User data and personalization models implemented on a blockchain

Patent metadata

Field	Value
Publication number	US-12531847-B2
Application number	US-202218076620-A
Country	US
Kind code	B2
Filing date	Dec 7, 2022
Priority date	Aug 3, 2022
Publication date	Jan 20, 2026
Grant date	Jan 20, 2026

Abstract

Systems and methods for the authorization of access to user data can include the use of one or more blockchains to store the user data and/or an authorization list. The systems and methods can receive and/or obtain an access request. The access request can be processed to determine if the requestor has authorization. The processing can include interactions with a user computing system and/or an authorization list. An authorized access can be provided such that the requestor can read the user data stored on the blockchain with limited copy and/or overwrite access.

First claim

What is claimed is:

1 . A computer-implemented method, the method comprising:
receiving, by a computing system comprising one or more processors, an access request from a third party computing system, wherein the access request is descriptive of a request to access a personalization model associated with a particular user, wherein the personalization model is stored on a blockchain, and wherein the personalization model is trained on training data from a plurality of entities; determining, by the computing system, a particular entity associated with the third party computing system, wherein the particular entity is associated with a web platform; determining, by the computing system, an access action based on whether the particular entity is associated with one or more authorized entities, wherein the one or more authorized entities are determined based on one or more user inputs, wherein the access action is associated with adjusting parameters of the personalization model; adjusting, by the computing system, one or more parameters of the personalization model based on additional data obtained from the third party computing system; and providing, by the computing system, blockchain data associated with the particular user, wherein the blockchain data is associated with a particular blockchain, wherein the blockchain data comprises access to the personalization model.

2 . The method of claim 1 , wherein the access action comprises:
obtaining, by the computing system, input data from the third party computing system; processing, by the computing system, the input data with the personalization model to generate output data; and providing, by the computing system, the output data to the third party computing system.

3 . The method of claim 1 , wherein the personalization model comprises a machine-learned model trained on user data associated with the particular user.

4 . The method of claim 1 , wherein the particular entity is a search engine entity, and wherein the access action further comprises utilizing the personalization model to adjust a ranking of one or more search results.

5 . A computing system, the system comprising:
one or more processors; and one or more non-transitory computer-readable media that collectively store instructions that, when executed by the one or more processors, cause the computing system to perform operations, the operations comprising:
receiving an access request from a third party computing system, wherein the access request is descriptive of a request to access a personalization model associated with a particular user, wherein the personalization model is stored on a blockchain, and wherein the personalization model is trained on training data from a plurality of entities;
determining a particular entity associated with the third party computing system, wherein the particular entity is associated with a web platform;
determining an access action based on whether the particular entity is associated with one or more authorized entities, wherein the one or more authorized entities are determined based on one or more user inputs, wherein the access action is associated with adjusting parameters of the personalization model;
adjusting one or more parameters of the personalization model based on additional data obtained from the third party computing system; and
providing blockchain data associated with the particular user, wherein the blockchain data is associated with a particular blockchain, wherein the blockchain data comprises access to the personalization model.

6 . The system of claim 5 , wherein the operations further comprise:
transmitting a notification to a particular user computing system, wherein the particular user computing system is associated with the particular user, wherein the notification is descriptive of the access request and the particular entity; and receiving user input data from a particular user computing system, wherein the user input data is descriptive of a user response to the access request.

7 . The system of claim 6 , wherein the access action further comprises:
generating a second notification in response to adjusting one or more parameters of the personalization model based on additional data obtained from the third party computing system; and providing the second notification to the third party computing system.

8 . The system of claim 5 , wherein the personalization model comprises a machine-learned model further trained on user data associated with the particular user.

9 . The system of claim 8 , wherein the user data comprises search history data descriptive of previously input search queries.

10 . The system of claim 8 , wherein the user data comprises preference data descriptive of one or more user preferences.

11 . The system of claim 10 , wherein the preference data was generated based on one or more user interactions in a previously-visited web platform.

12 . The system of claim 5 , wherein the access action comprises:
accessing a blockchain node based on the access request; identifying blockchain data associated with the particular user; and obtaining the personalization model.

13 . The system of claim 5 , wherein the particular entity is a social media entity.

14 . The system of claim 5 , wherein the particular entity is a search engine entity.

15 . One or more non-transitory computer-readable media that collectively store instructions that, when executed by one or more computing devices, cause the one or more computing devices to perform operations, the operations comprising:
receiving an access request from a third party computing system, wherein the access request is descriptive of a request to access a personalization model associated with a particular user, wherein the personalization model is stored on a blockchain, and wherein the personalization model is trained on training data from a plurality of entities; determining a particular entity associated with the third party computing system, wherein the particular entity is associated with a web platform; determining an access action based on whether the particular entity is associated with one or more authorized entities, wherein the one or more authorized entities are determined based on one or more user inputs, wherein the access action is associated with adjusting parameters of the personalization model; adjusting one or more parameters of the personalization model based on additional data obtained from the third party computing system; and providing blockchain data associated with the particular user, wherein the blockchain data is associated with a particular blockchain, wherein the blockchain data comprises access to the personalization model.

16 . The one or more non-transitory computer-readable media of claim 15 , wherein the operations further comprise:
generating the additional data based on one or more interactions with the third party computing system.

17 . The one or more non-transitory computer-readable media of claim 15 , wherein determining the access action based on whether the particular entity is associated with the one or more authorized entities comprises accessing an authorization list.

18 . The one or more non-transitory computer-readable media of claim 15 , wherein determining the access action based on whether the particular entity is associated with the one or more authorized entities comprises processing the access request with an authorization block.

19 . The one or more non-transitory computer-readable media

Assignees

• Google Llc

Inventors

• Badr Ibrahim

Classifications

• H04L9/50

  using hash chains, e.g. blockchains or hash trees · CPC title

• G06F16/24578

  using ranking · CPC title

• G06F16/9535

  Search customisation based on user profiles and personalisation · CPC title

• G06F16/9532

  Query formulation · CPC title

• G06F21/31

  User authentication · CPC title