NLP Pharmacy Order Intent Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current pharmacy systems lack the ability to automatically understand and respond to pharmacy customer messages sent via text, especially those that do not contain pre-determined keywords, leading to customer confusion and inefficiencies in handling orders.

Innovation Solution

A computer-implemented method using machine learning models to analyze customer messages, determine intent, and generate responses, allowing for automated handling of pharmacy orders without the need for keyword matching, enabling efficient communication and order management.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If keyword-based messaging systems are used to determine customer intent, then the system can identify specific pre-programmed keywords, but it cannot understand contextual information or messages sent in imprecise formats

Engineering Contradiction:

Improvekeyword identification accuracyVSAvoidmessage understanding capability

Core Design Contradiction:

Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent replaces the mechanical keyword-matching system with a natural language processing system that uses machine learning models to analyze and understand customer messages. The NLP system processes the full context of messages rather than relying on predefined keyword patterns, enabling the system to comprehend imprecise formats and contextual information while maintaining accurate intent determination.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Device complexity

If existing methods only support pre-programmed keywords, then the system structure remains simple, but it cannot handle messages expressing customer intent using unprogrammed language

Engineering Contradiction:

Improvesystem structure simplicityVSAvoidlanguage format flexibility

Core Design Contradiction:

Device complexityVSAdaptability or versatility

Solution Approach 1:

The patent substitutes the simple but rigid keyword-matching mechanism with an NLP-based system that can process diverse language formats. The machine learning models trained on message data enable the system to adapt to various customer communication styles without requiring complex manual programming of each possible message format.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system changes the operational parameters from fixed keyword patterns to dynamic natural language understanding. By training machine learning models on message data, the system adapts its parameters to recognize customer intent across multiple language formats, time periods, and communication styles, thereby increasing versatility while managing complexity through automated learning.

Inventive Principle:

Principle #35Parameter changes

3Ease of operation

If pharmacies use conventional telephone or in-person interaction methods, then customer intent can be understood through direct communication, but the process lacks automation and efficiency

Engineering Contradiction:

Improvecustomer interaction convenienceVSAvoidorder processing efficiency

Core Design Contradiction:

Ease of operationVSProductivity

Solution Approach 1:

The patent implements a self-service system where customers can communicate their prescription refill needs through text messages, and the NLP system automatically processes these messages to determine customer intent. This eliminates the need for direct pharmacist-customer interaction for routine refills, maintaining ease of operation for customers while dramatically improving processing efficiency through automation.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the manual telephone or in-person interaction process with an automated NLP-based text message system. The machine learning models analyze customer messages and automatically execute refill operations, substituting human communication and decision-making with an automated intelligent system that operates continuously without fatigue or delay.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

4Productivity

If pharmacies implement automated message handling, then operational efficiency improves, but the system lacks robust methods for automatically receiving and dispatching messages

Engineering Contradiction:

Improveorder handling efficiencyVSAvoidmessage processing reliability

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent replaces unreliable or non-existent automated message handling systems with a robust NLP-based platform. The machine learning models are trained on message data to accurately determine customer intent, and the system automatically dispatches appropriate actions based on this understanding, ensuring both high productivity and reliability in message processing.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS11790179B2Facilitating pharmacy customer orders through natural language processing

Publication Date: 2023.10.17 WALGREEN CO

AI summary

A pharmacy order facilitation method includes receiving a message; training a machine learning model; generating an intent; generating a response message; and transmitting the response message. A computing system includes a processor and a memory storing instructions that, when executed by the one or more processors, cause the computing system to: receive a message; train a machine learning model; generate an intent; generate a response message; and transmit the response message. A computing system includes a mobile device; a server device configured to: train a machine learning model; analyze the inbound message; identify a customer intent; perform an action based on the customer intent; and transmit an outbound message.