AI Interaction System for Intent-Based Query Modification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional search engine technologies require users to re-enter complete query strings for modifications, leading to inefficiencies in expressing and updating search needs, as they only allow users to fully express their needs in a single query round.
Innovation Solution
An interaction method and apparatus using artificial intelligence that analyzes previous and current interactive statements to determine intent maintenance relationships, updating limitation conditions for information retrieval, allowing users to supplement or modify queries without re-entering the complete query string by identifying intent-related words and statement combinations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If traditional search engine technology is used, then users can express their search needs, but users must re-enter complete query strings for modifications, leading to increased input time and reduced interaction efficiency
Solution Approach 1:
The system segments the query processing into two parts: maintaining the original complete query string and allowing incremental modifications. The neural network model analyzes the relationship between original and modified queries, enabling users to input only the modified portion rather than the complete query string, thus reducing input time while preserving search accuracy
Solution Approach 2:
The system performs preliminary analysis by storing and maintaining the original query string and its semantic understanding. When users need to modify their search, the system already has the baseline query ready, so users only need to provide the modification delta, not the complete query again, significantly reducing repeated input
2Adaptability or versatility
If traditional search engine technology is used, then basic search functionality is provided, but the system cannot understand intent maintaining relationships between multiple queries, reducing interaction intelligence
Solution Approach 1:
The patent introduces a neural network model as an intermediary between the user's modified query and the search engine. This intermediary analyzes the semantic relationship between original and modified queries, determines intent maintaining relationships, and translates incremental inputs into complete search queries, thereby enhancing intent understanding without requiring complete system redesign
Solution Approach 2:
The system implements feedback by analyzing the relationship between original queries and modified queries through the neural network model. The model provides feedback on whether the modification maintains the original intent, allowing the system to adaptively process multi-turn queries with improved intelligence while managing complexity through targeted AI processing
Data Source
AI summary
The present disclosure discloses an interaction method and apparatus based on artificial intelligence. A specific embodiment of the method comprises: receiving a current interactive statement entered by a user through a terminal; extracting at least one type of characteristic based on the current interactive statement and a previous interactive statement entered by the user; processing the at least one type of characteristic using a pretrained neural network model to determine whether an intent maintaining relationship exists between the current interactive statement and the previous interactive statement; and if the intent maintaining relationship exists, updating a limitation condition for the previous interactive statement using the current interactive statement, performing information retrieval using the previous interactive statement with the updated limitation condition, and pushing a retrieved retrieval result to the terminal. This embodiment reduces time spent in user entry.