-
公开(公告)号：US20230267351A1
公开(公告)日：2023-08-24
申请号：US17939778
申请日：2022-09-07
Applicant: Hitachi, Ltd.
Inventor： Hiroyuki NAMBA , Masaki HAMAMOTO , Masashi EGI
CPC classification number: G06N5/045 , G06K9/6235 , G06K2009/6237
Abstract: A generation apparatus is configured to access a set of pieces of learning data each being a combination of a value of an explanatory variable and a value of an objective variable, a function family list including, of functions each indicating a physical law and an attribute of each of the functions, at least the functions, and search range limiting information for limiting a search range of the function family list, wherein the processor is configured to execute: first generation processing of generating a first prediction expression by setting a first parameter for the explanatory variable to a first function included in the function family list; first calculation processing of calculating, based on the search range limiting information, a first conviction degree relating to the first prediction expression; and first output processing of outputting the first prediction expression and the first conviction degree.
-
公开(公告)号：US20230044694A1
公开(公告)日：2023-02-09
申请号：US17690300
申请日：2022-03-09
Applicant: Hitachi, Ltd.
Inventor： Masakazu TAKAHASHI , Masashi EGI , Yuxin LIANG
IPC: G06Q10/06
Abstract: To provide an action evaluation system capable of more efficiently planning a new action based on an execution result of a test for limited action conditions. A condition change tracking unit determines, based on execution result information obtained by executing a test related to an action for an action target having a predetermined action condition, a condition change which is a change in the action condition before and after the test. A result verification unit calculates, based on the execution result information, an evaluation value obtained by evaluating an effect of the action. A reward distribution unit calculates a change contribution degree which is a degree of contribution of the condition change to the evaluation value.
-
3.发明申请公开(公告)号：US20200242489A1
公开(公告)日：2020-07-30
申请号：US16702702
申请日：2019-12-04
Applicant: HITACHI, LTD.
Inventor： Naofumi HAMA , Masashi EGI , Yasuhide MORI
Abstract: A computer system stores interpretation factor conversion information for managing an interpretation factor interpreting a basis of a prediction result for input data, the interpretation factor is determined by a value of each of a plurality of feature quantities contained in the input data including values of the plurality of feature quantities, and a first evaluation value of each of the plurality of feature quantities contained in the input data. When evaluation target data is input, the computer system calculates a prediction result, calculates a contribution value of each of the plurality feature quantities contained in the evaluation target data, specifies a corresponding interpretation factor, based on a value and a contribution value of each of the plurality of feature quantities contained in the evaluation target data, by referring to the interpretation factor conversion information, and generates and outputs display information for presenting the specified interpretation factor.
-
4.发明申请公开(公告)号：US20200233836A1
公开(公告)日：2020-07-23
申请号：US16739198
申请日：2020-01-10
Applicant: Hitachi, Ltd.
Inventor： Naoaki YOKOI , Masashi EGI , Daisuke TASHIRO , Yuxin LIANG
IPC: G06F16/11 , G06F16/16 , G06F16/182 , G06F16/17
Abstract: Provided is a computer system to present information useful for achieving purposes related to an object by utilizing AI prediction. The computer system manages a prediction model for predicting an object event based on evaluation data and feature profiling database that defines a change rule of each of the plurality of feature values included in the evaluation data, generates change policy data by changing the plurality of feature values included in the evaluation data based on the feature profiling database, calculates an evaluation value indicating effectiveness of the change policy data, and generates display data for presenting the change policy data and the evaluation value as information useful for achieving purposes related to the object.
-
公开(公告)号：US20220351094A1
公开(公告)日：2022-11-03
申请号：US17761306
申请日：2021-01-22
Applicant: Hitachi, Ltd.
Inventor： Masaki HAMAMOTO , Masashi EGI , Daisuke TASHIRO , Naofumi HAMA
Abstract: Fairness of automated assessments of AI has become a significant issue in recent years, and techniques for adjusting assessment results are being sought. This information processing system is configured to include: a first predicting unit which outputs an assessed value from input information that does not include sensitive attribute information a user has decided is not to be input; a second predicting unit which has been trained in advance, using teacher data, to estimate the sensitive attribute information that the user has decided is not to be input, and which estimates the sensitive attribute information from the input information that does not include the sensitive attribute information; and a first quantizing unit which, on the basis of the estimated value of the sensitive attribute information obtained from the second predicting unit, adjusts the assessed value output by the first predicting unit, and outputs an assessment result.
