Voice Retrieval Output Redundancy Elimination
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing retrieval result providing devices struggle to simplify the voice output of multiple retrieval results, leading to information overload and user confusion when providing results based on keyword searches, as they uniformly output item values in a predetermined order without considering commonalities or redundancies.
Innovation Solution
The retrieval result providing device recognizes voice inputs, generates unprocessed sentences with item values arranged according to predetermined rules, and performs processes to erase redundant information based on commonalities between words, item values, or facility types, reducing the volume of information output by voice.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If individual retrieval results are uniformly provided by voice in a predetermined order, then the retrieval results are systematically presented, but the volume of information increases significantly causing user confusion
Solution Approach 1:
The patent extracts and removes redundant information from the retrieval results. Specifically, it eliminates duplicate facility names, addresses, and genres from the voice output, keeping only unique information while maintaining the structured presentation of retrieval results.
Solution Approach 2:
The patent merges multiple retrieval results that have common characteristics (same facility name, address, or genre) into a single unified output. Instead of listing each facility individually with repeated information, it combines them into consolidated entries that reduce overall information volume while preserving completeness.
2Loss of information
If all retrieval result items are output by voice, then complete information is provided, but the user cannot sequentially understand the content due to information overload
Solution Approach 1:
The patent extracts only the essential unique information from complete retrieval results and presents them in a condensed voice output format. It removes redundant repetitions of facility names, addresses, and genres while maintaining all necessary information for user understanding.
Solution Approach 2:
The patent applies different processing quality to different parts of the retrieval results. Unique facility information is preserved with high detail, while common repetitive elements are simplified or eliminated, creating a differentiated output that balances completeness with comprehensibility.
Data Source
AI summary
A retrieval result providing device includes a retrieval unit which acquires an individual retrieval result having item values of a plurality of items by a retrieval based on a keyword, an unprocessed sentence generation unit which generates an unprocessed sentence where retrieval result corresponding sentences with the item values arranged are arranged, an output sentence generation unit which performs at least one of a first process of erasing some of the sentences on the basis of a commonality between a word and the keyword contained in the retrieval result corresponding sentences, a second process of erasing some of the sentences on the basis of a commonality of the item values of specific items in the different sentences, and a third process of erasing some of the sentences on the basis of a commonality of the item values of a plurality of different items in one sentence so as to generate an output sentence, and an output sentence output unit which outputs a voice based on the output sentence.