# US 12,192,297 B2 · Real-time suggested actions based on user profile attributes

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 12,192,297 B2
- Document ID: US12192297B2
- Status: Granted
- Kind: B2
- Application number: 17/853,322
- Filed: 2022-06-29
- Published: 2022-12-22
- Granted: 2025-01-07
- Earliest claimed: 2019-06-28
- Assignees: Paypal, Inc.
- Applicants: Paypal, Inc.
- Inventors: Sumit Ranjan; Sriram Ramakrishnan; Ravi Shankar Chandrasekaran; Dinesh Damodharan
- Web page: https://patentgrep.com/patent/US12192297B2

## CPC

- G06F 16/9535: Search customisation based on user profiles and personalisation
- H04L 67/535: {Tracking the activity of the user (network monitoring arrangements H04L43/00; recording of computer activity G06F11/34)}
- G06F 9/453: {Help systems}
- G06F 16/955: using information identifiers, e.g. uniform resource locators [URL]
- G06N 20/00: Machine learning
- H04L 67/306: User profiles
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06N 20/20: Ensemble learning
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Techniques are disclosed relating to generating real-time suggested actions for a user based on their user profile attributes. In various embodiments, a server system may select, in real-time, a particular action to suggest to a user based on profile attributes associated with a user account of the user. The server system may then provide a message indicative of this particular action to a user device associated with the user. In some embodiments, the server system may then receive an indication that the user has initiated the particular action. In response to this indication, the server system may update the profile attributes associated with the user account to indicate that the user has initiated the particular action. Using these updated profile attributes, the server system may then select, in real-time, an updated action to suggest to the user that is different from the particular action.

## Claims

### Claim 1

A method, comprising:
using, by a computer system in an online payment service, a machine learning model to analyze online actions taken by a particular user associated with a particular account of the online payment service;
receiving, by the computer system from a user device, an access request associated with the particular account; and
in response to the access request:
predicting, by the computer system, a next action to be taken by the particular user, wherein the predicting includes:
based on the analyzed online actions of the particular user, updating one or more profile attributes associated with the particular account;
determining priority scores for a plurality of potential next actions based on the one or more updated profile attributes; and
selecting, based on the determined priority scores, at least one of the potential next actions as a predicted next action;
sending, by the computer system, the predicted next action to the user device;
in response to an indication of a selection of a next action by the particular user, predicting, by the computer system based on the selection of the next action, a subsequent action to be taken by the particular user; and
sending, by the computer system, the predicted subsequent action to the user device.

### Claim 2 (depends on 1)

The method of claim 1, wherein determining the priority scores for the plurality of potential next actions includes identifying one or more actions specified in the particular account of the particular user.

### Claim 3 (depends on 1)

The method of claim 1, wherein determining the priority scores for the plurality of potential next actions includes identifying one or more actions that are capable of being performed by the online payment service for the particular user.

### Claim 4 (depends on 1)

The method of claim 1, wherein determining the priority scores for the plurality of potential next actions includes identifying one or more actions that are eligible to be performed for the particular user.

### Claim 5 (depends on 1)

The method of claim 1, wherein updating the one or more profile attributes is performed in real-time.

### Claim 6 (depends on 1)

The method of claim 1, further comprising updating, by the computer system using an updated machine learning model analysis, the one or more profile attributes associated with the particular account of the particular user.

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
receiving, by the computer system from a third-party service, information regarding a subset of the online actions taken by the particular user; and
updating, by the computer system using the received information, the one or more profile attributes associated with the particular account of the particular user.

### Claim 8 (depends on 1)

The method of claim 1, further comprising, in response to the indication of the selection of the next action, predicting, by the computer system, that the predicted subsequent action to be taken by the particular user is the same as the predicted next action.

### Claim 9

A non-transitory, computer-readable medium having instructions stored thereon that are executable by a computer system, of an online payment service, to perform operations comprising:
analyzing, using a machine learning model, online activity of a of a particular user;
using the analyzed online activity to modify profile attributes in a particular account associated with the particular user;
after granting access to an account of the particular user, receiving an indication of a selection of a particular action by the particular user;
analyzing, using the machine learning model, the particular action of the particular user, wherein an analysis of the particular action is added to the analyzed online activity;
updating, based on the analyzed particular action, respective profile attributes in the account of the particular user;
determining priority scores for a plurality of potential next actions using the updated profile attributes in the particular account of the particular user;
predicting, based on the determined priority scores, that a particular one of the plurality of potential next actions will be taken by the particular user;
generate a message for a device of the particular user, the message including the predicted next action; and
in response to an indication of a selection of a next action by the particular user, repeat the updating of the respective profile attributes in the account of the particular user.

### Claim 10 (depends on 9)

The non-transitory, computer-readable medium of claim 9, wherein determining the priority scores for the plurality of potential next actions includes identifying one or more actions that are eligible to be performed for the particular user.

### Claim 11 (depends on 10)

The non-transitory, computer-readable medium of claim 10, wherein the actions include sending money to a contact associated with the particular user.

### Claim 12 (depends on 10)

The non-transitory, computer-readable medium of claim 10, wherein the actions include linking a financial transaction instrument to an account of the particular user.

### Claim 13 (depends on 9)

The non-transitory, computer-readable medium of claim 9, wherein generating the message for the device of the particular user includes selecting a particular presentation format from a plurality of presentation formats.

### Claim 14 (depends on 13)

The non-transitory, computer-readable medium of claim 13, further comprising selecting the particular presentation format based on a type of the device used by the particular user to access the online payment service.

### Claim 15

A system, comprising:
a non-transitory memory storing instructions; and
a processor configured to execute the instructions to cause the system to:
cause a machine learning model to analyze activity of a particular user;
update one or more profile attributes in an account of the particular user, wherein the update to the one or more profile attributes are based on the analyzed activity;
receive, from a device of the particular user, an account access request;
in response to an indication of additional activity by the particular user, cause the machine learning model to update the analyzed activity;
use the updated analyzed activity to modify the one or more profile attributes;
determine respective priority scores for a plurality of potential next actions based on the updated profile attributes;
based on the determined priority scores, predict that a particular one of the plurality of potential next actions will be taken by the particular user;
send the predicted next action to the device of the particular user; and
in response to an indication of a selection of a next action by the particular user, cause the machine learning model to update the analyzed activity.

### Claim 16 (depends on 15)

The system of claim 15, wherein to determine the respective priority scores, the processor is further configured to:
select one or more actions previously identified by the particular user; and
determine respective priority scores for the selected actions.

### Claim 17 (depends on 15)

The system of claim 15, wherein the processor is further configured to:
associate ones of the plurality of potential next actions with a respective eligibility rule; and
select a subset of the plurality of potential next actions using the respective eligibility rules.

### Claim 18 (depends on 17)

The system of claim 17, wherein to select the subset of the plurality of potential next actions, the processor is further configured, for ones of the plurality of potential next actions, to compare the respective eligibility rule to current values of the one or more profile attributes.

### Claim 19 (depends on 15)

The system of claim 15, wherein the plurality of potential next actions includes confirming user contact information.

### Claim 20 (depends on 15)

The system of claim 15, wherein the plurality of potential next actions includes linking a bank account to an account of the particular user.