Procedure for assessing the degree of identification of the subject of personal data through the attributes in given dataset of personal data

Abstract

The invention refers to a procedure or a system for the quantification of the identification of the records of a given Dataset of Personal Data. More specifically, it refers to a new method for assessing the identification of the subject of personal data by assessing the identification that the attributes of personal data, in given records of Dataset, can produce. The problem solved by the invention is to evaluate the degree of identification of the subject of personal data from records in the Datasets of personal data, in such a way that the records of personal data processed by a certain subject are ordered by value, from the most identifying to the least identifying, thus enabling the entity to achieve an adequate level of preservation of the identification of certain Datasets.

Description

[0001] PROCEDURE FOR ASSESSING THE DEGREE OF IDENTIFICATION OF THE SUBJECT OF PERSONAL DATA THROUGH THE ATTRIBUTES IN GIVEN DATASET OF PERSONAL DATA

[0002] Held of the Invention

[0003] The invention refers to a procedure or a system for the quantification of the identification of the records of a given Dataset of Personal Data. More specifically, it refers to a new method for assessing the Identification of the subject of personal data by assessing the identification that the attributes of personal data, in given records of Dataset, can produce.

[0004] State of the art

[0005] Each Dataset of personal data contains certain records (excel documents, data In databases,...) in which personal data are presented through specific values for that record, such as; first and last name, social security number, phone, email,... as types of attributes for a certain number of Personal Data Subjects. These values in the records more or less, depending on the type of the attribute, reveal the identity of the subject of the personal data to whom they refer. In doing so, the data can be from "anonymous", where it cannot be determined which subject of personal data they refer to, to "highly identifying", where it can be determined with a high degree of certainty which subject of personal data, such as natural persons they refer.

[0006] Identification is one of the key factors to evaluate the value of the Dataset of personal data, and thus the possible misuse. Therefore, assessing the degree of identification gives an accurate picture of the criticality of one Dataset versus another or one record of personal data versus another.

[0007] In terms of the state of the art, the most relevant is Ian Goldberg's doctoral dissertation "Pseudonymous Communications Infrastructure for the Internet", 2000 © Ian Goldberg. It covers the theoretical foundations used by the proposed solution, but in an upgraded version, form and with practical application in correlation with the object of the proposed Solution. The main idea of the dissertation is how to achieve pseudo anonymized communication, not to evaluate the identification of the Subject of personal data. According to the model, there is no evaluation in the dissertation, but only ranking, In terms of belonging to a certain segment, and not differences in the degree of identification within that segment.

[0008] In addition, from the patent literature that can be considered relevant in view of the subject of the invention, the patent EP2919148 was consulted, which covers a procedure for determining the privacy value of time-obtained measurement results from sensors in which a method of quantification of the confidentiality of the data taken during measurement and a way of their protection and distribution is suggested, in addition, the specification of the patent EP3449414B1 discloses a computer-implemented procedure for the secure exchange of Datasets containing personal data. Solution of the technical problem

[0009] The problem solved by the present invention is to evaluate the degree of identification of the subject of personal data from records in the Datasets of personal data, in such a way that the records of personal data processed by a certain subject are ordered by value, from the most identifying to the least identifying, thus enabling the entity to achieve an adequate level of preservation of the identification of certain Datasets,

[0010] Detailed description of the invention

[0011] Initial definitions

[0012] For the purposes of a correct understanding of the technical solution, the following definitions are used for the concepts and theoretical terms in the subject specification:

[0013] "Personal data" is any information that refers to an identified natural person or an identifiable natural person (subject, of personal data), and an identifiable natural person is a person whose identity can be determined directly or indirectly, specifically on the basis of an Identifier such as first and last name, citizen identification number, location data, online identifier, or on the basis of one or more features specific to his physical, physiological, genetic, mental, economic, cultural or social identity to that natural person;

[0014] "Dataset of personal data" is a structured group of personal data that is accessible according to specific criteria, regardless of whether it is centralized, decentralized or spread on a functional or geographical basis;

