Domain Assistant Query Flow for Adaptive Information Gathering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional Q&A systems use rigid conversational workflows with a fixed set of questions, limiting their ability to adapt to user-specific information needs and contexts.
Innovation Solution
A method that identifies known and unknown informational items associated with an object, generates tailored questions to determine unknown information, and provides responses based on known information, using a virtual agent and context-aware sequencing of questions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a fixed set of questions is used in a specific order, then the system structure is simple and easy to implement, but the system cannot adapt to user-specific information needs and contexts
Solution Approach 1:
The patent implements dynamic conversational workflows where the sequence and content of questions are adjusted in real-time based on user responses and context. The system transitions from static fixed-question sequences to dynamic adaptive sequences that modify their path based on information gaps detected during interaction, resolving the contradiction between adaptability and complexity.
Solution Approach 2:
The system incorporates feedback mechanisms where user responses are analyzed to determine what information has been obtained and what remains unknown. This feedback loop enables the system to adaptively select subsequent questions based on actual information needs rather than following a predetermined sequence, achieving adaptability while managing complexity through intelligent feedback processing.
2Productivity
If all informational items are queried regardless of known status, then information completeness is ensured, but user interaction time and system efficiency decrease
Solution Approach 1:
The patent applies partial action by querying only the necessary portion of informational items rather than all possible items. The system identifies information gaps and selectively queries only those items needed to resolve the current query, avoiding redundant questions about already-known information while maintaining completeness of essential information.
Solution Approach 2:
The system performs preliminary identification of known versus unknown informational items before generating questions. By pre-assessing what information is already available and what needs to be queried, the system avoids unnecessary interactions while ensuring all critical information is obtained, thereby improving efficiency without sacrificing completeness.
3Reliability
If context-aware question sequencing is implemented, then user-specific information needs are addressed effectively, but computational requirements and processing time increase
Solution Approach 1:
The patent segments the information gathering process into distinct phases: identifying known information, determining information gaps, selecting relevant questions, and executing queries. This segmentation allows the system to apply context-aware sequencing only where necessary rather than processing all information uniformly, reducing overall computational energy while maintaining reliability.
Data Source
AI summary
A method, computer program product, and computer system identifying intent relating to a query associated with an object. A plurality of informational items associated with the object may be identified. At least a first informational item associated with the object for which a first portion of information is already known may be identified. At least a second informational item associated with the object for which a second portion of information is unknown may be identified. A question may be generated to determine the second portion of information based upon the second portion of information being unknown. An answer may be received to determine the second portion of information. A response to the intent relating to the query may be provided based upon the first informational item for which the first portion of information is already known and the answer for the question generated to determine the second portion of information.