Conversational Agent for Event Processing Rule Authoring

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing solutions for authoring event-processing rules require users to learn controlled natural languages, limiting expressiveness and accessibility for non-technical users, as they often rely on complex languages or graphical interfaces that do not effectively bridge colloquial language to rule authoring.

Innovation Solution

A natural language conversational agent system that guides users through a dialog to author event-processing rules, using a data model to customize the interaction, parse natural language utterances, and construct a partial tree data structure, allowing users to specify rules in colloquial language without needing to learn a programming language, with capabilities for help, confirmation, and error correction.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If controlled natural language is used for rule authoring, then rule expressiveness is improved, but user accessibility and ease of operation deteriorate because users must learn the language

Engineering Contradiction:

Improverule expressivenessVSAvoiduser accessibility

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The patent introduces a conversational agent as an intermediary between the user and the rule authoring system. The agent translates colloquial user input into controlled natural language rules automatically, eliminating the need for users to learn CNL while preserving rule expressiveness. The agent acts as a mediator that handles the language translation task.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the manual mechanical process of learning and applying controlled natural language syntax with an automated natural language processing system. The conversational agent uses NLP techniques to automatically translate colloquial speech into structured CNL rules, substituting the manual language learning mechanism with an automated translation system.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Ease of operation

If existing rule authoring interfaces are simplified, then ease of operation is improved, but rule expressiveness deteriorates due to over-simplification

Engineering Contradiction:

Improveinterface simplicityVSAvoidrule expressiveness

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The conversational agent serves as an intermediary that allows users to interact with a simple, natural interface while the agent handles the complexity of translating into expressive controlled natural language rules. The simplicity of the conversational interface is maintained while the expressiveness is preserved through the agent's translation capabilities.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent segments the rule authoring process into two distinct layers: a simple user-facing conversational interface and a complex backend rule generation system. This segmentation allows the interface to remain simple while the backend maintains full rule expressiveness through structured CNL generation.

Inventive Principle:

Principle #1Segmentation

3Ease of operation

If graphical interfaces and spreadsheets are used for rule authoring, then ease of operation is improved, but the ability to effectively bridge colloquial language to rule authoring deteriorates

Engineering Contradiction:

Improveinterface usabilityVSAvoidlanguage bridging capability

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent replaces traditional graphical interface mechanisms with a natural language processing-based conversational system. Instead of requiring users to interact with graphical elements or spreadsheet structures, the system accepts colloquial speech and automatically translates it into rules, providing superior language bridging capability.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The conversational agent acts as an intermediary that directly processes colloquial language input and transforms it into structured rules. This intermediary capability bridges the gap between informal user speech and formal rule representations more effectively than traditional graphical interfaces can achieve.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS11100295B2Conversational authoring of event processing applications

Publication Date: 2021.08.24 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

A computer natural language conversational agent authors an event-processing rule by carrying out a dialog in natural language with a user. A data model that customizes a dialog and building of the event-processing rule is received. A partial tree data structure is constructed based on a rule's grammar, and specialized based on tokens extracted from the data model. An utterance is received from a user and interpreted according to the grammar as specialized to the data model. Based on the interpreting of the utterance, the grammar, the data model, and context of interactions with the user, a natural language prompt is determined for the computer natural language conversational agent to output to the user. The partial tree data structure is filled based on the natural language prompt and the utterance from the user. The event-processing rule is generated based on the partial tree data structure filled during the dialog.