[0015] "Controller" is a subject, natural or legal person, state authority, state authority or legal person established by the state for the exercise of public powers, agency or other body, which independently or jointly with others determines the purposes and method of processing personal data data, and when the purposes and method of personal data processing are deter mined by law, the same law determines the controller or the special criteria for its determination;

[0016] "Processor of a Dataset of personal data" is an entity, natural or legal person, state authority, state authority or legal person established by the state for the exercise of public powers, agency or other body that processes personal data on behalf of the controller;

[0017] From Ian Goldberg's original idea, the following definitions are used:

[0018] Definition 1: "Define the nymily of a transaction to be the amount of information about the identity of the participants that is revealed."

[0019] Definition 2: "These different amounts of revealed identity can be placed on a continuum, which we call the "Nymity Slider,"

[0020] Definition 3: "Verinyms have two important properties:

[0021] Linkability: Any verinymous transaction you perform can be linked back to you, and thus, to any other verinymous transaction you perform. Verinymous transactions therefore inherently contribute to the dossier effect; they make it possible, if not easy, to construct a large dossier on you by cross-referencing large numbers of databases which are each indexed by one of your verinyms.

[0022] 2. Permanence: Verinyms are, for the most part, hard to change, and, generally, even if you do change them, there is often a record of the change (thus linking your old name to your new one)."

[0023] Definition 4: "In contrast, at the extreme low end of the Nymity Slider are transactions that reveal no information at all about the identity of the participant. We say that transactions of this type provide unlinkable anonymity. "

[0024] Definition 5: "Above unlinkable anonymity on the Nymity Slider is the situation where a transaction does not reveal information about the identity of the participant, yet different transactions made by the same participant can, at least in some cases, be linked together."

[0025] Definition 6: "Persistent pseudonymity, and sits between linkable anonymity and verlnymity on the Nymity Slider."

[0026] Definitions derived from Goldberg's theory apply at the level of transactions, not Datasets of personal data. Most of all Personal Data in business operations belong to a highly identifiable segment and industries require a more granular assessment of identification in that segment, while the pseudoanonymized data segment is subject to other controls. Goldberg does not propose a way to evaluate, that is, identification intervals are only indicated, so certain records and Datasets may have the same level and thus It is not clear what their criticality or value is when they are compared. Whereas, when a particular transaction belongs to a particular segment / level, it does not affect how many other attributes like number are in the record and how they affect the change in grade. First name last name without attributes is rated lower in the proposed method than first name last name and nickname.

[0027] Description of the images

[0028] For easier understanding of the subject of the invention, several graphical representations are given with the following description:

[0029] Figure 1 represents a block diagram on which the steps for the realization of the identification quantification procedure (ID quantification) and preservation of the identification of Personal data are indicated; The marks have the following meaning:

[0030] 1.1 Dataset of records by the Collector / Processor;

[0031] 1.2 Structuring the information in the Dataset of Personal Data;

[0032] 1.3 Assigning appropriate values to all attributes of Personal Data;

[0033] 1.4 Grouping of Personal Data records depending on the assigned attribute values;

[0034] 1.5 Sorting records within groups in descending order;

[0035] 1.6 calculation of ID quantification values at appropriate intervals;

[0036] 1.7 preservation of the Iden tification of Personal Data.

[0037] Figure 2 is a view of the Technical Infrastructure and connection of the parts that, are necessary to realize the solution; 2.1 Part that precedes the ID quantification and consists of: Dataset of Personal Data records from the infrastructure of the controller / processor respectively marked in figure 1 as 1.1;

[0038] 2.2 Segment of the infrastructure that is responsible for:

[0039] 1.2 structuring the information in the Datasets of Personal Data;

[0040] 1.3 assigning appropriate values to all attributes of Personal Data;

[0041] 1.4 grouping of Personal Data records depending on the assigned attribute values.