-
Patent Agency Ranking
公开(公告)号：US20210117831A1
公开(公告)日：2021-04-22
申请号：US17071482
申请日：2020-10-15
Applicant: Hitachi, Ltd.
Inventor： Yuyao WANG , Masayoshi MASE , Masashi EGI
Abstract: To more appropriately explain bases of estimation in a machine learning model that estimates appropriate outputs as responses to a temporally changing state. A machine learning model estimates an appropriate output in an environment with a temporally changing state. One or more processors acquire an episode. The episode includes steps at different times. Each step in the steps indicates a state of the environment, and an output selected by the machine learning model in the state. The one or more processors form a plurality of phases including one or more consecutive steps on a basis of one or more changing indicators in the episode, and generate data that explains a basis of the machine learning model in the plurality of phases.
-
公开(公告)号：US20200234219A1
公开(公告)日：2020-07-23
申请号：US16554107
申请日：2019-08-28
Applicant: HITACHI, LTD.
Inventor： Hiroyuki NAMBA , Atsushi TOMODA , Hiromitsu NAKAGAWA , Masashi EGI
Abstract: A DB server 2 stores work achievement table 210 indicating a disposition target related to a work, an actual disposition place where the disposition target is disposed, and actual work time taken for the work for each work and location information 220 indicating a plurality of disposition places where the disposition targets can be disposed. A control portion 330 acquires a mutual action search policy including a plurality of mutual action emergence patterns indicating a relation between the two disposition places influencing the work time taken for the work. A generating portion (an item combination extraction portion 350, a mutual action set search portion 360, and a disposition change optimization portion 370) generates a disposition plan indicating a plan of disposition place where the disposition target is disposed on the basis of the work achievement information, the location information, and the mutual action search policy.
-
公开(公告)号：US20240169220A1
公开(公告)日：2024-05-23
申请号：US18379537
申请日：2023-10-12
Applicant: Hitachi, Ltd.
Inventor： Masayoshi MASE , Kohei MATSUSHITA , Masaki HAMAMOTO , Masashi EGI
IPC: G06N5/04
CPC classification number: G06N5/04
Abstract: A computer system is accessibly connected to model management information for managing model data, risk assessment management information for managing risk assessment data, and evaluation method management information for managing evaluation method data, and generates, as relation data, association of, model data, risk assessment data, and evaluation method data in a template. The computer system is configured to, when receiving an evaluation request, by referring to the model management information, search for model data of a model to be evaluated, search for the relation data associated with the model data, generate a template based on the relation data, store, in association with the relation data, an evaluation result based on an evaluation method corresponding to the evaluation method data associated with the relation data, and generate a report based on the template and the evaluation result.
-
9.发明公开公开(公告)号：US20230351281A1
公开(公告)日：2023-11-02
申请号：US18112537
申请日：2023-02-22
Applicant: Hitachi, Ltd.
Inventor： Yuta TSUCHIYA , Yasuhide MORI , Masashi EGI
IPC: G06Q10/0631 , G06Q50/06
CPC classification number: G06Q10/06312 , G06Q10/06311 , G06Q50/06
Abstract: Provided is a technique that allows a user to easily determine what kind of future scenario AI is outputting. A preferred aspect of the invention provides an information processing device including: an agent configured to output a response based on a state observed from an environment with stochastic state transitions; an individual evaluation model configured to evaluate the response assuming that a part of the stochastic state transitions occurs; and a plan explanation processing unit configured to output information based on the evaluation in association with information based on the response.
-
公开(公告)号：US20230161841A1
公开(公告)日：2023-05-25
申请号：US17950951
申请日：2022-09-22
Applicant: Hitachi, Ltd.
Inventor： Naoaki YOKOI , Masashi EGI
IPC: G06K9/62
CPC classification number: G06K9/6262 , G06K9/627
Abstract: A computer system is provided, which is capable of evaluating the degree of influence of training data on prediction accuracy of a decision tree type machine learning model, while suppressing increase in processing time thereof. A similarity score calculating unit uses a tree structure of a trained model of a target predictor to calculate, for each of training data used for learning this trained model, a similarity score in which is evaluated similarity between the training data in the trained model and other training data. An evaluating unit selects target data that is training data that is a target of evaluation from the training dataset on the basis of the similarity score, and calculates an influence score in which the degree of influence of the target data on accuracy of the trained model is evaluated.
-
-
-
-
-
-
-
-
-
Search Results
22
records
(took 0.026 seconds)
