Dynamic computing touchpoint journey recommendation platform

Patent metadata

Field	Value
Publication number	US-11972278-B2
Application number	US-202016880568-A
Country	US
Kind code	B2
Filing date	May 21, 2020
Priority date	May 21, 2020
Publication date	Apr 30, 2024
Grant date	Apr 30, 2024

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 system, comprising:
a processor that executes computer-executable components stored in a memory, the computer-executable components comprising:
an input component that receives a computing context of a client and a computing profile of the client, wherein the client is engaged in a computing touchpoint journey, wherein the computing context and the computing profile characterize at least an objective of the client, and wherein the computing context and the computing profile comprise information respective of a financial status of the client;
a prediction component that predicts, via a first machine learning classifier trained based on previous contexts and profiles associated with previous negative events, a negative event likely to occur on the computing touchpoint journey, wherein the first machine learning classifier receives as input the computing context and the computing profile, including the information respective of the financial status of the client, and generates as output the predicted negative event, and wherein the predicted negative event comprises a payment decline based on the financial status; and
a decision component that recommends in real-time, via a second machine learning classifier trained based on previous computing touchpoints that resolved the previous negative events, a recommended computing touchpoint to which to transfer the client to continue the computing touchpoint journey, wherein the second machine learning classifier receives as input the computing context, the computing profile, and the predicted negative event and generates as output the recommended computing touchpoint.

2. The system of claim 1 , wherein the computer-executable components further comprise:
a computing touchpoint journey component that records computing touchpoint journeys traversed by various clients and derives the previous contexts and profiles, the previous negative events, and the previous computing touchpoints to train at least one of the first machine learning classifier or the second machine learning classifier.

3. The system of claim 2 , wherein the computing touchpoint journey component records computing touchpoint journeys traversed by various clients in real-time and facilitates online training of at least one of the first machine learning classifier or the second machine learning classifier as the computing touchpoint journeys traversed by various clients are recorded.

4. The system of claim 1 , wherein the computer-executable components further comprise:
an execution component that transfers the client to the recommended computing touchpoint.

5. The system of claim 1 , wherein the computing context includes at least one of a current computing touchpoint visited by the client, a previous computing touchpoint visited by the client, an objective of the client, or a device modality of the client.

6. The system of claim 1 , wherein the computing profile includes at least one of an identification of the client, a computing touchpoint preference of the client, an age of the client, an ethnicity of the client, a location of the client, or financial instrument information of the client.

7. The system of claim 1 , wherein the decision component selects the recommended computing touchpoint from a set of available computing touchpoints based in part on at least one of a probability of resolving the predicted negative event or a load distribution among the set of available computing touchpoints.

8. The system of claim 1 , wherein the input component further receives extrinsic information associated with an environment of the client, and wherein the first and second machine learning classifiers receive as input the extrinsic information.

9. A computer-implemented method, comprising:
retrieving, by a device operatively coupled to a processor, profile data and context data associated with a client engaged in a computing touchpoint journey, wherein the profile data and context data characterize at least an objective of the client and are particular to at least a financial status of the client, and wherein the profile data and context data comprise information respective of a capability of the client;
forecasting, by the device, an unsuccessful event along the computing touchpoint journey of the client by employing a first machine learning algorithm that takes as input the profile data and the context data, including the information respective of the capability of the client, and produces as output the forecasted unsuccessful event, wherein the first machine learning algorithm is trained based on previous contexts and profiles associated with previous unsuccessful events; and
dynamically suggesting, by the device, a computing touchpoint for the client by employing a second machine learning algorithm that takes as input the profile data, the context data, the capability of the client, and the forecasted unsuccessful event and produces as output the dynamically suggested computing touchpoint, wherein the second machine learning algorithm is trained based on previous computing touchpoints that resolved the previous unsuccessful events.

10. The computer-implemented method of claim 9 , further comprising:
aggregating, by the device, computing touchpoint journeys of other clients in real-time; and
deriving, by the device and from the aggregated computing touchpoint journeys, the previous contexts and profiles, the previous unsuccessful events, and the previous computing touchpoints to train the first and second machine learning algorithms as the computing touchpoint journeys of other clients are aggregated.

11. The computer-implemented method of claim 9 , further comprising:
transferring, by the device, the client to the dynamically suggested computing touchpoint.

12. The computer-implemented method of claim 9 , wherein the dynamically suggesting the computing touchpoint comprises selecting, from a set of available computing touchpoints, a computing touchpoint having a likelihood of successful resolution of the forecasted unsuccessful event above a predetermined threshold.

13. The computer-implemented method of claim 9 , wherein the dynamically suggesting the computing touchpoint comprises selecting, from a set of available computing touchpoints, a computing touchpoint with a load level below a predetermined threshold.

14. The computer-implemented method of claim 9 , wherein the profile data comprises at least one of demographic information of the client or preference information of the client.

15. The computer-implemented method of claim 9 , further comprising:
retrieving, by the device, external data associated with a location of the client, wherein the first and second machine learning algorithms take as input the external data.

16. A computer program product for facilitating dynamic tailoring of computing touchpoint journeys, the computer program product comprising a computer readable memory having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:
obtain profile information and context information of a computing client currently engaged in a computing touchpoint journey, wherein the profile information and the context information characterize at least an objective of the computing client, and wherein the profile information and the context information are respective of a capability of the computing client;
predict, via a first machine learning classifier trained based on previous contexts and profiles associated with previous negative events, a negative event likely to occur on the computing touchpoin

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

• G06F9/453 Primary

  Help systems · CPC title

• G06F3/04883

  for inputting data by handwriting, e.g. gesture or text · CPC title