Abstract: A non-transitory computer-readable recording medium storing a rule update program for causing a computer to execute processing including: receiving first appropriateness determination for at least some determination rules among a plurality of determination rules derived through machine learning by using training data; performing second appropriateness determination for a determination rule other than the some determination rules, based on a result of the first appropriateness determination and similarity between the some determination rules and the determination rule other than the some determination rules; and updating the plurality of determination rules, based on the result of the first appropriateness determination and a result of the second appropriateness determination.

Abstract: A non-transitory computer-readable recording medium stores therein an allocation program that causes a computer to execute a process including: performing, by using a part of data including an objective variable and one or more explanatory variables corresponding to the objective variable as training data, training of a model that predicts the objective variable from the explanatory variables of the data; classifying test data obtained by excluding the training data from the data into a group according to a classification condition regarding at least a part of the explanatory variables of the data; predicting the objective variable from the explanatory variables of the test data using the trained model for each of groups by which classification has been performed at the classifying; and calculating a predetermined resource amount to be allocated to each of the groups based on the objective variable for each of the groups predicted at the predicting.

Abstract: A non-transitory computer-readable recording medium stores therein a prediction program that causes a computer to execute a process including obtaining a machine learning model trained by using training data, the machine learning model predicting presence or absence of purchase actions or predetermined actions of users corresponding to feature information on the users, the training data including feature information on users and information indicating the presence or the absence of the purchase actions of commercial products or the predetermined actions, receiving input of a budget amount in an entry field displayed on a display in association with a user group including users including a common feature in the feature information, and displaying, in association with the budget amount on the display, feature information on the users included in the user group corresponding to the entry field.

Abstract: A zinc-plated steel sheet for hot stamping according to an aspect of the present invention includes a base steel sheet satisfying a predetermined composition of chemical components, wherein an amount of solid-soluted B is 10 ppm or more and the base steel sheet has a hot-dip galvannealed layer or a hot dip galvanized layer on at least one face thereof.

Abstract: A non-transitory computer-readable storage medium storing an adjustment program that causes at least one computer to execute a process, the process includes acquiring a difference between first pattern information that includes a first condition which is one attribute value or a combination of a plurality of attribute values and a first label which corresponds to the first condition and second pattern information that includes a second condition and a second label; and changing an importance level for the first pattern information based on the difference when there is at least one selected from a discrepancy between the first condition and the second condition, and a discrepancy between the first label and the second label.

Abstract: A non-transitory computer-readable recording medium stores therein an extraction program that causes a computer to execute a process including: generating a plurality of combinations of conditions relating to a plurality of item values included in data; calculating an index value that indicates a degree of cooccurrence between a specified response variable and each of the plurality of combinations, by using a machine learning model that estimates a response variable from the plurality of item values, the machine learning model having been trained by using the data; and extracting a specific combination from among the plurality of combinations based on any one of the condition and the index value.

Abstract: An apparatus decomposes a first binary tree pattern into combinations of multiple binary tree units in accordance with a predetermined procedure. When a second binary tree pattern configured as a combination of binary tree units that are among the multiple binary tree units and include a top binary tree unit of the multiple binary units is associated with a subset of a target binary tree data, the apparatus searches the target binary tree data for the first binary tree pattern by using positions of the subset within the target binary tree data.

Abstract: A document evaluation apparatus acquires multiple judgement rules, each of which associates a condition for values of one or more characteristic variables with a document evaluation result, the one or more characteristic variables being amongst multiple characteristic variables that includes one or more first characteristic variables each indicating an occurrence frequency of words in a document and one or more second characteristic variables each indicating an attribute of a business operation corresponding to a document. The document evaluation apparatus calculates values of the characteristic variables corresponding to an evaluation subject document, and selects, amongst the judgement rules, a judgement rule whose condition matches the calculated values of the evaluation subject document and includes at least one of the one or more first characteristic variables. The document evaluation apparatus generates an evaluation result of the evaluation subject document based on the selected judgement rule.

Abstract: A low-strength steel sheet for hot stamping according to an aspect of the present invention satisfies a predetermined chemical composition, the Ac3 point (° C.) represented by Equation (1) is 890° C. or more, and an area ratio of ferrite at a depth to be ¼ of a steel sheet thickness is 80% or more. Ac3 point (° C.)=910?203×[C]1/2+44.7×[Si]?30×[Mn]+700×[P]+400×[Al]+400×[Ti] . . . (1) In Equation (1), [C], [Si], [Mn], [P], [Al], and [Ti] are values denoting the percentage contents of C, Si, Mn, P, Al, and Ti in terms of % by mass, respectively.

Abstract: To establish a method for obtaining a hot-press-formed steel member, which exhibits high strength, high tensile elongation (ductility) and high bendability, thereby having excellent deformation characteristics at the time of collision crush (crashworthiness), and which is capable of ensuring excellent delayed fracture resistance. A method for producing a hot-press-formed steel member by heating a steel sheet, which has a chemical component composition containing 0.10% (% by mass, and hereinafter the same shall apply) to 0.30% (inclusive) of C, 1.0% to 2.5% (inclusive) of Si, 1.0% to 3.0% (inclusive) of Si and Al in total and 1.5% to 3.0% (inclusive) of Mn, with the balance consisting of iron and unavoidable impurities, and hot press forming the steel sheet one or more times.

