Abstract: A support method includes: performing a coefficient setting process of receiving setting of a value of a risk aversion coefficient included in a heteroscedasticity acquisition function; and executing heteroscedasticity Bayesian optimization based on a first predictive distribution of an expected value of a response variable, a second predictive distribution of a variance of the response variable, a heteroscedasticity acquisition function, and an exploration range, to acquire, from within the exploration range, a recommended value of an explanatory variable that maximizes the heteroscedasticity acquisition function. The heteroscedasticity acquisition function is a function in which the larger the value of the risk aversion coefficient becomes, the higher a proportion of acquiring the recommended value from a region with a smaller variance of the response variable becomes.

Abstract: A vector acquisition method includes: inputting, into a learned model, at least one piece of text including at least two of a plurality of words obtained by dividing a compound, the compound being a word divisible into the plurality of words; outputting, from the learned model, an adjusted vector corresponding to at least one of the words obtained by dividing the compound in the input piece of text; and acquiring a compound vector corresponding to the compound using the adjusted vector output from the learned model. Classification accuracy of vectors corresponding to words can thereby be enhanced.

Abstract: Training data in which tag information is assigned to some document files extracted from a plurality of document files to be retrieved is acquired by a training data acquirer. A tag estimation model for estimating tag information to be assigned to a document file is constructed by a constructor by applying the acquired training data to a Transformer machine learning model on which learning has been carried out in advance using a corpus. The tag information is assigned to each of the plurality of document files to be retrieved by an assigner using the constructed tag estimation model.

Abstract: A similarity calculation apparatus according to the present invention includes: a name acquisition unit configured to acquire a first group name to which each word belonging to a first synonym group belongs and a second group name to which each word belonging to a second synonym group belongs; a name set generation unit configured to generate a first group name set and a second group name set; and a similarity calculation unit configured to calculate similarity between the first group name set and the second group name set. Therefore, even when a plurality of synonym groups are created, terms can be effectively unified.

Abstract: A vector acquisition method includes: inputting, into a learned model, at least one piece of text including at least two of a plurality of words obtained by dividing a compound, the compound being a word divisible into the plurality of words; outputting, from the learned model, an adjusted vector corresponding to at least one of the words obtained by dividing the compound in the input piece of text; and acquiring a compound vector corresponding to the compound using the adjusted vector output from the learned model. Classification accuracy of vectors corresponding to words can thereby be enhanced.

Abstract: A synonym determination method includes the steps of: converting words contained in a document into first vectors representing meanings of the words; obtaining a word similarity on the basis of the first vectors; converting sentences contained in the document into second vectors representing meanings of the sentences; obtaining a sentence similarity on the basis of the second vectors; classifying the words contained in the document according to topic; and determining whether the words contained in the document are synonyms on the basis of the word similarity, the sentence similarity, and the result of topic classification. Thus, the synonym determination method is provided so as to allow highly accurate automatic synonym determination.

Abstract: Learning data representing the relationship between explanatory variables and objective variables is acquired by an acquirer. In the learning data acquired by the acquirer, a hierarchical relationship among a plurality of items included in the objective variable is determined by a hierarchy determiner. A construction algorithm to be executed among a plurality of construction algorithms for construction of a learning model is determined by an algorithm determiner based on the hierarchical relationship determined by the hierarchy determiner. A first learning model is constructed by execution of the construction algorithm determined by the algorithm determiner by a learner.

Abstract: A similarity calculation apparatus according to the present invention includes: a name acquisition unit configured to acquire a first group name to which each word belonging to a first synonym group belongs and a second group name to which each word belonging to a second synonym group belongs; a name set generation unit configured to generate a first group name set and a second group name set; and a similarity calculation unit configured to calculate similarity between the first group name set and the second group name set. Therefore, even when a plurality of synonym groups are created, terms can be effectively unified.

Abstract: A parameter update apparatus according to the present invention includes: an input unit configured to receive input of teaching data; and an update unit configured to update a parameter for assigning at least one estimation label corresponding to each of a plurality of data items by performing multi-task learning by using a neural network for the plurality of data items of the input teaching data. The update unit updates the parameter so that a sum of errors between the assigned estimation label and a corresponding true label in the teaching data in the plurality of data items has a minimum value. Therefore, the plurality of data items constituting a hierarchical structure can be classified while preventing deterioration of classification accuracy.