Computer system and verification method for schedule system

Abstract

The invention provides a computer system and a verification method for a schedule system, which verifies the effect of an AI system in a development stage capable of generating a schedule. The computer system is capable of verifying a schedule system that, when receiving object data including a plurality of entries, which is data relating to an object of a schedule, generates a schedule comprising sorted entries using a model that calculates the probability of selection of the entries, and manages information of the model. The computer system comprises: a selection module selecting at least one of the entries based on the target data for verification; a feature amount calculation module generating feature amount data formed of each of the entries; a feature amount estimation module estimating a feature amount which is a feature amount not included in the feature amount data; a selection probability calculation module calculating a probability of selecting the at least one of the entries; and an effect estimation module executing selection processing of selecting a candidate entry to be included in the schedule based on the selection probability, and generating information indicating a search range of the scheduling system based on a result of the selection processing.

Description

technical field [0001] The present invention relates to a generation technique of a schedule such as a production plan of a product. Background technique [0002] The use of systems applying AI in various fields such as medical care and industry is expanding. Use of these systems is expected to automate tasks that are performed manually. In this specification, a system to which AI is applied is also described as an AI system. [0003] Algorithms, or models, that implement AI are generated through machine learning using learning data. By using learning data, business knowledge in various fields can be imported into AI. [0004] However, there are also business knowledge that is difficult to import from learning data, such as legal regulations and compliance. In addition, when there is little learning data, it may not be possible to sufficiently introduce business knowledge into AI. If business knowledge that cannot be directly imported into AI is not considered, it is no...

AI Technical Summary

Problems solved by technology

[0004] However, there are also business knowledge that is difficult to import from learning data, such as legal regulations and compliance

In addition, in the case of less learning data, there are also cases where business knowledge cannot be fully introduced into AI

If business knowledge that cannot be directly imported into AI is not considered, it is not suitable for practical use as a system

Therefore, for business knowledge that is difficult to import from learning data, additional logic needs to be developed and embedded in the AI ​​system

Images