Holistic user engagement across multiple communication channels

Patent metadata

Field	Value
Publication number	US-12477024-B2
Application number	US-202418431033-A
Country	US
Kind code	B2
Filing date	Feb 2, 2024
Priority date	Jan 31, 2022
Publication date	Nov 18, 2025
Grant date	Nov 18, 2025

Abstract

Disclosed are various embodiments facilitating a holistic engagement with a user across multiple communication channels of an organization or an enterprise based at least in part on a determined user intent. As users interact with various services associated with the organization through one or more communication channels, interaction data can be captured and stored. In various examples, the interaction data that is stored by the various services can be obtained and organized according to a predefined schema. The organized interaction data can be applied to a trained intent model that outputs a user intent based at least in part on observations of other users with similar histories. The predicted intent can be provided to the different services such that subsequent interactions between the user and the organization can be based at least in part on the intent in a consistent manner, regardless of the communication channel associated with the interaction.

First claim

Therefore, the following is claimed:

1 . A system, comprising:
a computing device comprising a processor and a memory; and machine-readable instructions stored in the memory that, when executed by the processor, cause the computing device to at least:
identify a user associated with a scheduled outreach, the scheduled outreach corresponding to an organization messaging the user with respect to a feature associated with the organization;
translate a first portion of user interaction data associated with the user from a first format to a second format, the first format being associated with a first type of interaction over a first communication channel of a plurality of communication channels;
translate a second portion of the user interaction data associated with the user from a third format to the second format, the third format being associated with a second type of interaction over a second communication channel of the plurality of communication channels;
determine a user intent of the user based at least in part on an output of a trained intent model and the user interaction data associated with the user, the user interaction data being formatted in the second format to comply with the trained intent model;
modify the scheduled outreach for the user based at least in part on the user intent;
generate one or more messages associated with the modified scheduled outreach; and
initiate the scheduled outreach by sending the one or more messages associated with the modified scheduled outreach to a client device associated with the user.

2 . The system of claim 1 , wherein the trained intent model is trained according to interaction history data associated with a plurality of interactions by a plurality of users with a plurality of services by the plurality of users over the plurality of communication channels.

3 . The system of claim 1 , wherein an input of the trained intent model is based at least in part on a collection of organized interaction data associated with a plurality of user interactions with a plurality of services by the user via the plurality of communication channels.

4 . The system of claim 3 , wherein the collection of organized interaction data comprises at least one of browsing history data, call history data, payment history data, transaction history data, or chat history data.

5 . The system of claim 1 , wherein the output of the trained intent model includes an identification of a plurality of user intents, the user intent being selected from the plurality of user intents.

6 . The system of claim 1 , wherein content included in at least one of the one or more messages is based at least in part on the user intent.

7 . The system of claim 1 , wherein modifying the scheduled outreach comprising modifying a number of messages to send to the user.

8 . The system of claim 1 , wherein the user interaction data is organized according to a predefined schema.

9 . A method, comprising:
initiating an interaction session with a client device associated with a user via a first communication channel associated with a first service; translating a first portion of user interaction data associated with the user from a first format to a second format; translating a second portion of the user interaction data from a third format to the second format, the second format being required by an intent model; determining a user intent of the user based at least in part on an output of the intent model, the output of intent model being determined according to an input associated with the user interaction data of the user, and the user interaction data being associated with a plurality of user interactions with a plurality of services via a plurality of communication channels, the first portion of the user interaction data is associated with a second communication channel of the plurality of communication channels and the second portion of the user interaction is being associated with a third communication channel of the plurality of communication channels; generating a user interface associated with the interaction session, the user interface including an indication of knowledge of the user intent; and causing the user interface to be rendered on the client device.

10 . The method of claim 9 , wherein the user interaction data is organized according to a predefined schema.

11 . The method of claim 9 , wherein determining the user intent comprises sending an application programming interface (API) request to an intent engine associated with the intent model, the API request triggering a collection and an organization of the user interaction data associated with the user of the client device.

12 . The method of claim 9 , wherein the interaction session comprises a chat session associated with the first service, the user interface comprises a chat user interface, and the user intent being based at least in part on the user interaction with a second service by the user associated with the client device, the second service being different from the first service.

13 . The method of claim 9 , further comprising collecting real-time interaction data based at least in part on the interaction session, the real-time interaction data being included in the input of the intent model.

14 . The method of claim 9 , wherein the user interaction data comprises at least one of browsing history data, call history data, payment history data, transaction history data, or chat history data.

15 . A non-transitory, computer-readable medium, comprising machine-readable instructions that, when executed by a processor of a computing device, cause the computing device to at least:
collect interaction data from a plurality of services, the interaction data being associated with a plurality of user interactions with the plurality of services over a plurality of communication channels; translate a portion of the interaction data into from a first format to a second format, the first format being associated with a first communication channel of the plurality of communication channels, the second format being required by a trained intent model; translate a second portion of the interaction data from a third format to the second format, the third format being associated a second communication channel of the plurality of communication channels; apply the interaction data translated in the second format as an input in to the trained intent model; determine a user intent of a user based at least in part on an output of the trained intent model; and notify the plurality of services of the user intent, wherein subsequent user interactions with any one of the plurality of services are based at least in part on the user intent.

16 . The non-transitory, computer-readable medium of claim 15 , wherein, when executed, the machine-readable instructions cause the computing device to at least receive an intent request from a first service of the plurality of services, the intent request requesting the user intent associated with the user interacting with the first service.

17 . The non-transitory, computer-readable medium of claim 15 , wherein, when executed, the machine-readable instructions cause the computing device to at least organize the interaction data according to a predefined schema prior to applying the interaction data as the input to the trained intent model.

18 . The non-transitory, computer-readable medium of claim 17 , wherein, when executed, the machine-readable instructions cause the computing device to at least determine that the first format

Assignees

• American Express Travel Related Services Co Inc

Inventors

• Bashetty Anil Kumar
• Gayam Swetha
• Johnson Mark E
• Kumar Deepak
• Ladji Mazhar
• Liu Cong
• Liu Zeyu
• Love David Keith
• Mahendran Amarnath E
• Meyer Matthew K
• Schoenly Emery
• Seideman Jeremy D
• Sharma Govind

Classifications

• G06Q50/182

  Alternative dispute resolution · CPC title

• G06Q40/02

  Banking, e.g. interest calculation or account maintenance (credit or loans G06Q40/03) · CPC title

• G06Q30/04

  Billing or invoicing · CPC title

• G06Q10/10

  Office automation; Time management · CPC title

• H04L65/403 Primary

  Arrangements for multi-party communication, e.g. for conferences (data switching systems for conference H04L12/18; arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities H04M3/56; television conferencing systems H04N7/15) · CPC title