Chatbot Query Processing for Unknown Words
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Chatbots used by employment agencies face challenges in processing search queries containing unknown words, leading to incomplete or inaccurate results, as they rely solely on dictionaries that do not recognize such terms, resulting in failed searches or irrelevant responses.
Innovation Solution
The system employs morphological analysis to extract words from search queries, assigns categories, and searches both repositories and the internet to find descriptions of unknown words, using correlation words to retrieve relevant resource data, thereby expanding the search scope beyond dictionary limitations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If chatbots rely solely on dictionaries for processing search queries, then the system structure remains simple and easy to operate, but the system cannot recognize unknown words leading to incomplete or inaccurate search results
Solution Approach 1:
The patent introduces an intermediary component (unknown word processing module) that mediates between the dictionary-based search system and unknown words. This module captures unknown words, searches the internet for their meanings, and replaces them with appropriate dictionary words, thereby maintaining search accuracy without requiring complete system redesign.
Solution Approach 2:
The patent segments the search processing into distinct stages: initial dictionary-based processing, unknown word identification, internet-based meaning retrieval, and result integration. This segmentation allows the system to maintain simple dictionary-based operation while adding specialized handling for unknown words, resolving the contradiction between simplicity and accuracy.
2Adaptability or versatility
If chatbots expand search scope to include internet descriptions and correlation words, then the system can handle unknown words effectively, but the search process becomes more complex and time-consuming
Solution Approach 1:
The patent applies partial action by selectively processing only unknown words through the time-consuming internet search process, while known words are handled immediately by the dictionary. This partial application of the extended search process maintains adaptability for unknown words while minimizing overall processing time.
Solution Approach 2:
The system performs preliminary classification of words into known and unknown categories before executing different processing paths. This preliminary action allows the system to quickly handle known words through the dictionary while preparing only unknown words for the more time-consuming internet search, reducing overall processing time.
3Measurement precision
If chatbots use morphological analysis and category assignment to process queries, then the system can extract meaningful information from unknown words, but the processing complexity increases
Solution Approach 1:
The patent introduces an intermediary processing layer that applies morphological analysis and category assignment specifically to unknown words. This intermediary module bridges the gap between raw unknown words and the dictionary-based search system, extracting meaningful information without requiring the entire system to become more complex.
Data Source
AI summary
A computer receives a search query from a user for finding a resource. The computer obtains a description on a page on a net on which an unknown word extracted from the search query is found. The computer extracts one or more second words from the description using morphological analysis. The computer assigns at least one second category to the one or more second words extracted from the description. The computer finds, among the one or more second words, a particular word to which a predetermined category is assigned, extracts a correlation word having a high correlation with the particular word, and finds, in a dictionary, a search word from among one or more first words extracted from the search query and assigned a first category that is the same as the predetermined category. The computer finds, from a repository, resource data using the correlation word and the search word.