[0042] 2.3 Segment of infrastructure In which the following steps take place:

[0043] 1.5 sorting records within groups in descending order and

[0044] 1.6 calculating ID quantification values at appropriate intervals.

[0045] 2.4 The segment of the infrastructure in which the final step takes place, which follows the ID quantification and consists of the preservation of the Identification of the Personal Data, which in Figure 1 is marked with 1.7.

[0046] The specific hardware parts that make up the infrastructure can be assumed but can vary and therefore are not specified. Additionally, for illustration purposes, they are elaborated in the description of the proposed performance.

[0047] Figure 3 is a representation of a performance of a system that is intended to implement the solution, while the designated positions indicate the following components and modules;

[0048] 3.1 Processor;

[0049] 3.2 Interface;

[0050] 3.3 Memory.

[0051] Memory (3.3) includes two components: modules (3.4) and data (3.5).

[0052] There are 7 modules (3.4) namely:

[0053] 3.4.1 Data collection module;

[0054] 3.4.2 Data structuring module;

[0055] 3.4.3 Value assignment module;

[0056] 3.4.4. Data grouping module;

[0057] 3.4.5 Data sorting module;

[0058] 3.4.6 Identification evaluation module;

[0059] 3.4.7 Identification storage module.

[0060] The data marked with position (3.5) include:

[0061] 3.5.1 Dataset of personal data;

[0062] 3.5.2 Other data. Figure 4 is a block diagram showing the process for adequate Identification quantification. The numbered steps have the following meaning:

[0063] 4.1 Collection of data and their attributes from the initial Dataset;

[0064] 4.2 Initial quantification of personal data and forwarding of identification information to step;

[0065] 4.3 Modification of the Dataset;

[0066] 4.4 Step of repeating the identification quantification procedure after the modification;

[0067] 4.5 Checking the adequacy of the identification;

[0068] 4.6 Stored Identification.

[0069] Description of the solution

[0070] The solution refers to an evaluation procedure whose steps can be performed in different environments that are known and that can be assumed. Several implementations of aspects of the described system and method for evaluating Identification and Its quantification, which are encompassed by the present invention, can be Implemented in various computer systems, environments and configurations.

[0071] Its application is described in the context of the system shown in Figure 2, which is taken as an example.

[0072] Figure 2 shows the technical infrastructure and the relational connection of the parts that are necessary to realize the solution and it includes the following 4 parts:

[0073] 2.1 The part that precedes the ID quantification and consists of the collection of Personal Data records from the Infrastructure of the controller / processor;

[0074] 2.2 Data preparation part, while this segment takes place:

[0075] 1.2 Structuring the information in the Datasets of Personal Data;

[0076] 1.3 Assigning appropriate values to all attributes of Personal Data;

[0077] 1.4 Grouping of Personal Data records depending on assigned attribute values.

[0078] 2.3 The part that consists of the processing of personal data where the operations are carried out:

[0079] 1.5 Sorting records within groups in descending order and

[0080] 1.6 Calculation of ID quantification values at appropriate intervals.

[0081] 2.4 Section on Preservation of Personal Data Identification.

[0082] Personal data at controllers / processors are stored in so-called Datasets of Personal Data that reveal to a greater or lesser extent the Identity of Personal Data Subjects through the records kept about them. In the section on the collection of records 2.1, the potential sources of records from the Datasets of personal data that an entity owns are shown symbolically.

[0083] The Controller has a certain number of different Datasets of Personal Data, whereby Personal Data for a particular subject is stored in a Dataset of Personal Data containing attributes. Based on the attributes, the Subjects of the personal data can be identified to a certain extent which is called "identifiability". The way the attributes are evaluated is based on the potential to Identify the natural person behind the personal data using one attribute or a combination of multiple attributes.

[0084] In segment 2.2 these records are structured (1.2) in such a way that It is determined which attributes of personal data exist in a given Dataset and for each attribute or group of attributes a value is assigned (1.3), depending on the degree of identification of the subject that it is (attribute) can produce it. As the last step in this step, grouping (1.4) is performed, whereby records from different Datasets are grouped in intervals from 1 to n. records belong to a given interval according to the highest value that the attributes have.

