Abstract: For a machine learning model that receives control parameters of a semiconductor processing device and outputs shape parameters that express a processed shape of a semiconductor sample processed by the semiconductor processing device, an experiment point obtaining learning data is recommended. A contribution of each control parameter to the prediction of the machine learning model is evaluated from feature quantity data that is a value of a control parameter of the learning data used for learning of the machine learning model, and the experiment point is recommended based on a stability evaluation and an uncertainty evaluation of the prediction by the machine learning model in a space defined by the control parameters selected based on the contribution as axes.

Abstract: A computer system includes an arithmetic device and a storage device. The storage device stores a model configured to output an action predicted based on an action value in response to input data. The arithmetic device is configured to acquire data to be explained including values of a plurality of components to be explained in order to explain first prediction processing of the model that outputs a first predicted action in response to first input data, determine contributions of each of the plurality of components to be explained to an action value and an uncertainty of the action value in the first prediction processing, detect one or more risk components in the first prediction processing from the plurality of components to be explained based on the contributions, and present information on the risk components.

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.

Abstract: There is provided is a computer system that outputs a predicted value of data to be evaluated using a predictor generated using learning data. The computer system includes the predictor; an index calculation unit that calculates an interpretation index of the data to be evaluated; and an extraction unit that selects the learning data useful for a user to interpret the predicted value of the data to be evaluated, wherein index management information for managing an interpretation index of the learning data is stored, the index calculation unit calculates the interpretation index of the data to be evaluated, and the extraction unit calculates a selection index based on the interpretation index of the data to be evaluated and the interpretation index of the learning data, selects the learning data based on the selection index, and outputs display information for presenting information indicating a processing result.

Abstract: A plan evaluation apparatus, which evaluates a schedule planned by combining a plurality of plans, includes: a feature conversion unit that divides the schedule into plan components based on a predetermined conversion rule, and convert the divided plan components into features; a model learning unit that uses the features as an input and creates a machine learning model having a key performance indicator (KPI) of the schedule as an objective variable; a contribution rate calculation unit that calculates a contribution rate of each of the features with respect to the machine learning model; and an influence degree calculation unit that calculates an influence degree of influence, on the KPI of the schedule, of the plan component which is a conversion source of the feature, based on the contribution rate of the feature.

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.

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.

Abstract: There is provided is a computer system that outputs a predicted value of data to be evaluated using a predictor generated using learning data. The computer system includes the predictor; an index calculation unit that calculates an interpretation index of the data to be evaluated; and an extraction unit that selects the learning data useful for a user to interpret the predicted value of the data to be evaluated, wherein index management information for managing an interpretation index of the learning data is stored, the index calculation unit calculates the interpretation index of the data to be evaluated, and the extraction unit calculates a selection index based on the interpretation index of the data to be evaluated and the interpretation index of the learning data, selects the learning data based on the selection index, and outputs display information for presenting information indicating a processing result.

Abstract: A computer system includes a processor for executing a program, a computer holding the program executed by the processor, a first database holding relevance between physical amounts measured under conditions different in at least one of time and place, and a second database holding relevance between pieces of information including texts and corresponding to the measured physical amounts. The processor is configured to: calculate, based on the relevance between the physical amounts held in the first database and the relevance between the pieces of information in the second database, relevance between each of the measured physical amounts and each of the pieces of information, and hold the calculated relevance between each of the physical amounts and each of the pieces of information in a third database; and refer to, when the physical amounts are input, the third database to present information highly relevant to the input physical amounts.

Abstract: Provided is an information recommendation system capable of recommending an unexpected item which a user is interested in but cannot assume easily. A server gives one or more times of initial recommendations of recommending information by a means of a user profile and a behavior history, and narrows down second recommended items to recommend next by using not only information relating to items having responses but also information relating to items having no response together. In narrowing down, the items are arranged by means of an item arrangement program by using the results of the initial recommendations, and it is identified depending on similarity by means of a boundary calculation program where the boundary between user's interest and no interest is positioned in all the items.

