Nippon Telegraph and Telephone Corporation

Masashi Toyama

Yoshiko Sueda

Koji Murakami

Shotaro Tora

Machiko Toyoda

Ryoichi Hayashi

Hiroyuki Fujiwara

Shinichiro Goto

Keita Mikami

Taku Sasaki

Kunihiro Moriga

A learning device allocates which feature value of a sub-object is extracted by a module from a group of sub-objects constituting an object of an image to each of modules that extract feature values of the object in the image in a deep neural network that is a learning target. After that, the learning device performs first learning to perform learning of the respective modules so that the respective modules are capable of precisely picking up regions of sub-objects allocated to the modules using information indicating the regions of the sub-objects in an image for each of images and second learning to perform learning of the respective modules so that analysis precision of an image analysis is further improved using a result of the image analysis based on the feature values of the sub-objects picked up by the respective modules.

Learning method, learning program, and learning device to accurately identify sub-objects of an object included in an image

An information distribution system includes a plurality of monitoring devices that monitor Information Technology (IT) systems associated with respective monitoring devices, and a sharing device that transmits and receives information to and from the monitoring devices, wherein each of the plurality of monitoring devices includes first processing circuitry configured to provide the sharing device with know-how information including at least detection information and handling procedure information, the detection information being information for detecting a failure based on a log message output from the corresponding IT system, the handling procedure information being information in which a log message related to each failure and a handling procedure for the failure are associated with each other, and acquire the know-how information managed by the sharing device, and the sharing device includes second processing circuitry configured to collect the know-how information provided by the plurality of monitoring devices, and merge the collected know-how information.

Information distribution system, monitoring device, sharing device and information distribution method

An anomaly detection apparatus () includes a storage unit () that stores dictionary information () in which a partial character string of a message representing a type of a message included in a text log output from a system and an ID set for the type of the message are associated with each other. The anomaly detection apparatus (), when the message included in the text log output from the system is acquired, refers to the dictionary information () stored in the storage unit (), classifies the message included in the text log by the type, and assigns the ID to the message that has been classified; and detects an anomaly based on the ID assigned to the message.

Anomaly detection device, anomaly detection method, and anomaly detection program

A service providing server collects call session information that identifies communication established between terminals and service usage IDs that identify the terminals for each terminal. Then, the service providing server identifies call session information pieces indicating the same communication and associates Web services with each other. When the service providing server provides the associated Web services to the terminals, the service providing server identifies service usage IDs that identify the terminals and control provision of the Web services so that each Web service is provided according to history information stored in a history information database in association with service usage IDs.

Providing services by managing communication relationships

Upon receipt of an access request from a Web terminal, a service providing server transmits a shop ID stored in an external information database to the Web terminal. When the shop ID is selected by the Web terminal, the service providing server acquires external connection destination information, and notifies a SIP proxy server of the information via the Web terminal. When notified of the information, the SIP proxy server identifies internal connection destination information in an internal information database, based on an IP address added at the time of the notification of the external connection destination information. After making a call to a telephone device with the use of the identified internal connection destination information, the SIP proxy server makes a call to the shop with the use of the external connection destination information. After that, the SIP proxy server establishes a connection between the telephone device and the shop.

Growing community of inventors

Musashino, Japan

Masashi Toyama