Search Result Term Identification via Visual Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search technologies fail to effectively identify and highlight conceptually related terms in search query results, making it difficult for users to find relevant information as they need to know various expressions of the concept they are searching for.
Innovation Solution
The technique involves inputting search query terms, identifying word tokens and potential phrases, and then using pre-built databases or conceptual relationship discovery methods to find conceptually related words and phrases in search results, which are visually distinguished for the user, such as through highlighting, to draw attention to relevant information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If search results display only exact query term matches, then precision of search results is improved, but recall of relevant information deteriorates because users cannot find conceptually related terms
Solution Approach 1:
The patent segments search results into two distinct visual categories: exact query term matches and conceptually related terms. This segmentation allows the system to maintain high precision for exact matches while simultaneously presenting conceptually related terms with appropriate visual distinction, thereby improving recall without compromising precision.
Solution Approach 2:
The patent applies local quality by using different visual styles (highlighting vs. non-highlighting) for different types of terms in the search results. Exact matches receive full highlighting while conceptually related terms receive different visual treatment, allowing users to distinguish between definitive matches and related concepts, thus improving information retrieval while maintaining precision.
2Loss of information
If search results highlight all conceptually related terms, then recall of relevant information is improved, but precision deteriorates because users cannot distinguish exact matches from related terms
Solution Approach 1:
The patent applies local quality by using different visual styles (highlighting vs. non-highlighting) for different types of terms in the search results. Exact matches receive full highlighting while conceptually related terms receive different visual treatment, allowing users to distinguish between definitive matches and related concepts, thus improving information retrieval while maintaining precision.
Solution Approach 2:
The patent segments search results into two distinct visual categories: exact query term matches and conceptually related terms. This segmentation allows the system to maintain high precision for exact matches while simultaneously presenting conceptually related terms with appropriate visual distinction, thereby improving recall without compromising precision.
3Loss of information
If search results present detailed conceptually related term information, then user understanding of search concepts is improved, but ease of operation deteriorates due to increased complexity in interpreting results
Solution Approach 1:
The patent performs preliminary action by pre-processing and organizing conceptually related terms before presentation. The system identifies, categorizes, and prepares conceptually related terms in advance, so that when results are displayed, users receive pre-organized information that is easier to interpret, thus improving information completeness while maintaining ease of operation.
Solution Approach 2:
The patent applies local quality by providing different levels of information detail in different parts of the search results interface. Conceptually related terms are presented with appropriate visual distinction and contextual information where needed, while maintaining a clean, simple overall layout that does not overwhelm users, thus balancing information completeness with ease of operation.
Data Source
AI summary
Conceptually related term identification technique embodiments are presented that involve identifying in the results of a search query, terms that are conceptually related to the search query terms. In one general embodiment, this is accomplished by first inputting the terms employed in a search query and the results of the search. Word tokens found in the search query terms are then identified, as are potential phrases that can be made from the identified word tokens. Conceptually related words and phrases are then identified in the search query results. These words and phrases correspond to the previously identified word tokens and potential phrases. The search query results are presented to a user on a display device in such a manner as to visually distinguish the conceptually related words and phrases from other words and phrases in the search query results.