公开(公告)号：US20200250211A1

公开(公告)日：2020-08-06

申请号：US16560714

申请日：2019-09-04

Applicant: Hitachi, Ltd.

Inventor： Kazuyuki OOTA ,  Toshiyuki Ukai ,  Kazuaki Tokunaga

IPC: G06F16/33 ,  G06K9/62 ,  G06F16/335 ,  G06F16/951 ,  G06F16/909

Abstract: An analysis system is configured to acquire data of a first numeric feature combination by referring to the parent population data. The data of the first numeric feature combination includes a score of a target indicator for each of category combinations. Each category combination of the category combinations is composed of categories of the numeric features of the first numeric feature combination. The analysis system is configured to determine a score at coordinates corresponding to each of the category combinations in a space having each of the numeric features of the first numeric feature combination as an axis, calculate a gradient feature vector representing a gradient for the score in the space, and determine, based on the gradient feature vector, whether to include the first numeric feature combination in numeric feature combinations to be extracted from the parent population data.

公开(公告)号：US20220334912A1

公开(公告)日：2022-10-20

申请号：US17680836

申请日：2022-02-25

Applicant: Hitachi, Ltd.

Inventor： Kana OKI ,  Shuntaro HITOMI ,  Kazuyuki OOTA

IPC: G06F11/07

Abstract: A system displays a fault tree of a generated event on the basis of input information including diagnosis result information representing results of diagnosis of the cause of the generated event. The input information includes information representing causal relationships between a plurality of elements, including the generated event, failure causes that may be a cause of the event, and check items associated with the failure causes. The diagnosis result information includes an occurrence probability of each failure cause. The system determines, as highlighting target edges, all edges belonging to a path from a node corresponding to the generated event to a node corresponding to a failure cause having an occurrence probability that satisfies predetermined probability conditions, and all or some edges coupling the node corresponding to the failure cause having an occurrence probability that satisfies the predetermined probability conditions to nodes corresponding to check items associated with the failure cause.

公开(公告)号：US20220270115A1

公开(公告)日：2022-08-25

申请号：US17439493

申请日：2020-12-16

Applicant: HITACHI, LTD.

Inventor： Kazuki YAMANE ,  Kazuaki TOKUNAGA ,  Kazuyuki OOTA ,  Hiroyuki NAMBA

IPC: G06Q30/02 ,  G06N5/04

Abstract: A learner generation unit generates, as a learner group, a plurality of learners that learned a correspondence of an attribute and an outcome in each of a plurality of learning data sets extracted from a data group associated with an attribute and an outcome of each of the targets. A target selection unit applies the learner group selected for inference to an inference data set and predicts, for each of the learners, an outcome corresponding to an attribute in the inference data set, calculates, for each attribute in the inference data set, at least one of an average of the outcomes predicted for each of the learners or an index value expressing an uncertainty of the outcomes, and selects, from the inference data set, the target to which the policy is to be executed based on at least one of the calculated average or the calculated index value.