Contextual Recommendation Engine with Translation Mediator

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Users traveling in foreign locations face difficulties in finding familiar activities and vendors that offer similar products or services due to language barriers and unfamiliarity with local establishments, making it hard to access comforts from home.

Innovation Solution

A system that uses location-based services and translation capabilities to identify and recommend nearby establishments matching a user's preferences, providing translated information and assistance for transactions, including menu ordering and payment, through a mobile application.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If translation capabilities are added to help users understand foreign language content, then language barrier is reduced, but system complexity increases

Engineering Contradiction:
Improvelanguage compatibilityVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent introduces a translation engine as an intermediary component that converts foreign language establishment information into the user's preferred language. This mediator resolves the language barrier without requiring the user device itself to become multilingual, thereby adding adaptability while containing complexity within the server-side translation module.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If contextual analysis of user profiles is performed to provide personalized recommendations, then recommendation accuracy is improved, but processing time increases

Engineering Contradiction:
Improverecommendation accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary analysis of user profiles and contextual information in advance, storing processed preferences and characteristics in the establishment information repository. When generating recommendations, the system retrieves pre-processed data rather than analyzing raw profiles from scratch, thereby maintaining high recommendation accuracy while reducing real-time processing time.

Inventive Principle:
Principle #10Preliminary action

3Loss of information

If comprehensive establishment information is stored in the repository, then information completeness is improved, but data management complexity increases

Engineering Contradiction:
Improveinformation completenessVSAvoiddata management complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The establishment information repository is segmented into multiple structured components including establishment details, activity descriptions, language fields, and user preference data. This segmentation allows the system to store comprehensive information in an organized manner, facilitating efficient retrieval and management while maintaining data completeness across different language and context requirements.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS11687995B2Contextually-aware recommendation and translation engine
Publication Date: 2023.06.27 THE TORONTO DOMINION BANK
  • US11687995B2 patent drawing
  • US11687995B2 patent drawing
  • US11687995B2 patent drawing

AI summary

The present disclosure involves systems, software, and computer implemented methods for presenting recommendations for suggested activities. One example method includes receiving a first signal from a device that includes a current context of the device that includes location information for the device. The device is associated with a particular profile. A preferred language associated with the device is determined from the profile. The profile is analyzed to determine a contextual activity preference associated with the device. A repository of establishment information is searched to identify an activity that matches the current context associated with the device and the contextual activity preference. An activity description of the identified activity is translated from a foreign language to the preferred language to create a translated activity description. A second signal is transmitted to the device that includes the translated activity description for presentation at the device.