[0085] In the section that serves to process personal data 2.3, sorting is performed in descending order according to the assigned values in each of the intervals (1.5), starting from the entry with the largest number of N values, then N-1 values, and so on until the last Interval. In the records arranged in this way, the values are calculated, and the Identification is evaluated, that is, the quantification is performed in the corresponding Intervals (1.6).

[0086] Identification is always a significant aspect in the protection of personal data and procedures to reduce identification such as pseudo-anonymization, anonymization,... are used, but they are not based on quantification and assessment of identification. Before applying these procedures, an Identification quantification should be applied to evaluate what identification potential the records possess and how much identification will be preserved after the Datasets are modified by any of the procedures. The identification should then be re evaluated to determine if the retention of the identification is adequate after the modification has been made. Step 2.4, preservation of identification, defines the difference between the initial assessment of the quantified identification and that Identification which is considered adequate after application of procedures to reduce the identification.

[0087] Figure 3 is a view of the entire system with Its components and modules. The system (3.0) consists of 3 parts:

[0088] 3.1 Processor;

[0089] 3.2 Interface;

[0090] 3.3 Memory,

[0091] Memory (3.3) includes two components: modules (3.4) and data (3.5).

[0092] There are 7 modules (3.4) namely:

[0093] 3.4.1 Data collection module;

[0094] 3.4.2 Data structuring module;

[0095] 3.4,3 Value assignment module;

[0096] 3.4.4. Data grouping module;

[0097] 3.4.5 Data sorting module;

[0098] 3.4.6 Identification evaluation module; 3.4.7 Identification storage module.

[0099] The data (3.5) Include:

[0100] 3.5.1 Dataset of Personal Data;

[0101] 3.5.2 Other data.

[0102] The system implementation of Figure 3 may include at least one processor 3.1, input / output interface 3.2, memory 3.3. A processor may be implemented with one or more microprocessors, microcomputers, microcontrollers, central processing units, and / or any devices that process data based on operational Instructions. One of processor 3.1 retrieves and executes computer-readable instructions that are stored or stored in memory 3.3.

[0103] Interface 3.2 allows the system to communicate with other computing devices, such as file structures, web services, APIs, and databases from which personal data information is retrieved (as in Figure 2). The input / output interface 3.2 can enable communications within multiple networks and protocols such as wired / wireless, cable, mobile or satellite networks, through one or more ports to connect the required number of devices from which personal data is read.

[0104] Any computer-readable media such as temporary memory, persistent memory, hard disks, dynamic memory, read-only memory, optical disks, programmable memory, flash memories, and magnetic tapes are examples of Memory 3.3. It includes modules 3.4 and data 3.5.

[0105] Modules 3.4 and 3.5 can be Implemented through programs, data structures, objects, components, etc. that perform certain tasks, functions or create certain data structures. In one implementation, modules 3.4 include 3.4.1 Data Collection Module; 3.4.2 Data structuring module; 3.4.3 Value assignment module; 3.4.4. Data grouping module; 3.4.5 Data sorting module; 3.4.6 Identification evaluation module; 3.4.7 Identification storage module.

[0106] Data 3.5 serves, among other things, to store data, whether generated or received through one of the modules 3.4. they may also Include database 3.5.1 and other data 3.5.2, The data generated as a result of the execution of one or more modules is saved as Other data 3.5.2.

[0107] The disclosure relates to system(s) and method(s) for measuring through quantification the identification of personal data from Datasets of Personal Data. Identification is quantified in terms of the value of attributes that are evaluated to quantify their potential to identify the holder of personal data. The identifier is quantified in a predefined range from 1 to n which is finite.

