Semantic Noun Phrase Extraction for E-commerce Product Recommendations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current Question Answering (QA) systems in e-commerce do not provide an easy and natural bridge from asking questions to shopping activities, lacking automation in highlighting relevant shopping recommendations within answers.
Innovation Solution
An automatic technique that uses a semantic similarity model to extract and rank noun phrases from answer text, associating them with relevant products, allowing users to seamlessly transition from questions to shopping by highlighting these phrases, which can launch product recommendations or searches.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If QA systems automatically answer user questions using natural language processing, then users receive helpful information for product searches, but the system lacks automation in providing direct shopping recommendations within answers
Solution Approach 1:
The system performs preliminary extraction of noun phrases from answer text and pre-ranks them using a semantic similarity model before user interaction. This preliminary processing enables the system to have shopping recommendations ready immediately, allowing seamless transition from question to product discovery without requiring users to manually reformulate search queries.
Solution Approach 2:
The system introduces an intermediary layer between the QA answer and product search functionality. Noun phrases extracted from answers act as intermediaries that bridge the gap between natural language questions and product catalogs. The semantic similarity model serves as another intermediary, matching these noun phrases with relevant products automatically.
2Productivity
If users manually reformulate search queries based on QA answers, then they can find relevant products, but this process requires additional time and effort
Solution Approach 1:
The system performs self-service by automatically extracting meaningful noun phrases from QA answers and generating relevant product recommendations without user intervention. The semantic similarity model autonomously ranks these phrases and retrieves corresponding products, allowing the system to serve itself in bridging the gap between questions and shopping results.
Solution Approach 2:
The system implements feedback by analyzing user interactions with highlighted noun phrases and product recommendations. This feedback loop allows the system to learn from user behavior patterns and continuously improve the accuracy of noun phrase extraction and product matching, thereby increasing shopping efficiency over time.
3Adaptability or versatility
If the system highlights and ranks noun phrases from answer text, then direct product recommendations are provided, but this increases system complexity
Solution Approach 1:
The system segments the complex task of providing shopping recommendations into distinct components: noun phrase extraction from answer text, semantic similarity calculation for ranking these phrases, and product retrieval based on ranked phrases. This segmentation allows each component to be optimized independently while maintaining overall system adaptability.
Solution Approach 2:
The system utilizes parameter changes in the semantic similarity model to adjust the ranking of noun phrases based on different contextual factors. By modifying similarity thresholds and weighting parameters, the system can adapt to various query types and answer formats without fundamentally changing the overall architecture, thereby managing complexity while maintaining versatility.
Data Source
AI summary
An automatic technique is disclosed to enrich presented answers by highlighting relevant shopping recommendations. The shopping recommendations can either be highlighted within the answer itself, or as an auxiliary list of suggestions. A model is described for selecting phrases from the answer text (sequences of consecutive terms called noun phrases) that refer to potential products that likely represent relevant shopping recommendation in context of the question-answer pair. The noun phrases are then ranked in order of importance. The top-ranked noun phrases are used to search products to be displayed in association with the noun phrases. Clicking or tapping on a highlighted noun phrase launches a shopping-related flow, such as presenting a widget with product recommendations or running a search in a search engine.