Omnichannel Recommendation Engine Coordination

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing omnichannel recommendation systems often fail to coordinate offers across different communication channels, leading to customers receiving irrelevant or duplicate offers, as they lack a unified framework for training machine learning engines with diverse channel-specific data.

Innovation Solution

An omnichannel recommendation engine system that routes recommendation requests through both channel-specific and centralized engines, utilizing a recommendation interface to train machine learning engines with data from various communication channels, ensuring consistent and relevant offer presentation across channels.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If separate channel-specific recommendation engines are used for each communication channel, then each channel can receive customized recommendations, but the system lacks unified coordination leading to duplicate or irrelevant offers

Engineering Contradiction:

Improvechannel-specific customizationVSAvoidoffer coordination consistency

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The patent merges separate channel-specific recommendation engines into a unified omnichannel recommendation engine that processes requests from multiple communication channels (email, web, mobile, in-person) through a single centralized system. This integration enables coordinated offer management across channels while maintaining channel-specific customization capabilities, eliminating duplicate offers and ensuring consistent customer experience.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The omnichannel recommendation engine serves multiple functions simultaneously: it processes recommendation requests from diverse communication channels, trains machine learning engines using data from all channels, coordinates offer presentation across channels, and provides unified customer profile management. This multi-functional design resolves the contradiction by enabling both channel-specific customization and unified coordination through a single universal system.

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Reliability

If a unified centralized recommendation engine is used for all communication channels, then offer coordination and consistency are improved, but channel-specific customization and relevance may be reduced

Engineering Contradiction:

Improveoffer coordination consistencyVSAvoidchannel-specific customization

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The system applies local quality by maintaining channel-specific recommendation engines that process and customize recommendations for each communication channel individually. These channel-specific engines preserve local customization capabilities while feeding data to the unified omnichannel engine, ensuring that each channel receives optimized recommendations tailored to its specific characteristics and customer interaction patterns.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The patent segments the recommendation system into separate channel-specific recommendation engines for each communication channel, with each engine independently processing and customizing recommendations for its specific channel. This segmentation allows channel-specific optimization while the unified omnichannel engine coordinates across channels, resolving the contradiction between centralization and customization.

Inventive Principle:

Principle #1Segmentation

3Measurement precision

If machine learning engines are trained using data from multiple communication channels, then recommendation relevance and accuracy are improved, but data integration complexity and system processing requirements increase

Engineering Contradiction:

Improverecommendation accuracyVSAvoiddata integration complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The unified omnichannel recommendation engine acts as an intermediary that receives data from multiple channel-specific recommendation engines and machine learning models, processes and integrates this diverse data, and generates coordinated recommendations. This intermediary function simplifies data integration complexity by providing a single processing layer that handles data from all channels uniformly, while still achieving high recommendation accuracy through comprehensive data utilization.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS20230100517A1Omnichannel recommendation engine systems and methods

Publication Date: 2023.03.30 JPMORGAN CHASE BANK NA

AI summary

A method may include receiving a first recommendation request context from a first communication channel; routing the first recommendation request context to a channel recommendation engine for the first communication channel; receiving a first recommendation from the channel recommendation engine for the first communication channel; providing the first recommendation and the first recommendation request context to a centralized recommendation engine that trains a machine learning engine; providing the first recommendation to the first communication channel that provides the first recommendation to the first customer; receiving a first result of the first recommendation from the first communication channel; receiving a second recommendation request context from the first communication channel; routing the second recommendation request context to the centralized recommendation engine; receiving a second recommendation from the centralized recommendation engine; and providing the second recommendation to the first communication channel that provides the second recommendation to the second customer.