Abstract: A system is configured to acquire, from history data, entity data similar to target entity data which is data including a feature value of each of plurality of features related to a target entity. The history data includes entity data for each of a plurality of entities at each past time point. For each entity, entity data at a past time point includes a feature value at the time point for each feature of the entity. The system is configured to create, for each controllable feature among the plurality of features related to the target entity, based on statistics of a plurality of feature values in related case data which is data including entity data similar to the target entity data, a proposal of a feature value change for reducing a risk predicted by inputting the target entity data to a prediction model. A user interface which displays the proposal.

Abstract: To improve resource utilization efficiency of query compliance check, which is check as to whether a query complies with a restriction imposed on data. The query compliance check is roughly divided into data flow policy check as to whether a data flow policy that defines a restriction on data transfer within a county or between countries is complied with, and organization rule check as to whether an organization rule that defines a restriction on sharing outside an organization is complied with, which are hierarchically configured. By analyzing a received query, a system identifies one or more data items as target input/output (I/O) data according to the query, and executes the data flow policy check on the identified one or more data items. When a result of the data flow policy check is false, the system returns a result that the query is compliance violation without executing the organization rule check.

Abstract: A data management system includes a processor. An estimated ETL level mapping processing unit is operated on the processor to estimate existence of unregistered ETL that is ETL not registered in a repository, to calculate a degree of similarity based on matching between an existing data model and retained data, and to extract a column to be a candidate based on the degree of similarity. The existence of the unregistered ETL is estimated by estimating the presence or absence of connectedness in the ETLs on the basis of correspondence between input data and output data in ETLs by using an execution ETL log relevant to an execution history of the ETL.

Abstract: Provided are a data management apparatus, a data management system, and a data management method capable of creating an alternative for a useful query when a query for operating a database violates a data handling regulation of the database. When data scheduled to be generated based on the database by the query violates a rule that is the data handling regulation of the database, a data processing server generates an alternative query candidate to replace the query. The data processing server determines whether the alternative query candidate violates the rule by determining whether data scheduled to be generated based on the database by the alternative query candidate complies with the rule. When the alternative query candidate does not violate the rule, the data processing server proposes the alternative query candidate as an alternative query.

Abstract: An information management apparatus is capable of reducing an effort for creating a rule for moving data stored in an OLTP database to an OLAP database, for example. A data movement optimization apparatus includes a table status update unit that acquires a table status in which data is stored for each of an OLTP database and an OLAP database selected from among a plurality of databases, a policy network learning unit that performs learning on the number of federated queries that are processing in which it is necessary to query both the OLTP database and the OLAP database for the table status, and a cost incurred when data is moved from the OLTP database to the OLAP database, and a data movement unit that performs control for moving data from the OLTP database to the OLAP database on the basis of a result of the learning and the table status.

Abstract: Provided is a search support device to perform a search related to a parameter representing an influence degree of a feature at high speed and with high accuracy. The search support device calculates at least one or more pieces of SHAP data indicating an influence degree of each feature in a trained model on output data output from the trained model; a process of generating compressed SHAP data, which is data obtained by compressing the SHAP data, for each of the SHAP data and storing the compressed SHAP data; verification target SHAP data which is SHAP data for output data output from the trained model by inputting input data to the trained model; a similarity between each of the calculated compressed SHAP data and the calculated verification target SHAP data, and specifies the compressed SHAP data in which the similarity with the verification target SHAP data satisfies a predetermined condition.

Abstract: To efficiently collect training data for training an AI model, an input of a training profile is received that includes item values corresponding to a plurality of data items, including analysis target data to be analyzed by the AI model and information on the model type. A first query is acquired to extract training data from a training database. The number of pieces of first training data to be extracted from the training database is calculated. The required number of pieces of the training data to train the AI model is calculated using the information on the model type. Whether the number of pieces of the first training data is equal to or greater than the required number is determined. When the determined number of pieces of the first training data is less than the required number, a supplementary query for extracting the training data is generated.

Abstract: Provided is an information processing system by which more appropriate lineage management is possible. A lineage unit management system 3 determines a lineage unit based on a processing content of data processing for generating output data including one or more elements from input data including one or more elements. A lineage management system 4 generates lineage information indicating correspondence relation between the elements of the input data and the elements of the output data in accordance with the lineage unit. Therefore, the lineage information is generated in accordance with the lineage unit corresponding to the content of the data processing, so that more appropriate lineage management is possible.

Abstract: A digital twin management system manages a virtual model that represents an actual physical system in a virtual space on a real-time basis. To generate an integrated virtual model by adding a second virtual model to a first virtual model, a processor of the digital twin system extracts multiple parts that can be used in common in the first virtual model and the second virtual model, generates multiple integrated virtual models that are candidates of an integrated virtual model by changing the extracted parts that can be used in common, calculates an evaluation of each of the generated integrated virtual models, and outputs configuration information regarding each of the integrated virtual model candidates and an evaluation of the integrated virtual model candidate in association with each other.

Abstract: A distributed transaction in which appropriate patterns are combined without modifying implementation of a management system even when a service characteristic of a participating system changes. A management system receives input of a distributed transaction flow defining respective call sequential numbers of participating systems and service characteristic information representing respective service characteristics of the participating systems. The management system specifies an applied pattern for each of the participating systems based on pattern information including information for each pattern that represents a constraint condition of a service characteristic of a participating system as a call target. The applied pattern is a pattern satisfying the constraint condition corresponding to the service characteristic of the participating system.

