Numerical Representation Models for Transaction Reconciliation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Reconciliation of financial records is challenging due to insufficiently detailed entries in financial systems, making it difficult for both humans and automated systems to identify relevant transaction information, particularly in the absence of standardized descriptions for transactions.

Innovation Solution

A method involving a numerical representation generation model and a transaction attribute prediction model, trained on historical records, to determine transaction attributes such as account codes and entity identifiers, facilitating automated reconciliation by generating and approving suggested attributes for financial records.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If automated reconciliation systems are used to process financial records, then productivity is improved, but measurement precision deteriorates due to insufficiently detailed entries in financial records

Engineering Contradiction:

Improvereconciliation speedVSAvoidtransaction attribute identification accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent introduces an intermediary natural language processing system that acts as a mediator between the financial record entries and the reconciliation process. This NLP system extracts and interprets transaction attributes from unstructured or semi-structured text descriptions, enabling automated reconciliation even when entries lack standardized formatting or sufficient detail.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system transforms the parameter representation of financial records by converting unstructured text descriptions into structured transaction attributes. This parameter transformation allows the reconciliation system to work with varied entry formats by standardizing the extracted attributes into a consistent structure that can be processed automatically.

Inventive Principle:

Principle #35Parameter changes

2Measurement precision

If manual analysis is used to identify transaction attributes, then measurement precision is improved, but loss of time increases

Engineering Contradiction:

Improvetransaction attribute identification accuracyVSAvoidreconciliation time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system implements self-service automation where the NLP model automatically extracts transaction attributes from financial record descriptions without requiring manual human analysis. The model learns from training data to independently identify and classify transaction attributes, eliminating the need for accountants to manually analyze each entry while maintaining high accuracy through machine learning.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary action by pre-training the NLP model on historical financial records and transaction attributes before actual reconciliation. This preliminary training phase enables the model to develop the capability to accurately extract attributes from various entry formats, so that during actual reconciliation, the process is already optimized for speed and accuracy without requiring manual intervention.

Inventive Principle:

Principle #10Preliminary action

3Ease of operation

If standardized descriptions are implemented in financial records, then ease of operation is improved, but adaptability deteriorates due to variability among different financial systems

Engineering Contradiction:

Improveautomated reconciliation capabilityVSAvoidhandling of diverse financial record formats

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent implements a universal NLP-based extraction system that can handle multiple financial record formats and descriptions from different financial systems. Rather than requiring each system to adhere to a specific standard, the universal model is designed to adapt to various entry formats by extracting relevant transaction attributes through natural language processing, making the reconciliation system compatible with diverse financial systems without requiring standardization.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS12423761B2Transaction data processing systems and methods

Publication Date: 2025.09.23 XERO

AI summary

Described embodiments relate to determining a candidate financial record associated with a transaction between a first accounting entity and a second entity, and determining, using a numerical representation generation model, a numerical representation of the candidate financial record, the numerical representation generation model having been trained on a corpus generated from historical transaction records. The method further comprises providing, to a transaction attribute prediction model, the numerical representation of the candidate financial record, the transaction attribute prediction model having been trained using a dataset of previously reconciled financial records, each associated with a respective first transaction attribute; and determining, by the transaction attribute prediction model, at least one first transaction attribute associated with the candidate financial record.