An information processing apparatus comprising at least one processor, wherein the at least one processor is configured to: derive, for each of predetermined property items, property information indicating a property of the property item from at least one image; receive, for each of the property items, a description regarding the property item to be selectable as to whether the description is necessary, unnecessary, or optional in a document; and generate a plurality of character string candidates including the description based on the property information regarding the property items that have been selected as the descriptions being necessary and optional by changing a combination of property items selected from among the property items that have been selected as the description being optional.