System for privacy-preserving monetization of big data and method for using the same

Patent metadata

Field	Value
Publication number	US-11088834-B2
Application number	US-201514698678-A
Country	US
Kind code	B2
Filing date	Apr 28, 2015
Priority date	Apr 28, 2015
Publication date	Aug 10, 2021
Grant date	Aug 10, 2021

Abstract

The current invention provides a system and method for Data Owners to share with Data Seekers extracted insights from the Big Data, instead of raw data or anonymized raw data, thus reducing or eliminating privacy concerns on the data owned by the Data Owners. An Oblivious Pseudo Random Function (OPRF) is used, with operations using OPRFs occur over encrypted data, thus Data Owners learn only the primary object from Data Seeker and nothing else about the remainder of Data Owners' data. Similarly, Data Seeker learns a list of associated secondary objects and nothing else about Data Owners' data. The extent of sharing can be limited using a predefined threshold depending how much private information Data Owner is willing to share or Data Seeker is willing to pay.

First claim

What is claimed is:

1. A computer-implemented method for privacy preserving insight sharing, the method comprising:
maintaining, by one or more servers, at least one data structure for a data owner comprising primary objects each comprising a first occurring event, service or good and associated objects each comprising a further event, service or good occurring after the primary object and associated with one or more of the primary objects; and
allowing access to the maintained data while preserving privacy of the data owner, comprising:
receiving, by at least one of the one or more servers, a query comprising an identity of one of the primary objects and an obfuscated list of secondary objects each comprising a further event, service or good occurring after one of the primary objects from a requesting party;
comparing the query to the primary objects of the data owner;
identifying one of the primary objects maintained for the data owner that matches the identity of the primary object in the query from the requesting party;
generating a list of relationships, comprising:
learning, by a machine-learning algorithm, insights into relationships between the primary objects and the associated objects;
computing, using the machine-learning algorithm, association relationships between the matching primary object and two or more of the associated objects for that matching primary object to obtain the list of relationships; and

modifying the list of relationships based on a number of the insights to be shared based on a predefined threshold;
obfuscating, by at least one of the one or more servers, the modified list of the relationships comprising encrypting the associated objects of the data structure for the matching primary object and the relationships to the matching primary object;
transmitting the obfuscated list of the relationships to the requesting party; and
controlling access to the data by the requesting party by computing a set intersection between the obfuscated list of the secondary objects and the obfuscated list of the relationships as results of the query.

2. A method according to claim 1 , wherein the secondary objects and the obfuscated list of the relationships are obfuscated via an Oblivious Pseudo Random Function.

3. A method according to claim 2 , wherein the Oblivious Pseudo Random Function is based on at least one of RSA algorithm, Diffie-Hellman algorithm, or a hashing algorithm.

4. A method according to claim 1 , further comprising the steps of:
obfuscating the list of the secondary objects by computing {H(x1)·r e , H(x2)·r e , . . . , H(xn)·r e };
modifying the obfuscated list of the secondary objects by computing {(H(x1)· re ) d , (H(x2)·r e ) d , . . . , (H(xn)·r e ) d }; and
transmitting the obfuscated list of the relationships to the requesting party in the form of {H(x1) d , H(x2) d , . . . , H(xm) d },
wherein H(x) is the cryptographic hash function, e is the public key of a RSA algorithm, d is a the private key of the RSA algorithm, r is a random integer, the x1, x2, . . . , xn are the secondary objects, and the x1, x2, . . . , xm constitute the list of the relationships.

5. A method according to claim 1 , further comprising:
receiving a payment from the requesting party in exchange for the obfuscated list of the relationships.

6. A method according to claim 1 , further comprising the step of:
selecting the list of the relationships based on at least one of a number of the relationships, a specification from the receiving party, and a strength of the association relationship between the primary object and the associated objects.

7. A method according to claim 1 , wherein the secondary objects comprise a mathematical description of at least one of goods, services, activities, and events.

8. A method according to claim 1 , further comprising:
computing the relationships by the steps of:
maintaining an inventory of goods;
obtaining shopping data on the inventory of the goods; and
computing an association relationship between purchasing one good and purchasing another good based on the shopping data.

9. A method according to claim 8 , wherein the association is positive or negative.

10. A non-transitory computer readable storage medium storing code for executing on a computer system to perform the following steps:
maintaining at least one data structure for a data owner comprising primary objects each comprising a first occurring event, service or good and associated objects each comprising a further event, service or good occurring after the primary object and associated with one or more of the primary objects; and
allowing access to the maintained data while preserving privacy of the data owner, comprising:
receiving a query comprising an identity of one of the primary objects and an obfuscated list of secondary objects each comprising a further event, service or good occurring after one of the primary objects from a requesting party;
comparing the query to the primary objects of the data owner;
identifying one of the primary objects maintained for the data owner that matches the identity of the primary object in the query from the requesting party;
generating a list of relationships, comprising:
learning, by a machine-learning algorithm, insights into relationships between the primary objects and the associated objects;
computing, using the machine-learning algorithm, association relationships between the matching primary object and two or more of the associated objects for that matching primary object to obtain the list of relationships; and
modifying the list of relationships based on a number of the insights to be shared based on a predefined threshold;
obfuscating the list of the relationships comprising encrypting the associated objects of the data structure for the matching primary object and the relationships to the matching primary object;
transmitting the obfuscated list of the relationships to the requesting party; and
controlling access to the data by the requesting party by providing a set intersection between the obfuscated list of the secondary objects and the obfuscated list of the relationships as a result of the query by enabling the requesting party to compare the obfuscated list of the secondary objects and the obfuscated list of the relationships.

11. A computer-implemented system for privacy-preserving insight sharing, comprising:
a storage device to maintain data for a data owner comprising primary objects each comprising a first occurring event, service or good, and associated objects for each of the primary objects, each associated object comprising a further event, service or good occurring after that primary object; and
a server comprising a central processing unit, memory, an input port to receive the uncoded concepts and reference concepts from the database, and an output port wherein the central processing unit is configured to:
allow access to the maintained data while preserving privacy of the data owner, comprising:
receive a query comprising an identity of one of the primary objects and an obfuscated list of secondary objects each comprising a further event, service or good occurring after one of the primary objects from a requesting party;
compare the query to the primary objects of the data owner;
identify one of the primary objects maintained for the data owner that matches the identity of the primary object in the query from the requesting party;
generate a list of relationships, comprising:
learn, by a machine-learning algorithm, insights into relationships between the primary objects and the associated objects;
compute, using the machine-learning algorithm, association relatio

Assignees

• Palo Alto Res Ct Inc

Inventors

• Freudiger Julien
• Rane Shantanu
• Brito Alejandro E
• Uzun Ersin

Classifications

• G06F21/6245 Primary

  Protecting personal data, e.g. for financial or medical purposes · CPC title

• G06Q30/0201

  Market modelling; Market analysis; Collecting market data · CPC title

• G06F16/951

  Indexing; Web crawling techniques · CPC title

• G06F2216/03

  Data mining · CPC title

• H04L2209/24

  Key scheduling, i.e. generating round keys or sub-keys for block encryption · CPC title