Natural Language Consumer Segmentation via NLP Parsing

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing consumer segmentation tools are complex and difficult to use, requiring specialized training and knowledge, making it challenging for marketers to define and interact with consumer segments effectively.

Innovation Solution

The use of natural language processing techniques to define, manipulate, and interact with consumer segmentations, allowing users to input queries in natural language and parse them into formal segment definitions using a token repository and custom thesaurus, reducing the need for formal syntax and specialized knowledge.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If existing consumer segmentation tools are used, then consumer segmentation functionality is provided, but the tools are complex and difficult to use, requiring specialized training and knowledge

Engineering Contradiction:

Improveease of useVSAvoidtool complexity

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The patent introduces a natural language processing intermediary layer that translates user-friendly natural language queries into formal segmentation definitions. This mediator handles the complexity internally while presenting a simple interface to users, resolving the contradiction between ease of operation and tool complexity.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the mechanical system of formal syntax and structured input requirements with a natural language processing system. Users speak or type in natural language instead of following complex syntax rules, eliminating the need for specialized training while maintaining full segmentation functionality.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If formal syntax is required for defining consumer segments, then precise segment definitions can be created, but specialized training and knowledge are needed to use the tools

Engineering Contradiction:

Improvesegment definition accuracyVSAvoidease of use

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The patent substitutes the mechanical syntax-based input system with a natural language processing system. The NLP engine parses colloquial language and converts it into precise segment definitions, maintaining measurement precision while dramatically improving ease of use by eliminating syntax requirements.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The natural language processing system acts as an intermediary that translates imprecise natural language into precise formal definitions. This mediator preserves the accuracy needed for measurement while allowing users to interact in their own language without specialized training.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Adaptability or versatility

If complex segmentation tools are used, then comprehensive consumer segmentation is achieved, but the tools are difficult to interact with on mobile devices

Engineering Contradiction:

Improvesegmentation comprehensivenessVSAvoidmobile device usability

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The patent replaces complex mechanical interfaces with voice-based natural language processing. Users can define comprehensive segments by speaking naturally into mobile devices, eliminating the need to navigate complex menus or type lengthy queries, thus improving mobile usability while maintaining segmentation comprehensiveness.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The natural language interface provides universal access to comprehensive segmentation functionality across all device types. The same voice-based interface that works on mobile devices also provides full segmentation capabilities, making the tool equally effective on mobile and desktop without sacrificing comprehensiveness for usability.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS10102246B2Natural language consumer segmentation

Publication Date: 2018.10.16 ADOBE INC

AI summary

Techniques are disclosed for using natural language processing techniques to define, manipulate, and interact with consumer segmentations. In such embodiments a content consumption analytics engine can be configured to receive and process a natural language segmentation query. The query may comprise, for example, a command that defines a new segmentation, a command that manipulates existing segmentations, or a command that solicits information relating to existing consumer segmentations. The query is parsed to identify individual grammatical tokens which are then correlated with specific segment token types through the use of a token repository. A custom thesaurus is used to identify synonymous terms for grammatical tokens which may not exist in the token repository. User feedback enables the custom thesaurus to learn additional synonyms for future use. Once the grammatical tokens are mapped onto the identified segment token types, a formal segment definition can be constructed based on a segment definition structure.