Contextual Transaction Data Collection Through LLM Chat
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing financial transaction management applications require manual navigation through multiple interfaces and rely on predefined scripts, leading to inefficiencies and errors, especially for users unfamiliar with the system.
Innovation Solution
Implementing a chat application with a large language model that automatically generates responses based on user inputs to seamlessly collect and manage transaction data, allowing for natural and interactive communication.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional manual navigation through application sections is used, then users can complete transactions, but the process is time-consuming and error-prone
Solution Approach 1:
The patent replaces the mechanical manual navigation system with an AI-based natural language processing system. The chat interface allows users to communicate in natural language instead of manually navigating through application sections, significantly reducing the time required to complete transactions while maintaining accuracy through automated data validation.
Solution Approach 2:
The system enables self-service by allowing users to initiate and complete transactions through conversational commands without requiring manual navigation or assistance. The AI assistant automatically processes user requests, retrieves necessary information, and completes transactions based on natural language inputs, empowering users to independently manage their financial operations efficiently.
2Adaptability or versatility
If predefined scripts are used for transaction management, then the system is easy to implement, but it cannot handle natural language inputs and contextual understanding
Solution Approach 1:
The patent introduces an AI language model as an intermediary layer between the user and the transaction management system. This intermediary translates natural language inputs into structured commands that the backend system can process, enabling the system to understand contextual nuances and intent while maintaining a relatively simple underlying architecture. The intermediary handles the complexity of natural language interpretation, allowing the core transaction system to remain straightforward.
3Reliability
If users manually enter transaction data, then data accuracy can be maintained, but the process is tedious and error-prone for unfamiliar users
Solution Approach 1:
The patent replaces manual data entry with automated natural language processing. Users simply describe their transaction intent in natural language, and the AI system automatically extracts, validates, and structures the necessary data fields. This substitution maintains high data accuracy through automated validation rules while dramatically improving ease of operation, especially for users unfamiliar with the system's data requirements.
4Ease of operation
If standard user interfaces are used, then the application is straightforward to develop, but it requires manual navigation and reduces user engagement
Solution Approach 1:
The patent transforms the static standard user interface into a dynamic conversational interface. The chat system adapts to user inputs in real-time, dynamically generating appropriate responses and guiding users through transactions based on their specific needs and context. This dynamic interaction significantly improves both ease of operation and transaction completion efficiency compared to rigid standard interfaces.
Data Source
AI summary
A mobile electronic device includes a network interface and one or more processors coupled to memory. The one or more processors can be configured to receive a message comprising transaction data regarding a transaction and a request regarding activating a chat application stored in the memory; the chat application, wherein the chat application is configured to execute a large language model using the transaction data and account data as input to generate a first string of text requesting further data regarding the transaction; present the first string of text at a chat interface of the chat application; receive additional transaction data; execute the large language model using the additional transaction data as input to generate a second string of text indicating storage of the additional data in a record; and present the second string of text at the chat interface.