Abstract: A computer system includes a processor for executing a program, a computer holding the program executed by the processor, a first database holding relevance between physical amounts measured under conditions different in at least one of time and place, and a second database holding relevance between pieces of information including texts and corresponding to the measured physical amounts. The processor is configured to: calculate, based on the relevance between the physical amounts held in the first database and the relevance between the pieces of information in the second database, relevance between each of the measured physical amounts and each of the pieces of information, and hold the calculated relevance between each of the physical amounts and each of the pieces of information in a third database; and refer to, when the physical amounts are input, the third database to present information highly relevant to the input physical amounts.

Abstract: Model data is generated from performance information sorted by day of the week, time period, and process status by a performance information analysis section and a process status analysis section. An abnormality determination section detects abnormality using appropriate model data. What the graph of an expected status is like, how much the graph of the current status that has been determined abnormal differs from the graph of the expected status, and how much the current status is like the expected status are displayed allowing a system manager to observe detailed information about abnormality determination.

Abstract: An environmental control system according to the present invention is a system for controlling environmental devices by which a work status and a behavior status are monitored and the environmental devices are finely controlled in accordance with the statuses to improve comfort. The environmental control system includes a communication unit, a unit for detecting environments, a unit for detecting a work status, a unit for obtaining power consumption, a unit for determining the control of a device, and a unit for transmitting a control signal, and enables fine control in accordance with a work type.

Abstract: A home system for supporting a life behavior, in which a user can effectively select a function or content quickly according to attributes and states of display devices arranged in respective locations and the user behavior. A storage unit holds location attribute information on the devices, time band dependent use frequency for each user, and location dependence of each. A user identifier input unit identifies a user using a function or content. When displaying a menu for the user to select a content and a function, a calculation unit references each database of the storage unit in accordance with the menu display state and generates menu content information correlated to the content and the function. A display unit displays such a menu that the user can easily select a content and a function with higher priority rank according to the menu content information.

Abstract: Provided is an information recommendation system capable of recommending an unexpected item which a user is interested in but cannot assume easily. A server gives one or more times of initial recommendations of recommending information by a means of a user profile and a behavior history, and narrows down second recommended items to recommend next by using not only information relating to items having responses but also information relating to items having no response together. In narrowing down, the items are arranged by means of an item arrangement program by using the results of the initial recommendations, and it is identified depending on similarity by means of a boundary calculation program where the boundary between user's interest and no interest is positioned in all the items.

Abstract: According to one embodiment of the present invention, a skill level of a staff member is discriminated from an actual job log of the staff member, productivity including the skill level, a salary, and combination efficiency with another staff member is calculated, and a staff arrangement plan maximizing a productive efficiency is outputted.

Abstract: An environmental control system according to the present invention is a system for controlling environmental devices by which a work status and a behavior status are monitored and the environmental devices are finely controlled in accordance with the statuses to improve comfort. The environmental control system includes a communication unit, a unit for detecting environments, a unit for detecting a work status, a unit for obtaining power consumption, a unit for determining the control of a device, and a unit for transmitting a control signal, and enables fine control in accordance with a work type.

Abstract: Model data is generated from performance information sorted by day of the week, time period, and process status by a performance information analysis section and a process status analysis section. An abnormality determination section detects abnormality using appropriate model data. What the graph of an expected status is like, how much the graph of the current status that has been determined abnormal differs from the graph of the expected status, and how much the current status is like the expected status are displayed allowing a system manager to observe detailed information about abnormality determination.

Abstract: A home system for supporting a life behavior, in which a user can effectively select a function or content quickly according to attributes and states of display devices arranged in respective locations and the user behavior. A storage unit holds location attribute information on the devices, time band dependent use frequency for each user, and location dependence of each. A user identifier input unit identifies a user using a function or content. When displaying a menu for the user to select a content and a function, a calculation unit references each database of the storage unit in accordance with the menu display state and generates menu content information correlated to the content and the function. A display unit displays such a menu that the user can easily select a content and a function with higher priority rank according to the menu content information.

Abstract: With respect to a data transfer over a network, data is stored in each cache of the network and the retrieving processing following the second retrieving processing is executed by using a cache, thereby resulting in a transfer amount being decreased. Statistics information of a data transfer over the network is obtained. When transfer data is stored in a low-speed storage such as a disk, only data of high access frequency is stored and data of low access frequency is discarded, thereby solving such a problem that a speed of a disk apparatus becomes a bottleneck.