Query Interaction System for Ambiguous Search Intent Resolution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In complex search scenarios, the diversity and ambiguity of user expressions often lead to search engines failing to accurately capture real search intentions, resulting in deviations between search results and users' actual needs.
Innovation Solution
A method and apparatus for determining interaction information by generating questioning dimensions based on query information and historical query data, guiding users to provide more detailed information through questioning, and thereby improving the accuracy and relevance of search results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If search engines directly process user queries without additional interaction, then the search process is fast and simple, but the search results may not accurately reflect user intentions due to expression diversity and ambiguity
Solution Approach 1:
The system performs preliminary analysis of query information and historical query information to generate questioning dimensions before the actual search execution. This preliminary action identifies potential ambiguity in user expressions and prepares targeted questions in advance, allowing the system to clarify user intentions before final search result generation, thereby improving accuracy without significantly increasing overall process complexity
Solution Approach 2:
The system implements a feedback mechanism where query results are analyzed to determine whether questioning is needed. If the initial search results do not adequately address user needs (as determined by evaluating semantic consistency), the system generates follow-up questions based on identified questioning dimensions. This feedback loop ensures that additional interaction complexity is only introduced when necessary to improve search accuracy
2Measurement precision
If the system generates multiple questioning dimensions to clarify user intent, then the accuracy of search results improves, but the user interaction time and process length increase
Solution Approach 1:
The system generates multiple questioning dimensions but does not necessarily present all of them to users. Instead, it selects a subset of the most relevant questioning dimensions based on the analysis of query information and historical data. This partial action approach ensures that only the necessary number of questions are asked to achieve adequate clarification of user intent, balancing accuracy improvement with time efficiency
Solution Approach 2:
The system applies different questioning strategies to different aspects of the query based on where ambiguity is most pronounced. Rather than uniformly questioning all aspects, it focuses questioning efforts on specific dimensions (such as time, location, or topic specifics) where the greatest uncertainty exists, thereby minimizing overall interaction time while maintaining search accuracy
3Adaptability or versatility
If the system uses historical query information to generate questioning dimensions, then the personalization and relevance of search improves, but the complexity of data processing increases
Solution Approach 1:
The system processes historical query information to extract multiple types of useful data simultaneously, including user preferences, behavioral patterns, and contextual information. This multi-functional processing of historical data allows the system to generate questioning dimensions that are personalized to each user while reusing the same historical data for multiple purposes, thereby reducing overall processing complexity
Solution Approach 2:
The system creates simplified representations or copies of complex historical query patterns that can be quickly referenced when generating questioning dimensions. Instead of reprocessing entire historical query datasets each time, it uses pre-processed templates or condensed versions of historical information, reducing the computational complexity while maintaining the personalization benefits
Data Source
Figure 1~2
Figure 3A
Figure 3B
AI summary
The present disclosure provides a method and an apparatus of determining interaction information, an electronic device and a storage medium, which relates to a field of artificial intelligence technology, in particular to a large model, a generative model, an NLP, an intelligent search and other fields. The specific implementation plan is to determine a plurality of questioning dimensions according to query information of a subject and historical query information, where each questioning dimension includes a dimension name and a plurality of options; determine a target questioning dimension from the plurality of questioning dimensions according to evaluation values of the plurality of questioning dimensions and whether semantic information of the plurality of questioning dimensions are consistent with semantic information of a query result associated with the query information; and determine the interaction information according to the dimension name and the plurality of options in the target questioning dimension.