Search System Keyword Extraction for Virtual Shopping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In virtual shopping malls, product search systems often extract unnecessary keywords from product titles, leading to decreased accuracy in finding similar products, as these keywords are included in search conditions, resulting in irrelevant search results.
Innovation Solution
A search system that extracts items not selected by the user, acquires unique words from the selected item's text information, and sets search conditions based on these words to improve the accuracy of similar product searches, excluding irrelevant keywords.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If multiple keywords are extracted from product titles to improve search coverage, then the quantity of search keywords increases, but the accuracy of search conditions deteriorates due to inclusion of unnecessary keywords
Solution Approach 1:
The patent extracts and removes unnecessary keywords from product titles before forming search conditions. The system identifies keywords that are not essential for representing the product's actual characteristics and excludes them from the search condition, thereby maintaining search coverage while improving accuracy.
Solution Approach 2:
The patent applies different processing to different parts of the product title. Instead of treating all keywords uniformly, the system selectively processes specific keywords based on their relevance to the product's actual characteristics, giving different weights or treatments to different keyword segments.
2Adaptability or versatility
If all keywords from selected product title are used for search, then the search condition includes more terms, but irrelevant keywords reduce search result quality
Solution Approach 1:
The system extracts and removes irrelevant keywords from the product title before forming the search condition. By identifying and excluding keywords that do not represent the product's actual characteristics, the system maintains comprehensive search coverage while ensuring high search result quality.
Solution Approach 2:
The system uses feedback from multiple selected products to refine the search condition. By analyzing common keywords across multiple selected products and comparing them against the target product, the system can identify and exclude keywords that are not relevant to the actual product characteristics.
Data Source
AI summary
An item extraction unit extracts, when a user selects an item from a list of items to be selected by the user, at least one item from among items that are not selected by the user. A word acquisition unit acquires a word that is contained in text information associated with the item selected by the user and is not contained in text information associated with the item extracted by the item extraction unit. A search condition setting unit sets a search condition for searching for an item that is similar to the item selected by the user based on the word acquired by the word acquisition unit. A search execution unit executes a search based on the search condition.