Query Gateway for Context-Retained Search-to-Chat Transitions

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing search engine services lack a framework for integrating context-retention between autosuggest and generative language models, leading to inefficiencies and inaccuracies in transitioning between these systems, particularly on devices with smaller displays.

Innovation Solution

A query gateway system that facilitates context-retained autosuggest queries from an autosuggest query system to a generative language model system, utilizing AI chat eligibility and reformulation models to enhance computational efficiency and accuracy, and minimize navigational disruptions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If search engine services and generative language models operate independently, then each service can maintain its own functionality, but there is no context-retention between services and no mechanism to leverage advancements from one service to improve the other

Engineering Contradiction:
Improvecontext-retention between servicesVSAvoidintegration framework complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent introduces an intermediary mechanism that enables context-retention between search engine services and generative language models. This intermediary allows the two independently operating services to share context and leverage each other's capabilities without requiring full integration, thus maintaining functionality while enabling cross-service context retention.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Productivity

If features are enhanced in one service, then that service's performance improves, but there is no mechanism to leverage these advancements to improve the other service

Engineering Contradiction:
Improveservice performanceVSAvoidcross-service feature leverage
Core Design Contradiction:
ProductivityVSAdaptability or versatility

Solution Approach 1:

The patent implements a universal framework where advancements and features from one service (search engine or generative language model) can be leveraged to improve the other service. This multi-functionality allows context and capabilities to flow bidirectionally between services, enabling cross-service feature leverage while maintaining each service's core functionality.

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Ease of operation

If users manually navigate between search and chat systems, then they can access both services, but this causes navigational disruptions and requires manual re-entry of queries

Engineering Contradiction:
Improveservice accessibilityVSAvoidnavigational time
Core Design Contradiction:
Ease of operationVSLoss of time

Solution Approach 1:

The patent merges the navigation experience between search and chat services by maintaining context across service transitions. Users can access both services without manual re-entry of queries, as the system preserves context and automatically continues the interaction flow, eliminating navigational disruptions and reducing time loss.

Inventive Principle:
Principle #5Merging (Combining)

4Measurement precision

If the system reformulates autosuggest queries using AI chat eligibility and reformulation models, then computational efficiency and accuracy improve, but the system complexity increases

Engineering Contradiction:
Improvequery accuracyVSAvoidmodel integration complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies preliminary action by using AI chat eligibility models and reformulation models to pre-process autosuggest queries before they are executed. This preliminary processing improves query accuracy and computational efficiency by identifying eligible queries for chat conversion and reformulating them in advance, reducing the complexity of real-time processing.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS20260057018A1Generating narrative query responses utilizing generative language models from search-based autosuggest queries
Publication Date: 2026.02.26 MICROSOFT TECHNOLOGY LICENSING LLC
  • US20260057018A1 patent drawing
  • US20260057018A1 patent drawing
  • US20260057018A1 patent drawing

AI summary

This disclosure describes a query gateway system that provides an efficient and flexible framework for providing context-retained autosuggest queries from an autosuggest query system (e.g., a search engine query experience) to a generative language model system (e.g., an AI chat experience). For instance, the query gateway system establishes a framework to leverage the features and services of the autosuggest query system and automatically provides context-retained queries to the generative language model system using separate user interfaces that do not disrupt user navigation or require manual duplicative user input. Additionally, the query gateway system incorporates additional enhancements, including an AI chat eligibility model and a query reformulation model, to improve the computational efficiency and accuracy of the AI chat system.