Attribute Extraction and Visual Ranking for Mobile Product Reviews
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face difficulty in identifying the top attributes of products amidst a plethora of information, as existing technologies lack effective methods to visually highlight and rank attributes based on user reviews and descriptions.
Innovation Solution
A filtering system that extracts attributes from product descriptions, assigns weights to them based on positive reviews, and ranks them, with corresponding images superimposed over product images or descriptions to visually identify top attributes, allowing users to select and view other products with similar attributes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If product descriptions and reviews contain comprehensive information about all attributes, then the information completeness is improved, but the difficulty of identifying top attributes increases
Solution Approach 1:
The system extracts only the most relevant attribute information from comprehensive product descriptions and reviews, separating top attributes from the full body of information. This allows the system to maintain complete information availability while presenting only the most important attributes to users, thereby reducing identification difficulty without losing information completeness.
Solution Approach 2:
The system introduces an intermediary processing layer that analyzes comprehensive product information and generates simplified attribute representations. This intermediary layer processes the full information set and presents it in an easily identifiable format, resolving the contradiction between having complete information and making it easy to identify top attributes.
2Ease of operation
If visual elements are added to highlight top attributes, then the ease of operation is improved, but the device complexity increases
Solution Approach 1:
The system applies visual highlighting selectively to specific top attributes rather than uniformly across all content. By concentrating visual elements only on the most important attributes, the system improves ease of operation while minimizing the addition of complex visual processing requirements, thus resolving the contradiction between usability and system complexity.
Data Source
AI summary
Top attributes of a product are identified from text content of an electronic document and are presented as visual depictions of the attributes. The attributes are identified and ranked based on the text content, such as whether the text content describes the attribute in a positive or negative manner. Top attributes are selected from the ranking and a visual depiction of the top attributes is identified. The visual depiction can be a universally recognized symbol or a custom image designated to an attribute. The visual depiction is superimposed on the text content associated with the attributes when the electronic document is presented at a display. In this way, top attributes for a product can be presented in a manner that condenses the relevant information provided by the electronic document into a format better suited for providing the information on small screens of mobile devices.