Abstract: In an embodiment of the present invention, a memory stores case performances on anomaly handling of a plurality of apparatuses. A hardware processor performs: identification processing of identifying an anomaly cause of an abnormal apparatus in the plurality of apparatuses; selection processing of selecting an estimation model for estimating a handling method suitable for the anomaly cause from a plurality of estimation models based on the case performance of the abnormal apparatus; estimation processing of estimating a handling method suitable for the anomaly cause among a plurality of handling methods based on the selected estimation model; and output processing of outputting information indicating the estimated handling method.

Abstract: There is provided a network management device (1) including a capacity management unit (10) for managing the capacity in a network to be managed and a storage unit (20) for storing management information. The storage unit stores specification information of entities included in the network, and entity information including information indicative of relationships between the entities. The capacity management unit 10 includes a capacity request acquisition section (11) which receives a generation request of a first entity; reads the specification information about the first entity from the storage unit, and determines whether or not the first entity needs to consume a resource; when it is determined that the first entity needs to consume a resource, identifies a second entity capable of providing capacity consumed by the first entity, based on the entity information stored in the storage unit; and outputs information about the identification result.

Abstract: In an embodiment of the present disclosure, a prior probability is used by an approach of Bayesian statistics, for all nodes stored in fault handling history data or for a target node for which a fault cause has been identified and all nodes of the same type as the target node, restoration probabilities of handling methods for an identical fault cause are calculated, priorities are set for the handling methods based on the calculated restoration probabilities, and a handling method to be presented is determined in accordance with the priorities.

Abstract: A network management device according to an embodiment includes: a path selection processing unit configured to perform path selection processing of selecting a path of a physical layer between a start point and an end point of a network based on a first entity stored in a first storage device configured to store the first entity, the first entity representing an entity of an information object of the network; and an entity generation processing unit configured to perform entity generation processing of generating a second entity of a logical layer corresponding to the path of the physical layer selected by the path selection processing unit based on a specification of the information object stored in a second storage device configured to store the specification.