AI Search Request Processing with Validated Result Fields

Solution Overview

Problem

Existing search systems face inefficiencies in processing search requests due to the overhead of contacting database systems for search result data, which can be time-consuming and resource-intensive, and there is a need for improved handling of search requests using artificial intelligence and machine-learning techniques to enhance accuracy and relevance.

Innovation Solution

A method utilizing a generative artificial intelligence model to generate first data fields and a machine-learning model to validate these fields, combined with a database system to determine second data fields, optimizing the search result generation process.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a database system is contacted for every search request to obtain search result data, then data accuracy and completeness are improved, but response time and resource consumption increase

Engineering Contradiction:

Improvedata accuracyVSAvoidresponse time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The search platform pre-generates search result data using the generative AI model and stores it in a cache before actual search requests are made. When a search request arrives, the platform first checks the cache for pre-generated results, returning them immediately if available, thus avoiding the time-consuming database contact while maintaining data accuracy through the AI model's pre-computation

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system creates copies of search result data by using the generative AI model to produce synthetic search results that mirror the structure and content of actual database results. These AI-generated copies are stored in cache and can be returned instead of contacting the database, reducing response time while maintaining sufficient data accuracy for most search scenarios

Inventive Principle:

Principle #26Copying

2Reliability

If a database system is contacted for every search request to obtain search result data, then data completeness is improved, but resource consumption increases

Engineering Contradiction:

Improvedata completenessVSAvoidresource consumption

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The search platform pre-generates search result data using the generative AI model and stores it in a cache before actual search requests are made. When a search request arrives, the platform first checks the cache for pre-generated results, returning them immediately if available, thus avoiding the time-consuming database contact while maintaining data accuracy through the AI model's pre-computation

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system creates copies of search result data by using the generative AI model to produce synthetic search results that mirror the structure and content of actual database results. These AI-generated copies are stored in cache and can be returned instead of contacting the database, reducing response time while maintaining sufficient data accuracy for most search scenarios

Inventive Principle:

Principle #26Copying

3Productivity

If a generative AI model is used to generate search result data, then response time is improved, but data accuracy may deteriorate

Engineering Contradiction:

Improveresponse timeVSAvoiddata accuracy

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

A validation model is introduced as an intermediary between the generative AI model and the search result output. The validation model checks the AI-generated search results for accuracy and relevance, filtering or correcting results that do not meet quality standards before returning them to the user, thus maintaining both fast response times and high data accuracy

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the traditional mechanical database query system with an AI-based generative system that can produce search results without direct database access. This substitution enables faster response times while the integrated validation mechanism ensures data accuracy, effectively replacing the slow but accurate database system with a fast and equally accurate AI system

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20250291860A1Search request processing

Publication Date: 2025.09.18 AMADEUS SAS

AI summary

Method, systems and computer programs for handling search requests at a search platform are provided. The search platform receives a search request determining a number of search results by generating one or more values for a first set of data fields by using a generative artificial intelligence model and determining, on the basis of the generated one or more values for the first set of data fields and by using the database system, one or more values for a second set of data fields. The search platform assembles a number of completed search results on the basis of the generated first set of data fields and the determined second set of data fields and returns at least one of the completed search results.