Abstract: A diagnosis device (10) includes an acquirer (101) and a diagnoser (140). The acquirer (101) acquires a series of input values as an input signal to be diagnosed as to presence or absence of abnormality. The diagnoser (140) diagnoses the presence or absence of the abnormality from (i) a first index value indicating a distance between an input vector and a predetermined first reference vector, the input vector having components that are the input values of the series acquired by the acquirer (101), and (ii) a second index value indicating an angle between the input vector and a predetermined second reference vector.

Abstract: A diagnostic device (10) includes an acquirer (101) and a diagnoser (140). The acquirer (101) acquires a plurality of input signals including a target signal to be diagnosed for abnormality. The diagnoser (140) diagnoses, using a first index value relating to the target signal and a second index value relating to the plurality of input signals based on a correlation between the plurality of input signals, whether an abnormality occurs. The first index value indicates a degree of similarity of a waveform of the target signal to a predetermined reference waveform. The second index value is a value that is based on comparison between the target signal and a predetermined pattern and is calculated from values of the plurality of input signals.

Abstract: Provided is a data amount sufficiency determination device capable of determining the sufficiency of the data amount of learning data with higher accuracy. A data amount sufficiency determination device according to the present disclosure includes a time series data acquisition unit to acquire time series data, a data division unit to divide the time series data into a plurality of pieces of substring data, a data set generation unit to generate a plurality of substring data sets that are sets of substring data, a feature amount calculation unit to calculate a feature amount of the substring data, a probability distribution generation unit to generate probability distribution of the feature amount for each substring data sets, and a determination unit to determine whether or not the probability distribution has converged.

Abstract: A signal selection device (10) selects, from a plurality of candidate signals, a training signal for learning a model (20) usable for data analysis. The signal selection device (10) includes a first acquirer (11) that acquires the plurality of candidate signals and training labels associated with the plurality of candidate signals and being status values corresponding to results of analysis performed using the model, a feature calculator (13) that calculates one or more features for each of the plurality of candidate signals, and a selector (16) that selects the training signal from the plurality of candidate signals based on a degree of relevance between the one or more features and the training labels.

Abstract: A signal selection device (10) selects, from a plurality of candidate signals, a training signal for learning a model (20) usable for data analysis. The signal selection device (10) includes a first acquirer (11) that acquires the plurality of candidate signals and training labels associated with the plurality of candidate signals and being status values corresponding to results of analysis performed using the model, a feature calculator (13) that calculates one or more features for each of the plurality of candidate signals, and a selector (16) that selects the training signal from the plurality of candidate signals based on a degree of relevance between the one or more features and the training labels.

Abstract: A diagnostic device (10) includes an acquirer (101) and a diagnoser (140). The acquirer (101) acquires a plurality of input signals including a target signal to be diagnosed for abnormality. The diagnoser (140) diagnoses, using a first index value relating to the target signal and a second index value relating to the plurality of input signals based on a correlation between the plurality of input signals, whether an abnormality occurs. The first index value indicates a degree of similarity of a waveform of the target signal to a predetermined reference waveform. The second index value is a value that is based on comparison between the target signal and a predetermined pattern and is calculated from values of the plurality of input signals.

Abstract: The time-series data diagnosis device includes a storage, a difference-degree calculator, a diagnosis-result-information generator, an evaluation information acquirer, and an updater. The difference-degree calculator calculates a difference degree between diagnosis target time-series data and a learned-sample subsequence data item stored in the storage. The diagnosis-result-information generator generates, based on the difference degree calculated by the difference-degree calculator, diagnosis result information about the diagnosis target time-series data. The evaluation information acquirer acquires evaluation information indicating evaluation as to whether a diagnosis result indicated by the diagnosis result information is valid.

Abstract: A diagnosis device (10) includes an acquirer (101) and a diagnoser (140). The acquirer (101) acquires a series of input values as an input signal to be diagnosed as to presence or absence of abnormality. The diagnoser (140) diagnoses the presence or absence of the abnormality from (i) a first index value indicating a distance between an input vector and a predetermined first reference vector, the input vector having components that are the input values of the series acquired by the acquirer (101), and (ii) a second index value indicating an angle between the input vector and a predetermined second reference vector.

Abstract: The time-series data diagnosis device includes a storage, a difference-degree calculator, a diagnosis-result-information generator, an evaluation information acquirer, and an updater. The difference-degree calculator calculates a difference degree between diagnosis target time-series data and a learned-sample subsequence data item stored in the storage. The diagnosis-result-information generator generates, based on the difference degree calculated by the difference-degree calculator, diagnosis result information about the diagnosis target time-series data. The evaluation information acquirer acquires evaluation information indicating evaluation as to whether a diagnosis result indicated by the diagnosis result information is valid.

