Data processing method and apparatus, device, and computer-readable storage medium

Patent metadata

Field	Value
Publication number	US-12254121-B2
Application number	US-202218072313-A
Country	US
Kind code	B2
Filing date	Nov 30, 2022
Priority date	May 26, 2021
Publication date	Mar 18, 2025
Grant date	Mar 18, 2025

Abstract

A data processing method includes: acquiring a first intersection set, acquiring a second intersection set, calculating an intersection between the first intersection set and the second intersection set to obtain an intersection result set that includes an intersecting portion of the first intersection data and the second intersection data, and obfuscating the intersection result set to obtain an obfuscation set that includes obfuscated data based on data in the second intersection set and an intersection data set based on the intersection result set.

First claim

What is claimed is:

1. A data processing method, performed by a first node comprising a computer device, the data processing method comprising:
acquiring a first intersection set comprising N pieces of first intersection data, the first intersection data comprising a first plurality of user identifiers from raw data from a storage of the computer device, and N being a positive integer;
acquiring a second intersection set comprising M pieces of second intersection data, the second intersection data comprising a second plurality of user identifiers received from a second node, and M being a positive integer;
calculating an intersection between the first intersection set and the second intersection set to obtain an intersection result set that includes an intersecting portion of the first intersection data and the second intersection data;
obfuscating the intersection result set to obtain an obfuscation set that comprises:
obfuscated data based on data in the second intersection set, and
an intersection data set based on the intersection result set,
wherein the obfuscated data is not correlated with data in the intersection data set;

generating a first training data set based on the obfuscation set, wherein the first training data set comprises a plurality of obfuscated user identifiers of the obfuscation set aligned with first user data;
calculating a first gradient of the first training data set;
transmitting the obfuscation set to the second node, such that the raw data is not exposed to the second node, to cause the second node to calculate and transmit a second gradient to a third node;
transmitting the first gradient to the third node; and
receiving from the third node a total gradient based on the first gradient and the second gradient.

2. The data processing method according to claim 1 , wherein the obfuscating comprises:
selecting, from the second intersection set according to an obfuscation parameter, P pieces of second intersection data that does not belong to the intersection result set as the obfuscated data, P being a positive integer; and
adding the obfuscated data to the intersection result set to obtain the obfuscation set.

3. The data processing method according to claim 1 , wherein the acquiring the first intersection set comprises:
acquiring first signature data, the first signature data being data obtained based on first encrypted data being signed using a private key of the second node, the first encrypted data being data obtained based on encrypting first to-be-processed data; and
calculating the first intersection data corresponding to the first signature data according to the first signature data; and
the acquiring the second intersection set comprises:
acquiring the second intersection data, the second intersection data being data obtained based on second signature data being mapped, the second signature data being data obtained based on mapped data being signed using the private key of the second node, the mapped data being data obtained based on second to-be-processed data being mapped.

4. The data processing method according to claim 3 , wherein the first encrypted data is obtained by operations including:
mapping the first to-be-processed data by using a first mapping rule to obtain first intermediate data;
acquiring a public key of the second node, and encrypting an original random number by using the public key of the second node to obtain an encrypted random number corresponding to the first intermediate data; and
generating the first encrypted data according to the first intermediate data and the encrypted random number corresponding to the first intermediate data.

5. The data processing method according to claim 4 , wherein the calculating the first intersection data comprises:
calculating original signature data according to the original random number and the first signature data, the original signature data matching data obtained based on the first intermediate data being signed using the private key of the second node; and
mapping the original signature data by using a second mapping rule, to obtain the first intersection data corresponding to the first signature data.

6. The data processing method according to claim 1 , wherein the acquiring the first intersection set comprises:
encrypting, based on an encryption algorithm, second intermediate data through a public key of the first node to obtain third encrypted data, the second intermediate data being obtained based on first to-be-processed data being mapped according to a third mapping rule;
transmitting the third encrypted data to the second node; and
receiving the first intersection data returned by the second node to obtain the first intersection set comprising the first intersection data; the first intersection data being obtained based on the third encrypted data being encrypted through a public key of the second node based on the encryption algorithm;
wherein the acquiring the second intersection set comprises:
receiving fourth encrypted data of the second node, the fourth encrypted data being obtained based on third intermediate data being encrypted through the public key of the second node based on the encryption algorithm, the third intermediate data being obtained based on second to-be-processed data of the second node being mapped through the third mapping rule; and
encrypting the fourth encrypted data through the public key of the first node to obtain the second intersection data, so as to obtain the second intersection set comprising the second intersection data; and
wherein the encryption algorithm is a commutative encryption algorithm.

7. The data processing method according to claim 1 , wherein the acquiring the first intersection set comprises:
mapping and calculating, according to a fourth mapping rule, first to-be-processed data recorded by the first node to obtain the first intersection data; and
the acquiring the second intersection set comprises:
mapping and calculating a plurality of pieces of first to-be-processed data of the first node respectively according to the fourth mapping rule, and obtaining an oblivious polynomial about the first to-be-processed data according to mapping and calculation results, the oblivious polynomial taking the mapping and calculation results as roots;
performing coefficient encryption on the oblivious polynomial through a public key of the first node to obtain a coefficient encryption polynomial;
acquiring an intermediate intersection set, the intermediate intersection set comprising a plurality of result values, one result value in the intermediate intersection set corresponding to one piece of second to-be-processed data of the second node, the result value being obtained in the following manner: substituting fourth intermediate data into the coefficient encryption polynomial to calculate an intermediate result value, and homomorphically calculating the intermediate result value through a homomorphic operation rule to obtain the result value, the fourth intermediate data being data obtained based on the second to-be-processed data of the second node being mapped and calculated according to the fourth mapping rule; and
decrypting the result values in the intermediate intersection set through a private key of the first node to obtain the second intersection data.

8. The data processing method according to claim 7 , wherein the homomorphically calculating comprises:
performing homomorphic scalar multiplication on the intermediate result value and a random number, and performing homomorphic addition with the fourth intermediate data corresponding to the intermediate result value, to obtain the result value.

9. A first node comprising a data processin

Assignees

• Tencent Tech Shenzhen Co Ltd
• Tencent Tech Shenzhen Company Ltd

Inventors

• Fu Fangcheng
• Jiang Jie
• Pan Junwei
• Hou Chen
• Xue Huanran
• Cheng Yong
• Liu Yuhong
• Chen Peng
• Tao Yangyu

Classifications

• G06F21/602

  Providing cryptographic facilities or services · CPC title

• G06Q30/0242

  Determining effectiveness of advertisements · CPC title

• G06F21/645 Primary

  using a third party · CPC title

• G06F21/6245 Primary

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