Intention Inference System for Complex Sentence Execution Order
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing intention inference systems struggle to accurately infer the execution order of multiple intentions in complex sentences, failing to accurately process user inputs with multiple intentions, such as 'tokyo tower mo yoritai ga, saki ni skytree he yotte (Indeed I want to visit Tokyo Tower, but visit Skytree first)', where multiple intentions are involved.
Innovation Solution
An intention inference system comprising a morphological analyzer, syntactic analyzer, intention inference unit, feature extractor, and execution order inference unit, which performs morphological and syntactic analysis to divide complex sentences into simple sentences, extract features indicating operation execution order, and infer the correct execution order of operations based on these features.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If intention inference models trained by statistical methods are used to process user expressions, then a wide variety of user expressions can be processed, but multiple intentions in complex sentences cannot be inferred accurately
Solution Approach 1:
The complex sentence is divided into multiple simple sentences based on syntactic analysis. Each simple sentence is then processed separately by the intention inference model to extract individual intentions. This segmentation allows the system to handle multiple intentions that would otherwise be confused in a complex sentence structure.
Solution Approach 2:
A feature extraction module is introduced as an intermediary between syntactic analysis and intention inference. This module extracts execution order features from each simple sentence, which are then used to determine the correct sequence of operations. The intermediary feature extraction bridges the gap between sentence structure and intention execution order.
2Measurement precision
If division point probabilities of complex sentences are used to infer proper division points, then complex sentences can be divided into simple sentences, but the execution order of machine commands corresponding to multiple inferred intentions cannot be determined
Solution Approach 1:
The system performs preliminary extraction of execution order features from each simple sentence before determining the final execution order. By extracting features such as temporal markers and sequence indicators in advance, the system preserves execution order information that would otherwise be lost during the division process.
Solution Approach 2:
The feature extraction module provides feedback about execution order features to the intention inference process. This feedback mechanism allows the system to adjust its interpretation of multiple intentions based on the extracted features, ensuring that the execution order reflects the user's original intent.
Data Source
AI summary
An intention inference system includes, a morphological analyzer to perform morphological analysis for a complex sentence with multiple intentions involved, a syntactic analyzer to perform syntactic analysis for the complex sentence morphologically analyzed by the morphological analyzer and to divide it into the first simple sentence and the second simple sentence, an intention inference unit to infer the first intention involved in the first simple sentence and the second intention involved in the second simple sentence, a feature extractor to extract as the first feature a morpheme showing execution order of operations involved in the first simple sentence and to extract as the second feature a morpheme showing execution order of operations involved in the second simple sentence, and an execution order inference unit to infer the execution order of the first operation corresponding to the first intention and the second operation corresponding to the second intention on the basis of the first feature and the second feature extracted by the feature extractor. This enables the system to infer user's intentions accurately.