Supply chain data chart generation method driven by large language model, computer device and computer readable storage medium

By combining chart domain knowledge and supply chain data in a large language model, the system automatically recommends and generates suitable visualization charts, solving the problems of insufficient adaptation and complexity in the generation of supply chain charts in existing technologies. This reduces the operational threshold and meets the unique visualization needs of the supply chain.

CN121787537APending Publication Date: 2026-04-03ZHENGZHOU UNIV
View PDF 1 Cites -1 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-12-22
Publication Date
2026-04-03

AI Technical Summary

Technical Problem

Existing chart generation methods based on large language models are not well adapted to the supply chain field, are prone to generating erroneous content, are difficult to meet complex visualization needs, and have high operational barriers, failing to meet the unique analytical needs of the supply chain.

Method used

By acquiring supply chain data visualization analysis tasks, we use large language models to match data sources and extract data, combine chart domain knowledge to recommend suitable chart types, and perform data processing and visualization to generate complex visualization charts that conform to the unique characteristics of the supply chain.

Benefits of technology

It enables the automated generation of complex visualization charts adapted to each link of the supply chain, lowers the operational threshold, and meets the unique analytical needs of the supply chain.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121787537A_ABST
    Figure CN121787537A_ABST
Patent Text Reader

Abstract

The invention belongs to the technical field of supply chain data visualization analysis, and particularly relates to a supply chain data chart generation method driven by a large language model, a computer device and a computer readable storage medium. The method comprises the following steps: firstly, obtaining a proposed supply chain data visual analysis task, matching a data source most relevant to the analysis task, and extracting required supply chain data from the data source; and then, inputting a chart recommendation framework based on the supply chain data visualization task type as chart domain knowledge into the large language model, and outputting a chart type recommendation result matched with the analysis task and the extracted supply chain data by utilizing the large language model learning the chart domain knowledge. Processing the extracted supply chain data based on the requirements of the recommended chart type; and finally, performing chart visualization of the supply chain data according to the analysis task, the recommended chart type and the processed supply chain data. The visual chart generated by the method can meet specific complex visual requirements of the supply chain.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Food cold chain data visualization automatic generation method based on large language model

    CN120144106A