LEARNING MANAGEMENT SYSTEM AND LEARNING MANAGEMENT METHOD

• US 20200134509A1
• Filed: 10/30/2019
• Published: 04/30/2020
• Est. Priority Date: 10/31/2018
• Status: Active Grant

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Ito, Kiyoto, Fuji, Taiki, Esaki, Kanako, Matsumoto, Kohsei
• Granted Patent: US 11,475,373 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 17/15 Correlation function computation including computation of convolution operations arithmetic circuits for sum of products per se, e.g. multiply-accumulators G06F7/5443; digital filters, e.g. FIR, IIR, adaptive filters H03H17/00
• CPC Class Codes: G06F 30/20 Design optimisation, verification or simulation optimisation, verification or simulation of circuit designs G06F30/30
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 20/20 Ensemble learning
• CPC Class Codes: G06Q 10/08 Logistics, e.g. warehousing, loading or distribution; Inventory or stock management

Abstract

A retail agent determines a parameter of an activity proposal model by using data stored in a past record database, and determines parameters of an activity determination model and an activity value evaluation model by further using base activity simulation data. Consequently, it is possible to appropriately determine parameters of a subsystem control method in a complex system which cannot be embodied as a simulator and shows a significant change with respect to past record data.

Claims

1. A learning management system which learns a behavior of a predetermined control target, the learning management system comprising:

a record data storage unit which accumulates past record data of the control target;

a first model storage unit which stores a first correlation model which outputs measure proposal data from data related to the behavior of the control target;

a second model storage unit which stores a second correlation model which outputs measure data from simulation state data and the measure proposal data, the simulation state data simulating the behavior of the control target;

a third model storage unit which stores a third correlation model which outputs a measure evaluation value from the simulation state data, the measure proposal data, and the measure data;

a first record learning unit which determines a parameter of the first correlation model by calculating a correlation between the data related to the behavior of the control target, and the measure proposal data based on a predetermined evaluation value and the past record data stored in the record data storage unit;

a simulation state data obtaining unit which obtains the simulation state data which simulates the behavior of the control target;

a measure data generating unit which generates the measure proposal data by inputting the simulation state data obtained by the simulation state data obtaining unit to the first correlation model, and generates the measure data by inputting the simulation state data obtained by the simulation state data obtaining unit and the measure proposal data to the second correlation model;

an activity learning unit which determines parameters of the second correlation model and the third correlation model based on the simulation state data obtained by the simulation state data obtaining unit, the measure proposal data generated by the measure data generating unit, the measure data generated by the measure data generating unit, and a predetermined evaluation logic; and

a second record learning unit which determines the parameter of the first correlation model again by calculating the correlation between the data related to the behavior of the control target and the measure proposal data based on an evaluation value obtained by the third correlation model, and the past record data stored in the record data storage unit.

2. The learning management system according to claim 1, further comprising a simulation activity data storage unit which associates and stores the simulation state data obtained by the simulation state data obtaining unit, and the measure proposal data and the measure data generated by the measure data generating unit.

3. The learning management system according to claim 1, wherein the simulation state data obtaining unit newly obtains simulation state data based on an adjustment amount of the parameter determined by the second record learning unit.

4. A learning management method executed by a learning management system which learns a behavior of a predetermined control target, wherein

the learning management system includes:

a record data storage unit which accumulates past record data of the control target;

a first model storage unit which stores a first correlation model which outputs measure proposal data from data related to the behavior of the control target;

a second model storage unit which stores a second correlation model which outputs measure data from simulation state data and the measure proposal data, the simulation state data simulating the behavior of the control target; and

a third model storage unit which stores a third correlation model which outputs a measure evaluation value from the simulation state data, the measure proposal data, and the measure data, and

the learning management method comprises;

a first record learning step of determining a parameter of the first correlation model by calculating a correlation between the data related to the behavior of the control target, and the measure proposal data based on a predetermined evaluation value and the past record data stored in the record data storage unit;

a simulation state data obtaining step of obtaining the simulation state data which simulates the behavior of the control target;

a measure data generating step of generating the measure proposal data by inputting the simulation state data obtained in the simulation state data obtaining step to the first correlation model, and generating the measure data by inputting the simulation state data obtained in the simulation state data obtaining step and the measure proposal data to the second correlation model;

an activity learning step of determining parameters of the second correlation model and the third correlation model based on the simulation state data obtained in the simulation state data obtaining step, the measure proposal data generated in the measure data generating step, the measure data generated in the measure data generating step, and a predetermined evaluation logic; and

a second record learning step of determining the parameter of the first correlation model again by calculating the correlation between the data related to the behavior of the control target and the measure proposal data based on an evaluation value obtained by the third correlation model, and the past record data stored in the record data storage unit.