Transaction Time Prediction Using User Position Matching

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing transaction classification systems face inaccuracies due to the lack of precise transaction time data, which is often unavailable or incorrect in electronic records, leading to flawed classification and training data.

Innovation Solution

Utilize satellite positioning data to predict the actual transaction time by associating user positions with transaction records, enhancing the classification model's accuracy by incorporating timestamped user location data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If accurate transaction time data is obtained from the bank, then transaction classification accuracy is improved, but cost increases significantly

Engineering Contradiction:
Improvetransaction time accuracyVSAvoidcost
Core Design Contradiction:
Measurement precisionVSLoss of energy

Solution Approach 1:

The patent introduces positioning data as an intermediary element to indirectly determine transaction time. Instead of directly obtaining expensive accurate transaction time data from the bank, the system uses freely available positioning data from the user's mobile device to infer the transaction time by matching the user's location with the merchant's location. This intermediary approach resolves the contradiction by providing accurate transaction time information without incurring significant additional costs.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If transaction time data is manually obtained from the bank for each transaction, then transaction classification accuracy is improved, but productivity decreases

Engineering Contradiction:
Improvetransaction time accuracyVSAvoidprocessing efficiency
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent implements self-service by automatically collecting positioning data from the user's mobile device and using it to determine transaction time. The system processes the positioning data automatically without requiring manual intervention from users to contact the bank for each transaction. This automation resolves the contradiction by maintaining high transaction time accuracy while preserving processing efficiency through bulk automated processing of positioning data.

Inventive Principle:
Principle #25Self-service

3Ease of operation

If electronic transaction records are used without accurate timestamps, then ease of operation is maintained, but measurement precision deteriorates

Engineering Contradiction:
Improvedata collection simplicityVSAvoidtransaction time accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent merges positioning data with electronic transaction records to create enhanced transaction data. The system combines the easily obtainable electronic transaction records with positioning data from the user's mobile device, automatically matching them based on location and time proximity. This merging resolves the contradiction by maintaining the simplicity of electronic record collection while improving transaction time accuracy through the integrated positioning information.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentEP3776439B1Transaction classification based on transaction time predictions
Publication Date: 2025.11.19 INTUIT INC
  • EP3776439B1 patent drawingFigure 1
  • EP3776439B1 patent drawingFigure 2
  • EP3776439B1 patent drawingFigure 3

AI summary

Certain aspects of the present disclosure provide techniques for predicting a transaction time based on user position data. In certain aspects, a method for predicting a transaction time based on user position data includes obtaining a transaction record and one or more user positions associated with a user. The method also includes obtaining one or more business records associated with each respective user position. The method further includes calculating one or more similarity scores, where each similarity score is based on a similarity between a respective business record and the transaction record. The method also includes associating the transaction record with a business record based on a maximum similarity score of the one or more similarity scores. The method further includes determining a predicted transaction time for the transaction record based on at least a timestamp of a user position associated with the business record associated with the transaction record.