Information processing method, information processing apparatus, molding machine system and non-transitory computer readable recording medium

An information processing for detecting conditions of a plurality of manufacturing devices respectively used by a plurality of entities, comprising:

• acquiring sensor value data obtained by detecting physical quantities related to the plurality of manufacturing devices respectively used by the plurality of entities;
• individually storing sensor value data acquired from the plurality of manufacturing devices in a plurality of databases prepared respectively for the entities that use the manufacturing devices;
• generating or updating by machine learning a plurality of learning models for detecting conditions of the manufacturing devices based on sensor value data stored in the plurality of databases;
• storing identifying information of the entities in association with model selection information indicating one or more of the plurality of learning models selected by the entities;
• calculating a condition of a manufacturing device of one of the entities by inputting sensor value data acquired from the manufacturing device of the one of the entities to the one or more of the learning models indicated by the model selection information associated with the identifying information of the one of the entities;
• storing identifying information identifying the plurality of entities in association with information indicating which one of the learning models between the learning model generated based on sensor value data stored in the plurality of databases and the learning model for detecting a condition of the manufacturing device generated based on sensor value data acquired from a manufacturing device as a testing machine or by a simulator is to be used by each of the entities, and
• calculating a condition of the manufacturing device of the one of the entities by inputting sensor value data acquired from the manufacturing device of the one of the entities to the learning model indicated by the information associated with the identifying information of the one of the entities.

An information processing apparatus for detecting conditions of a plurality of manufacturing devices respectively used by a plurality of entities, comprising:

• an acquisition unit that acquires sensor value data obtained by detecting physical quantities related to the plurality of manufacturing devices respectively used by the plurality of entities;
• a plurality of databases that individually store sensor value data acquired from the plurality of manufacturing devices for each of the entities that use the manufacturing devices;
• and
• a processing unit,
• the processing unit
• generating or updating by machine learning a plurality of learning models for detecting conditions of the manufacturing devices based on sensor value data stored in the plurality of databases,
• storing identifying information of the entities in association with model selection information indicating one or more of the plurality of the learning models selected by the entities,
• calculating a condition of a manufacturing device of one of the entities by inputting sensor value data acquired from the manufacturing device of the one of the entities to the one or more of the learning models indicated by the model selection information associated with the identifying information of the one of the entities;
• fine-tuning at least one of the plurality of learning models based on sensor value data acquired from at least one of the plurality of manufacturing devices;
• storing identifying information identifying the plurality of entities in association with information indicating which one of the learning models each of the entities uses between the learning model that is not fine-tuned and the fine-tuned learning model;
• and
• calculating a condition of the manufacturing device of one of the entities by inputting sensor value data acquired from the manufacturing device of the one of the entities to the learning model indicated by the information associated with the identifying information of the one of the entities.

A non-transitory computer readable recording medium storing a computer program causing a computer to execute processing of detecting a condition of a plurality of manufacturing devices respectively used by a plurality of entities, comprising:

• acquiring sensor value data obtained by detecting physical quantities related to the plurality of manufacturing devices respectively used by the plurality of entities;
• individually storing sensor value data acquired from the plurality of manufacturing devices in a plurality of databases prepared respectively for the entities that use the manufacturing devices;
• generating or updating by machine learning a plurality of learning models for detecting conditions of the manufacturing devices based on sensor value data stored in the plurality of databases;
• storing identifying information of the entities in association with model selection information indicating one or more of the plurality of learning models selected by the entities;
• calculating a condition of a manufacturing device of one of the entities by inputting sensor value data acquired from the manufacturing device of the one of the entities to the one or more of the learning models indicated by the model selection information associated with the identifying information of the one of the entities;
• fine-tuning at least one of the plurality of learning models based on sensor value data acquired from at least one of the plurality of manufacturing devices;
• storing identifying information identifying the plurality of entities in association with information indicating which one of the learning models each of the entities uses between the learning model that is not fine-tuned and the fine-tuned learning model;
• and
• calculating a condition of the manufacturing device of one of the entities by inputting sensor value data acquired from the manufacturing device of the one of the entities to the learning model indicated by the information associated with the identifying information of the one of the entities.

An information processing apparatus for detecting conditions of a plurality of manufacturing devices respectively used by a plurality of entities, comprising:

• an acquisition unit that acquires sensor value data obtained by detecting physical quantities related to the plurality of manufacturing devices respectively used by the plurality of entities;
• a plurality of databases that individually store sensor value data acquired from the plurality of manufacturing devices for each of the entities that use the manufacturing devices;
• and
• a processing unit,
• the processing unit
• generating or updating by machine learning a plurality of learning models for detecting conditions of the manufacturing devices based on sensor value data stored in the plurality of databases,
• storing identifying information of the entities in association with model selection information indicating one or more of the plurality of the learning models selected by the entities,
• calculating a condition of a manufacturing device of one of the entities by inputting sensor value data acquired from the manufacturing device of the one of the entities to the one or more of the learning models indicated by the model selection information associated with the identifying information of the one of the entities,
• storing identifying information identifying the plurality of entities in association with information indicating which one of the learning models between the learning model generated based on sensor value data stored in the plurality of databases and the learning model for detecting a condition of the manufacturing device generated based on sensor value data acquired from a manufacturing device as a testing machine or by a simulator is to be used by each of the entities, and
• calculating a condition of the manufacturing device of the one of the entities by inputting sensor value data acquired from the manufacturing device of the one of the entities to the learning model indicated by the information associated with the identifying information of the one of the entities.

A non-transitory computer readable recording medium storing a computer program causing a computer to execute processing of detecting a condition of a plurality of manufacturing devices respectively used by a plurality of entities, comprising:

• acquiring sensor value data obtained by detecting physical quantities related to the plurality of manufacturing devices respectively used by the plurality of entities;
• individually storing sensor value data acquired from the plurality of manufacturing devices in a plurality of databases prepared respectively for the entities that use the manufacturing devices;
• generating or updating by machine learning a plurality of learning models for detecting conditions of the manufacturing devices based on sensor value data stored in the plurality of databases;
• storing identifying information of the entities in association with model selection information indicating one or more of the plurality of learning models selected by the entities;
• calculating a condition of a manufacturing device of one of the entities by inputting sensor value data acquired from the manufacturing device of the one of the entities to the one or more of the learning models indicated by the model selection information associated with the identifying information of the one of the entities;
• storing identifying information identifying the plurality of entities in association with information indicating which one of the learning models between the learning model generated based on sensor value data stored in the plurality of databases and the learning model for detecting a condition of the manufacturing device generated based on sensor value data acquired from a manufacturing device as a testing machine or by a simulator is to be used by each of the entities;
• and
• calculating a condition of the manufacturing device of the one of the entities by inputting sensor value data acquired from the manufacturing device of the one of the entities to the learning model indicated by the information associated with the identifying information of the one of the entities.