Method for analysis on interim result data of de-identification procedure, apparatus for the same, computer program for the same, and recording medium storing computer program thereof

1. A method for de-identification for data, the method comprising:

receiving, through a transceiver, an initial data and storing the initial data in a memory;

applying, by a processor, a first de-identification process to the initial data to obtain first interim result data;

obtaining and outputting, by the processor, final result data based on a part of data subsets included in the first interim result data, when first analysis metric for the first interim result data satisfies a first de-identification criterion, thereby reducing time or resources to output the final result data;

applying, by the processor, a second de-identification process to the first interim result data, when a first analysis metric for the first interim result data does not satisfy the first de-identification criterion to obtain second interim result data; and

obtaining and outputting, by the processor, final result data based on a part of data subsets included in the second interim result data, when a second analysis metric for the second interim result data satisfies a second de-identification criterion, thereby reducing time or resources to output the final result data,

wherein the first interim result data includes the initial data and a result of the first de-identification process, and the result of the first de-identification process is accumulated on the initial data,

wherein the second interim result data includes initial data, the result of the first de-identification process, and a result of the second de-identification process, and the result of the second de-identification process is accumulated on the first interim result data.

2. The method according to claim 1 , wherein:

the first analysis metric is obtained based on a part of all of data subsets included in the first interim result data; and

the second analysis metric is obtained based on a part of all of data subsets included in the second interim result data.

3. The method according to claim 1 , wherein:

the first de-identification process corresponds to a first type de-identification process; and

the second de-identification process corresponds to a second type de-identification process.

4. The method according to claim 3 , further comprising:

applying, to the first interim result data or the first interim result data, at least one additional de-identification process corresponding to the first type de-identification process or the second type de-identification process to obtain an additional interim result data, when the first analysis metric does not satisfy the first de-identification criterion or the second analysis metric does not satisfy the second de-identification criterion; and

obtaining and outputting final result data based on a part of data subsets included in the additional interim result data, when an additional analysis metric for the additional interim result data satisfies an additional de-identification criterion, thereby reducing time or resources to output the final result data.

5. The method according to claim 3 , wherein:

the first type de-identification process includes at least one de-identification process applied before or after the second type de-identification process; and

the second type de-identification process includes at least one de-identification process of applying a predetermined privacy protection model.

6. The method according to claim 1 , wherein:

the first analysis metric includes standardized measurement data applicable to a result of the first de-identification process; and

the second analysis metric includes standardized measurement data applicable to a result of the second de-identification process.

7. An apparatus for de-identification for data, the apparatus comprising:

a transceiver;

a memory;

a user interface; and

a processor,

wherein the processor is configured to:

receive an initial data through the transceiver;

store the initial data in the memory;

apply a first de-identification process to the initial data to obtain first interim result data;

obtain and to output final result data based on a part of data subsets included in the first interim result data, when first analysis metric for the first interim result data satisfies a first de-identification criterion, thereby reducing time or resources to output the final result data;

apply a second de-identification process to the first interim result data, when a first analysis metric for the first interim result data does not satisfy the first de-identification criterion to obtain second interim result data; and

obtain and to output final result data based on a part of data subsets included in the second interim result data, when a second analysis metric for the second interim result data satisfies a second de-identification criterion, thereby reducing time or resources to output the final result data,

wherein the first interim result data includes the initial data and a result of the first de-identification process, the result of the first de-identification process is accumulated on the initial data, and

wherein the second interim result data includes initial data, the result of the first de-identification process, and a result of the second de-identification process, and the result of the second de-identification process is accumulated on the first interim result data.

8. A non-transitory computer-readable storing medium storing a computer program for executing a method at a computer according to claim 1 .

9. The method according to claim 3 , wherein:

the first type de-identification process includes at least one of data value deletion, pseudonymization, totalization, categorization, or data masking; and

the second type de-identification process includes applying at least one privacy protection model of K-anonymity, L-diversity, or T-closeness.