Abstract: Provided is a method for manufacturing a steel member through hot press forming using a steel sheet that contains a comparatively large amount of Si. The steel sheet includes, in mass ratio, C: 0.15% to 0.35%, Si: 1.0% to 3.0%, Mn: 1.0% to 3.0%, Al: more than 0% up to 0.10%, Ti: ([N]×48/14)% to 0.10% (where [N] denotes the amount of N in the steel sheet), B: 5 ppm to 50 ppm, P: more than 0% to less than 0.015%, S: more than 0% up to 0.010%, and N: more than 0% up to 0.010%, the balance being iron and unavoidable impurities. The average oxygen concentration from an outermost surface of the steel sheet down to a depth of 10 ?m in a sheet thickness direction is 0.70 mass % or higher.

Abstract: In a method for obtaining a hot-press-formed steel member, a steel sheet containing 0.10-0.30 mass % of C, 1.0-2.5 mass % of Si, 1.0-3.0 mass % of Si and Al in total, and 1.5-3.0 mass % of Mn is heated at a heating temperature of not less than the Ac3 transformation point. The steel sheet is hot-press formed for one or more times. The starting temperature of the hot pressing is not more than the heating temperature but not less than the Ms point. The average cooling rate from (Ms point?150)° C. to 40° C. is 5° C./s or less. The hot-press-formed steel member has high strength, high tensile elongation, high bendability, excellent deformation characteristics at the time of collision crush, and excellent delayed fracture resistance.

Abstract: A manufacturing method of a laminate for manufacturing a fuel cell which uses a roll-to-roll technique includes: a first step of preparing a first laminate formed by stacking the release layer, the electrolyte membrane and an electrode layer in this order on a back sheet, a second step of stacking and bonding a gas diffusion layer on the electrode layer of the first laminate to obtain a second laminate, and a third step of peeling the back sheet from the second laminate to obtain a third laminate; and the bonding temperature in the second step is less than 170° C., and a tension X (N) applied to the back sheet, and a conveyance speed Y (m/min) at which the second step to the third step are continuously executed satisfy a following equation (1). Y?12.09exp (?0.15X) ??. . . (1).

Abstract: A steel plate for hot stamping contains, in % by mass, C: 0.25% or more and 0.4% or less, Si: 1.05% or more and 1.4% or less, Mn: 0% or more and 1.4% or less, Cr: 0.6% or more and 3.0% or less, P: 0% or more and 0.03% or less, S: 0% or more and 0.02% or less, Al: 0.01% or more and 1% or less, N: 0% or more and 0.01% or less, B: 0.0005% or more and 0.005% or less, Ti: 0.005% or more and 0.1% or less, and iron and inevitable impurities as remainder. This steel plate for hot stamping exhibits excellent hardness stability in addition to a balance between strength and toughness as a relational expression of [C]2/9[Si]+7/9[Mn]+8/9[Cr]?7/4>0 is satisfied.

Abstract: A non-transitory computer-readable recording medium stores therein a prediction program that causes a computer to execute a process including obtaining a machine learning model trained by using training data, the machine learning model predicting presence or absence of purchase actions or predetermined actions of users corresponding to feature information on the users, the training data including feature information on users and information indicating the presence or the absence of the purchase actions of commercial products or the predetermined actions, receiving input of a budget amount in an entry field displayed on a display in association with a user group including users including a common feature in the feature information, and displaying, in association with the budget amount on the display, feature information on the users included in the user group corresponding to the entry field.

Abstract: A non-transitory computer-readable recording medium stores therein an extraction program that causes a computer to execute a process including: generating a plurality of combinations of conditions relating to a plurality of item values included in data; calculating an index value that indicates a degree of cooccurrence between a specified response variable and each of the plurality of combinations, by using a machine learning model that estimates a response variable from the plurality of item values, the machine learning model having been trained by using the data; and extracting a specific combination from among the plurality of combinations based on any one of the condition and the index value.

Abstract: A non-transitory computer-readable recording medium stores therein an allocation program that causes a computer to execute a process including: performing, by using a part of data including an objective variable and one or more explanatory variables corresponding to the objective variable as training data, training of a model that predicts the objective variable from the explanatory variables of the data; classifying test data obtained by excluding the training data from the data into a group according to a classification condition regarding at least a part of the explanatory variables of the data; predicting the objective variable from the explanatory variables of the test data using the trained model for each of groups by which classification has been performed at the classifying; and calculating a predetermined resource amount to be allocated to each of the groups based on the objective variable for each of the groups predicted at the predicting.

Abstract: An apparatus decomposes a first binary tree pattern into combinations of multiple binary tree units in accordance with a predetermined procedure. When a second binary tree pattern configured as a combination of binary tree units that are among the multiple binary tree units and include a top binary tree unit of the multiple binary units is associated with a subset of a target binary tree data, the apparatus searches the target binary tree data for the first binary tree pattern by using positions of the subset within the target binary tree data.

Abstract: Provided is a method for manufacturing a steel member through hot press forming using a steel sheet that contains a comparatively large amount of Si. The steel sheet includes, in mass ratio, C: 0.15% to 0.35%, Si: 1.0% to 3.0%, Mn: 1.0% to 3.0%, Al: more than 0% up to 0.10%, Ti: ([N]×48/14)% to 0.10% (where [N] denotes the amount of N in the steel sheet), B: 5 ppm to 50 ppm, P: more than 0% to less than 0.015%, S: more than 0% up to 0.010%, and N: more than 0% up to 0.010%, the balance being iron and unavoidable impurities. The average oxygen concentration from an outermost surface of the steel sheet down to a depth of 10 ?m in a sheet thickness direction is 0.70 mass % or higher.

Abstract: A learning device creates a plurality of decision trees, using pieces of training data respectively including an explanatory variable and an objective variable, which are configured by a combination of the explanatory variables and respectively estimate the objective variable based on true or false of the explanatory variables. The learning device creates a linear model that is equivalent to the plurality of decision trees, and lists all terms configured by a combination of the explanatory variables without omission. The learning device outputs a prediction result by using the linear model from input data.