Abstract: A learning apparatus, including: a learning unit configured to learn a parameter of a score function for two-class classification so as to maximize a Partial Area Under the Curve (pAUC), based on training data of a positive instance and a negative instance and a setting value for setting a range of the pAUC; a score calculation unit configured to calculate a score for validation data of the positive instance and the negative instance, using the score function; and an adjustment unit configured to adjust the setting value based on the score.

Abstract: A learning system (100) includes an information transfer apparatus (10) and a learning processing apparatus (20). The information transfer apparatus (10) includes: an analysis unit (11) that obtains data serving as a learning target, compares the obtained data with a reference model, and assigns, to the data, an index indicating a degree of worthiness of the data as the learning target; and a transmission processing unit (12) that transmits the data to the learning processing apparatus (20) based on a rule that has been set using the index. The learning processing apparatus (20) includes a learning processing unit (21) that updates the model or generates a new model based on the data transmitted from the information transfer apparatus (10).

Abstract: The data processing device includes a display unit, a touch panel unit that detects a touch operation and outputs detection information, a flick detection unit, a label determination unit, and a teacher data generation unit. The flick detection unit detects a flick direction from the detection information of the touch panel unit. The label determination unit determines a label representing a category to which content belongs, based on the flick direction. The teacher data generation unit displays the content on the display unit, and generates teacher data including the displayed content and the label determined by the label determination unit.

Abstract: A moving image acquiring part acquires a moving image. A still image accumulating part stores still images. An image processing part calculates gains obtained by previously storing based on the costs of extraction of still images from a moving image, and extracts some still images with higher gains from among the still images composing the moving image and stores into the still image accumulating part. A request processing part retrieves a still image requested by a request source from the still image accumulating part and transmits to the request source and, when the still image requested by the request source is not stored in the still image accumulating part, extracts the still image requested by the request source from the moving image acquired by the moving image acquiring part and transmits to the request source.

Abstract: A learning system (100) includes an information transfer apparatus (10) and a learning processing apparatus (20). The information transfer apparatus (10) includes: an analysis unit (11) that obtains data serving as a learning target, compares the obtained data with a reference model, and assigns, to the data, an index indicating a degree of worthiness of the data as the learning target; and a transmission processing unit (12) that transmits the data to the learning processing apparatus (20) based on a rule that has been set using the index. The learning processing apparatus (20) includes a learning processing unit (21) that updates the model or generates a new model based on the data transmitted from the information transfer apparatus (10).

Abstract: A load information acquiring unit (230) sets load information based on the history that is acquired by a process history acquiring unit (220). A test period determining unit (240) sets a test period based on the load information. The test period is a period during which a test policy can be used. The test policy is a policy for a test out of control policies used by an information processing system (100). A system control unit (260) measures performance capability of the information processing system (100) under the test policy as a test result by testing the test policy under a production environment of the information processing system (100) by using the test policy instead of a practical policy that is actually used in the test period. A policy changing unit (270) changes the practical policy based on the test policy in a range in which the test result satisfies a reference.

Abstract: The data processing device includes a display unit, a touch panel unit that detects a touch operation and outputs detection information, a flick detection unit, a label determination unit, and a teacher data generation unit. The flick detection unit detects a flick direction from the detection information of the touch panel unit. The label determination unit determines a label representing a category to which content belongs, based on the flick direction. The teacher data generation unit displays the content on the display unit, and generates teacher data including the displayed content and the label determined by the label determination unit.

Abstract: A data processing device includes a storage part, a machine learning part, a classifying part, and a user interface part. The storage part stores a plurality of teacher data each including content and a label representing a category to which the content belongs. The machine learning part generates a classification model by using the plurality of teacher data. The classifying part determines the category that the content of each of the plurality of teacher data belongs by using the classification model. The user interface part causes a display part to display the content and label of the teacher data and the category that the content belongs determined by the classifying part.

Abstract: A moving image acquiring part acquires a moving image. A still image accumulating part stores still images. An image processing part calculates gains obtained by previously storing based on the costs of extraction of still images from a moving image, and extracts some still images with higher gains from among the still images composing the moving image and stores into the still image accumulating part. A request processing part retrieves a still image requested by a request source from the still image accumulating part and transmits to the request source and, when the still image requested by the request source is not stored in the still image accumulating part, extracts the still image requested by the request source from the moving image acquired by the moving image acquiring part and transmits to the request source.

