Copywriting Generation Method Using Semantic Prompt Updates
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing copywriting generation methods using deep learning models often struggle to accurately understand the semantic attributes of user input requirements, leading to low-quality or mismatched feedback copywriting.
Innovation Solution
The method updates the copywriting prompt information based on a copywriting generation operation related to the input requirement, generating a first target copywriting requirement that includes a target copywriting prompt related to the semantic attribute. This updated information is then processed using a pre-trained deep learning model to generate accurate feedback copywriting.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If deep learning models are used for copywriting generation, then complex data processing capability is improved, but semantic understanding accuracy deteriorates
Solution Approach 1:
The patent introduces prompt information as an intermediary between user requirements and the deep learning model. This prompt information explicitly encodes semantic attributes (such as target audience, tone, style, and key messages) that guide the model's generation process, thereby improving semantic understanding accuracy while maintaining the model's complex data processing capabilities
Solution Approach 2:
The patent performs preliminary processing of user requirements into structured prompt information before inputting them to the deep learning model. This preliminary action includes extracting and organizing semantic attributes into a standardized format, which prepares the input data in a way that enhances the model's ability to understand and generate accurate copywriting
2Device complexity
If generic copywriting generation is used, then system complexity is reduced, but copywriting quality deteriorates
Solution Approach 1:
The patent changes the parameters of the input information by transforming generic user requirements into enriched prompt information with specific semantic attributes. This parameter change includes adding dimensions such as target audience, tone, style, and key messages, which significantly improves copywriting quality without requiring changes to the underlying deep learning model structure
Data Source
AI summary
A copywriting generation method, an electronic device and a storage medium are provided and relate to a field of artificial intelligence technology, in particular to fields of deep learning and natural language processing technologies, and may be applied to scenarios of large language models and generative dialogues. The copywriting generation method includes: updating, in response to an input copywriting requirement information being received, a copywriting prompt information in the copywriting requirement information according to a copywriting generation operation related to the copywriting requirement information, so as to obtain a first target copywriting requirement information, where the first target copywriting requirement information includes a target copywriting prompt information related to a semantic attribute of the copywriting requirement information; and processing the first target copywriting requirement information based on a pre-trained deep learning model, so as to generate a first feedback copywriting corresponding to the copywriting requirement information.