Candidate Answer Passages Generation for Question Queries

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Search engines often fail to provide comprehensive and relevant answers to question queries, relying solely on factual information or 'answer boxes' without offering explanatory passages that combine structured and unstructured content, which limits user understanding and satisfaction.

Innovation Solution

A method is developed to generate and score candidate answer passages from both structured and unstructured content using specific selection criteria, incorporating query-dependent and query-independent signals to provide more informative and relevant responses to question queries, separate from standard search results.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If search engines provide only factual information or answer boxes, then the processing requirements are reduced, but the user understanding and satisfaction deteriorate due to lack of explanatory passages

Engineering Contradiction:

Improveprocessing efficiencyVSAvoidexplanatory information

Core Design Contradiction:

ProductivityVSLoss of information

Solution Approach 1:

The patent segments the answer content into two distinct types: factual information (for answer boxes) and explanatory passages (for detailed explanations). This segmentation allows the system to process and present different types of information separately, maintaining processing efficiency while providing comprehensive explanatory content when needed.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system dynamically selects between providing only answer boxes or providing both answer boxes and explanatory passages based on the query type and user needs. For simple factual queries, only answer boxes are provided to maintain efficiency. For complex queries requiring understanding, explanatory passages are generated and provided alongside answer boxes.

Inventive Principle:

Principle #15Dynamics

2Productivity

If search engines provide only answer boxes with factual information, then the processing requirements are reduced, but the comprehensiveness and relevance of answers deteriorate

Engineering Contradiction:

Improveprocessing efficiencyVSAvoidanswer comprehensiveness

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system performs preliminary analysis of the query to determine whether it requires explanatory passages. For queries that need comprehensive answers, the system pre-identifies and retrieves relevant explanatory content from web pages before presenting the final answer, ensuring both efficiency and comprehensiveness.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary component that bridges factual answer boxes and explanatory passages. This intermediary selectively generates explanatory passages from relevant web content and combines them with answer boxes, ensuring that the final response is both comprehensive and relevant without requiring full processing of all web content.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Loss of information

If search engines generate explanatory passages from web pages, then user understanding is improved, but the processing requirements and complexity increase

Engineering Contradiction:

Improveexplanatory informationVSAvoidprocessing complexity

Core Design Contradiction:

Loss of informationVSDevice complexity

Solution Approach 1:

The system applies local quality by focusing processing resources only on specific portions of web pages that are relevant to the query. Instead of processing entire web pages, the system identifies and extracts only the relevant explanatory passages, reducing processing complexity while maintaining information quality.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The patent changes the parameter of processing scope from entire web pages to specific relevant passages. By adjusting this parameter, the system reduces the volume of content that needs to be processed while still providing comprehensive explanatory information, thereby reducing processing complexity.

Inventive Principle:

Principle #35Parameter changes

4Reliability

If search engines provide detailed explanatory passages, then user satisfaction is improved, but the processing time and resource requirements increase

Engineering Contradiction:

Improveanswer qualityVSAvoidprocessing time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system applies partial action by providing explanatory passages only for the portions of queries that require them, rather than generating explanations for all queries. This selective approach maintains high answer quality for complex queries while avoiding unnecessary processing time for simple queries that only need factual answers.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS10180964B1Candidate answer passages

Publication Date: 2019.01.15 GOOGLE LLC

AI summary

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating candidate answer passages. In one aspect, a method includes receiving a query determined to be a question query data identifying resources determined to be responsive to the query; for each resource in a top-ranked subset of the resources: identifying a plurality of passage units in the resource; applying a set of passage unit selection criterion to the passage units, each passage unit selection criterion specifying a condition for inclusion of a passage unit in a candidate answer passage, wherein a first subset of passage unit selection criteria applies to structured content and a second subset of passage unit selection criteria applies to unstructured content; and generating, from passage units that satisfy the set of passage unit selection criterion, a set of candidate answer passages.