Semantic Structure Search Encoding for Incomplete Sentences
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing semantic structure search technologies face challenges when dealing with incomplete sentences, as they require significant computational resources and are inefficient in handling missing morphemes, leading to increased calculation amounts and reduced accuracy.
Innovation Solution
The proposed solution involves an encoding program that generates semantic structure information from documents, encodes morphemes into codes, and adds missing-portion information to specific codes, allowing for efficient processing and reduced resource usage during semantic structure search by integrating morpheme matching and semantic structure information matching.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If semantic structure search is performed by performing morphological analysis and semantic analysis on text data in a plurality of documents, then search accuracy for semantic structure is improved, but calculation amount increases and processing efficiency deteriorates
Solution Approach 1:
The patent performs morphological analysis and semantic analysis in advance to generate encoded documents with pre-computed semantic structures, codes, and missing-portion information. This preliminary processing allows the search phase to simply compare pre-generated structures rather than performing complex analysis during search, thereby maintaining high accuracy while dramatically improving processing efficiency
Solution Approach 2:
The patent divides the search process into separate stages: encoding phase (morphological analysis, semantic analysis, code generation) and search phase (structure comparison). By segmenting the complex analysis tasks from the search tasks, the system can pre-process documents once and then perform rapid searches by comparing pre-generated semantic structures without re-performing the heavy analysis work
2Reliability
If missing morphemes are handled by complementing information in incomplete sentences, then search completeness is improved, but processing load increases
Solution Approach 1:
The patent identifies and marks missing morphemes during the encoding phase by analyzing semantic structure completeness. It adds missing-portion information to specific codes before storage, so that during search, the system only needs to compare pre-marked missing portions rather than performing complex anaphora resolution and complementation operations, thereby reducing processing load while maintaining search completeness
Solution Approach 2:
The patent introduces an intermediary structure (encoded document with semantic structures, codes, and missing-portion information) that bridges the gap between raw text and search queries. This intermediary pre-processes and marks all missing information, allowing the search system to work with simplified, pre-prepared data structures rather than raw text requiring complex analysis during search
Data Source
AI summary
A computer generates semantic structure information from a document. The semantic structure information includes a plurality of semantic structures in a plurality of sentences in the document and a plurality of morphemes included in each of the plurality of sentences belong to a corresponding semantic structure. The computer generates a plurality of codes by encoding the plurality of morphemes for each of the plurality of sentences. The computer specifies a specific code that corresponds to a specific morpheme from among the plurality of morphemes included in each of the plurality of sentences, wherein at least one morpheme is potentially missing in a semantic structure that the specific morpheme belongs to. A missing-portion information indicates the missing morpheme is included in a prior sentence in the document. The computer adds missing-portion information to the specific code for each of the plurality of sentences.