Abstract: A NOx generation amount control device includes: a cumulative amount calculating part calculating a cumulative NOx amount obtained by adding together a plurality of NOx exhaust amounts calculated for each prescribed time interval; a specifying part specifying a target value of the cumulative NOx amount associated with a movement distance of a moving body or an output value of an engine; an estimating part estimating a predicted NOx amount indicating a predicted cumulative NOx amount based on a rotation speed of the engine and a fuel injection amount; a judging part judging whether the sum of the predicted NOx amount and the cumulative NOx amount exceeds the target value; and a determining part determining a scheduled NOx exhaust amount and determining at least one of an opening degree of the EGR valve and an opening degree of a turbocharger.

Abstract: A non-transitory computer-readable recording medium stores an information searching program causing a computer to execute processing of: in an information search using a trained machine learning model generated by machine learning using training data in a first language, when a search condition is in the first language, translating the search condition to a second language different from the first language; re-translating the search condition translated to the second language to the first language; and performing the information search by inputting the search condition re-translated to the first language to the machine learning model; and when the search condition is in a language different from the first language, translating the search condition to the first language, and performing the information search by inputting the search condition translated to the first language to the machine learning model.

Abstract: A non-transitory computer-readable recording medium stores an information generating program causing a computer to execute processing of: in an information search using a trained machine learning model generated by machine learning using training data in a first language, converting a search condition in a second language different from the first language to the search condition in the first language; searching information in the first language by inputting the search condition converted to the first language to the machine learning model; and generating training data with the search condition converted to the first language as a feature value and the searched information in the first language as a correct answer label.

Abstract: A machine learning method includes: obtaining first teacher data, which includes first encrypted words and corresponding search word information including one or more second encrypted words to be used for search, the first encrypted words being generated such that the first encrypted word includes a code sequence different from other encrypted words even though both of the first encrypted words and the other encrypted words have been generated from a same word; obtaining a group of words from among the first encrypted words by using a trapdoor scheme; generating second teacher data by using one encrypted word included in the obtained group to replace a rest of the obtained group of words; and performing, on the basis of the second teacher data, machine learning of a parameter to determine, in response to receiving of one or more encrypted words, one or more encrypted words to be used for search.

Abstract: A text classification method is performed in a computer. The method includes: receiving a plurality of texts. When detecting that a text among the received plurality of texts includes a pause part satisfying a specific condition, dividing the text at the pause part and generating a new plurality of texts. The method may also include classifying texts, among the received plurality of texts, not including the pause part satisfying the specific condition, and the generated new plurality of texts into a plurality of clusters.

Abstract: A non-transitory computer-readable storage medium for storing a determination processing program which causes a processor to perform processing that includes: obtaining an importance degree vector for a plurality of feature amounts by training a first machine learning model based on machine-learning data, the machine-learning data including pieces of training data, each of the pieces of training data including the plurality of feature amounts and being associated with a corresponding determination result; training a second machine learning model of a k-nearest neighbors algorithm in accordance with the machine-learning data and the importance degree vector; and determining, from among the pieces of training data, a piece of data that is similar to data to be predicted, by using the trained second machine learning model and the data to be predicted.

Abstract: A text classification method is performed in a computer. The method includes: receiving a plurality of texts. When detecting that a text among the received plurality of texts includes a pause part satisfying a specific condition, dividing the text at the pause part and generating a new plurality of texts. The method may also include classifying texts, among the received plurality of texts, not including the pause part satisfying the specific condition, and the generated new plurality of texts into a plurality of clusters.

Abstract: A machine learning method includes obtaining a first plurality of pieces of teacher data including encrypted words associated with first information indicating words received for search and encrypted words associated with second information indicating words used for search, generating a second plurality of pieces of teacher data in which a first encrypted word is replaced with a second encrypted word on the basis of the first plurality of pieces of teacher data, a plain text of the first encrypted word being equal to a plain text of the second encrypted word, and performing, on the basis of the second plurality of pieces of teacher data, machine learning of a parameter with which an encrypted word associated with the second information is determined in response to receiving an encrypted word associated with the first information.

Abstract: A non-transitory computer-readable storage medium storing a prediction program that causes a computer to execute a process includes storing accumulated information in a storage unit, in association with a task having previously occurred, the task being a process that needs work performed by an operator, from among a plurality of operation processes executed by an information processing apparatus, the accumulated information including a status information on the information processing apparatus obtained at a time of execution of a determination process from which subsequent processes branch depending on a determination result and which is executed before the task, and a branching result of the determination process and predicting whether the task is to occur after a predetermined timing based on the status information on the information processing apparatus obtained at the predetermined timing and the accumulated information.

Abstract: A non-transitory computer-readable recording medium having stored therein a program for causing a computer to execute a process, the process includes; dividing multiple processes in a process definition, in which the multiple processes for an operation target in an information processing system are defined, into multiple groups based on partition information indicating a partition of a unit of the processes; determining a type of each of the divided groups based on the processes belonging to the group; and determining a type of the process definition based on the determined types of the groups.

Abstract: A computer-readable recording medium has stored therein a program for causing a computer to execute a test supporting process. The computer supports testing of a series of tasks related to system administration of a system. The test supporting process includes acquiring, by the computer, input data concerning a given task that is among the series of tasks and operates a given device included in the system; retrieving, by the computer, execution history data concerning the given task, from a storage device that associates and stores therein execution history data including input data and output data of each task that has been executed in the system, and identification information of the tasks; and outputting, by the computer and from among the retrieved execution history data, the output data included in the execution history data that includes the acquired input data of the given task.