Autonomous Virtual Assist for Resource Data Verification

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems lack efficient methods for compiling and presenting resource advancement requestor-specific dashboards that summarize resource advancement data, identify data omissions and anomalies, and provide corrective actions, thereby hindering effective decision-making in resource advancement requests.

Innovation Solution

The implementation of intelligent autonomous software (bots) that execute predetermined queries on a database storing resource advancement data, identify data omissions and anomalies, and generate corrective actions, while also receiving and processing on-demand queries to update dashboard presentations and modify predetermined queries using machine-learning models.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual data verification and assessment methods are used for resource advancement requests, then users can review and verify data accuracy, but the decision-making process becomes time-consuming and inefficient

Engineering Contradiction:

Improvedata accuracy verificationVSAvoiddecision-making time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs automated self-verification of resource advancement data using machine learning models that independently assess data accuracy, validate resource information, and generate verification reports without requiring manual user review. This self-service approach maintains reliability while eliminating time-consuming manual verification steps.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

Manual mechanical verification processes are replaced with automated machine learning models and algorithms that perform data validation, assessment, and verification. The ML-based system substitutes human reviewers with intelligent software agents that can process and verify data rapidly while maintaining or improving accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If comprehensive data analysis and verification processes are implemented for resource advancement requests, then data quality and decision accuracy improve, but system complexity and processing requirements increase

Engineering Contradiction:

Improvedata analysis accuracyVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The comprehensive data analysis system is segmented into multiple specialized machine learning models, each responsible for specific verification tasks such as resource validation, data quality assessment, and anomaly detection. This segmentation allows complex analysis to be distributed across modular components, improving precision while managing system complexity through division of labor.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The machine learning framework implements universal data verification capabilities that can handle multiple types of resource advancement requests and data formats through a single integrated system. The ML models are designed to perform diverse verification functions (accuracy check, completeness validation, consistency verification) within a unified architecture, reducing overall system complexity.

Inventive Principle:

Principle #6Universality (Multi-functionality)

3Productivity

If automated machine learning models are used for data verification and assessment, then processing efficiency and speed improve, but the need for manual oversight and verification may be reduced or eliminated

Engineering Contradiction:

Improvedata processing speedVSAvoiduser control over verification

Core Design Contradiction:

ProductivityVSEase of operation

Solution Approach 1:

The automated ML verification system incorporates feedback mechanisms that allow users to review ML-generated verification results, provide corrections, and adjust verification parameters. This feedback loop maintains user control and ease of operation while leveraging automated processing speed, enabling users to override or refine ML decisions when necessary.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system performs preliminary automated verification and assessment using ML models before presenting results to users for final review. This preliminary action filters out obvious errors and pre-validates data, reducing the burden on users and making the subsequent manual review process easier and more focused on critical decisions rather than routine verification.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS20250103848A1Intelligent virtual assist for resource advancement

Publication Date: 2025.03.27 BANK OF AMERICA CORP

AI summary

Intelligent autonomous software (i.e., a “bot”) configured to compile and present resource advancement requestor-specific dashboards that summarize the results of analysis of resource advancement data related to the resource advancement request/requestor. In compiling a dashboard presentation for a specific resource advancement requestor, the intelligent autonomous software executes a set of predetermined queries directed to a database that stores the results of the data analysis. In response to receiving the responses to the queries, the intelligent autonomous software is configured to identify data omissions/anomalies in the data that will prevent approval of the resource advancement request and identify, and in some instances generate, corrective action(s) that will rectify the data omissions/anomalies. Subsequently, a resource advancement requestor-specific dashboard presentation is generated and communicated to the user that (i) summarizes the data responsive to the predetermined queries, and (ii) highlights the data omissions/anomalies and the corrective actions necessary to rectify the data omissions/anomalies.