Transaction Description Translation via Neural Network Enhancement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Credit card users with primary languages other than English or German face difficulties in understanding transaction descriptions in these languages, which can lead to issues with fraud detection, double purchases, and budgeting, highlighting a need for dynamic translation solutions.
Innovation Solution
A system utilizing one or more processors to receive transaction data, identify merchant names, retrieve additional data, generate enhanced descriptions, and translate them using trained neural networks based on the user's location, creating a graphical user interface to display the translated data in the user's preferred language.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If transaction descriptions are provided in the primary language of the country where the credit card was used (e.g., English for US, German for Germany), then the transaction data is accurate and complete, but users whose primary language is not English or German have difficulty understanding the descriptions
Solution Approach 1:
The patent introduces a translation system as an intermediary between the transaction description (in the original language) and the user (who speaks a different language). The system retrieves additional data about the transaction and uses neural networks to translate the enhanced description into the user's preferred language, thereby resolving the language barrier without losing any transaction information
Solution Approach 2:
The system performs preliminary actions by retrieving additional data about the transaction (such as merchant information, location, category) before translation. This enhanced data is then used to generate more accurate and context-rich translations, ensuring that the user receives complete information in their preferred language rather than a literal translation of incomplete data
2Ease of operation
If the system translates transaction descriptions, then users can understand transactions in their preferred language, but the system complexity increases due to data retrieval, enhancement, and translation processes
Solution Approach 1:
The patent implements a multi-functional system that performs multiple tasks: retrieving additional transaction data, enhancing the original description, selecting appropriate neural network models, and translating the content. By consolidating these functions into a single integrated system, the patent manages complexity while providing comprehensive language translation services for credit card transactions
Solution Approach 2:
The system incorporates feedback mechanisms where users can provide input about their language preferences and the system can learn from this feedback to improve future translations. This feedback loop helps optimize the translation accuracy and reduces the need for complex manual configuration, thereby managing system complexity through intelligent adaptation
3Measurement precision
If additional data is retrieved and used to enhance transaction descriptions, then the translation accuracy improves, but the processing time and data handling complexity increase
Solution Approach 1:
The system retrieves additional transaction data in advance before the translation process begins. By pre-fetching and storing this additional information (such as merchant details, transaction categories, and location data), the system eliminates the need for time-consuming data retrieval during the translation process, thereby improving translation accuracy without significantly increasing processing time
Solution Approach 2:
The patent merges the original transaction description with the retrieved additional data into a single enhanced description before translation. This consolidation ensures that all relevant information is translated together as a cohesive unit, improving translation accuracy while avoiding the time penalty of processing multiple separate data elements
Data Source
AI summary
Disclosed embodiments may include a method that includes receiving description data in an originating language for a user and a location associated with the user, identifying one or more names from the description data, retrieving additional data in the originating language based on the one or more names, generating enhanced description data in the originating language for the user based on the description data and the additional data, identifying a target language based on the location associated with the user, selecting a first trained neural network from a plurality of trained neural networks based the target language, providing the enhanced description data in the originating language to the first trained neural network, translating, via the first trained neural network, the enhanced description data from the originating language to the target language, and generating a graphical user interface for display that comprises the enhanced description data in the target language.