Abstract: A service provision quality control device according to the present invention includes a simulation processing unit which predicts a group of state predicting vector values on the basis of vector values of a current state and a past state of measurement statistic, a judging unit which judges whether a control operation is necessary or not on the basis of the state predicting vector value and a target state vector value whose control target is agreed service level, and an adjusting unit which adjusts evaluation condition of an execution environment repeatedly until control deviation becomes not larger than a predetermined value under the condition that iteration number is not larger than a predetermined value which is corresponding to an upper limit value.

Abstract: Disclosed are a workflow monitoring control system, method, and program, wherein, when workflows are executed by passing through processing sections, each provided with business application software, in order, the service quality of the workflows can be ensured in as many workflows as possible with limited computer resources. A workflow monitoring and control system connected to a plurality of processing sections each of which executes a unit process assigned respectively, a unit process being one of parts constituting business data processing, by using business application software and computer resources, comprises a workflow defining means, a service quality lower limit setting means, a service quality calculation means, a quality insufficiency judging means, a computer resource reallocation means.

Abstract: A rejection determination is made taking into consideration of an agreed service level for a combine workflow executed on a combine workflow system wherein a plurality of business application are collaborated with one another for business collaborations. A state is expressed which will appear when the combined workflow is hypothetically rejected, based on the progress thereof. A processing operation of the combined workflow is predicted based on the expressed state, taking into consideration the influence exerted on the plurality business application systems and the plurality of workflow systems in respect of response performance. A processing operation, which is the result of the prediction, and historical information of event information from the event information recording means are retrieved, and an evaluation value is calculated based on the result of the statistical processing of the historical information.

Abstract: A load information acquiring unit (230) sets load information based on the history that is acquired by a process history acquiring unit (220). A test period determining unit (240) sets a test period based on the load information. The test period is a period during which a test policy can be used. The test policy is a policy for a test out of control policies used by an information processing system (100). A system control unit (260) measures performance capability of the information processing system (100) under the test policy as a test result by testing the test policy under a production environment of the information processing system (100) by using the test policy instead of a practical policy that is actually used in the test period. A policy changing unit (270) changes the practical policy based on the test policy in a range in which the test result satisfies a reference.

Abstract: Disclosed are a workflow monitoring control system, method, and program, wherein, when workflows are executed by passing through processing sections, each provided with business application software, in order, the service quality of the workflows can be ensured in as many workflows as possible with limited computer resources. A workflow monitoring and control system connected to a plurality of processing sections each of which executes a unit process assigned respectively, a unit process being one of parts constituting business data processing, by using business application software and computer resources, comprises a workflow defining means, a service quality lower limit setting means, a service quality calculation means, a quality insufficiency judging means, a computer resource reallocation means.

Abstract: An object of the present invention is to provide a feed forward type control method, a service provision quality control device, a system, a program and a recording medium which resolve problems of “lack of an evaluation function of a proper control plan”, “lack of a control-oriented evaluation function and a control-oriented execution function” and “lack of a correcting function and a verifying function of a control plan” The present invention includes a simulation processing unit 504, which predicts a group of state predicting vector values on the basis of vector values of a current state and a past state of measurement statistic after compensating at a future time, and a judging unit 506 which compares sequentially the state predicting vector value, which is predicted, and a target state vector value whose control target is agreed service level, and then calculates control deviation and judges whether a control operation is necessary or not.

Abstract: A rejection determination is made taking into consideration of an agreed service level for a combine workflow executed on a combine workflow system wherein a plurality of business application are collaborated with one another for business collaborations. A state is expressed which will appear when the combined workflow is hypothetically rejected, based on the progress thereof. A processing operation of the combined workflow is predicted based on the expressed state, taking into consideration the influence exerted on the plurality business application systems and the plurality of workflow systems in respect of response performance. A processing operation, which is the result of the prediction, and historical information of event information from the event information recording means are retrieved, and an evaluation value is calculated based on the result of the statistical processing of the historical information.

Abstract: Disclosed is a distributed systems monitoring system comprising information monitoring units for acquiring monitoring information from monitoring targets, and a monitoring information collecting and integrating unit for integrating the monitoring information acquired from the information monitoring units and for presenting the integrated monitoring information to a user. Upon receipt of monitoring information from the monitoring target, the information monitoring unit determines whether or not the monitoring information has a high degree of urgency. If the information has a high degree of urgency, then the monitoring information is notified to the monitoring information collecting and integrating unit. Otherwise, the monitoring information is stored in a monitoring information holding section, and is transmitted each time a monitoring information request is received from the monitoring information collecting and integrating unit.