View source for 18391417. SYSTEMS AND METHODS FOR DETERMINING FINANCIAL SECURITY RISKS USING SELF-SUPERVISED NATURAL LANGUAGE EXTRACTION simplified abstract (Capital One Services, LLC)

=SYSTEMS AND METHODS FOR DETERMINING FINANCIAL SECURITY RISKS USING SELF-SUPERVISED NATURAL LANGUAGE EXTRACTION=


==Organization Name==

[[:Category:Capital One Services, LLC|Capital One Services, LLC]]


[[Category:Capital One Services, LLC]]

==Inventor(s)==

[[:Category:Minnie Virk of Jersey City NJ (US)|Minnie Virk of Jersey City NJ (US)]][[Category:Minnie Virk of Jersey City NJ (US)]]

[[:Category:Rohan Mehta of Brooklyn NY (US)|Rohan Mehta of Brooklyn NY (US)]][[Category:Rohan Mehta of Brooklyn NY (US)]]

[[:Category:Alberto Silva of Brooklyn NY (US)|Alberto Silva of Brooklyn NY (US)]][[Category:Alberto Silva of Brooklyn NY (US)]]

[[:Category:Anthony Shewnarain of Valley Stream NY (US)|Anthony Shewnarain of Valley Stream NY (US)]][[Category:Anthony Shewnarain of Valley Stream NY (US)]]

[[:Category:Steven Freeman of Cranford NJ (US)|Steven Freeman of Cranford NJ (US)]][[Category:Steven Freeman of Cranford NJ (US)]]

[[:Category:Stephen Jurcsek of Jersey City NJ (US)|Stephen Jurcsek of Jersey City NJ (US)]][[Category:Stephen Jurcsek of Jersey City NJ (US)]]

[[:Category:Leah Lewy of Jersey City NJ (US)|Leah Lewy of Jersey City NJ (US)]][[Category:Leah Lewy of Jersey City NJ (US)]]

[[:Category:Ross Arkin of Brooklyn NY (US)|Ross Arkin of Brooklyn NY (US)]][[Category:Ross Arkin of Brooklyn NY (US)]]

==SYSTEMS AND METHODS FOR DETERMINING FINANCIAL SECURITY RISKS USING SELF-SUPERVISED NATURAL LANGUAGE EXTRACTION - A simplified explanation of the abstract==


This abstract first appeared for US patent application 18391417 titled 'SYSTEMS AND METHODS FOR DETERMINING FINANCIAL SECURITY RISKS USING SELF-SUPERVISED NATURAL LANGUAGE EXTRACTION

==Simplified Explanation==

The abstract describes a system for dynamic detection of security features based on self-supervised natural language extraction from unstructured data sets. The system analyzes financial narratives to identify potential risks and take security actions when necessary.

* The system receives unstructured financial data and extracts discrete risk narratives.
* It builds a tokenization dictionary and calculates relevancy and sentiment scores for each narrative.
* An overall risk score is determined based on a weighted average of the relevancy and sentiment scores.
* Security actions are executed when the overall risk score exceeds a predetermined threshold.

== Potential Applications ==
This technology could be applied in financial institutions for real-time risk detection and security enhancement.

== Problems Solved ==
This system helps in identifying potential security risks in financial data and taking proactive security measures.

== Benefits ==
The system provides a dynamic and automated way to detect security features in financial narratives, improving overall security measures.

== Potential Commercial Applications ==
Potential commercial applications include financial institutions, cybersecurity companies, and any organization dealing with sensitive financial data.

== Possible Prior Art ==
One possible prior art could be traditional risk assessment methods in financial institutions, which may not be as dynamic and automated as the system described in the patent application.

== Unanswered Questions ==

=== How does the system handle false positives in risk detection? ===
The system's ability to differentiate between actual security risks and false alarms is not clearly addressed in the abstract.

=== What is the scalability of the system for large volumes of unstructured data? ===
The abstract does not mention the system's capability to handle large data sets and its scalability in real-world applications.


==Original Abstract Submitted==

Systems and methods for dynamic detection of security features based on self-supervised natural language extraction from unstructured data sets are disclosed. The system may receive an unstructured data array including a full text of financial narrative. The system may serialize the unstructured data array to form one or more first data arrays including portions of the full text as discrete financial risk narratives. The system may build a tokenization dictionary and determine condensed summaries for each portion of the full text. The system may determine a relevancy score and a sentiment score for each condensed summary and calculate an overall relevancy score as a weighted average of the relevancy score and the sentiment score. When the overall risk score exceeds a predetermined threshold, the system may execute one or more security actions.



[[Category:G06Q40/03]]
[[Category:G06F40/279]]
[[Category:G06N20/00]]
[[Category:G06Q20/38]]