Data creation apparatus and data creation method

A data creation method comprising:

• a node extraction step in which a node extraction unit extracts a node on a trace path of a dependency analysis tree based on an input document;
• a token verification step in which a token verification unit performs token verification to verify whether metadata generated by inputting the document into a large language model is appropriate or not using the metadata and a token obtained from the nodes;
• a token match score calculation step in which a token match score calculation unit obtains a token match score on the basis of a result of the token verification;
• a grouping step in which a grouping unit groups the metadata in accordance with user's interest terms data which reflects a user's interests using the metadata as it is if the token match score satisfies a predetermined condition;
• a confidence score calculation step in which a confidence score calculation unit calculates a confidence score for the grouped metadata;
• a rank calculation step in which a rank calculation unit ranks the metadata in accordance with the confidence score;
• and
• a display step in which a reviewing unit displays the ranked metadata on a rank display screen together with the rank.