LLM Financial Event Response for Clear Reason Code Explanations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional reason codes generated by AI and ML models for financial transactions are vague and difficult for users to understand, leading to poor adoption and increased manpower requirements for interpretation.
Innovation Solution
A computer-implemented method using a Large Language Model (LLM) to determine prompt intent, type, and attributes, extracting relevant information from a database, and generating a curated response in natural language to facilitate user understanding.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If conventional reason codes are used to communicate financial event outcomes, then the information can be easily understood by computing equipment, but the codes become vague and difficult for human users to understand
Solution Approach 1:
The patent introduces an intermediary system that translates between reason codes and natural language explanations. This intermediary layer maintains the efficiency of code-based communication while adding human-understandable context, resolving the contradiction between machine readability and human comprehension.
Solution Approach 2:
The system segments the information delivery into two distinct parts: the structured reason code for machine processing and the natural language explanation for human understanding. This segmentation allows each part to serve its specific purpose effectively without compromising the other.
2Loss of information
If detailed reason codes are provided for each financial event, then the information completeness is improved, but the complexity of interpretation increases requiring more manpower
Solution Approach 1:
The system enables self-service by automatically generating natural language explanations from reason codes without requiring human interpreters. The automated translation service handles the complexity of interpretation, freeing human users from manually analyzing detailed reason codes while maintaining complete information availability.
3Ease of operation
If standardized reason codes are used across the payment network, then the ease of communication between entities is improved, but the adaptability to specific user contexts is reduced
Solution Approach 1:
The system dynamically adapts the communication by taking static reason codes and transforming them into context-aware natural language explanations. The translation process adjusts the output based on the specific financial event and user context, maintaining standardization benefits while adding adaptability.
Data Source
AI summary
Methods and systems for responding to prompts related to financial events are described herein. A method performed by a server system includes determining, by a Large Language Model (LLM) associated with the server system, a prompt intent based, at least in part, on a prompt from a user. The method includes determining a prompt type of the prompt based, at least in part, on the prompt intent. The method includes identifying, by the LLM, prompt attributes associated with the prompt. The prompt attributes indicate information describing financial events associated with an entity. The method includes extracting relevant information associated with the entity from a database based on the prompt intent, the prompt type, and the prompt attributes. The method includes generating, by the LLM, a prompt response based, at least in part, on the relevant information and the prompt intent. The method includes transmitting the prompt response to the user.