Non-transitory computer-readable recording medium, specifying method, and information processing apparatus
AssigneeFujitsu Limited
InventorsTakuya YOKOTA, Yuri NAKAO
Life of this patent
Estimating the term…
Abstract
A non-transitory computer-readable recording medium has stored therein a specifying program that causes a computer to execute a process including acquiring an attribute of training data, acquiring a document related to a decision-making condition for a specific attribute of a user inputting a prompt including the attribute of the training data and a token of the document related to the decision-making condition to a large-scale language model and outputting an appearance probability of a token related to the attribute and specifying a label of a training target of a machine learning model from the training data based on the output appearance probability of the token.
Claims18
A non-transitory computer-readable recording medium having stored therein a specifying program that causes a computer to execute a process comprising:
- acquiring an attribute of training data;
- acquiring a document related to a decision-making condition for a specific attribute of a user;
- inputting a prompt including the attribute of the training data and a token of the document related to the decision-making condition to a large-scale language model and outputting an appearance probability of a token related to the attribute;
- and
- specifying a label of a training target of a machine learning model from the training data based on the output appearance probability of the token.
A specifying method comprising:
- acquiring an attribute of training data;
- acquiring a document related to a decision-making condition for a specific attribute of a user;
- inputting a prompt including the attribute of the training data and a token of the document related to the decision-making condition to a large-scale language model and outputting an appearance probability of a token related to the attribute;
- and
- specifying a label of a training target of a machine learning model from the training data based on the output appearance probability of the token, by using a processor.
An information processing apparatus comprising:
- a memory;
- and
- a processor coupled to the memory and configured to:
- acquire an attribute of training data;
- acquire a document related to a decision-making condition for a specific attribute of a user;
- input a prompt including the attribute of the training data and a token of the document related to the decision-making condition to a large-scale language model and output an appearance probability of a token related to the attribute;
- and
- specify a label of a training target of a machine learning model from the training data based on the output appearance probability of the token.
Dependencies are inferred from the claim text.