Intelligent scheduling method and system based on large language model

By constructing a structured production scheduling dataset and performing supervised fine-tuning on a large language model, the problem of generating feasible scheduling schemes in complex manufacturing scenarios using traditional production scheduling methods is solved, achieving rapid response and efficient production scheduling, and improving production efficiency and order delivery reliability.

CN122198481APending Publication Date: 2026-06-12BEIJING WENYUYUN TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
BEIJING WENYUYUN TECHNOLOGY CO LTD
Filing Date
2026-03-12
Publication Date
2026-06-12

AI Technical Summary

⚠Technical Problem

Existing technologies struggle to respond quickly to sudden disturbances in highly dynamic and tightly coupled manufacturing scheduling scenarios, and traditional methods are computationally inefficient in high-dimensional, multi-constraint scenarios, making it difficult to generate feasible scheduling solutions.

⚗Method used

We construct an intelligent scheduling system based on a large language model. By building a structured scheduling dataset and performing supervised fine-tuning, we use the large language model to generate scheduling schemes that conform to industrial constraints. By combining role-playing, context injection, and structured instructions, we simulate the cognitive process of a human scheduler and optimize the parameters of the large language model to generate efficient scheduling schemes.

🎯Benefits of technology

It enables rapid response to dynamic changes in complex manufacturing environments, generates efficient and feasible production scheduling solutions, improves production efficiency and order delivery reliability, and expands the application scope of large language models in the field of operations research and optimization.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122198481A_ABST
    Figure CN122198481A_ABST
Patent Text Reader

Abstract

The application discloses an intelligent production scheduling method and system based on a large language model, and relates to the technical field of production scheduling. The method comprises the following steps: constructing a production scheduling data set based on real production data, wherein the production scheduling data set comprises a plurality of production scheduling instances, the production scheduling instance is structured data composed of an input part and an output part, the input part comprises role setting, context information and task instruction, and the output part comprises a standard production scheduling scheme; using the production scheduling data set to supervise and fine-tune a pre-trained large language model to obtain an intelligent production scheduling model; and inputting a target production scheduling task into the intelligent production scheduling model to output a target production scheduling scheme corresponding to the target production scheduling task. The application can accurately map structured production scheduling into a daily production scheduling scheme conforming to table specifications, thereby expanding the application range of the large language model in the field of operational optimization and providing a new technical path for data-driven intelligent manufacturing.
Need to check novelty before this filing date? Find Prior Art