Search

WO-2026096015-A1 - SELECTION OF THE PRIMARY USER FOR A MULTI-USER DEVICE

WO2026096015A1WO 2026096015 A1WO2026096015 A1WO 2026096015A1WO-2026096015-A1

Abstract

A system and method for identifying the primary user of a shared device leverages authorization events, such as logins of consumers to various publisher websites or apps, as well as data contained in a hypertext transfer protocol (HTTP) header such as user agent and IP address, to determine the user that is most frequently using a multi-user device and most likely to be using that device in the future when a targeted message is sent, while at the same time maximizing the stability of user assignment to those who actually live together in the same household or at the same address. This information is stored in a holistic online reach identity graph, which links cookies and/or devices to identifiers for users, and assigns a value to each user relative to the likelihood that such user is the primary user or less active user of the corresponding device.

Inventors

  • CHETTAYAR, Krishna
  • Tichenor, Matthew
  • WOOD, JOHN
  • HAN, Ellie
  • HOWELL, Connor
  • SIMONSON, Kyle
  • SALDANHA, Luca
  • WEBER, JULIEN

Assignees

  • LIVERAMP, INC.

Dates

Publication Date
20260507
Application Date
20250715
Priority Date
20241028

Claims (20)

  1. 1. A method for identifying a primary user of a shared device, comprising: receiving a plurality of authorization events associated with a device, each authorization event corresponding to a user identifier; storing the authorization events, device information, and corresponding user identifiers in a database; constructing a holistic online reach graph based on the stored authorization events, and associated device details and observations, wherein the graph comprises nodes corresponding to device identifiers, user behavioral and location data, and user identifiers; applying one of an algorithm or a machine-learning approach to the holistic online reach graph to determine a likelihood that each user identifier corresponds to a primary user of the device; assigning a value to each user identifier for the device, wherein the value is proportional to the likelihood that the user identifier corresponds to the primary user; determining the primary user of the device based on the assigned values; and updating an online identity graph with the determined primary user information.
  2. 2. The method of claim 1, wherein the authorization events comprise login events to publisher websites or applications.
  3. 3. The method of claim 1, wherein the device identifiers comprise one or more of cookies, mobile ad IDs, CTV IDs, and proxies for such identifiers associated with the device.
  4. 4. The method of claim 1, wherein the user and household identifiers are unique for each user and household within a particular geography. Attorney Docket No. RAMP-00313-WO
  5. 5. The method of claim 1, further comprising the step of using the updated online identity graph to target digital messaging to the primary user of the device.
  6. 6. The method of claim 1, wherein the value assigned to each user identifier is between 0 and 1.
  7. 7. The method of claim 1, further comprising receiving event and device signal information from a tracking pixel, whether in batch or real time, from a publisher website or mobile app provider in response to an authorization event.
  8. 8. A system for identifying a primary user of a shared device, comprising: a processor; a memory coupled to the processor and storing instructions that, when executed by the processor, cause the system to: receive a plurality of authorization events associated with a device, each authorization event corresponding to a user identifier; store the authorization events and corresponding user identifiers in a database; construct a holistic online reach graph based on the stored authorization events, wherein the graph comprises nodes corresponding to device identifiers and user identifiers and at least one of user behavioral and pseudonymous location data; apply an algorithm or a machine-learning approach to the holistic online reach graph to determine a likelihood that each user identifier corresponds to a primary user of the device; assign a value to each user identifier for the device, wherein the value is proportional to the likelihood that the user identifier corresponds to the primary user; determine the primary user of the device based on the assigned values; and Attorney Docket No. RAMP-00313-WO update an online identity graph with the determined primary user information.
  9. 9. The system of claim 8, wherein the authorization events comprise login events to publisher websites or mobile applications.
  10. 10. The system of claim 8, wherein the device identifiers comprise at least one of cookies, mobile Ad IDs, CTV IDs, RampIDs, and proxies associated with the device.
  11. 11. The system of claim 8, wherein the user identifiers are unique for each user within a particular geography.
  12. 12. The system of claim 8, wherein the instructions further cause the system to use the updated online identity graph to target digital messaging to the primary user of the device.
  13. 13. The system of claim 8, wherein the instructions further cause the system to receive device information or user information or both from a publisher tracking pixel signal, or other such mechanism, implemented on a website or mobile application in response to an authorization event.
  14. 14. The system of claim 8, wherein constructing the holistic online reach graph comprises linking nodes corresponding to device IDs from user devices to nodes corresponding to user identifiers within a provider's system.
  15. 15. A method for targeting digital messaging to a primary user of a shared device, comprising: receiving a plurality of authorization events associated with a device, each authorization event corresponding to a user identifier; storing the authorization events and corresponding user identifiers in a database; constructing a holistic online reach graph based on the stored authorization events, wherein the graph comprises nodes corresponding to device identifiers and user identifiers; Attorney Docket No. RAMP-00313-WO applying one of an algorithm or a machine-learning approach to the holistic online reach graph to determine a likelihood that each user identifier corresponds to a primary user of the device; assigning a value to each user identifier for the device, wherein the value is proportional to the likelihood that the user identifier corresponds to the primary user that is most likely to be the dominant user seen in the future; determining the primary user of the device based on the assigned values; retrieving additional information about the primary user from the online identity graph; and sending a targeted digital message to the shared device based on the additional information about the primary user.
  16. 16. The method of claim 15, wherein constructing the holistic online reach graph comprises linking nodes corresponding to device IDs from user devices to nodes corresponding to user identifiers within a provider's system.
  17. 17. A non-transitory computer-readable storage medium storing instructions that, when executed by a processor, cause the processor to: receive a plurality of authorization events associated with a device, each authorization event corresponding to a user identifier; store the authorization events and corresponding user identifiers in a database; construct a holistic online reach graph based on the stored authorization events, wherein the graph comprises nodes corresponding to device identifiers and user identifiers; Attorney Docket No. RAMP-00313-WO apply one of an algorithm or a machine-learning approach to the holistic online reach graph to determine a likelihood that each user identifier corresponds to a primary user of the device; assign a value to each user identifier for the device, wherein the value is proportional to the likelihood that the user identifier corresponds to the primary user; determine the primary user of the device based on the assigned values; and update an online identity graph with the determined primary user information.
  18. 18. The method of claim 17, wherein the authorization events comprise login events to publisher websites or applications.
  19. 19. The method of claim 17, wherein the device identifiers comprise one or more of cookies, mobile Ad IDs, CTV IDs, RampIDs, or proxies associated with the device.
  20. 20. The method of claim 17, further comprising the step of using the updated online identity graph to target digital messaging to the primary user of the device.

