Sentiment-Based Knowledge Base for Product Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional information retrieval systems provide limited and biased information about products and services, making it tedious and time-consuming for users to find decision-relevant information, especially when comparing multiple options, as they often lack detailed and unbiased subjective assessments.
Innovation Solution
A computer-automated method for harvesting, analyzing, and aggregating information from unstructured sources to create a searchable knowledge base that includes both objective and subjective attributes, using rule-based grammar and machine learning techniques to extract and score decision-relevant features, and presenting them in a structured format for easier user access.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If conventional information retrieval systems are used to search for product information, then basic objective information can be obtained, but detailed subjective assessments and unbiased reviews are missing
Solution Approach 1:
The patent segments information into two distinct categories: structured objective information (from databases) and unstructured subjective information (from reviews and blogs). This segmentation allows the system to process and retrieve each type of information through appropriate methods, ensuring both objective data and subjective assessments are captured without overwhelming the system with undifferentiated data.
Solution Approach 2:
The patent introduces an intermediary processing layer that bridges structured databases and unstructured review sources. This intermediary component analyzes unstructured text from reviews and blogs, extracts subjective assessments, and integrates them with objective database information, thereby recovering lost subjective information without requiring direct user interaction with complex source materials.
2Loss of information
If users review multiple sites and entries to form informed opinions, then comprehensive information can be gathered, but the process becomes tedious and time-consuming
Solution Approach 1:
The patent merges information from multiple sources (vendor databases, third-party reviews, blogs) into a single integrated knowledge base. By combining structured and unstructured information from numerous sites into one unified system, users can access comprehensive information that would otherwise require visiting multiple separate websites, significantly reducing the time needed to gather complete product assessments.
Solution Approach 2:
The patent performs preliminary analysis and aggregation of information from multiple sources before user queries are submitted. The system pre-processes reviews and blogs to extract and store subjective assessments in the knowledge base, so when users search, the comprehensive information is already organized and ready for immediate retrieval, eliminating the need for users to manually review multiple entries.
3Loss of information
If users go through hundreds or thousands of documents to assess multiple options, then complete comparison can be made, but the task becomes onerous and time-consuming
Solution Approach 1:
The patent extracts only the decision-relevant information from large volumes of documents. The system identifies and extracts key subjective assessments, opinions, and comparative data from reviews and blogs, separating this essential information from irrelevant content. This extraction process delivers decision-relevant information directly to users without requiring them to wade through hundreds of complete documents.
Solution Approach 2:
The patent replaces the mechanical process of manual document review with automated computational analysis. The system uses natural language processing and text analysis algorithms to automatically evaluate and compare products across multiple documents, substituting human effort with machine-based information synthesis that quickly delivers comparative assessments without manual intervention.
4Ease of manufacture
If vendor-provided information is used, then structured data is available, but the information may be biased and not trustworthy
Solution Approach 1:
The patent introduces an intermediary analysis layer that processes third-party review information between the source (independent reviewers) and the user. This intermediary component objectively analyzes unstructured review data, extracts verified subjective assessments, and integrates them with vendor-provided structured data, thereby providing trustworthy information that balances structured formatting with independent verification.
Solution Approach 2:
The patent creates a composite information structure that combines vendor-provided structured data with independently verified subjective assessments from third-party reviews. This composite approach merges the advantages of both sources: the structured organization from vendor databases and the unbiased credibility from independent reviewers, producing a more reliable and trustworthy information profile than either source alone.
Data Source
AI summary
A computer-automated method and system of providing a searchable knowledge base with decision-relevant attributes (including some subjective or sentiment-based attributes) for a plurality of individual items within a choice set are described. First, information (including texts) relevant to the plurality of individual items in the choice set is harvested from Internet sources. Next, normalized representations of statements are extracted from excerpts of the harvested texts that pertain to attributes of interest for the choice set, and corresponding scores for the attributes are derived from each of the normalized representations. The scores derived from the various harvested sources are aggregated for each attribute of each item. Finally, the knowledge base of the plurality of individual topics is generated.