Conversation Automation Mapping for Unstructured Chat Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing chat-bots lack access to comprehensive information, limiting their ability to provide insights or drive key performance indicators (KPIs) due to unstructured conversational data, which is often free-form and lacks semantic structure.
Innovation Solution
Automatically map conversations to high-level semantic groups, cluster similar conversations, and assign representative utterances to create structural metadata, enabling performance metric determination and automation recommendations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If chat-bots are used to provide automated information, then productivity and cost efficiency are improved, but the functionality is limited due to lack of access to comprehensive information from unstructured conversational data
Solution Approach 1:
The patent introduces an intermediary system comprising a conversation mapping service and analytics service that bridges the gap between unstructured conversational data and chat-bot functionality. This intermediary automatically maps conversations to semantic groups, extracts insights, and makes structured information available to chat-bots, thereby enhancing their functionality without sacrificing automation efficiency
Solution Approach 2:
The system performs preliminary actions by automatically mapping and analyzing conversations before they are needed for decision-making. Conversation histories are pre-processed, tagged with semantic groups, and stored in an analytics database, so that when chat-bots need information, structured insights are already available rather than processing unstructured data in real-time
2Quantity of substance
If unstructured conversational data is used directly, then data quantity is maximized, but measurement precision and business intelligence capability deteriorate due to lack of semantic structure
Solution Approach 1:
The patent applies segmentation by dividing the large volume of unstructured conversational data into meaningful segments organized by semantic groups. The conversation mapping service segments conversations based on topics, customer issues, and interaction types, making the data measurable and analyzable while preserving the complete data quantity
Solution Approach 2:
The system changes the parameters of conversational data by transforming unstructured text into structured metadata with defined parameters such as semantic group tags, conversation outcomes, and sentiment indicators. This parameter transformation enables precise measurement and business intelligence extraction from the same data volume
3Measurement precision
If manual analysis of conversations is performed, then measurement precision and insights are improved, but productivity and time consumption deteriorate
Solution Approach 1:
The system implements self-service by enabling automated self-mapping of conversations to semantic groups without human intervention. The conversation mapping service automatically analyzes conversation content, identifies semantic patterns, and assigns appropriate tags, providing measurement precision equivalent to manual analysis while maintaining high productivity through automation
Solution Approach 2:
The analytics service provides feedback loops where conversation insights are continuously refined based on performance metrics and business outcomes. The system learns from analyzed conversations and improves its mapping accuracy over time, maintaining high measurement precision while keeping analysis速度快 through automated iterative improvement
Data Source
AI summary
Database systems and methods are provided for assigning structural metadata to records and creating automations using the structural metadata. One method of assisting creation of an automation for conversational interactions involves providing a first graphical user interface (GUI) display including graphical indicia of a plurality of semantic groups associated with historical conversations, in response to selection of a semantic group, providing a second GUI display including second graphical indicia of a plurality of cluster groups of conversations associated with the selected semantic group, in response to second selection of a cluster group, providing a third GUI display including third graphical indicia of representative utterances associated with respective conversations of a subset of historical conversations assigned to the selected cluster group, and in response to third selection of a GUI element on the third GUI display, providing a fourth GUI display including GUI elements for defining the automation.