Abstract: An index outputter (120) of a learning processor (100) outputs an index for selection of an analysis procedure based on attributes of an analysis target. The attributes to be inputted include features of the analysis target itself and features of the environment surrounding the analysis target. The analysis procedure selector (170) selects an analysis procedure among analysis procedures as an analysis procedure for which diagnosis target data to be outputted by the analysis target is to be analyzed. The selected analysis procedure is a procedure in which an evaluation value of a property of data analysis satisfies a preset condition in connection with the index.

Abstract: A learning device (10) includes an acquirer (11), a learner (12), and a generator (14). The acquirer (11) acquires a learning signal. The learner (12) performs, in accordance with similarities indicating degrees of similarity between waveforms, clustering of partial signals cut out from the learning signal acquired by the acquirer (11), and learns reference waveforms that each indicate a waveform of a corresponding partial signal of the clustered partial signals. The generator (14) generates, based on at least one of a distribution of the similarities or characteristics of clusters that each include a corresponding partial signal of the clustered partial signals, progress information indicating a progress status of the learning by the learner (12), and outputs the progress information.

Abstract: A learning device (10) includes an acquirer (11), a learner (12), and a generator (14). The acquirer (11) acquires a learning signal. The learner (12) performs, in accordance with similarities indicating degrees of similarity between waveforms, clustering of partial signals cut out from the learning signal acquired by the acquirer (11), and learns reference waveforms that each indicate a waveform of a corresponding partial signal of the clustered partial signals. The generator (14) generates, based on at least one of a distribution of the similarities or characteristics of clusters that each include a corresponding partial signal of the clustered partial signals, progress information indicating a progress status of the learning by the learner (12), and outputs the progress information.

Abstract: An index outputter (120) of a learning processor (100) outputs an index for selection of an analysis procedure based on attributes of an analysis target. The attributes to be inputted include features of the analysis target itself and features of the environment surrounding the analysis target. The analysis procedure selector (170) selects an analysis procedure among analysis procedures as an analysis procedure for which diagnosis target data to be outputted by the analysis target is to be analyzed. The selected analysis procedure is a procedure in which an evaluation value of a property of data analysis satisfies a preset condition in connection with the index.

Abstract: An information processing apparatus includes a data acquisition unit to acquire input data that is time-series data; a sampling error upper limit calculation unit to calculate, when similar learning subsequences selected from among a plurality of learning subsequences extracted from learning data that is time-series data are integrated to generate a sample subsequence. The information processing apparatus further includes a sampling error upper limit using data taken from the input data, the sampling error upper limit being an upper limit on dissimilarity between the learning subsequences to be integrated; and a sample subsequence generation unit to generate the sample subsequence from the learning data using the sampling error upper limit.

Abstract: An information processing apparatus includes a data acquisition unit to acquire input data that is time-series data; a sampling error upper limit calculation unit to calculate, when similar learning subsequences selected from among a plurality of learning subsequences extracted from learning data that is time-series data are integrated to generate a sample subsequence. The information processing apparatus further includes a sampling error upper limit using data taken from the input data, the sampling error upper limit being an upper limit on dissimilarity between the learning subsequences to be integrated; and a sample subsequence generation unit to generate the sample subsequence from the learning data using the sampling error upper limit.

Abstract: Provided are: a data related information generating unit for generating data related information DL including detection data and air conditioner information of air conditioners; a class classifying unit for creating a plurality of classes on the basis of the air conditioner information related to alarm data extracted by an alarm data extracting unit among the air conditioner information and for classifying the data related information DL into the plurality of classes; a priority setting unit for setting priority to each of a plurality of types of alarm data and the plurality of classes; and a priority calculating unit for assessing co-occurrence of anomaly data extracted by an anomaly data extracting unit and the alarm data, assessing co-occurrence of the alarm data and the plurality of classes, assigning priority about the alarm data and the plurality of classes to the co-occurred anomaly data, and calculating priority of anomaly data.

Abstract: A device and method allowing input/output processing of a plurality of data to be processed in parallel at each I/O device of a PLC. An operation data extraction unit of each I/O device inputs a received different station's input of one of the other I/O devices and a received different station's output of one of the other I/O devices, and also inputs an own station's input and an own station's output. The operation data extraction unit extracts operation data from each of the own station's input and output, and the different station's input and output, according to parameters (which specify a selected type, a data position, a selected station number, and an own station number) stored in a parameter unit. An operation unit executes a plurality of operation processing in parallel by using the operation data extracted by the operation data extraction unit and according to operation processing.