Automated Narrative Generation Triggering System

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for automatically generating narrative stories from data lack effective criteria for determining when and how to generate stories, leading to inefficiencies and irrelevant content.

Innovation Solution

A system that evaluates data against a set of story angles and applicability conditions to determine whether a narrative story should be generated, using a processor to access an angle set data structure, process the data, and produce an evaluation indicator for story generation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If automated narrative generation is performed without evaluation criteria, then story generation can proceed freely, but the relevance and quality of generated stories deteriorates

Engineering Contradiction:

Improvestory generation throughputVSAvoidstory relevance accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system performs preliminary evaluation by processing data against multiple story angles and applicability conditions before actually generating narratives. This pre-filtering mechanism ensures that only data suitable for story generation is selected, improving both relevance and efficiency.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system generates evaluation indicators that provide feedback on whether data satisfies story angle conditions. This feedback mechanism guides the story generation process by indicating which data should be processed further and which should be discarded, enhancing story relevance.

Inventive Principle:

Principle #23Feedback

2Measurement precision

If multiple story angles and applicability conditions are evaluated, then story relevance improves, but system complexity increases

Engineering Contradiction:

Improvestory angle applicability accuracyVSAvoidevaluation system complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The evaluation system is segmented into distinct components: multiple story angles are defined separately, each with its own applicability conditions. This modular structure allows the system to evaluate different story perspectives independently, improving accuracy while maintaining manageable complexity through organized decomposition.

Inventive Principle:

Principle #1Segmentation

3Manufacturing precision

If data is processed against multiple applicability conditions, then story quality improves, but processing time increases

Engineering Contradiction:

Improvenarrative generation qualityVSAvoiddata processing time

Core Design Contradiction:

Manufacturing precisionVSLoss of time

Solution Approach 1:

The system evaluates data against multiple story angles and conditions, potentially more than strictly necessary for a single story. This excessive evaluation ensures high quality by checking all possible angles, and the system can prioritize or skip certain evaluations based on initial assessments, balancing quality with processing efficiency.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS11521079B2Method and apparatus for triggering the automatic generation of narratives

Publication Date: 2022.12.06 SALESFORCE INC

AI summary

Method and Apparatus for Triggering the Automatic Generation of Narratives Artificial intelligence methods and systems for triggering the generation of narratives are disclosed. Specific embodiments relate to real-time evaluation and automated generation of narrative stories based on received data. For example, data can be tested against data representative of a plurality of story angles to determine whether a narrative story incorporating one or more such story angles is to be automatically generated.