US 12,423,327 B2
Information processing apparatus, information processing method and program for anonymizing data
Yoshiyuki Mihara, Tokyo (JP)
Assigned to NIPPON TELEGRAPH AND TELEPHONE CORPORATION, Tokyo (JP)
Appl. No. 17/609,765
Filed by NIPPON TELEGRAPH AND TELEPHONE CORPORATION, Tokyo (JP)
PCT Filed May 21, 2019, PCT No. PCT/JP2019/020165
§ 371(c)(1), (2) Date Nov. 8, 2021,
PCT Pub. No. WO2020/235015, PCT Pub. Date Nov. 26, 2020.
Prior Publication US 2022/0229853 A1, Jul. 21, 2022
Int. Cl. G06F 16/28 (2019.01)
CPC G06F 16/285 (2019.01) [G06F 16/282 (2019.01)] 11 Claims
OG exemplary drawing
 
1. An information processing device which anonymizes data composed of records including one or more items through statistical processing, the information processing device comprising:
a memory, and
a processor configured to:
determine one or more sets of data by classifying records based at least on:
masking target items for marking items of the records,
a dictionary which expresses categories of item values of at least an item of the records in a tree structure for each of the masking target items, and
a selected hierarchy level indicating a hierarchy level selected among the hierarchy levels in the tree structure of the dictionary for each of the masking target items;
calculate a number of one or more records belonging to each of the one or more sets;
determine a set to be deleted and a set to be statistically processed among the one or more sets based on the number of the records belonging to each of the one or more sets and a predetermined number, wherein a number of one or more records belonging to the set to be deleted being less than the predetermined number, and a number of one or more records belonging to the set to be statistically processed being greater than or equal to the predetermined number; and
generate anonymized data by deleting the one or more records belonging to the set to be deleted and statistically processing the one or more records belonging to the set to be statistically processed, wherein anonymizing data comprises automatic determination of amount of data pertaining to identification of an individual to be deleted or replaced,
wherein the one or more sets are determined based on categories in the selected hierarchy level, and upon selection of a hierarchy level by a user, information of corresponding items expressed in a hierarchy level lower than the selected hierarchy level is masked.