Systems and methods for multi-channel customer communications content recommender

Patent metadata

Field	Value
Publication number	US-2021279658-A1
Application number	US-202117191521-A
Country	US
Kind code	A1
Filing date	Mar 3, 2021
Priority date	Mar 3, 2020
Publication date	Sep 9, 2021
Grant date	—

Abstract

Interaction events collected across disparate customer communication channels of an enterprise are processed to generate an encoded unique content item identifier for each content item referenced in an interaction event such that the content item is resolvable to a location in a content repository. A training data set is built using the interaction events thus processed and a multi-channel content recommendation model is trained using the training data set. The multi-channel content recommendation model thus trained stores data points representing intersections of customers and content items that the enterprise has been tracking, with each data point having an effectiveness score for an associated content item. The multi-channel content recommendation model thus trained can be queried by content designers of the disparate customer communication channels through a recommender application for content recommendations based on the effectiveness of the content, agnostic to the disparate customer communication channels.

First claim

What is claimed is:

1 . A method, comprising:
receiving, by a system executing on a processor, interaction events collected across disparate customer communication channels of an enterprise, an interaction event of the interaction events referencing a content item; processing the interaction events, the processing comprising:
generating an encoded unique content item identifier that encodes a location in a content repository and the content item referenced in the interaction event; and
modifying the interaction event with the encoded unique content item identifier such that the content item is resolvable to the location in the content repository;
building, by the system, a training data set using the interaction events thus processed; training, by the system, a multi-channel content recommendation model using the training data set, the training comprising:
populating a matrix representing a universe of customers of the enterprise and a universe of content items across the disparate customer communication channels of the enterprise with event-based data points from the interaction events, the event-based data points representing sparse intersections of the customers and the content items that can be determined from the interaction events;
determining, based on the event-based data points, additional data points for the matrix, the additional data points representing intersections of the customers and the content items that cannot be determined from the interaction events; and
computing an effectiveness score for each of the content items; and
providing, by the system, the multi-channel content recommendation model thus trained to a recommender application accessible by content designers of the disparate customer communication channels.

2 . The method according to claim 1 , wherein the generating the encoded unique content item identifier comprises:
determining a content item identifier from the interaction event; determining the location in the content repository; and applying an encoding function to the content item identifier and the location in the content repository.

3 . The method according to claim 2 , wherein the encoding function comprises a Base 64 encoding function.

4 . The method according to claim 1 , wherein the effectiveness score comprises a floating-point number between 0 and 1.

5 . The method according to claim 1 , further comprising:
receiving, through the recommender application, a request for a recommendation on what content is effective for a customer or a customer segment of the enterprise; and querying the multi-channel content recommendation model on the customer or the customer segment of the enterprise, wherein multi-channel content recommendation model returns a set of content items for the customer or the customer segment of the enterprise, each of the set of content items having an effectiveness score.

6 . The method according to claim 1 , further comprising:
applying a decoding function to the encoded unique content item identifier to obtain the location where the content item is stored in the content repository.

7 . A system, comprising:
a processor; a non-transitory computer-readable medium; and stored instructions translatable by the processor for:
receiving interaction events collected across disparate customer communication channels of an enterprise, an interaction event of the interaction events referencing a content item;
processing the interaction events, the processing comprising:
generating an encoded unique content item identifier that encodes a location in a content repository and the content item referenced in the interaction event; and
modifying the interaction event with the encoded unique content item identifier such that the content item is resolvable to the location in the content repository;

building a training data set using the interaction events thus processed;
training a multi-channel content recommendation model using the training data set, the training comprising:
populating a matrix representing a universe of customers of the enterprise and a universe of content items across the disparate customer communication channels of the enterprise with event-based data points from the interaction events, the event-based data points representing sparse intersections of the customers and the content items that can be determined from the interaction events;
determining, based on the event-based data points, additional data points for the matrix, the additional data points representing intersections of the customers and the content items that cannot be determined from the interaction events; and
computing an effectiveness score for each of the content items; and

providing the multi-channel content recommendation model thus trained to a recommender application accessible by content designers of the disparate customer communication channels.

8 . The system of claim 7 , wherein the generating the encoded unique content item identifier comprises:
determining a content item identifier from the interaction event; determining the location in the content repository; and applying an encoding function to the content item identifier and the location in the content repository.

9 . The system of claim 7 , wherein the stored instructions are further translatable by the processor for:
receiving, through the recommender application, a request for a recommendation on what content is effective for a customer or a customer segment of the enterprise; and querying the multi-channel content recommendation model on the customer or the customer segment of the enterprise, wherein multi-channel content recommendation model returns a set of content items for the customer or the customer segment of the enterprise, each of the set of content items having an effectiveness score.

10 . The system of claim 7 , wherein the stored instructions are further translatable by the processor for:
applying a decoding function to the encoded unique content item identifier to obtain the location where the content item is stored in the content repository.

11 . A computer program product comprising a non-transitory computer-readable medium storing instructions translatable by a processor for:
receiving interaction events collected across disparate customer communication channels of an enterprise, an interaction event of the interaction events referencing a content item; processing the interaction events, the processing comprising:
generating an encoded unique content item identifier that encodes a location in a content repository and the content item referenced in the interaction event; and
modifying the interaction event with the encoded unique content item identifier such that the content item is resolvable to the location in the content repository;
building a training data set using the interaction events thus processed; training a multi-channel content recommendation model using the training data set, the training comprising:
populating a matrix representing a universe of customers of the enterprise and a universe of content items across the disparate customer communication channels of the enterprise with event-based data points from the interaction events, the event-based data points representing sparse intersections of the customers and the content items that can be determined from the interaction events;
determining, based on the event-based data points, additional data points for the matrix, the additional data points representing intersections of the customers and the content items that cannot be determined from the interaction events; and
computing an effectiveness score for each of the content items; and

Assignees

• Open Text Sa Ulc

Inventors

• Pruitt Byron Steven

Classifications

• G06Q30/0204

  Market segmentation · CPC title

• G06Q30/0281 Primary

  Customer communication at a business location, e.g. providing product or service information, consulting · CPC title

• G06Q10/0637 Primary

  Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals · CPC title

• G06Q30/0201

  Market modelling; Market analysis; Collecting market data · CPC title