Menu Category Classification via Morphological Analysis and Feature Vectors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for category classification of restaurant menus using morphological analysis and artificial intelligence face challenges such as low accuracy in determining parts of speech, over-learning leading to inconsistent classifications, and difficulty in linking menu names to category names uniquely across different types of businesses.
Innovation Solution
An information processing apparatus that includes an input unit for menu names, a storage unit for associating menu and category names, a morphological analysis unit to divide menu names into words and determine parts of speech, and a specification unit that generates a feature amount vector to specify categories based on learning results, using neural networks to adapt to different business types and exclude irrelevant words for accurate classification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If artificial intelligence is used to create a complex model by overfitting the information to learning data, then the model can capture detailed patterns in training data, but the generalization performance decreases and classification accuracy becomes inconsistent
Solution Approach 1:
The patent extracts and removes unnecessary words from menu names through morphological analysis and filtering mechanisms. By eliminating irrelevant terms (such as promotional language, redundant descriptors, and non-essential modifiers), the system focuses on core semantic elements that truly define menu categories, thereby preventing overfitting while maintaining classification accuracy
Solution Approach 2:
The patent transforms menu names into feature amount vectors that quantify the presence and importance of specific words. This parameter transformation converts unstructured text into standardized numerical representations, enabling consistent comparison and classification while improving generalization performance across different restaurants and menu styles
2Difficulty of detecting and measuring
If morphological analysis is used to decompose menu names into words and parts of speech, then basic structure analysis is achieved, but high-level semantic analysis and category classification remain difficult
Solution Approach 1:
The patent introduces an intermediary processing layer that bridges morphological analysis and category classification. This layer includes mechanisms for extracting semantic features, identifying key nouns and verbs, and transforming text into feature amount vectors. These intermediary steps convert basic word-level analysis into meaningful semantic representations that enable accurate category classification
Solution Approach 2:
The patent transitions from one-dimensional text analysis to multi-dimensional feature space representation. By converting menu names into feature amount vectors with multiple dimensions (each representing different linguistic features), the system enables sophisticated pattern recognition and classification that goes beyond simple morphological decomposition
Data Source
AI summary
An information processing apparatus includes: an input unit configured to input a menu name of a restaurant; an output unit configured to output a category name; a storage unit configured to store the menu name and the category name corresponding to the menu name so as to be associated with each other; a morphological analysis unit configured to execute morphological analysis to divide the inputted menu name into words and determine parts of speech; and a specification unit configured to generate, in a case where no category name corresponding to the inputted menu name is stored, a feature amount vector characterizing whether each of the words is included in the menu name or not as a result of the morphological analysis, and specify a category name corresponding to the inputted menu name based on a result of learning the menu name and the category name.