Automated Bot Generation from Observed User Behavior

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current robotic process automation (RPA) techniques require manual expertise to build bots that interact with user interfaces, leading to inefficiencies and bots that may not be optimized for common use cases, as they are designed based on limited human observations.

Innovation Solution

The system automatically generates bots based on observed user behavior by analyzing frontend process mining data, identifying bottlenecks, and optimizing bot generation through heatmap analysis and parameter selection, reducing the effort in both automation and bot usage.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If experts manually build RPA bots based on limited human observations, then the bots can be created with domain knowledge, but the effort and time required for bot creation increases significantly

Engineering Contradiction:

Improvebot accuracyVSAvoidbot creation time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system automatically generates bot code by copying and analyzing actual user interaction patterns with the UI. Instead of experts manually designing bot logic, the system observes real user behavior and replicates it through generated code, thereby reducing creation time while maintaining accuracy through real-world data

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The system enables self-service bot generation by automatically analyzing user interactions and generating functional bot code without requiring expert intervention. The bot creation process serves itself by using observed behavior data to automatically produce working automation scripts

Inventive Principle:

Principle #25Self-service

2Adaptability or versatility

If experts manually design bot interactions with UI, then the bots can be optimized for specific use cases, but the complexity of the automation process increases

Engineering Contradiction:

Improvebot optimizationVSAvoidautomation complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system copies actual user interaction sequences to create bot behavior patterns. By observing and replicating real user actions rather than designing theoretical interactions, the system achieves adaptability to specific use cases while avoiding the complexity of manual expert design

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The system replaces the mechanical process of manual expert bot design with an automated observation and generation system. Instead of experts manually configuring bot interactions, the system automatically captures and translates user behavior into bot code, reducing automation complexity

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Loss of time

If bots are designed based on limited human observations, then the design process can be completed quickly, but the bots may not be optimized for common use cases

Engineering Contradiction:

Improvedesign timeVSAvoidworkflow optimization

Core Design Contradiction:

Loss of timeVSAdaptability or versatility

Solution Approach 1:

The system implements continuous observation of user interactions to gather comprehensive behavior data. This continuous data collection enables the generation of bots optimized for common use cases while maintaining efficient design timelines through automated processing of observed patterns

Inventive Principle:

Principle #20Continuity of useful action

Solution Approach 2:

The system copies extensive user interaction patterns rather than relying on limited expert observations. By systematically capturing and analyzing real user behavior data, the system generates bots that are optimized for actual common use cases while maintaining efficient design throughput

Inventive Principle:

Principle #26Copying

4Reliability

If manual expert methods are used to create bots, then the quality of bot design can be maintained, but the computing resources and effort required increase

Engineering Contradiction:

Improvebot qualityVSAvoidcomputing resources

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system replaces resource-intensive manual expert design processes with automated observation and code generation. By using computational algorithms to analyze user interactions and generate bot code, the system maintains bot quality while optimizing computing resource utilization through automation

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20240256302A1Generation of bots based on observed behavior

Publication Date: 2024.08.01 SAP SE

AI summary

An application server provides an application to client devices. Users of the client devices interact with the application to perform a business process. Data regarding user interactions with the application is transmitted from the client devices to the application server. Based on an analysis of the received data, a bot generation server generates a bot to automate a process step. The bot generation server provides a heatmap user interface (UI) that provides information regarding the process steps. Using the heatmap UI, the administrator selects a process step for automation. In response to the selection, the bot generation server identifies, based on the observed behavior, relationships between input fields, typical values for input fields, typical order of data entry into input fields, or any suitable combination thereof. Based on the identified patterns, the bot generation server generates a bot to automate some or all of the process step.