Crowdsourced Answer Generation for Search Engines
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users often face unsatisfied information needs when relying on conventional search engines and social networking applications, as direct answers are not always provided promptly or accurately, leading to inefficiencies in obtaining relevant information.
Innovation Solution
A system employing a collective of crowd workers to identify and generate high-quality answers by analyzing user behavior, crowd voting, and editing processes, ensuring that answers are relevant and readily consumable, which can be presented inline with search results or through other communication channels in real-time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional search engines provide direct answers, then user information needs are satisfied more efficiently, but answer quality and relevance deteriorate due to lack of verification
Solution Approach 1:
The system implements a feedback mechanism where crowd workers vote on proposed answers and search engine results. Users can indicate whether answers are helpful, and this feedback is used to re-rank and re-order results, continuously improving answer quality while maintaining efficiency.
Solution Approach 2:
The system enables users to participate in the information retrieval process by allowing them to vote on answers and mark helpful results. This self-service approach improves answer quality through collective intelligence while maintaining the efficiency of direct answer provision.
2Loss of time
If search engines provide direct answers quickly, then user satisfaction improves, but the system complexity increases due to multiple processing stages
Solution Approach 1:
The system performs preliminary actions by pre-processing search results and generating potential answers before user interaction. This allows for faster response times while the complexity is managed through automated prioritization and filtering mechanisms.
Solution Approach 2:
The system segments the information retrieval process into distinct stages: initial search, answer generation, crowd voting, and final selection. This segmentation allows each stage to be optimized independently, managing overall system complexity while maintaining speed.
3Measurement precision
If crowd workers vote on answers, then answer relevance improves through collective expertise, but the time required for answer generation increases
Solution Approach 1:
The system applies partial action by selecting a representative sample of crowd workers to vote on answers rather than requiring input from all users. This maintains answer relevance through collective expertise while significantly reducing the time required for answer generation.
Solution Approach 2:
The system maintains continuity of useful action by continuously processing votes and updating answer rankings in real-time. This allows the system to provide timely answers while incorporating collective wisdom from crowd workers.
Data Source
AI summary
Technologies pertaining to generating crowd-sourced answers are described herein. A text string is received, and the text string is parsed to determine if the text string represents an information need that is desirably answered by a collective of crowd workers. When it is determined that the information need is desirably answered by the collective of crowd workers, a query or question that represents the information need is provided to a first plurality of crowd workers, who generate proposed answers for the information need. The proposed answers are provided to a second plurality of crowd workers, who vote on the proposed answers. An answer to the information need is output based upon responses of the crowd workers.