LLM Scheduling Pipeline for Temporal Expression Normalization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current systems for managing candidate availability for engagements are time-consuming, prone to human errors, and inefficient, relying heavily on manual intervention and leading to scheduling conflicts.

Innovation Solution

An apparatus and method using a large language model to generate, transmit, and process queries and responses to identify and normalize temporally structured information, enabling automated scheduling through a processor and memory system.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If manual intervention is used to interpret and schedule candidate availability, then flexibility and understanding of natural language inputs are improved, but time consumption and human errors increase

Engineering Contradiction:

Improveinterpretation of natural language inputsVSAvoidtime consumption for scheduling

Core Design Contradiction:

Ease of operationVSLoss of time

Solution Approach 1:

The system enables self-service by allowing the LLM to autonomously generate communications, extract temporal expressions, normalize time data, and schedule engagements without human intervention. The automated pipeline processes candidate responses and manages scheduling independently, eliminating manual time consumption while maintaining operational effectiveness.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical manual scheduling process with an automated computational system. The LLM-based communication generation and temporal expression normalization substitute human cognitive and administrative work, converting manual interpretation tasks into automated language processing and data normalization operations.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Adaptability or versatility

If manual scheduling processes are used, then adaptability to individual cases is improved, but productivity and efficiency deteriorate

Engineering Contradiction:

Improvehandling of individual scheduling casesVSAvoidscheduling efficiency

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The system changes parameters by transforming unstructured natural language temporal expressions into normalized temporal data structures. The LLM adjusts and standardizes time-related parameters from varied input formats, enabling efficient processing while maintaining adaptability to different expression styles and individual case requirements.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The automated system achieves universality by handling multiple scheduling scenarios through a single LLM-based pipeline. It processes various communication channels, different temporal expression formats, and diverse engagement types uniformly, maintaining adaptability across individual cases while improving overall productivity through standardized automated processing.

Inventive Principle:

Principle #6Universality (Multi-functionality)

3Measurement precision

If human operators manage candidate availability, then accuracy in understanding contextual nuances is improved, but the system complexity and operational costs increase

Engineering Contradiction:

Improveunderstanding of temporal expressionsVSAvoidsystem operational complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The LLM serves as an intermediary between unstructured natural language inputs and structured scheduling data. It mediates the transformation by generating communications, extracting temporal expressions, and normalizing time data, thereby achieving precise temporal understanding while simplifying the overall system architecture through a single intelligent mediation layer.

Inventive Principle:

Principle #24Intermediary (Mediator)

4Productivity

If automated systems are implemented to reduce manual work, then productivity is improved, but accuracy in interpreting natural language may worsen

Engineering Contradiction:

Improvescheduling automation speedVSAvoidaccuracy of temporal information extraction

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system incorporates feedback mechanisms where the LLM generates communications based on extracted temporal expressions, which are then normalized and used to schedule engagements. The feedback loop allows the system to refine its temporal expression understanding and extraction accuracy through iterative processing, maintaining high precision while achieving automation speed.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS12505146B1Apparatus and method for training a model to detect temporally structured information within an unstructured dataset

Publication Date: 2025.12.23 HEALSGOOD ARTIFICIAL INTELLIGENCE

AI summary

An apparatus and method for automatically managing candidate's availability using language processing. The apparatus includes at least a processor and a memory communicatively connected to the at least a processor. The memory instructs the processor to generate, using a large language model, a first communication, wherein the first communication comprises a first query, transmit the first communication, using a first communication channel of a plurality of communication channels, receive a first response, wherein the first response comprises temporally structured information associated with the first communication, generate, using the large language model, a follow-up communication, transmit the follow-up communication, using at least a communication channel of the plurality of communication channels, receive a follow-up response, display, using a client device, the first communication and the follow-up communication.