Fujitsu Corporation

Kento Ikkaku

Kouichirou Amemiya

Norinao Kouma

Jun Ogawa

Kazuhito Matsuda

Miho Kawano

An analysis method includes acquiring target data collected at edges; determining first analysis target satisfying a first condition, and specifying a first detection position indicating a position at which the first analysis target is detected at the edges and a first detection time; calculating a correlation coefficient of the feature amount; specifying a first range of the first detection position and a second range of the first detection time of the analysis target for which the correlation coefficient satisfies a predetermined relationship; determining second analysis target satisfying a second condition, and specifying a second detection position and a second detection time; determining whether the analysis target in which the second detection position is included in the first range and the second detection time; and acquiring any one of the analysis target from the edges when it is determined that the analysis target is included.

Analysis apparatus, analysis method, and storage medium

A data collection device includes a memory and a processor coupled to the memory and the processor configured to acquire, for a plurality of data transmission requests, first predicted values of a delay from transmission of the respective data transmission requests to a start of reception of data and second predicted values of a throughput regarding the reception of the data, classify the plurality of data transmission requests into groups based on first dispersion of the first predicted values and second dispersion of the second predicted values, and determine transmission timings of the respective data transmission requests in a unit of the group.

Data collection device and data collection method

A storage medium storing a data collecting program for making a process performed, the process includes identifying a data obtainment target period and a plurality of areas based on a request from a user, extracting a plurality of apparatuses present in each area in each time frame as a data obtainment unit of the period, assigning, for each set of the time frame and the area, an apparatus as a collection source of a data block corresponding to the set of the time frame and the area based on a given condition from among the extracted plurality of apparatuses, and collecting the data block from the apparatus assigned as the collection source for each set of the time frame and the area.

Storage medium, data collecting device, and data collecting method

A task deployment method executed by a processor of a task development apparatus, the task development method includes acquiring, at a predetermined interval, a number of processes in a queue that stores the processes executed by a plurality of calculation devices included in at least one of one or more nodes; determining, for each of the plurality of calculation devices, a process execution rate for a new process; calculating, for each of the plurality of calculation devices, an execution completion point for the new process based on the acquired number of processes in the queue and the determined process execution rate for each of the respective calculation devices; and determining, from among the plurality of calculation devices, a calculation device to execute the new process based on the calculated execution completion point for each of the plurality of calculation devices.

Task deployment method, task deployment apparatus, and storage medium

A non-transitory computer-readable storage medium storing a program that causes a computer to execute a process, the process includes acquiring a number of processes in a queue storing a process executed by a node; generating information for specifying an execution completion point for a new process in a case where the node is to execute the new process based on the acquired number of processes in the node, information regarding a process execution rate in the node, and information regarding a communication delay between a management node generating the new process and the node; and transmitting the generated information for specifying the execution completion point generated for the node to the management node.

Growing community of inventors

Kawasaki, Japan

Kento Ikkaku