[3M5-OS-12b] OS-12

[3M5-OS-12b-01] Development of a Dataset Representing Agricultural Product Prices for Generative AI of Agricultural Extension Specialist.

〇Akio Kobayashi¹, Hiroki Sakaji², Tetsuo Katsuragi¹, Shotaro Mori⁴, Akira Hashimoto³, Masahiro Suzuki⁵, Takahiro Kawamura¹ (1. Research Center for Agricultural Information Technology, NARO, 2. Hokkaido University, 3. University of Tsukuba, 4. Himika, Inc., 5. The University of Tokyo)

Keywords:Agricultural Informatics, Price Prediction, Dataset Construction

In the Cabinet Office's Project of "programs for Bridging the gap between R & d and the IDeal society (society 5.0) and Generating Economic and social value," the AI Agricultural Society Implementation Project aims to establish AI technologies to compensate for the decrease in agricultural labor force caused by the declining number of farmers.
Among the challenges, the reduction of prefectural extension workers, who directly instruct farmers, is significant.
This project is working on creating AI systems capable of answering questions like an extension worker, utilizing Large Language Models (LLM).
This research focuses on frequently asked questions by farmers to extension workers, specifically on adjusting the timing of shipments and planting to maximize sales.
Answering such questions requires knowledge of market trends for agricultural products, as well as information about the state and geographical details of the farmers' fields.
Therefore, as a first step towards achieving this, this paper reports on the construction of a dataset combining market trends of agricultural products with data on fields and the crops grown, to support the realization of such an AI extension worker system.