Dynamic computing touchpoint journey recommendation platform

Patent metadata

Field	Value
Publication number	US-12386642-B2
Application number	US-202418586029-A
Country	US
Kind code	B2
Filing date	Feb 23, 2024
Priority date	May 21, 2020
Publication date	Aug 12, 2025
Grant date	Aug 12, 2025

Abstract

Systems and techniques that facilitate computing touchpoint journey recommendations are provided. In various embodiments, an input component can receive a computing context of a client and a computing profile of a client. In various instances, the client can be engaged in a computing touchpoint journey. In various embodiments, a prediction component can predict, via a first machine learning classifier, a negative event likely to occur on the computing touchpoint journey. In various cases, the first machine learning classifier can receive as input the computing context and the computing profile and can generate as output the predicted negative event. In various embodiments, a decision component can recommend in real-time, via a second machine learning classifier, a computing touchpoint to which to transfer the client. In various aspects, the second machine learning classifier can receive as input the computing context, the computing profile, and the predicted negative event and produce as output the recommended computing touchpoint. In various embodiments, an execution component can transfer the client to the recommended computing touchpoint. In various embodiments, a computing touchpoint journey component can record computing touchpoint journeys traversed by various clients and trains the first and second machine learning classifiers on the recorded computing touchpoint journeys.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
determining, based on journey data, that a customer is engaged in a customer journey with a certain objective, wherein the customer journey corresponds to a product or service experience accessed by the customer via a plurality of touchpoints;
predicting, using a first machine learning (ML) model trained at least based on previous journey data and associated previous unsuccessful events, a predicted occurrence of an unsuccessful event along the customer journey, wherein said predicting comprises the first ML model using at least the journey data as input; and
providing a suggestion, using a second ML model trained at least based on previous suggested touchpoints that resolved the previous unsuccessful events, of a certain touchpoint as a next touchpoint in the customer journey, wherein said providing the suggestion comprises the second ML model using at least the predicted occurrence of the unsuccessful event predicted by the first ML model as input;
wherein the training data of the second ML model includes different data from the training data of the first ML model;
wherein the second ML model is configured to provide the certain touchpoint before the predicted occurrence of the unsuccessful event predicted by the first ML model occurs.

2. The method of claim 1 , wherein the data comprises profile data and context data, wherein the profile data indicates one or more characteristics of the customer;
and wherein the context data indicates one or more characteristics of the customer journey including the objective.

3. The method of claim 1 , further comprising:
aggregating a plurality of journey data for a plurality of customer journeys of other customers; and;
determining one or more of a first training data and a second training data based, at least in part, on the plurality of journey data, wherein the first training data is used to train the first ML model and wherein the second training data is used to train the second ML model.

4. The method of claim 3 ,
wherein the first ML model being trained at least based on the previous journey data and the associated unsuccessful events comprises the first ML model being trained based on the first training data, a plurality of corresponding negative unsuccessful events, and a plurality of corresponding next touchpoints in the corresponding ones of the plurality of customer journeys.

5. The method of claim 3 ,
wherein the second ML model being trained at least based on the previous suggested touchpoints that resolved the previous unsuccessful events comprises the second ML model being trained based on the second training data, a plurality of corresponding negative unsuccessful events, and a plurality of corresponding outcomes of the plurality of customer journeys.

6. The method of claim 1 , further comprising:
transferring the customer from a current touch point in the customer journey that uses a first communication platform to the certain touchpoint that uses a second communication platform.

7. The method of claim 1 , further comprising:
providing the certain touchpoint to the customer to direct a next customer interaction with the certain touchpoint instead of interaction with a potential other touchpoint in the customer journey.

8. The method of claim 1 , wherein said providing the suggestion comprises selecting, from a set of available touchpoints, the certain touchpoint that has a likelihood of successful resolution of the predicted occurrence of the unsuccessful event above a certain threshold.

9. The method of claim 1 , wherein the data indicates various characteristics of the customer journey including characteristics of each of the plurality of touchpoints and the product or service experience as related to the certain objective.

10. A system, comprising:
a non-transitory memory storing instructions; and
a processor configured to execute the instructions to cause the system to:
determine, based on journey data, that a customers engaged in a customer journey with a certain objective, wherein the customer journey is for transaction associated with a product or service, wherein the customer progresses through the customer journey by accessing ones of a plurality of touchpoints of the customer journey;
predict, using a first machine learning (ML) model trained at least based on previous journey data and associated unsuccessful events, a predicted occurrence of an unsuccessful event before the customer accesses a potential next touchpoint in the plurality of touchpoints of the customer journey; and
direct the customer to a new touch point as a next touch point in the customer journey before the customer accesses the potential next touchpoint in the plurality of touchpoints, wherein the new touchpoint is predicted using a second ML model trained at least based on previous suggested touchpoints that resolved previous unsuccessful events, wherein the second ML model uses at least the predicted occurrence of the unsuccessful event predicted by the first ML model as an input;
wherein at least a portion of the training data of the second ML model includes different data from the training data of the first ML model;
wherein the certain touchpoint of the second ML model is configured to precede the predicted occurrence of the unsuccessful event of the first ML model.

11. The system of claim 10 , wherein the first ML model being trained at least based on the previous journey data and the associated unsuccessful events comprises the first ML model being trained based on the first training data, a plurality of corresponding negative unsuccessful events, and a plurality of corresponding next touchpoints in the corresponding ones of the plurality of customer journeys.

12. The system of claim 10 , wherein the second ML model being trained at least based on the previous suggested touchpoints that resolved the previous unsuccessful events comprises the second ML model being trained based on the second training data, a plurality of corresponding negative unsuccessful events, and a plurality of corresponding outcomes of the plurality of customer journeys.

13. The system of claim 10 , wherein the journey data comprises computing context that includes at least one of a current touchpoint accessed by the customer, a previous touchpoint accessed by the customer, the objective, or a device modality of the customer.

14. The system of claim 10 , wherein the journey data comprises computing profile that includes at least one of an identification of the customer, a touchpoint preference of the customer, an age of the customer, an ethnicity of the customer, a location of the customer, or financial instrument information of the customer.

15. The system of claim 10 , wherein said directing the customer to the new touchpoint comprises transferring the customer from a current touchpoint in the customer journey that uses a first communication platform to the certain computing-touchpoint that uses a second communication platform.

16. A non-transitory machine-readable medium having instructions stored thereon, the instructions executable to cause performance of operations comprising:
determine, based on journey data, that a customer is engaged in a customer journey with a certain objective, wherein the customer journey is for transaction associated with a product or service, wherein the customer journey is accessible by the customer via a plurality of touchpoints;
predict, using a first machine learning (ML) model trained at least based on previous journey data and associated unsuccessful events, a pre

Assignees

• Paypal Inc

Inventors

• Chirakkil Vinesh
• Sarin Pankaj
• Doran Thomas
• Fundus Matthew

Classifications

• G06N3/09

  Supervised learning · CPC title

• G06N3/0499

  Feedforward networks · CPC title

• G06N3/092

  Reinforcement learning · CPC title

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06N5/04

  Inference or reasoning models · CPC title