Nippon Telegraph and Telephone Corporation

Keita Hasegawa

Masashi Tanaka

Yasushi Okano

Takuma Koyama

Yoshihito Oshima

Takafumi Harada

Tomoaki Washio

Yuichiro Dan

An action learning system includes a memory, and a processor configured to train, based on first data indicating a property of an environment in which data is collected from multiple devices and to which an action determined by a first neural network according to a state of the environment is applied and second data indicating a property of the environment to which the action is not applied, a second neural network that calculates a similarity degree between distributions of the first data and the second data, and train, after the second neural network is trained, the first neural network that determines an action according to the state of the environment, by reinforcement learning including, in a reward, a value that changes based on a relationship between a similarity degree and a parameter set by a user, the similarity degree being calculated by the second neural network based.

Behavior learning system, behavior learning method and program

An information processing apparatus includes a generation unit configured to generate, from a log obtained from a device, a graph structure indicating one or more associations between one or more processes and one or more objects related to the one or more processes, and an identifying unit configured to, in a case where one of objects of the device is specified, identify at least one process related to the specified one of the objects, based on the generated graph structure, and identify one or more objects related to the identified at least one process.

Information processing apparatus, log analysis method and program

A storage processing unit configured to store, in a storage unit, first data output by a device or any one of multiple devices in association with first context information related to the first data, and a determining unit configured to obtain second context information related to second data in a case where the second data is received from the device or any one of the multiple devices, and determine whether an analysis of the received second data is necessary based on the received second data and the obtained second context information and based on the first data and the first context information stored in the storage unit, are provided.

Information processing apparatus, data analysis method and program

A storage processing unit configured to store, in a storage unit, first data output by a device or any one of multiple devices in association with a first feature context related to the first data, and an analyzing unit configured to obtain a second feature context related to second data in a case where the second data is received from the device or any one of the multiple devices, and analyze an anomaly of the received second data based on the received second data and the obtained second feature context and based on the first data and the first feature context stored in the storage unit, are provided.

Information processing apparatus, anomaly analysis method and program

A device includes a memory; and a processor configured to execute first determining, for each data item generated in the device, a priority upon transmitting said each data item to an information processing apparatus, based on one or more rules set in advance; second determining, for said each data item, whether or not it is necessary to transmit said each data item to the information processing apparatus, based on the priority determined for said each data item; and transmitting a data item to the information processing apparatus among data items generated in the device for a predetermined period of time, the data item being determined by the second determining that it is necessary to transmit the data item to the information processing apparatus.

Growing community of inventors

Tokyo, Japan

Keita Hasegawa