Cross-Language Search Query Translation and Result Presentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional search systems fail to effectively facilitate cross-language information retrieval, limiting users' ability to access and utilize non-English content and knowledge.

Innovation Solution

A cross-language information retrieval system that translates queries from a source language into a target language, allows users to modify translations, and presents search results in both languages, enabling users to refine searches and access multilingual resources.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If conventional search systems are used for cross-language information retrieval, then users can access content in their native language, but users cannot effectively access and utilize non-English content and knowledge

Engineering Contradiction:
Improvelanguage accessibilityVSAvoidaccess to non-English content
Core Design Contradiction:
Adaptability or versatilityVSLoss of information

Solution Approach 1:

The patent introduces machine translation as an intermediary component that translates user queries from English to target languages and translates search results from target languages back to English. This mediator enables cross-language information retrieval without requiring users to know foreign languages, thereby resolving the contradiction between maintaining language accessibility and accessing non-English content.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If machine translation is used to translate queries and results, then users can access content in multiple languages, but the system complexity increases

Engineering Contradiction:
Improvemultilingual capabilityVSAvoidsystem architecture
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent combines multiple functions into an integrated search system: the search engine, machine translation service, and result presentation are merged into a unified workflow. The system automatically translates queries, performs searches in target languages, and translates results back to English without requiring separate manual translation steps, thereby managing complexity while maintaining multilingual capability.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The system implements self-service translation where the machine translation component automatically translates user queries and search results without human intervention. The translation service is invoked seamlessly within the search workflow, allowing the system to handle multilingual content autonomously and reducing the operational complexity of managing manual translation processes.

Inventive Principle:
Principle #25Self-service

3Productivity

If automatic translation is performed without user input, then processing speed is maintained, but translation accuracy and user control are reduced

Engineering Contradiction:
Improvesearch processing speedVSAvoidtranslation accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The patent implements a feedback mechanism where users can review and modify automatically translated queries before final execution. The system presents the machine-translated query to the user, allowing corrections or adjustments, and then uses this refined query for the actual search. This feedback loop improves translation accuracy while maintaining reasonable processing speed by only requiring user intervention when necessary.

Inventive Principle:
Principle #23Feedback

Data Source

PatentUS8799307B2Cross-language information retrieval
Publication Date: 2014.08.05 GOOGLE LLC
  • US8799307B2 patent drawing
  • US8799307B2 patent drawing
  • US8799307B2 patent drawing

AI summary

Methods, systems, and apparatus, including computer program products, for cross-language information retrieval. A source query in a source language is received. The source query is translated into a target query in a target language. One or more target-language resources that satisfy the target query are identified. The identified resources are translated into the source language. Search results corresponding to the translated resources are presented.