Method for generating universal learned model

Abstract

Generating a universal learned model that appropriately controls a group of operating devices having the same configuration. Steps comprise subjecting a predetermined machine learning model to learning based on predetermined initial data to generate an initial learned model and an integration step of incorporating the initial learned model that controls a predetermined operating device into a plurality of operating devices, and integrating a plurality of individual learned models obtained by additional learning based on respective operation data obtained by operating the respective operating devices, thereby providing a universal learned model.

1 . A method comprising:
 generating a learned model at respective information processing devices that are connected through a network by performing machine learning based on data stored in the respective information processing devices;   providing the learned model to an integration processing server from the respective information processing devices;   integrating, at the integration processing server, the respective learned models to generate an integrated learned model;   providing the integrated learned model to the respective information processing devices.   
     
     
         2 . The method, according to  claim 1 , wherein the integrating respective learned models comprises:
 selectively integrating the respective learned models according to accompanying information corresponding to the respective learned models.   
     
     
         3 . The method, according to  claim 1 , wherein the integrating the respective learned models comprises:
 determining whether the integration is possible before integrating the respective learned models.   
     
     
         4 . The method, according to  claim 1 , wherein the data comprises data generated by the respective information processing devices. 
     
     
         5 . The method, according to  claim 1 , further comprising:
 providing, by at least one of the respective information processing devices, an interface configured to receive a selection indicating whether the integrated learned model is to be applied to the respective information processing device.   
     
     
         6 . The method, according to  claim 1 , wherein the machine learning comprises subjecting additional learning to the existing learned model based on the data stored in the respective information processing devices. 
     
     
         7 . The method, according to  claim 1 , wherein the machine learning comprises subjecting additional learning to an initial learned model that is obtained by performing machine learning on a prescribed machine learning model based on prescribed initial data. 
     
     
         8 . The method, according to  claim 1 , wherein the integrating the respective learned models comprises multi-stage integration comprising the integration between the integrated learned models. 
     
     
         9 . The method, according to  claim 1 , wherein the learned model comprises a learned model having a tree structure. 
     
     
         10 . A system, comprising:
 a plurality of information processing devices and an integration processing server connected with the respective information processing devices through a network,   wherein each information processing device comprises:   a memory coupled to a processor, the memory storing instructions that when executed by the processor, configure the processor to:   generate a learned model by performing machine learning based on data stored in the respective information processing device, and   provide the learned model to the integration processing server,   wherein the integration processing server comprises:   a memory coupled to a processor, the memory storing instructions that when executed by the processor, configure the processor to:   integrate the respective learned models to generate an integrated learned model, and   provide the integrated learned model to the respective information processing devices.