[0108] Referring to Figure 3, the order In which the method is described should not be limiting. Any modification of the method such as addition, subtraction or other change in the steps that will produce the same results, that is, there will be no deviation from the context, application and scope is within the scope of the method. Further, the method may be implemented in any suitable hardware, software, or combination thereof. However, for ease of explanation, in the applications described below, the method may be considered to be implemented within the infrastructure and system of Figure 2.

[0109] Personal data records are collected by the controller / processor infrastructure (1.1) and are actually presented through attributes. The proposed procedure for evaluating the Identification of the Subject of personal includes a structuring step (1.2) and a step assigning values to attributes or a combination of attributes (1.3).

[0110] At the same time, for each attribute or combination of attributes in accordance with the scale from 1 to n (where 1 represents the index for the lowest possibility of identification while n value for the highest possibility of Identification) a score (1.3) is assigned.

[0111] A combination of attributes, based on the potential of a particular set of attributes to identify a natural person, is assigned a score. A combination of attributes can only be applied to a group of attributes that will Increase the identification score, where the value of the group must be higher than the highest value in the attribute group. Based on this all attributes in the group receive the grade assigned to the group. For example, a combination of date of birth, place of birth, and gender as a group (or address and phone) have a much higher identification score than all individual attribute values.

[0112] The procedure is used to evaluate the possibility of Identification of personal data by quantification in a Dataset, bu t the real value is obtained when they are compar ed based on the possibility of identification In the controller, process, service, ...

[0113] Within the segments based on the Personal Data Subjects, the following steps are repeated: all attributes of the personal data are marked with the corresponding value based on a predefined table of values from 1 to n, where n is the highest degree of identification, assignment 1 is the lowest. The personal data (1.4) that have at least one highest value n in one group are grouped; in the second group the personal data with the highest value n-1, and so on until the last group with the highest value 1. In this way, at most n groups are obtained for each Dataset of personal data. Within the groups, the (1.5) entries are sorted in descending order by the largest number of n, then the largest number of (n-1), and so on up to 1. This way, ordered subgroups are obtained in each group.

[0114] In each group, the value (1.6) is calculated for the ordered subgroups in the corresponding interval (i, i+1) where i=0,1,2,...,n-1 in the following way, For the ith group, a sum (Sr) of the values for each record is calculated, and then a sum (S) of all the values in that subgroup is calculated. Then, for each record, the IDr value in the interval (i, i+1) is calculated as IDr=i+Srs / S, where Srs is the sum of all Srs starting from the current record to the last record.

[0115] In each group in the Datasets, the value for the ordered subgroups is calculated in the corresponding interval (i, i+1) where i=0,1,2,...,n-1 in the following way.

[0116] First, the parameters used are described.

[0117] 1. Ds indicates the number of Datasets

[0118] 2. j denotes the counter for Ds, (j=1,2..., Ds)

[0119] 3. i denotes interval counter, (i=0 is Interval (0,1), i-1 is interval (1,2),.., i=n-1 is interval (n-1,n))

[0120] 4. Kijdenotes the group from the jthDataset of personal data in the interval (i,i+1)

[0121] 5. PD_KijIndicates the value of the Personal Data in the group Kij, 1=0,1, 2, ..n-1, j=1,2...,Ds

[0122] The sums S_ Kijare calculated for each group Kij: where I is the number of elements in the group Kij.

[0123] Next, sums are calculated for each subgroup within the groups. The following parameters are used for this. 1. s, which Indicates the number of subgroups arranged in descending order according to the largest number of the value of the Personal Data PD_ Kij

[0124] 2. t, which indicates a counter for subgroups in PD_ Kij, (1=1,2..., s)

[0125] 3. which indicates the value of the Personal Data in the subgroup t of Kij, i=0,1,2,..,(n-1), j= 1,2..., Ds, t=1,2..., s

[0126] The sums for each subgroup in the Kijtgroups are calculated. where m is the number of elements in the Kijt subgroup.

[0127] Finally, is calculated, which indicates the value of the Personal Data In the appropriate interval in the subgroup

[0128] For subgroups that have the same elements, one (same) IDr value is calculated.