Abstract: A distributed transaction in which appropriate patterns are combined without modifying implementation of a management system even when a service characteristic of a participating system changes. A management system receives input of a distributed transaction flow defining respective call sequential numbers of participating systems and service characteristic information representing respective service characteristics of the participating systems. The management system specifies an applied pattern for each of the participating systems based on pattern information including information for each pattern that represents a constraint condition of a service characteristic of a participating system as a call target. The applied pattern is a pattern satisfying the constraint condition corresponding to the service characteristic of the participating system.

Abstract: A data management system includes a processor. An estimated ETL level mapping processing unit is operated on the processor to estimate existence of unregistered ETL that is ETL not registered in a repository, to calculate a degree of similarity based on matching between an existing data model and retained data, and to extract a column to be a candidate based on the degree of similarity. The existence of the unregistered ETL is estimated by estimating the presence or absence of connectedness in the ETLs on the basis of correspondence between input data and output data in ETLs by using an execution ETL log relevant to an execution history of the ETL.

Abstract: A digital twin management system manages a virtual model that represents an actual physical system in a virtual space on a real-time basis. To generate an integrated virtual model by adding a second virtual model to a first virtual model, a processor of the digital twin system extracts multiple parts that can be used in common in the first virtual model and the second virtual model, generates multiple integrated virtual models that are candidates of an integrated virtual model by changing the extracted parts that can be used in common, calculates an evaluation of each of the generated integrated virtual models, and outputs configuration information regarding each of the integrated virtual model candidates and an evaluation of the integrated virtual model candidate in association with each other.

Abstract: Provided is a data processing assistant system, a data processing assistant method, and a data processing assistant program. The data processing assistant system includes: a processing record accumulation unit that accumulates processing records in which one or more pieces of data, data processing performed using the data, and a processing result of the data processing are associated with each other; a correspondence relation data creation unit that creates, based on the processing records, correspondence relation data indicative of a correspondence relation among a data type indicating a type of the data, a question to be solved by the data processing, and the processing result; and a processing information presentation unit that presents, upon receiving designation of the data type and the question, information related to appropriate data processing based on the correspondence relation data.

Abstract: An analysis management server stores a factory A catalog group including a plurality of catalogs in factory A, an application destination catalog including a plurality of catalogs in factory B, and an application source analysis data correspondence table associating columns between a target table of factory A and a defect factor analysis table. A CPU is configured to: identify an unconnected catalog for which a catalog of factory B having an identical correspondence does not exist among the plurality of catalogs of factory A included in the application source analysis data correspondence table; identify an unconnected correspondence, which is a correspondence of the unconnected catalog in the application source analysis data correspondence table, sensor data of factory B, and an identical path correspondence which is a correspondence of a catalog on a path including the unconnected catalog; and display information of the unconnected correspondence and the identical path correspondence.

Abstract: The disclosure is to present quantitative information for evaluating model transparency. A computer configured to support selection of a model generated by machine learning includes a transparency score calculation unit configured to execute analysis processing for analyzing traceability of a generation process of a target model, and calculate a transparency score indicating a degree of the traceability of the generation process of the target model based on a result of the analysis processing, and a report generation unit configured to generate a report for presenting the transparency score.

Abstract: A CPU of a data integration server detects first rare words whose number existing as words relating to configurations of tables of a factory data model is equal to or smaller than a predetermined number, detects second rare words whose number existing as words relating to configurations of tables in a common data model is equal to or smaller than a predetermined number, determines whether or not determination conditions for determining that a second column included in the common data model is a synonymous column candidate of a first column of the factory data model are satisfied, and, in the case where the determination conditions are satisfied, selects the second column as the synonymous column candidate of the first column. The determination conditions include a condition that one of the first rare words around the first column matches one of the second rare words around the second column.

Abstract: The present invention realizes reuse of an analysis application having different contexts such as data units and data acquisition times of on-site data in short man-hour without requiring specialized knowledge on an analyzed object. A data management system providing IoT data to a service system includes a storage device storing an asset catalog containing information of a manufacture line and devices constructing a manufacture line, an application catalog containing calculation information of a KPI as required by the service system, and a data catalog containing information for accessing the IoT data. A control unit retrieves an asset to be analyzed from the catalog, and when the KPI does not exist in the asset catalog, retrieves the KPI calculation information from the application catalog, and calculates a KPI of the asset to be analyzed as the KPI as the requirement specification of the service system by using the retrieved calculation information.

Abstract: An analysis management server stores a factory A catalog group including a plurality of catalogs in factory A, an application destination catalog including a plurality of catalogs in factory B, and an application source analysis data correspondence table associating columns between a target table of factory A and a defect factor analysis table. A CPU is configured to: identify an unconnected catalog for which a catalog of factory B having an identical correspondence does not exist among the plurality of catalogs of factory A included in the application source analysis data correspondence table; identify an unconnected correspondence, which is a correspondence of the unconnected catalog in the application source analysis data correspondence table, sensor data of factory B, and an identical path correspondence which is a correspondence of a catalog on a path including the unconnected catalog; and display information of the unconnected correspondence and the identical path correspondence.

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.