user queries.

== Potential Commercial Applications ==
Potential commercial applications of this technology include customer support systems, knowledge management platforms, and information retrieval tools.

== Possible Prior Art ==
One possible prior art for this technology could be existing question answering systems that utilize natural language processing techniques to retrieve information from documents and provide answers to user queries.

=== Unanswered Questions ===

=== How does this technology handle multi-turn conversations in a chatbot system? ===
This technology focuses on retrieving answers to single queries from documents. Handling multi-turn conversations may require additional techniques for context retention and dialogue management.

=== What is the impact of the size of the document store on the performance of this technology? ===
The performance of this technology may vary depending on the size of the document store and the complexity of the queries. Further research may be needed to evaluate its scalability and efficiency with large document repositories.


==Original Abstract Submitted==

techniques are disclosed herein for integrating document question answering in an artificial intelligence-based platform, such as a chatbot system. the techniques include receiving a query from a user, rewriting the query to include one or more specific descriptors, computing an embedding vector for the rewritten query, retrieving one or more textual passages from a document store utilizing the embedding vector for the rewritten query, determining one or more answers to the rewritten query within the one or more textual passages, and returning the one or more answers.



[[Category:G06F16/332]]
[[Category:G06F40/30]]
[[Category:H04L51/02]]
[[Category:H04L51/216]]