Neural Network Context Maintenance for Conversational Search Queries

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional conversation systems struggle to effectively maintain context between queries, relying on rigid rule-based systems that limit query inputs and require users to rephrase or learn specific inputs, leading to suboptimal user experience.

Innovation Solution

A media guidance application employs an artificial neural network to determine whether to merge or replace queries based on input words, using a training dataset to update weights and predict merge or replace operations, allowing for more flexible and accurate context management.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If rule-based systems are used to determine context switching, then the system structure is simple and easy to implement, but the system has limited query inputs and requires users to learn specific inputs

Engineering Contradiction:

Improveease of implementationVSAvoidquery input flexibility

Core Design Contradiction:

Ease of manufactureVSAdaptability or versatility

Solution Approach 1:

The patent replaces the mechanical rule-based system with a neural network-based semantic analysis system. Instead of using predefined rules to determine context switching, the system uses machine learning models to analyze the semantic meaning of queries and automatically determine whether to maintain or switch context, thereby achieving both implementation feasibility and query flexibility.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent changes the parameter of context determination from discrete rule matching to continuous semantic similarity scoring. By using similarity thresholds and weighted feature analysis, the system can dynamically adjust context maintenance decisions based on the degree of semantic overlap between current and historical queries, enabling flexible adaptation to various query types.

Inventive Principle:

Principle #35Parameter changes

2Device complexity

If rule-based systems are used to maintain context, then the system complexity is low, but the user experience is suboptimal due to rigid query requirements

Engineering Contradiction:

Improvesystem complexityVSAvoiduser experience

Core Design Contradiction:

Device complexityVSEase of operation

Solution Approach 1:

The patent replaces rigid rule-based context management with a flexible neural network-based semantic analysis system. The system automatically understands user intent through machine learning, eliminating the need for users to learn specific query formats while maintaining manageable system complexity through modular architecture.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces dynamic context management where the system adaptively adjusts context maintenance decisions based on real-time semantic analysis. Instead of static rules, the system dynamically determines context relevance using similarity scoring and historical query patterns, providing optimal user experience without excessive complexity.

Inventive Principle:

Principle #15Dynamics

3Ease of operation

If conventional search systems are used, then the system is simple to operate, but the system cannot effectively maintain context between queries

Engineering Contradiction:

Improvesystem operabilityVSAvoidcontext information retention

Core Design Contradiction:

Ease of operationVSLoss of information

Solution Approach 1:

The patent implements preliminary context analysis by maintaining a history of previous queries and pre-computing semantic relationships. Before processing each new query, the system preliminarily identifies relevant historical contexts and prepares appropriate context maintenance strategies, ensuring neither information loss nor operational complexity.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces conventional search systems that process queries independently with a neural network-based system that continuously maintains contextual information. The system uses semantic similarity analysis to automatically retain and apply relevant context from historical queries, preventing information loss while keeping the interface simple for users.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20250005054A1Methods and systems for performing context maintenance on search queries in a conversational search environment

Publication Date: 2025.01.02 ADEIA GUIDES INC

AI summary

Systems and methods are described herein that maintain a context in a conversational search systems. An artificial neural network accepts current and previous queries as input and outputs a value indicating whether the previous query and the current query should undergo a merge operation or a replacement operation to maintain an intent of the user. To perform a merge operation, the previous query and the current query are combined to form a search query. To perform a replace operation, a portion of the previous query is replaced with a portion of the current query.