Centralized privacy management system for automatic monitoring and handling of personal data across data system platforms

1. A method of operating a privacy management system for managing personal data within a plurality of client data systems, the plurality of client data systems including a first data system having a memory element, the method comprising:

receiving a first input indicative of a first user activity in accessing personal data stored within the memory element;

receiving a data set within the first input, differentiating personal data from general data contained within the data set, and generating metadata for the differentiated personal data;

creating an activity model based on the first input, the activity model indicative of typical activity in accessing personal data stored in the memory element;

receiving a second input indicative of a second user activity in accessing personal data stored within the memory element;

accessing the generated metadata to determine whether the second user activity affects personal data;

recognizing, according to the activity model, the second user activity as being anomalous to the typical activity in accessing personal data stored in the memory element; and

generating, as a result of recognizing the second user activity as being anomalous, a command that causes at least one of the plurality of client devices to perform an anomaly corrective action.

2. The method of claim 1 , wherein receiving the data set includes receiving a stored data set stored on the memory element, wherein generating metadata includes generating metadata that indicates a storage location of personal data on the memory element, a data structure for the personal data on the memory element, and a storage time of the personal data on the memory element.

3. The method of claim 1 , wherein receiving the second input includes receiving, in the second input, at least one of:

a first signal identifying the client device that supplied the second input;

a second signal indicative of a global location from which the second input was supplied;

a third signal indicative of a storage location of requested personal data among the plurality of client data systems;

a fourth signal indicative of a category of requested personal data; and

a fifth signal indicative of a time of day at which the second input was supplied.

4. The method of claim 3 , wherein receiving the second input includes receiving each of the first, second, third, fourth, and fifth signals.

5. The method of claim 3 , wherein receiving the first input includes receiving, in the first input, at least one of:

a first signal identifying the client device that supplied the second input;

a second signal indicative of a global location from which the second input was supplied;

a third signal indicative of a storage location of requested personal data among the plurality of client data systems;

a fourth signal indicative of a category of requested personal data; and

a fifth signal indicative of a time of day at which the second input was supplied;

wherein creating the activity model includes training a predictive data model using the at least one of the first, second, third, fourth, and fifth signals; and

as a result of the training, outputting a trained classifier that receives as input the second input and that produces as output a prediction of whether second user activity is anomalous.

6. The method of claim 1 , wherein generating the command includes generating an alert command that causes an output device of the at least one of the client devices to output an alert.

7. The method of claim 1 , wherein generating the command includes generating a denial command that causes the at least one of the client devices to deny a request associated with the second user activity.

8. A centralized privacy management system for managing personal data comprising:

a plurality of client data systems in a computerized system, the plurality of client data systems including a first data system having a memory element, the privacy management system including:

a processor configured to communicate with the plurality of client data systems;

the processor configured to receive a first input indicative of a first user activity in accessing personal data stored within the memory element;

the processor programmed to receive a data set within the first input, differentiate personal data from general data contained within the data set, and generate metadata for the differentiated personal data;

the processor programmed to create an activity model based on the first input, the activity model indicative of typical activity in accessing personal data stored in the memory element;

the processor configured to receive a second input indicative of a second user activity in accessing personal data stored within the memory element;

the processor programmed to access the generated metadata to determine whether the second user activity affects personal data;

the processor programmed to recognize, according to the activity model, the second user activity as being anomalous to the typical activity in accessing personal data stored in the memory element; and

the processor programmed to generate, as a result of recognizing the second user activity as being anomalous, a command that causes at least one of the plurality of client devices to perform an anomaly corrective action.

9. The system of claim 8 , wherein the processor, substantially concurrent with receiving the data set stored on the memory element, is programmed to generate metadata that indicates a storage location of personal data on the memory element, a data structure for the personal data on the memory element, and a storage time of the personal data on the memory element.

10. The system of claim 8 , wherein the second input includes at least one of:

a first signal identifying the client device that supplied the second input;

a second signal indicative of a global location from which the second input was supplied;

a third signal indicative of a storage location of requested personal data among the plurality of client data systems;

a fourth signal indicative of a category of requested personal data; and

a fifth signal indicative of a time of day at which the second input was supplied.

11. The system of claim 10 , wherein the second input includes each of the first, second, third, fourth, and fifth signals.

12. The system of claim 10 , wherein the first input includes at least one of:

a first signal identifying the client device that supplied the second input;

a second signal indicative of a global location from which the second input was supplied;

a third signal indicative of a storage location of requested personal data among the plurality of client data systems;

a fourth signal indicative of a category of requested personal data; and

a fifth signal indicative of a time of day at which the second input was supplied;

wherein the processor is programmed to create the activity model by training a predictive data model using the at least one of the first, second, third, fourth, and fifth signals; and

as a result of the training, outputting a trained classifier that receives as input the second input and that produces as output a prediction of whether second user activity is anomalous.

13. The system of claim 8 , wherein the processor is programmed to generate an alert command for causing an output device of the at least one of the client devices to output an alert.

14. The system of claim 8 , wherein the processor is programmed to generate a denial command that causes the at least one of the client devices to deny a request associated with the second user activity.