Intent Classification for Contextual Content Delivery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional online search engines struggle to provide relevant supplementary content due to their reliance on keywords, which fail to capture the intent behind a query, especially when contextual information is lacking.
Innovation Solution
A computing system that utilizes conversational data from interactions between a client device and a generative model to classify user intent, generate anchor text, and create content queries, thereby providing intent-specific and contextually relevant content.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If keywords are used to identify supplementary content, then the content retrieval process is simple and fast, but the relevance of supplementary content to user intent deteriorates
Solution Approach 1:
The patent introduces an intent classification module as an intermediary between the query processing system and the content retrieval system. This module analyzes conversational data to determine user intent, which then guides the content retrieval process. The intermediary translates simple keyword queries into intent-aware content selection, resolving the contradiction between fast retrieval and relevant content delivery.
2Reliability
If conversational data processing with intent classification is implemented, then content relevance to user intent is improved, but computational resources and system complexity increase
Solution Approach 1:
The system performs preliminary intent classification on conversational data before content retrieval. By pre-processing the conversational input to determine user intent, the system avoids complex real-time analysis during content delivery. This preliminary action simplifies the overall system architecture while maintaining high content relevance.
3Use of energy by moving object
If conventional keyword-based content identification is used, then the system operates with minimal computational resources, but the number of iterations needed to find relevant information increases
Solution Approach 1:
The patent implements a feedback mechanism where the intent classification module continuously refines content selection based on conversational data. The system uses feedback from user interactions and conversational context to improve content relevance over time, reducing the number of iterations needed to find relevant information while maintaining efficient resource usage.
Data Source
AI summary
A computing system is disclosed that includes a processor and memory. The memory stores instructions that, when executed by the processor, cause the processor to perform several acts. The acts comprise receiving conversational data indicative of an interaction between a client computing device and a generative model. The conversational data is provided as input into an intent classification module and the intent classification module produces an output indicative of a user intent based upon the conversational data. An anchor generation module generates anchor text indicative of portions of the conversational data correlated with the user intent. A content query based upon the anchor text is generated and content responsive to the content query is obtained and presented at the client computing device.