# US 10,484,868 B2 · Configuring privacy policies by formulating questions and evaluating responses > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,484,868 B2 - Document ID: US10484868B2 - Status: Granted - Kind: B2 - Application number: 15/407,887 - Filed: 2017-01-17 - Published: 2018-07-19 - Granted: 2019-11-19 - Earliest claimed: 2017-01-17 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Marco Pistoia; Omer Tripp - Web page: https://patentgrep.com/patent/US10484868B2 ## CPC - H04W 12/02: Protecting privacy or anonymity, e.g. protecting personally identifiable information [PII] - G06F 21/604: {Tools and structures for managing or administering access control systems} - G06F 21/6245: {Protecting personal data, e.g. for financial or medical purposes} - G06N 20/00: Machine learning - H04L 63/20: {for managing network security; network security policies in general (filtering policies H04L63/0227)} - H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract Configuring a privacy policy by identifying one or more applications that are installed on a mobile device. A set of privacy-related questions are formulated based upon the one or more identified applications. A response to the set of privacy-related questions is received from a user. One or more classified privacy instances are determined for the user from the received response. A latent, implicit privacy policy is established from the one or more classified privacy instances. ## Claims ### Claim 1 A method for configuring a privacy policy, the method comprising: identifying one or more applications that are installed on a user's mobile device; formulating a set of privacy-related questions based upon the one or more identified applications; receiving a response from the user to the set of privacy-related questions; determining one or more classified privacy instances for the user from the received response; and establishing a latent, implicit privacy policy from the one or more classified privacy instances using a machine learning classification procedure; receiving a new privacy instance for classification; and performing a calculation to determine a proximity of a new privacy instance to each of the one or more classified privacy instances for the user, the calculation being performed using a natural distance metric that considers an intensity level of the new privacy instance with respect to a normalized average intensity level of data that the user is willing to release based upon the received response. ### Claim 2 (depends on 1) The method of claim 1 wherein the machine learning classification procedure comprises a K-star clustering-based classification method. ### Claim 3 (depends on 2) The method of claim 2 wherein the K-star clustering-based classification method is performed by defining a metric space such that the new privacy instance is projected into the metric space. ### Claim 4 (depends on 1) The method of claim 1 further comprising classifying the new privacy instance as one of legitimate or illegitimate, based on the proximity of the new privacy instance to each of the one or more classified privacy instances. ### Claim 5 (depends on 1) The method of claim 1 wherein the calculation is performed using a natural distance metric that considers a data category related to the new privacy instance. ### Claim 6 A computer program product comprising a non-transient computer-readable storage medium having a computer-readable program stored therein, wherein the computer-readable program, when executed, causes a computer to perform a method for configuring a privacy policy, the method comprising: identifying one or more applications that are installed on a user's mobile device; formulating a set of privacy-related questions based upon the one or more identified applications; receiving a response from the user to the set of privacy-related questions; determining one or more classified privacy instances for the user from the received response; and establishing a latent, implicit privacy policy from the one or more classified privacy instances using a machine learning classification procedure; receiving a new privacy instance for classification; and performing a calculation to determine a proximity of a new privacy instance to each of the one or more classified privacy instances for the user, the calculation being performed using a natural distance metric that considers an intensity level of the new privacy instance with respect to a normalized average intensity level of data that the user is willing to release based upon the received response. ### Claim 7 (depends on 6) The computer program product of claim 6 wherein the machine learning classification procedure comprises a K-star clustering-based classification method. ### Claim 8 (depends on 7) The computer program product of claim 7 further configured for performing the K-star clustering-based classification method by defining a metric space such that the new privacy instance is projected into the metric space. ### Claim 9 (depends on 6) The computer program product of claim 6 further configured for classifying the new privacy instance as one of legitimate or illegitimate, based on the proximity of the new privacy instance to each of the one or more classified privacy instances. ### Claim 10 (depends on 6) The computer program product of claim 6 further configured for performing the calculation using a natural distance metric that considers a data category related to the new privacy instance. ### Claim 11 An apparatus for configuring a privacy policy, the apparatus comprising a processor and a memory coupled to the processor, wherein the memory comprises instructions which, when executed by the processor, cause the processor to: identify one or more applications that are installed on a user's mobile device; formulate a set of privacy-related questions based upon the one or more identified applications; receive a response from the user to the set of privacy-related questions; determine one or more classified privacy instances for the user from the received response; and establish a latent, implicit privacy policy from the one or more classified privacy instances using a machine learning classification procedure; receive a new privacy instance for classification; and perform a calculation to determine a proximity of a new privacy instance to each of the one or more classified privacy instances for the user, the calculation being performed using a natural distance metric that considers an intensity level of the new privacy instance with respect to a normalized average intensity level of data that the user is willing to release based upon the received response. ### Claim 12 (depends on 11) The apparatus of claim 11 wherein the machine learning classification procedure comprises a K-star clustering-based classification method for defining a metric space such that the new privacy instance is projected into the metric space.