Abstract: A machine learning development support system includes: a data storage unit that stores training data; a data attribute extraction unit that refers to definition information whereby a conversion condition for converting the training data into an attribute thereof is defined and extracts data acquisition conditions from the training data; and an experiment record information storage unit that stores experiment record information., The machine learning product including a machine learning program and a trained model is divided into versions and recorded, and an accuracy of an inference obtained by each version is recorded in association with the version, the trained model, and the training data; and a processing specification unit that refers to the experiment record information, and specifies, for each of the data acquisition conditions, a machine learning product in which the accuracy of the inference is improved between old and new versions of the machine learning product.

Abstract: A system for performing operation management of a machine learning model includes a task-inference ID association unit configured to, on the basis of a system data stream for outputting content of a task performed by a system that calls a machine learning model and a recorded data stream for inputting/outputting data when inference of the machine learning model is processed, calculate, with regard to association between the system data stream and the recorded data stream, the association between the system data stream and the recorded data stream from configuration information representing dependency between the system and the machine learning model.

Abstract: A grouping unit, with the use of facility order priority information and facility order rule information, determines a group to which facility orders belong, stores the group in grouping information, performs grouping of facility orders, which do not include a sequential relation in a reverse direction among facility orders, into the same group, performs grouping of facility orders, which include a sequential relation in a reverse direction among facility orders, into a different group, integrates the facility orders grouped in the same group, and sets the integrate facility order as a display facility order of the group.

Abstract: When an event such as maintenance occurs, a model in which a tendency of input data changes due to an influence of the maintenance and retraining is required is specified. Model identifiers that specify the machine learning models and are unique to the machine learning models and sensor identifiers that specify the sensors that output the sensor data serving as the input data of the machine learning models and are unique to the sensors are managed to be in association with each other. A degree of influence indicating a change in tendency of the sensor data before and after the maintenance operation is performed is obtained for each maintenance event identifier that specifies a maintenance operation performed on a device and is unique to the maintenance operation, and the degree of influence is managed in association with each of the sensor identifiers.

Abstract: A system for performing operation management of a machine learning model includes a task-inference ID association unit configured to, on the basis of a system data stream for outputting content of a task performed by a system that calls a machine learning model and a recorded data stream for inputting/outputting data when inference of the machine learning model is processed, calculate, with regard to association between the system data stream and the recorded data stream, the association between the system data stream and the recorded data stream from configuration information representing dependency between the system and the machine learning model.

Abstract: A grouping unit, with the use of facility order priority information and facility order rule information, determines a group to which facility orders belong, stores the group in grouping information, performs grouping of facility orders, which do not include a sequential relation in a reverse direction among facility orders, into the same group, performs grouping of facility orders, which include a sequential relation in a reverse direction among facility orders, into a different group, integrates the facility orders grouped in the same group, and sets the integrate facility order as a display facility order of the group.

Abstract: A production management supporting system analyzes past record information including information showing, for each product loaded in a production line in which a plurality of steps are performed, an execution time of each of the steps on the basis of one or more attentional perspectives to detect, from among objects displayed on a diagram chart showing a production situation, display objects each satisfying one or more requirements associated with the one or more attentional perspectives. The production management supporting system performs accentuated display of at least one of the detected display objects.

Abstract: A power transaction plan planning support system for planning an electrical power transaction plan includes: a suppressible power consumption amount calculation unit which calculates a suppressible power consumption amount; a market information acquisition unit which acquires a market price and a position amount; a transaction plan planning rule which defines a position amount threshold value which serves as a criterion to determine whether the position amount is insufficient or not, as a determination condition to determine whether to buy electrical power from an electrical power transaction market or not; and a transaction plan planning unit which reduces the position amount threshold value by the suppressible power consumption amount and calculates an amount of the electrical power to be purchased from the electrical power transaction market on the basis of the reduced position amount threshold value, the market price, and the transaction plan planning rule.

Abstract: A suitable Tier ratio is determined according to the I/O performance and I/O characteristic of a virtual volume. A storage apparatus which is connected via a network to a host computer which requests data writing comprises storage devices of a plurality of types of varying performance; and a controller which manages storage areas provided by each of the storage devices of a plurality of types by means of storage tiers of a plurality of different types, and which assigns the storage areas in page units to virtual volumes from any of the storage tiers among the storage tiers of the plurality of types according to the data write request from the host computer, wherein the controller monitors performance information which includes I/O characteristic information for each of the virtual volumes and determines the storage tiers corresponding to the performance information thus monitored, and assigns the storage areas in page units to the virtual volumes from the determined storage tiers.

