Feature Term Classification for Search Result Relevance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search methods for sightseeing information often result in a large scope of search results, making it difficult for users to find desired information, as feature terms like 'explanation' and 'experience' lead to undesired search results due to their conceptual nature.
Innovation Solution
A feature term classification method that extracts feature terms from Web pages, classifies them based on the presence of corresponding images, and stores these classifications to differentiate between actual and conceptual terms, thereby refining search results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If feature terms are used for search without classification, then the search scope becomes large and comprehensive, but undesired search results are listed high and it becomes difficult to acquire desired information
Solution Approach 1:
The patent segments feature terms into two distinct categories: actual terms (concrete entities like sightseeing spots, restaurants, shops) and conceptual terms (abstract concepts like explanations, experiences). This segmentation is achieved by performing image searching for each feature term and classifying based on whether images are detected. By dividing the feature term set into these two groups, the system can selectively prioritize actual terms in search results, thereby maintaining comprehensive search coverage while improving result accuracy by suppressing conceptual terms that generate undesired results.
2Adaptability or versatility
If conceptual feature terms like 'explanation' and 'experience' are included in search, then comprehensive information is covered, but undesired search results are listed high
Solution Approach 1:
The patent performs preliminary classification of feature terms into actual and conceptual categories before the search execution. This preliminary action involves extracting feature terms from Web pages, performing image searching for each term, and classifying them based on image detection results. By completing this classification beforehand, the system prepares the groundwork for selective result presentation, ensuring that comprehensive information coverage is maintained while reliability is improved through prioritization of actual terms in the final search results.
3Device complexity
If all feature terms are treated equally in search, then simple search processing is performed, but relevant actual entities are not prioritized in results
Solution Approach 1:
The patent changes the parameter of feature term classification by introducing a new attribute (actual vs. conceptual) based on image detection results. This parameter change enables the system to differentiate between feature terms that represent concrete entities and those representing abstract concepts. By modifying this classification parameter, the system achieves improved result relevance through prioritization of actual terms without significantly increasing processing complexity, as the classification is based on simple image presence/absence detection.
Data Source
AI summary
A feature term classification method executed by a processor included in an information processing apparatus including a display device and a memory, the feature term classification method includes extracting a feature term from a Web page displayed on a screen of the display device; executing image searching using the extracted feature term; classifying the feature term based on whether an image has been detected as information corresponding to the feature term in the image searching; storing the information corresponding to the feature term in the memory; when a new feature term has been input, extracting a Web page corresponding to the new feature term from the stored information corresponding to the feature terms; and displaying the extracted Web page.