Server device, learned model providing program, learned model providing method, and learned model providing system

Abstract

A server device configured to communicate, via a communication network, with at least one device including a learner configured to perform processing by using a learned model, includes processor, a transmitter, and a storage configured to store a plurality of shared models pre-learned in accordance with environments and conditions of various devices. The processor is configured to acquire device data including information on an environment and conditions from the at least one device, and select an optimum shared model for the at least one device based on the acquired device data. The transmitter is configured to transmit a selected shared model to the at least one device.

1 - 12 . (canceled) 
     
     
         13 . A model generating device comprising:
 at least one storage; and   at least one processor configured to:
 obtain data of a first device, the data of the first device including at least data for model learning, acquired by the first device; 
 generate a first model for the first device based on the obtained data; and 
 transmit the first model. 
   
     
     
         14 . The model generating device according to  claim 13 , wherein the first device is an operating machine, and the data for model learning is acquired during on an operation of the first device. 
     
     
         15 . The model generating device according to  claim 13 , wherein the first device is an operating machine that handles an object, and the data of the first device includes information on the object. 
     
     
         16 . The model generating device according to  claim 13 , wherein a use of the first model for the first device is not determined by the first device but the model generating device. 
     
     
         17 . The model generating device according to  claim 13 , wherein the at least one storage stores one model, and
 the at least one processor is configured to perform additional learning on the one model stored in the at least one storage using the data for model learning to generate the first model.   
     
     
         18 . The model generating device according to  claim 17 , wherein the one model is a newly generated model by using the data for model learning acquired by the first device. 
     
     
         19 . The model generating device according to  claim 17 , wherein the at least one storage stores a plurality of models including the one model, and the at least one processor is configured to:
 select the one model from the plurality of models; and   perform the additional learning on the selected one model using the data for model learning to generate the first model.   
     
     
         20 . The model generating device according to  claim 19 , wherein the plurality of models stored in the at least one storage includes an additional learned model by using data for model learning acquired by another device. 
     
     
         21 . The model generating device according to  claim 19 , wherein the plurality of models stored in the at least one storage includes an additional learned model by using data for model learning acquired by the first device. 
     
     
         22 . The model generating device according to  claim 19 , wherein the at least one processor is configured to select the one model from the plurality of models based on scores calculated by using the data of the first device. 
     
     
         23 . The model generating device according to  claim 19 , wherein
 the at least one processor is configured to select the one model from the plurality of models based on the predefined rule.   
     
     
         24 . The model generating device according to  claim 17 , wherein the at least one processor is configured to update a part of parameters of the one model to generate the first model. 
     
     
         25 . The model generating device according to  claim 17 , wherein the at least one processor is configured to add new parameters to the one model to generate the first model. 
     
     
         26 . The model generating device according to  claim 13 , wherein the at least one processor is configured to generate the first model by using data of another device. 
     
     
         27 . The model generating device according to  claim 13 , wherein the first model is a neural network. 
     
     
         28 . The model generating device according to  claim 13 , wherein the transmitting device is a server device. 
     
     
         29 . A device comprising:
 at least one storage; and   at least one processor configured to:
 transmit data to at least one model generating device, the transmitted data including at least data for model learning; and 
 receive, from the at least one model generating device, a first model generated based on the transmitted data. 
   
     
     
         30 . The device according to  claim 29 , wherein the device is an operating machine, and the data for model learning is acquired during an operation of the device. 
     
     
         31 . The device according to  claim 29 , wherein the device is an operating machine that handles an object, and the transmitted data includes information on the object. 
     
     
         32 . The device according to  claim 29 , wherein a use of the first model is determined by the at least one model generating device. 
     
     
         33 . The device according to  claim 29 , wherein the first model is a model generated by additional learning based on the transmitted data. 
     
     
         34 . The device according to  claim 29 , wherein
 the at least one processor is configured to perform additional learning on the first model by using acquired data to generate a second model.   
     
     
         35 . The device according to  claim 34 , wherein
 the at least one processor is configured to transmit the second model to the at least one model generating device.   
     
     
         36 . The device according to  claim 34 , wherein
 the at least one processor is configured to transmit information about the second model to the at least one model generating device without transmitting the second model to the at least one model generating device.   
     
     
         37 . A model transmitting method comprising:
 obtaining, by at least one processor, data of a first device, the data of the first device including at least data for model learning, acquired by the first device;   generating, by the at least one processor, a first model for the first device based on the obtained data; and   transmitting, by the at least one processor, the first model.   
     
     
         38 . A method comprising:
 transmitting, by at least one processor, data to at least one model generating device, the transmitted data including at least data for model learning; and   receiving, by the at least one processor, from the at least one model generating device, a first model generated based on the transmitted data.