Nippon Telegraph and Telephone Corporation

Keishiro Watanabe

Yasuhiro Ikeda

Keisuke Ishibashi

Ryoichi Kawahara

Yusuke Nakano

Yoichi Matsuo

Kengo Tajiri

A feature value generation device includes a generator configured to generate vectors whose elements are feature values of data items collected at a plurality of timings from a target of anomaly detection, so as to normalize or standardize the vectors based on a set of predetermined vectors; a learning unit configured to learn the predetermined vectors so as to output a learning result; and a detector configured to detect, for each of the vectors normalized or standardized by the generator, an anomaly based on said each of the vectors and the learning result. The set of predetermined vectors is a set of vectors with which no anomaly is detected by the detector, and the set of vectors is updated in accordance with no anomaly being detected by the detector.

Anomaly detection method using an autoencoder learning from data items collected by measuring devices

A model construction apparatus according to an embodiment includes a first collection unit that collects pieces of first observed data related to a communication network system that is a target for estimation of a location or a cause of an abnormality; a second collection unit that collects pieces of second observed data related to a plurality of services provided by the communication network system; and a model construction unit that constructs a causal model for estimating the location or the cause of the abnormality and an abnormal service among the plurality of services, using the pieces of first observed data and the pieces of second observed data.

Model construction apparatus, estimation apparatus, model construction method, estimation method and program

An anomaly factor estimation apparatus includes a memory and a processor configured to execute training an anomaly detection model for performing anomaly detection based on an error of output data with respect to input data represented by a multidimensional numerical vector; inputting test data into the anomaly detection model, to determine whether the test data corresponds to an anomaly based on output data output from the anomaly detection model and the test data; and calculating a degree of contribution to the anomaly for each dimension of the test data based on a likelihood of said each dimension, in response to determining that the test data corresponds to the anomaly.

Anomaly factor estimation apparatus, anomaly factor estimation method and program

A feature value generation device includes a generator configured to digitize non-numerical text data items collected at a plurality of timings from a target of anomaly detection, to generate vectors whose elements are feature values corresponding to the digitized data items; a learning unit configured to learn the vectors during a learning period so as to output a learning result; and a detector configured to detect, during a test period, for each of the vectors generated by the generator, an anomaly based on said each of the vectors and the learning result.

Feature value generation device, feature value generation method, and program

An anomaly detection apparatus having a function of an autoencoder that includes an input layer, hidden layers, and an output layer, and that learns parameters such that data of the input layer is reproduced in the output layer, the anomaly detection apparatus including: input means that input normal data of a plurality of types; learning means that learn parameters such that normal data of the input layer is reproduced in the output layer by learning a feature across data types using data of a dimension which is smaller than a dimension of the normal data; and anomaly degree calculation means that input test data to the autoencoder using the parameters learned by the learning means, and calculate anomaly degree of the test data based on output data of the autoencoder and the test data.

Anomaly detection apparatus, anomaly detection method, and program

A device for estimating a cause of an anomaly comprises: a detection unit to detect an anomaly in a detection target based on a learner trained on first numerical vectors obtained from a detection target when the detection target is under a normal condition and second numerical vectors to be obtained from the detection target at multiple time; and a first computing unit to compute, for each metric of a second numerical vector from which an anomaly has been detected, as information for estimating a metric of cause of the anomaly, a value obtained by subtracting, from a value of the metric, an average of the metric in the first numerical vectors, and dividing a result of the subtracting by standard deviation of the metric in the first numerical vectors. This device supports estimation of the cause of an anomaly detected in a target object for detecting an anomaly.

Anomaly factor estimation device, anomaly factor estimation method, and storage medium

An anomaly location identification device includes a determination unit configured to determine presence or absence of an anomaly by inputting part or all of information items output from a plurality of devices into an anomaly detection algorithm; a calculation unit configured to calculate, in response to a determination made by the determination unit that an anomaly is present, with respect to one of the information items, an index indicating a degree of contribution to the anomaly; and an identification unit configured to perform calculation by an analysis algorithm using a causal model receiving the index as input, to identify an anomalous device, to improve the precision and calculation speed related to identification of an anomaly location.

Anomaly location identification device, anomaly location identification method, and program

An apparatus for estimating anomaly information includes an input unit configured to input anomaly data detected as anomaly by an anomaly detecting algorithm that outputs an anomaly degree of input data for vectors, using learning of the vectors in a normal state, and an estimate unit configured to search for one or more vectors that decrease the degree of anomaly when added to the anomaly data, taking into account a likelihood, for each dimension, of a given dimension being a cause of the anomaly, and estimate the cause of the anomaly based on the searched vectors whereby it is possible to estimate detailed information on a detected anomaly.

Growing community of inventors

Musashino, Japan

Keishiro Watanabe