Abstract:
A non-transitory computer-readable recording medium stores an information processing program for causing a computer to execute processing including: generating, from first data in which values of a plurality of attributes included in each sample are accumulated for each sample, second data obtained by binarizing, for each sample, the values of the plurality of attributes included in each sample based on an attribute condition set in advance; enumerating, by using the second data, sets of attribute conditions in which all sample sets indicate true values; computing, for each set of attribute conditions, a correlation between the plurality of attributes in the first data in a sample set associated with each set of attribute conditions; and selecting a set of attribute conditions determined to have a correlation as a condition to be causally searched.
Abstract:
A non-transitory computer-readable recording medium stores therein a program for causing a computer to execute a process. The process includes obtaining, for each predetermined time period, from packets transmitted in a system, a packet set with a combination of a transmission source and a transmission destination different from a predetermined combination of a transmission source and a transmission destination; extracting, for the each predetermined time period, from the packets transmitted in the system, a related packet related to the obtained packet; generating, based on the extracted related packet, information indicating a degree of propagation; and outputting the generated information.
Abstract:
An information presentation device generates a plurality of training models by executing machine learning that uses training data. The information presentation device generates hierarchical information that represents, in a hierarchical structure, a relationship between hypotheses shared as common and hypotheses regarded as differences for a plurality of hypotheses extracted from each of the plurality of training models and each designated by a combination of one or more explanatory variables.
Abstract:
A data generation method includes: with regard to a target in which a plurality of sets of reference source data and reference target data are connectable by using edges, extracting information that corresponds to a complete bipartite graph from the connected target; and when there are a plurality of sets of reference source data and a plurality of sets of reference target data that are the extracted information and that constitute the complete bipartite graph, generating a virtual node between the reference source data and the reference target data.
Abstract:
A non-transitory computer-readable recording medium storing an information processing program for causing a computer to execute a process includes receiving a hypothesis to be interpreted, by using a first storage that includes, for each piece of knowledge that indicates a plurality of resources and a relationship between the resources, basis information that serves as a basis of the knowledge and a rule identifier connected with a rule used to interpret the hypothesis, acquiring the basis information and the rule identifier that correspond to the hypothesis to be interpreted, and by using a second storage that includes, for each rule identifier, a probability that the rule and the hypothesis coincide with existing knowledge, acquiring the probability of coinciding with the existing knowledge that corresponds to the acquired rule identifier.
Abstract:
A non-transitory computer-readable recording medium storing an information processing program for causing a computer to execute processing including: extracting, for a plurality of pieces of combination data each of which is a combination of a plurality of feature amounts that includes an invariable feature amount and a variable feature amount that represent features of a target, combination data to be processed based on the plurality of pieces of combination data according to relation between the respective pieces of combination data; executing causal search processing for the variable feature amount according to the invariable feature amount by using the combination data to be processed; and selecting, based on a result of the causal search processing, a specific variable feature amount that corresponds to the specified invariable feature amount, to present the selected specific variable feature.
Abstract:
A computer-readable recording medium contains a program for causing a computer to execute a process. The process includes executing multiple change point detection processes that detect respective change points of first time-series data with multiple granularities that are different in the width of a unit time. A first detection pattern that indicates the order of detection of the change points is stored in a storage part. Change points of second. time-series data subsequent to the first time-series data are detected with the different granularities. An output is generated that differs depending on whether a second detection pattern matches the stored first detection pattern. The second detection pattern indicates the order of detection of the change points of the second time-series data.
Abstract:
A load-distribution system includes: a first computer to: determine a common portion of conditions among different models, and store one or more models in each of third computers that determines a state of an event, by applying a model stored in a built-in memory; and a second computer to: specify, from the third computers, a first third computer that stores a first model of the models including the identical-common portion, which corresponds to an attribute included in event information which has been input, specify, from the third computers, a second third computer that store a second model including a common portion identical to a common portion included in the first model, decide which one of the first third computer and the second third computer is caused to perform determining the state, and cause the decided one of the third computers to perform the processing of determining the state.
Abstract:
A computer obtains a load value relating to a detection process from each of a plurality of server devices that execute, in units of pieces of identification information, the detection process of a pattern of data distributed by a transfer device that distributes input data in accordance with identification information. When a load value obtained from a first server device among the plurality of server devices exceeds a specified allowable range, the computer executes a process for moving, in units of combinations, a combination of identification information and one pattern corresponding to the identification information from the first server device to a second server device among the plurality of server devices depending on whether load values of the first server device and the second server device respectively fall within the allowable range.
Abstract:
A control method for controlling a distributed processing system that performs distributed processing using a plurality of devices is executed by a processor. The method including acquiring load information from each of the plurality of devices, identifying a source device and a destination device based on the acquired load information, the source device being a device of a migration source of an allocated processing operation and the destination device being a device of a migration destination of the allocated processing operation. The method further including selecting as a processing operation of a migration target from among a plurality of processing operations allocated to the source device, a processing operation with which a rate that data used by the processing operation at the source device is to be used at the destination device is relatively high or higher than a predetermined rate.