[0129] With the proposed procedure, it is possible to sort all groups in descending order in all segments of Personal Data Datasets and Personal Data Subjects and at the same time obtain a sequence of records for Identification of all records of personal data for the controller.

[0130] If there is a deformation in the distribution of values in that segment, it is recommended to remove the values 1 in the largest record and apply the proposed method again. In this way, the distribution of values will be improved.

[0131] This completes step (1.6) for the initial quantification of the Identity, but it can be repeated as shown in Figure 4, which actually explains step (1.7) for saving the identity.

[0132] The step (1.7) that follows the initial quantification of the Identification results in the preservation of the adequately modified Identification of the Personal Data.

[0133] Figure 4 is a block diagram showing the process of adequate ID quantification. The steps in the process of adequate ID quantification of the data have the following meaning:

[0134] 4.1 The first step of the process is the collection of data and their attributes from the initial Dataset;

[0135] 4.2 The second step consists of ID quantification and forwarding the information about the Identification to step 4.5 (check for adequacy of the ID quantification) for the purpose of comparison to determine the degree of preservation of the Identification;

[0136] 4.3 The third step is the modification of the Datasets depending on the adequacy of the Identification to be achieved. At the same time, the modification can be done using different procedures, but each of them will mean removing part of the attributes from the Datasets of personal data;

[0137] 4.4 The fourth step is repeating the identification quantification procedure after the modification;

[0138] 4.5 The fifth step is checking whether the quantification of the Identification is adequate. If It is not adequate, go to step 4.3 (re-modification), and if it is adequate, go to step 4.6; 4.6 The sixth step is the realization of the preserved Identification which can be presented in a quantitative form.

[0139] Adequacy, which is mentioned in the process of saving the Identification, depends on the assessment, that is, on the requirements of the Controller / Processor, which is the degree that is adequate, how the intervals from 1 to n are defined (for example, with which score a pseudoanonymization) and the given processing context, which dictates what is adequate (for example, anonymization is required for personal data used for statistical purposes).

[0140] EXAMPLE in order to describe the procedure with an example, a scale with values is given, in this case a rating in the rank of 1 to 5 of the identification based on the attributes of the personal data records with implicit definitions and explicit enumeration of the attributes (Table 1). Users can extend the scale with additional degrees from 1 to n.

[0141] Table 1: Example of Definitions of Identification

[0142] According to the definitions in Table 1, the attributes are evaluated with grades, whereby the record R1 according to the grades is obtained from personal data such as email with a grade of 4 and EMBG and Social Security number with grades of five.

[0143] For simplicity, this example takes 14 records from different Datasets. In the assumed 14 records (R1, R2, ..., R13, R14) all values of personal data attributes with values from 1 to 5 are indicated. Table 2: Value assignement of attributes

[0144] Next, the personal data that have at least one highest value of 5 are grouped in one group, In the second group the personal data with the highest value of 4 and so on until the last group with the highest value of 1. In this way, a maximum of 5 groups are obtained for each Dataset. Within groups, records are sorted in descending order by the largest number of 5, then the largest number of 4, and so on to 1.

[0145] For the group of records having at least one largest value 5 (R1, R2, R6, R9, R10, R14), the following ordered records are obtained (R1, R9, R14, R10, R6, R2). Table 3: Evaluation of the records ie quantification of the identification

[0146] In this way ordered subgroups are obtained in each group. in each group, a value is calculated for the ordered subgroups in the corresponding interval (i, i+1) where i=0, 1,2,..., 4. In the example, the ID values for this group are calculated as follows:

[0147] First, the sum (Sr) of the values for each record is calculated (for R1 the sum Sr is 14, for R9 it is 10 ...)

[0148] Next, the surn (S) of all values in this subset is calculated. For this subgroup S-82.

[0149] Then, for each record, the IDr value in the interval (4, 5) is calculated as IDr=4+Srs / S, where Srs is the sum of all Srs starting from the current record to the last record.

