- Patent Title: Privacy-sensitive training of user interaction prediction models
-
Application No.: US18350860Application Date: 2023-07-12
-
Publication No.: US12147500B2Publication Date: 2024-11-19
- Inventor: Lukas Zilka
- Applicant: GOOGLE LLC
- Applicant Address: US CA Mountain View
- Assignee: GOOGLE LLC
- Current Assignee: GOOGLE LLC
- Current Assignee Address: US CA Mountain View
- Agency: Brake Hughes Bellermann LLP
- Main IPC: G06F18/214
- IPC: G06F18/214 ; G06F17/18 ; G06F18/2415 ; G06N3/02 ; G06N20/00 ; G06V10/46

Abstract:
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for collaboratively training an interaction prediction machine learning model using a plurality of user devices in a manner that respects user privacy. In one aspect, the machine learning model is configured to process an input comprising: (i) a search query, and (ii) a data element, to generate an output which characterizes a likelihood that a given user would interact with the data element if the data element were presented to the given user on a webpage identified by a search result responsive to the search query.
Public/Granted literature
- US20230350978A1 PRIVACY-SENSITIVE TRAINING OF USER INTERACTION PREDICTION MODELS Public/Granted day:2023-11-02
Information query