Cognitive Process Code Generation for Dynamic Business Adaptation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Traditional business process management systems are inflexible and unable to adapt process logic in real-time due to the sequential nature of Define-Execute-Improve, which is inadequate for handling dynamic business processes influenced by changing external data and unstructured information sources.

Innovation Solution

Generating cognitive executable process graphs from a hybrid process knowledge graph, which includes different node types and traverses through task nodes to create executable code blocks, enabling continuous adaptation and execution of processes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If conventional business process management systems are used with sequential Define-Execute-Improve cycle, then process execution is straightforward and controllable, but the system cannot adapt process logic in real-time to changing external data and unstructured information

Engineering Contradiction:

Improveadaptability to changing external dataVSAvoidprocess model complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent transforms static process models into dynamic cognitive process graphs that can adapt during execution. The system uses cognitive agents that continuously learn from unstructured information sources and external data, enabling the process model to dynamically reconfigure its logic, actions, and sequencing based on real-time observations without requiring complete redesign.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The patent introduces a cognitive layer as an intermediary between the conventional BPM system and external unstructured information sources. This cognitive layer includes cognitive agents that process unstructured data, generate insights, and translate them into process execution decisions, allowing the system to adapt to changing conditions without direct modification of the core process model.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If process models are designed to handle all possible variations in unstructured information, then completeness is improved, but the complexity and difficulty of process specification becomes impossible to manage

Engineering Contradiction:

Improveprocess execution reliabilityVSAvoidprocess specification complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent establishes a foundational cognitive process graph structure that includes predefined nodes for consuming unstructured information and cognitive agents for processing such data. This preliminary setup provides a reliable framework for handling variations, while the actual adaptation to specific scenarios occurs dynamically during execution through learning from observed data patterns.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The cognitive agents in the system autonomously learn from unstructured information sources and automatically adjust process execution logic without requiring manual process specification for every possible scenario. The system self-adapts by observing data patterns and generating appropriate process variations, eliminating the need for exhaustive upfront process modeling.

Inventive Principle:

Principle #25Self-service

3Adaptability or versatility

If manual handling of unstructured information is used, then flexibility in processing is maintained, but productivity and automation extent are significantly reduced

Engineering Contradiction:

Improveflexibility in processing unstructured informationVSAvoidprocess execution productivity

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The patent replaces manual mechanical processing of unstructured information with cognitive agents that use machine learning and natural language processing capabilities. These cognitive agents automatically consume, interpret, and derive insights from unstructured data sources such as emails, social media, and documents, transforming flexible manual processing into high-speed automated cognitive processing.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The cognitive agents are designed with universal capabilities to process multiple types of unstructured information sources (text, images, audio, social media data) using the same underlying cognitive framework. This multi-functional approach maintains the flexibility to handle diverse information types while achieving high productivity through automated processing rather than manual handling.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS11488029B2Cognitive process code generation

Publication Date: 2022.11.01 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

One embodiment provides for generating a cognitive executable process graph including obtaining, by a processor, a hybrid process knowledge graph generated based process fragments and a set of actionable statements and business constraints. The hybrid process knowledge graph including different node types. The hybrid knowledge graph is traversed from a root of a process through each task in the hybrid process knowledge graph to obtain an action and metadata for each task node. Based on the action and metadata, at least one statement in an equivalent executable code block is created to represent the action. A cognitive executable process graph is generated based on at least one executable code block.