Food Knowledge Graph Matching for Health Tracking Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing health tracking systems lack robust information about food items, limiting user interaction to basic text searching and making it cumbersome to find foods and beverages in large databases.
Innovation Solution
A health tracking system utilizing a food knowledge graph that includes a database with labels and relationships between consumable items, enabling more informative and efficient user interactions by providing structured and detailed knowledge about consumables.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If a large crowdsourced database of foods and beverages is used to track food consumption, then the quantity of food records is increased, but user interaction becomes limited to basic text searching and it becomes cumbersome to find foods
Solution Approach 1:
The patent introduces a food knowledge graph as an intermediary layer between the user and the large food database. This knowledge graph contains structured information about food categories, ingredients, nutritional properties, and relationships between food items. When a user searches for food, the system queries the knowledge graph first to understand the intent and then retrieves relevant records from the large database, making the interaction much more efficient despite the database size.
Solution Approach 2:
The patent replaces the traditional mechanical text-searching mechanism with an intelligent query system based on the food knowledge graph. Instead of relying on simple keyword matching in a large database, the system uses semantic understanding and structured relationships from the knowledge graph to retrieve food records, significantly improving search efficiency and user experience.
2Device complexity
If minimal information is stored about food items (basic user-generated text description and nutritional content), then the database complexity is reduced, but the information robustness is insufficient for diverse user interactions
Solution Approach 1:
The patent segments food information into two distinct parts: a compact food knowledge graph containing structured, standardized information about food categories, ingredients, and relationships; and a large-scale food database containing detailed food records. This segmentation allows the system to maintain low complexity in the knowledge representation layer while preserving rich information in the database layer.
Solution Approach 2:
The patent adds a new dimension to food information storage by introducing the food knowledge graph as a separate, structured layer. This knowledge graph organizes food information in a hierarchical and relational manner (categories, ingredients, nutritional properties), providing robust information for diverse interactions without increasing the complexity of individual food records in the main database.
Data Source
AI summary
A health tracking system and related method are disclosed herein. The method comprises: storing a food knowledge graph having a plurality of labels describing consumable items and a plurality of relationships between pairs of labels, some of the labels being generic names for consumable items; receiving a data record having a descriptive string regarding a consumable item from a first health tracking device; matching the descriptive string to at least one label in the plurality of labels; and updating one or more information fields of the data record to associate the data record with the at least one label to which the descriptive string was matched. In some embodiments, the method further includes receiving a request for data records from a health tracking device and matching the request to the plurality of labels to provide an improved response to the request for data records.