Description

Attorney Docket No. RAMP-00313-WO SELECTION OF TH E PRIMARY USER FOR A MULTI-USER DEVICE REFERENCES TO PRIOR APPLICATIONS [0001] This application claims priority to US provisional patent application no. 63/712,904, filed October 28, 2024. Such application is incorporated by reference herein in its entirety. BACKGROUN D OF THE INVENTION [0002] Personally Identifiable Information (PH) refers to data that can be used to identify, contact, or locate a specific individual or user. This includes direct identifiers like names, addresses, and social security numbers, as well as indirect identifiers that can be combined with other information to identify a person. [0003] Identity resolution is the process of combining multiple identifiers and data points to create a unified, accurate profile of an individual user. It involves linking these disparate pieces of information from different sources to form a cohesive view of a person's identity across digital and offline interactions. [0004] The data used for identity resolution may be stored in a data structure known as an identity graph. An identity graph is a database that connects various data to a single user profile, enabling organizations to track and understand user behavior across different platforms and devices. [0005] Identity graphs are often differentiated as being first-party, second-party, or third-party graphs. A first-party identity graph is one that is created and owned by a single organization using data collected directly from the users with which it interacts. A second-party identity graph is the first-party graph of a different organization; data may be shared from second-party identity graphs through a partnership between two or more organizations sharing their first- party data. Third-party identity graphs contain data compiled by data aggregators using data Attorney Docket No. RAMP-00313-WO from multiple sources, generally without direct relationships with the users. The owners of these third-party identity graphs may provide services to the owners of first-party graphs, whereby the first-party graphs are improved in various ways using data from the provider's more comprehensive third-party graph. [0006] Onboarding in digital advertising refers to the process of integrating offline customer data into online digital marketing platforms. This allows advertisers to connect their first-party customer information, such as customer relationship management (CRM) data, loyalty program details, or offline purchase histories, with online identifiers like cookies or email addresses. The onboarding process typically involves working with a data onboarding provider who securely matches and anonymizes the offline data with online profiles. This creates a bridge between physical and digital customer interactions, enabling more personalized and targeted messaging campaigns across various digital channels. Successful onboarding enhances audience segmentation, improves cross-channel marketing efforts, and allows for more accurate measurement of marketing impact by connecting online ad exposures with offline behaviors. Global identifiers may be used for onboarding, such as the RampID identifiers supplied by LiveRamp, Inc. of San Francisco, California. [0007] It is not uncommon for users to share electronic communications devices, including desktop computers, laptop computers, tablets, mobile phones, and connected televisions (CTVs). Even mobile phones, which are often assumed to be highly personal devices, are shared more often than previously thought. It has been found that more than ten percent of mobile devices are shared among multiple users regularly. Investigations by the inventors hereof have shown that an estimated 83% of all electronic communications devices have multiple users. [0008] The fact that devices are often shared greatly complicates the task of targeted messaging to a device, since the party sending the message cannot know which user of the Attorney Docket No. RAMP-00313-WO multi-user device will see the message. It is therefore important and valuable to determine the primary user of the device, that is, the user who is most likely to see a message that is sent to the device. Previous attempts to determine the primary user have been quite simplistic, such as simply assuming that the first-seen or last-seen user is the primary user, but this does not generate good results. The first-seen approach generates stability in ID assignment to a device, but is often inaccurate. The last-seen approach of ID assignment to a device gets better accuracy, but is highly unstable as the identity of the supposed primary user changes frequently. SUMMARY OF THE INVENTION [0009] The invention is directed to a system and method for identifying the primary and less active users (secondary, tertiary, etc.) of a shared device for use in targeting digital messaging and maximizing message effectiveness. [0010] In certain embodiments, the invention leverages authori