Mitsubishi Electric Corporation

Ryo Kashiwagi

Osamu Nasu

Jijun Jin

Yuki Hikawa

Katsuhiko Nakamura

Takanari Fujimoto

Motoyuki Ozaki

Natsuko Fujii

Shinichiro Nishiuma

Miwa Fukuda

A learning system () generates a diagnosis model through machine learning using learning data, and diagnoses diagnosis target data based on the diagnosis model. A feedback processor () outputs incorrect diagnosis data when acquiring a user input indicating that a diagnosis result is incorrect, and corrects the incorrect diagnosis data based on the user input. A similarity determiner () determines similarity, to the incorrect diagnosis data output by the feedback processor () before being corrected, of the learning data or another diagnosis result of the diagnosis results yet to undergo the feedback process. The feedback processor () performs the feedback process on similarity data with at least a specific level of similarity. The learner () performs relearning using data including the incorrect diagnosis data corrected in the feedback process.

Learning system, learning method, and recording medium

A data processing apparatus executes a process on each piece of data repetitively transmitted from a device and transmits processing information on the process to a receiving apparatus, and includes an outputter and a GW communicator. The outputter acquires conditional information, indicating whether a transmission condition required for transmission of generation data generated in execution of the process to the receiving apparatus is satisfied, after every generation of generation data. When the conditional information indicates satisfaction of the transmission condition for the piece of generation data, the outputter outputs additional information on satisfaction or dissatisfaction of the transmission condition for at least one of another piece of generation data generated immediately before or after the piece of generation data. The GW communicator transmits the processing information including the generation data for which the condition is satisfied and the additional information to the receiving apparatus.

Data processing apparatus, data transmission method, and recording medium

A data processing apparatus includes a first processing unit that executes real-time processing with respect to data, a second processing unit that executes batch processing with respect to data that is output from the first processing unit as a result of processing by the first processing unit, and a monitor that monitors a status of the processing by the first processing unit and a status of processing by the second processing unit. The first processing unit includes a plurality of subprocessing units and buffers, and the second processing unit also includes a plurality of subprocessing units and buffers. The second processing unit includes a storage. The monitor includes a first monitor that monitors, for each of the buffers included in the first processing unit, an amount of the data stored in the corresponding buffer and a second monitor that monitors a total amount of the data stored in the buffers included in the second processing unit and the data stored in the storage.

Data processing device, monitoring method, and program

A data management device () includes an insertion position determiner () to determine an insertion position of dummy data to be inserted into transmission target data, a dummy data inserter () to insert the dummy data in the insertion position of the transmission target data to create dummy-inserted data, an insertion position encryptor () to encrypt data indicating the insertion position with a public key (PUBa) to create insertion-position-encrypted data; and a deliverer () to deliver the dummy-inserted data and the insertion-position-encrypted data.

Data management device, data management system, data management method, and program

A collector () included in a data delivery control apparatus () collects data from a PLC () and outputs the data to which collection time information indicating collection time is added. A validity determiner () determines whether the data is valid based on whether the collection time indicated by the collection time information added to the data is at or later than a starting time indicating a time at which a data sequence as a preset data processing sequence is started. A deliverer () delivers the data in accordance with a data sequence setting defining the data sequence in response to validity determination means determining that the data is valid.

Data delivery control apparatus, method, and program

A data processing apparatus () includes a receiver (), a specifier (), and a task controller (). The receiver () receives a setting of a process flow defining subprocesses that are sequentially executed with respect to data output from a device (). The specifier () specifies, based on the setting received by the receiver (), processing units () for execution of the subprocesses. The task controller () determines, based on the setting received by the receiver (), and launches the tasks in accordance with the order, an order for launching tasks for achievement of the processing units () specified by the specifier ().

Determining an order for launching tasks by data processing device, task control method, and computer readable medium

A collector included in a data collection apparatus performs data collection to collect data from a PLC. A controller included in the data collection apparatus determines whether the collector is valid depending on whether the collector at a time when an instruction to start the data collection is provided matches the collector at a preset time, and causes the collector to start the data collection in response to the collector being valid.

Data collection apparatus, method, and program

A direct relationship extraction unit generates a direct relationship list indicating a set of a direct dependence source, a direct dependence destination, and a direct dependence type. A storage unit stores an indirect relationship rule including a plurality of direct dependence types, an element relationship, a dependence source element, and a dependence destination element. An indirect relationship extraction unit extracts, from a direct relationship list, a plurality of pieces of direct relationship information corresponding to the plurality of direct dependence types and the element relationship included in the indirect relationship rule, extracts an indirect dependence source which is an element corresponding to a dependence source element in the indirect relationship rule from the extracted plurality of pieces of direct relationship information, and extracts an indirect dependence destination corresponding to a dependence destination element in the indirect relationship rule from the extracted plurality of pieces of direct relationship information.

Growing community of inventors

Tokyo, Japan

Ryo Kashiwagi