Placeholder-Based Sentence Adjustment for Accurate Preposition Insertion

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing natural language generation technologies require significant computing resources and are complex, making them unsuitable for resource-sensitive applications, and struggle to ensure readability and accuracy without excessive resource consumption.

Innovation Solution

The method involves adding prepositions to natural language sentences based on placeholder positions and types to improve readability and accuracy, and converting these sentences into low-code representations for efficient workflow execution.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If existing natural language generation technologies are used to generate understandable text, then the readability and accuracy of generated sentences can be improved, but the computing resources required and system complexity increase significantly

Engineering Contradiction:
Improvereadability and accuracy of generated sentencesVSAvoidcomputational complexity and resource consumption
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the natural language generation process into distinct components: identifying sentence constituents (subject, predicate, object, adverbial, complement), determining their positions, and selectively adding prepositions based on specific grammatical patterns. This segmentation allows each component to be processed independently with simple rules rather than requiring complex holistic NLP models.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent changes the approach from using complex AI models to using configurable parameters such as placeholder type attributes and position attributes. By adjusting these parameters and applying corresponding preposition addition rules, the system achieves reliable sentence generation with controlled computational resources.

Inventive Principle:
Principle #35Parameter changes

2Manufacturing precision

If complex natural language generation models are deployed to ensure sentence accuracy, then the quality of generated text improves, but the ease of operation and resource efficiency deteriorate

Engineering Contradiction:
Improvesentence accuracyVSAvoidresource efficiency and operational simplicity
Core Design Contradiction:
Manufacturing precisionVSEase of operation

Solution Approach 1:

The system automatically identifies sentence constituents and determines their positions without requiring manual intervention or complex model inference. The placeholder elements self-identify their types and positions, and the system automatically adds appropriate prepositions based on these attributes, achieving high accuracy through automated rule-based processing rather than resource-intensive modeling.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent uses configurable parameters (placeholder type attributes, position attributes) to control sentence structure and preposition addition. This parameter-based approach allows easy adjustment and operation while maintaining sentence accuracy, avoiding the need for complex model deployment and tuning.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS20250284885A1Method and Apparatus for Adjusting Natural Language Sentence
Publication Date: 2025.09.11 SIEMENS AG
  • US20250284885A1 patent drawing
  • US20250284885A1 patent drawing
  • US20250284885A1 patent drawing

AI summary

Embodiments of this application disclose a method and an apparatus for adjusting a natural language sentence, and a storage medium. The method includes: receiving a natural language sentence including a placeholder, where the placeholder includes a type attribute, and the placeholder is occupied by a sentence constituent matching the type attribute; determining a position of the placeholder in the natural language sentence; and adding a preposition to the natural language sentence based on the type attribute of the placeholder and the position of the placeholder in the natural language sentence. The preposition is automatically added to the natural language sentence through the placeholder, so that readability and accuracy of the natural language sentence can be improved. In addition, when a word order of the natural language sentence is adjusted, the preposition is automatically updated correspondingly, which ensures the readability and the accuracy of the sentence.