Conversational AI Interface for Backend Data Transactions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional user interaction paradigms in business applications are cumbersome and unintuitive, requiring repetitive navigation through multiple pages and manual data entry, which is time-consuming and difficult for users unfamiliar with the application's UI workflows.
Innovation Solution
A conversational AI system that enables users to perform application tasks via natural language, automatically collecting user interaction data to populate a knowledge database and transaction function list, using a retrieve-augment-generate approach with a large language model to execute data transactions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional UI workflow with multiple pages is used, then data transaction functionality is achieved, but user interaction time and complexity increase
Solution Approach 1:
The patent segments the traditional multi-page UI workflow into a single conversational interface. Instead of requiring users to navigate through multiple pages (customer details page, address page, contact details page), the system segments these functions into a unified natural language processing task where a single conversation handles all data collection and transaction execution.
Solution Approach 2:
The patent introduces a conversational AI system as an intermediary between the user and the backend data store. This intermediary translates natural language user intent into structured data transactions, eliminating the need for users to directly interact with complex multi-page UI workflows while ensuring accurate data transmission and transaction execution.
2Reliability
If traditional UI workflow with multiple pages is used, then data transaction functionality is achieved, but operational efficiency decreases
Solution Approach 1:
The patent segments the traditional multi-page UI workflow into a single conversational interface. Instead of requiring users to navigate through multiple pages (customer details page, address page, contact details page), the system segments these functions into a unified natural language processing task where a single conversation handles all data collection and transaction execution.
Solution Approach 2:
The conversational AI system performs self-service by automatically interpreting user intent, collecting necessary information, validating data, and executing transactions without requiring users to manually navigate through multiple pages or understand complex UI workflows. The system autonomously manages the entire data transaction process.
3Adaptability or versatility
If manual data set assembly is required, then system customization is achieved, but implementation complexity increases
Solution Approach 1:
The system performs self-service by automatically collecting user interaction data from the software application during normal operation. This collected data is used to automatically populate the knowledge database with text tokens and embeddings, and to generate the transaction function list, eliminating the need for manual data set assembly by data scientists or developers.
Solution Approach 2:
The system performs preliminary actions by continuously collecting and processing user interaction data in the background during normal application usage. This preliminary data collection and processing prepares the knowledge database and transaction function list in advance, so that when a user submits a natural language request, the system already has the necessary structured information ready for rapid processing.
Data Source
AI summary
A conversational artificial intelligence (AI) system is provided that enables the users of a software application to perform application tasks (and in particular, initiate data transactions against a backend data store) using natural language. In one set of embodiments, the system can automatically collect user interaction data from the software application “on-the-fly,” while the users interact with the application via the application's conventional UI workflows. The system can then use this collected user interaction data to process user natural language requests via a retrieve-augment-generate (RAG) approach that leverages a large language model (LLM).