Selective Breeding Assistance Using Learned Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Breeding for desirable traits in animals and plants is labor-intensive and time-consuming, requiring repeated processes to find a new variety with intended characteristics.
Innovation Solution
A selective breeding assistance apparatus and method that uses a learned model to generate response information for crossbreeding candidates by analyzing the properties and breeding processes of existing varieties, reducing the need for manual trial and error.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual breeding processes are used to select and crossbreed varieties, then breeding can be performed with simple equipment, but it requires a lot of labor and time
Solution Approach 1:
The patent replaces manual mechanical breeding operations with an automated information processing system. The selective breeding assistance apparatus uses a learned model to automatically analyze variety properties, predict crossbreeding outcomes, and generate breeding recommendations, substituting human manual work with computational processes that operate faster and more efficiently.
Solution Approach 2:
The patent introduces a learned model as an intermediary between the breeding goal and the actual crossbreeding process. This model serves as a mediator that processes variety information, predicts breeding outcomes, and guides the selection of crossbreeding candidates, thereby reducing the need for repeated manual trial-and-error breeding cycles.
2Measurement precision
If repeated breeding processes are performed to find a new variety with intended character, then accurate variety selection can be achieved, but labor and time consumption increases
Solution Approach 1:
The patent performs preliminary analysis and prediction before actual crossbreeding takes place. The learned model pre-evaluates potential crossbreeding combinations by analyzing variety properties and predicting outcomes, allowing breeders to select the most promising candidates in advance and avoid unnecessary breeding experiments.
Solution Approach 2:
The patent implements a feedback mechanism where the learned model continuously learns from breeding data and improves its predictions. The system analyzes the results of breeding processes and uses this information to refine variety selection, creating a closed-loop system that increases accuracy while reducing the number of iterations needed.
3Loss of information
If manual variety selection and crossbreeding monitoring are performed, then detailed breeding processes can be tracked, but significant labor is required
Solution Approach 1:
The patent enables the breeding information system to serve itself by automatically collecting, processing, and analyzing breeding data. The learned model autonomously processes variety information and breeding process data, generating insights and recommendations without requiring manual data entry or analysis, thereby reducing labor while maintaining comprehensive information tracking.
Data Source
AI summary
In order to suitably assist breeding, a selective breeding assistance apparatus (1) includes: a reception section (11) for receiving a request pertaining to breeding; a generation section (12) for generating response information based on the request using a learned model which has learned a relation between a property of an existing variety and a breeding process of the existing variety, the response information including information pertaining to an existing variety that serves as a crossbreeding candidate for developing a new variety; and an output section (13) for outputting the response information.