[0150] In this particular example, for RIO the IDr value is obtained as IDr=4+(18+16+14) / 82=4.58S366.

[0151] For subgroups that have the same elements (in this example R9 and R14), the same value is obtained for IDr=4.829268. In this way It is possible to sort all groups in descending order in all segments of Datasets and Data Subjects and at the same time obtain a record order for the Identification of all personal data records for the controller.

[0152] The example given is of an Illustrative nature and refers to a specific case.

Claims

PATENT CLAIMS1. A procedure for the quantification of identification of personal data that includes a Dataset of personal data with attributes that have the potential to be identified by the holder of personal data, in a predefined scope is designated by Including a step of structuring (1.2) of personal data according to attributes and step assigning values to attributes or combination of attributes (1.3), where for each attribute or combination of attributes according to a scale from 1 to n in which 1 represents an index for the lowest possibility of identification, while n a value for the highest possibility of identification, on the basis of evaluated attributes or a combination of attributes personal data are grouped. (1.4), where a maximum of n groups are obtained for each set of personal data, then, within the groups, the records are sorted (1.5) In descending order into subgroups according to the largest number of highest scores, a value is calculated for the subgroups thus arranged (1.6) for the summary scores of the attributes of each record in a subgroup and the sum of scores from the beginning of the interval to the end of the descending sequence according to a formula that predicts the specific interval and the ratio between these two sums, and results in a step that follows the initial quantification of the identification, of saving the personal data (1.7) modified with appropriate identification quantification values.

2. A procedure including a hardware system or a computer-enabled environment intended for carrying out an identification quantification procedure, which includes at least one processor (3.1), input / output interface (3.2), memory (3.3), wherein the processor is capable of downloading and executing computer-readable Instructions that are stored or stored in memory (3.3) and interface (3.2) allows the system to communicate with other computing devices such as data structures, web services, APIs and databases from which personal data information is retrieved, memory indudes modules (3.4) and data (3.5) is distinguished by the fact that, modules 3.4 implemented through programs, data structures, objects, components that perform certain tasks, functions or create certain data structures Include, data collection module (3.4.1), data structuring module (3.4.2), value assignment module (3.4.3), data grouping module (3.4.4), data sorting module (3.4.5), identity evaluation module (3.4.6), module to preserve identification (3.4.7).

3. A hardware system or a computer-implemented solution In an environment Intended for the implementation of a data processing procedure, In which the Identification quantification procedure takes place according to claim 1, which includes, a section for downloading Datasets of personal data (2.1), a section fortheir preparation (2.2), a part for processing (2.3) of that data as well as a part for saving (2,4) is indicated by the fact that In the part of preparation the data is structured (1.2) in a way that determines which attributes of personal data in a given Dataset exist and each attribute or group of attributes is assigned a value records from different Datasets are grouped into intervals from 1 to n according to the highest value, which the attributes have, thus structured records with assigned values and appropriately grouped pass to the processing section which represents an appropriatehardware or software processing environment-module, in which sorting is performed into subgroups in descending order, the same according to the number of evaluated attributes are grouped and evaluated starting from the entry with the largest number of N values, then N-1 values and so on until the last interval, in the records arranged in this way, the total values of the subgroup and the value of the interval from the special member to the end of the sequence are calculated, so in combination with the number of the current sequence, the identification value of each individual record is determined and this data is saved in the section for conservation (2.4).

4. A procedure for the quantification of the quantification of the identification of personal data In accordance with any of the previous requirements (which includes a predetermined adequacy by the controller), is Indicated In that, depending on the requirements of the control, it can be applied in an adjustment procedure to the controller's requirements by using a step to check the adequacy of the quantification and a step to modify the data Dataset, by removing part of the attributes from the Datasets of personal data, repeating the procedure of quantification of The identification is adequate, If it is not adequate, repeated modification is carried out the step is to realize the saved identification to present it In a quantitative form.

Images