Information Processing System Using Segmented LLM Components
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The expansion of large language models has made it difficult for individuals to incorporate and operate them within their own facilities, leading to a reliance on external services for natural language processing tasks.
Innovation Solution
An information processing system comprising three components: a first component that receives natural language text and queries, a second component that processes using a large language model to generate intermediate code, and a third component that classifies text, generates prompts, and interacts with databases to provide design assets and code generation capabilities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If large language models are expanded to increase natural language processing capacity, then processing capability is improved, but device complexity and operational difficulty increase
Solution Approach 1:
The patent divides the complex large language model into multiple specialized components: a text classification component that categorizes input text, a prompt generation component that creates tailored prompts based on classification results, and a code generation component that produces final output. This segmentation allows each component to handle specific tasks independently, reducing the operational complexity of the overall system while maintaining high processing capacity.
Solution Approach 2:
The patent introduces an intermediary prompt generation layer between the input text and the code generation process. The prompt generation component acts as a mediator that translates diverse natural language inputs into standardized prompt formats suitable for the code generation model. This intermediary layer simplifies the interaction interface and reduces the complexity of directly operating the large language model.
2Reliability
If large language models are deployed at one's own facilities, then data security and control are improved, but operational difficulty and resource requirements increase
Solution Approach 1:
The patent implements self-service functionality where the system automatically performs text classification, prompt generation, and code generation without requiring manual intervention or complex configuration. The automated workflow handles data processing independently, reducing operational difficulty while maintaining security through local deployment. Users simply provide input text and receive processed output without needing to manage the underlying complex model infrastructure.
3Manufacturing precision
If detailed operation manuals and expertise are provided, then code generation accuracy is improved, but ease of operation deteriorates
Solution Approach 1:
The patent changes the input parameters from requiring detailed operational parameters to accepting simple natural language text. The text classification and prompt generation components automatically interpret and transform user-friendly text inputs into the precise parameters needed for accurate code generation. This parameter transformation maintains high code generation accuracy while significantly improving ease of operation, as users no longer need to provide complex operational details.
Data Source
AI summary
A novel information processing system that is highly convenient, useful, or reliable is provided. The information processing system includes a first component, a second component, and a third component. The first component has a function of receiving a text written in a natural language and a query for performing retrieval in design assets and transferring the text and the query to the third component, a function of providing a code, and a function of emphasizing a portion related to the code and then providing the design assets. The second component has a function of generating an intermediate code from the text in accordance with a prompt and transferring the intermediate code to the third component. The third component has a function of classifying the text into a predetermined class, generating the prompt, and transferring the prompt to the second component. The third component has a function of generating the code from the command using the received intermediate code as an argument in accordance with the syntax, and transferring the code to the first component.