Abstract: A suitable Tier ratio is determined according to the I/O performance and I/O characteristic of a virtual volume. A storage apparatus which is connected via a network to a host computer which requests data writing comprises storage devices of a plurality of types of varying performance; and a controller which manages storage areas provided by each of the storage devices of a plurality of types by means of storage tiers of a plurality of different types, and which assigns the storage areas in page units to virtual volumes from any of the storage tiers among the storage tiers of the plurality of types according to the data write request from the host computer, wherein the controller monitors performance information which includes I/O characteristic information for each of the virtual volumes and determines the storage tiers corresponding to the performance information thus monitored, and assigns the storage areas in page units to the virtual volumes from the determined storage tiers.

Abstract: An object of the present invention is to manage various containment relationships such as packing relationships and loading relationships of an article, to efficiently search for sensor information measured by a sensor associated with the article, and thereby to provide the sensor information to the user. A system 100 includes a relationship information registration part 1001 and a sensor information searching part 1002.

Abstract: In an assembled product, a decrease in reading efficiency is avoided from being deteriorated by reading the electronic tags of the parts and the assembled product, registering their configuration information, and by placing read restriction on the electronic tags of the parts. For this purpose, manufacturing instruction information, used for assembling parts into an assembled product, is used. When replaced, the electronic tags of the assembled product are read, read restriction is removed from the assembled product, the electronic tag is read, the electronic tag of a new part to be installed is read, read restriction is placed on the electronic tag, and the configuration information is updated. An invalid part replacement is detected by comparing the configuration information.

Abstract: There is a need for facilitating configuration of the right to reference varied work histories and searching for work histories. A work history management apparatus according to an embodiment of the invention includes: a work history classification section that classifies a work history in accordance with a content of the work history and assigns a classification identifier; a work history registration section that associates the classification identifier with the work history and stores the work history in a storage device; and a work history reference section that responds to a work history reference request from a user, references a reference condition associating a user capable of referencing the work history with the classification identifier, and searches for the work history stored in the storage device so as to be able to be referenced by the user and correspond to the classification identifier.

Abstract: An ID reading device in an ID reading system that acquires IDs from a reader that reads identification labels, comprises an expected ID acquisition unit that acquires IDs to be read; a read attribute acquisition unit that acquires a correspondence between read attributes and the IDs, the read attributes being classifications of articles based on a possibility that, there is actually an article to which the identification label is attached; a complement condition storage unit that stores a correspondence between complement conditions for complementing the IDs and the read attributes; and a complement unit that compares the IDs acquired by the expected ID acquisition unit with the IDs received by the reader for each of the read attributes where their correspondence is stored in a read attribute storage unit and complements the IDs acquired by the reader with the IDs acquired by the expected ID acquisition unit.

Abstract: A failure of execution of an R/W control command with respect to plural RF tags that are attached to a moving thing occurs. There are disclosed a method and apparatus for controlling an R/W (reader/writer) that performs a read/write operation on RF tags attached to a moving body. In this case, the RF tags that are attached to the moving body are detected using the R/W. A schedule that determines execution timing of a control command of the R/W that performs a data read/write operation on the RF tags in accordance with the detected RF tags is created. The R/W control command is executed with respect to the RF tags using the R/W in accordance with timing that is determined in the created schedule.

Abstract: A history concerning circumstances surrounding each item during distribution is obtained from a reusable measuring apparatus attached to the item or measuring apparatuses placed in locations such as rooms. Information about items of products in a distribution channel are managed by associating position information indicating the locations at both ends of a place where circumstance information is measured with measuring apparatuses with the information indicating the measuring apparatuses. When items are moved during distribution, information contained in a tag attached to the items is read at the locations at both ends of the place and is managed. To obtain information about circumstances surrounding an item at a particular place in the distribution channel, values measured with the measuring apparatuses during a relevant period are obtained on the basis of the position information indicating the locations at both ends of the particular place and on the read dates and times.

Abstract: In a sharing forecast system for forming a forecast by sharing two companies, upon accidentally matching forecast values formed based on different factors by transaction companies, a difference on estimation is found and it can easily be specified, and the forecast values can easily be corrected. Two companies share both a forecast value and basis information obtained by patterning a factor for calculating the forecast value. Upon satisfying criteria that the basis information of the two companies does not match each other, it is determined that there is a different estimation of the forecast value. In the case of the determination, the basis information is presented to the two companies, a recommended value for correcting the forecast value is calculated based on the basis information, and the calculated value is presented to the two companies.