IP Library Granted Patent US 12,417,837
Granted Patent B2
US 12,417,837 · App. 18/423,603 · Granted Sep 16, 2025

Food knowledge graph for a health tracking system

Inventors: Hesamoddin Salehian (Austin, TX); Poojit Sharma (Austin, TX); Kent Frazier (Austin, TX); Surender Reddy Yerva (Austin, TX); Iman Barjasteh (Austin, TX); Layla Martin (Austin, TX)
Assignee: MyFitnessPal, Inc.
G16H20/60G06N5/02G09B19/0092
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,417,837
App. No.
18/423,603
Granted
Sep 16, 2025
Kind
B2
Abstract

A method of operating a health tracking system is disclosed. 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.

Claims (29)

1. A method of operating a health tracking system, the method comprising:

storing in a database, a plurality of data records wherein each data record includes at least one descriptive string regarding one of a plurality of consumable items;

storing in a memory, a food knowledge data web comprised of a plurality of nodes and a plurality of connections between the nodes, wherein the nodes of the food knowledge data web are defined by a plurality of labels describing consumable items and the connections of the food knowledge data web are defined by a plurality of relationships between pairs of labels in the plurality of labels, at least some of the labels in the plurality of labels being generic names for consumable items, and wherein, for each pair of labels, one food relationship is defined between a first label and a second label of said pair of labels, said one food relationship identifying one of (i) the second label as an allergen of the first label, (ii) the second label as a substitute for the first label, and (iii) the second label as a flavor of the first label;

receiving a request for a consumable item from a health tracking device;

matching the request to the at least one first label or the at least one second label of one of said pair of labels in the food knowledge data web by implementing a machine learning model in order to match at least one descriptive string in the request to the at least one first label or the at least one second label of the one of said pair of labels in the food knowledge data web;

in response to the request being matched to the at least one first label or the at least one second label, identifying a data record from one of the plurality of data records by matching the matched at least one first or second label to a data record from the plurality of data records in the database;

transmitting the identified data record to the health tracking device;

displaying a menu on the health tracking device allowing the user to select a first option for recommended similar items, a second option for recommended substitutes, and a third option for recommended healthier items in lieu of the identified data record;

when the first option is selected at the health tracking device, transmitting to the health tracking device by wireless transmission a first set of one or more additional data records in the database that are associated with a first minimum threshold amount of same descriptive labels as the identified data record in the database, and immediately displaying the first set on the health tracking device following receipt of the selection of the first option;

when the second option is selected at the health tracking device, transmitting to the health tracking device by wireless transmission a second set of one or more additional data records in the database that are each either (i) represented by one of the nodes in the food knowledge data web that is connected to another of the nodes in the food knowledge data web representing the identified data record by one of the connections of the food knowledge data web indicating a substitute relationship between the additional data record and the identified data record, or (ii) associated with a second minimum threshold amount of the same descriptive labels as the identified data record, wherein the second minimum threshold is greater than the first minimum threshold, and immediately displaying the second set on the health tracking device following receipt of the selection of the second option; and

when the third option is selected at the health tracking device, transmitting to the health tracking device by wireless transmission a third set of one or more additional data records in the database that are associated with a third minimum threshold amount of the same descriptive labels as the identified data record in the database and also have a health score in the database that is greater than a health score of the identified data record, and immediately displaying the third set on the health tracking device following receipt of the selection of the third option.

2. The method of claim 1 further comprising:

receiving a data record comprising at least one descriptive string regarding a first consumable item from the health tracking device; and

including the received data record within the database.

3. A non-transitory computer-readable medium which, when executed on one or more processors of a health tracking system, cause the one or more processors to:

store in a database, a plurality of data records wherein each data record includes at least one descriptive string regarding one of a plurality of consumable items;

store in a memory, a food knowledge data web comprised of a plurality of nodes and a plurality of connections between the nodes, wherein the nodes of the food knowledge data web are defined by a plurality of labels describing consumable items and the connections of the food knowledge data web are defined by a plurality of relationships between pairs of labels in the plurality of labels, at least some of the labels in the plurality of labels being generic names for consumable items, and wherein, for each pair of labels, one food relationship is defined between a first label and a second label of said pair of labels;

receive a request for a consumable item from a health tracking device;

match the request to the at least one first label or the at least one second label of one of said pair of labels in the food knowledge data web by implementing a machine learning model in order to match at least one descriptive string in the request to the at least one first label or the at least one second label of the one of said pair of labels in the food knowledge data web;

in response to the request being matched to the at least one first label or the at least one second label, identify a data record from one of the plurality of data records by matching the matched at least one first or second label to a data record from the plurality of data records in the database;

transmit the identified data record to the health tracking device;

display a menu on the health tracking device allowing the user to select a first option for recommended similar items, a second option for recommended substitutes, and a third option for recommended healthier items in lieu of the identified data record;

when the first option is selected at the health tracking device, transmit to the health tracking device by wireless transmission a first set of one or more additional data records in the database that are associated with a first minimum threshold amount of same descriptive labels as the identified data record in the database, and immediately displaying the first set on the health tracking device following receipt of the selection of the first option;

when the second option is selected at the health tracking device, transmit to the health tracking device by wireless transmission a second set of one or more additional data records in the database that are each either (i) represented by one of the nodes in the food knowledge data web that is connected to another of the nodes in the food knowledge data web representing the identified data record by one of the connections of the food knowledge data web indicating a substitute relationship between the additional data record and the identified data record, or (ii) associated with a second minimum threshold amount of the same descriptive labels as the identified data record, wherein the second minimum threshold is greater than the first minimum threshold, and immediately displaying the second set on the health tracking device following receipt of the selection of the second option; and

when the third option is selected at the health tracking device, transmit to the health tracking device by wireless transmission a third set of one or more additional data records in the database that are associated with a third minimum threshold amount of the same descriptive labels as the identified data record in the database and also have a health score in the database that is greater than a health score of the identified data record, and immediately displaying the third set on the health tracking device following receipt of the selection of the third option.

4. The non-transitory computer-readable medium of claim 3 wherein said one food relationship identifies one of (i) the second label as an allergen of the first label, (ii) the second label as a substitute for the first label, and (iii) the second label as a flavor of the first label.

5. The non-transitory computer-readable medium of claim 3 wherein the one or more processors are further configured to:

receive a data record comprising at least one descriptive string regarding a first consumable item from the health tracking device; and

include the received data record within the database.

Assignments (3)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 15, 2024
From: SALEHIAN, HESAMODDIN; SHARMA, POOJIT; FRAZIER, KENT; YERVA, SURENDER REDDY; BARJASTEH, IMAN; MARTIN, LAYLA
To: UNDER ARMOUR, INC.
Reel/Frame 068301/0503 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 15, 2024
From: UNDER ARMOUR, INC.
To: UA CONNECTED FITNESS, INC.
Reel/Frame 068301/0508 →
CHANGE OF NAME Recorded Aug 15, 2024
From: UA CONNECTED FITNESS, INC.
To: MYFITNESSPAL, INC.
Reel/Frame 068301/0613 →
Continuity (3)
Continuation 16417291 · May 20, 2019
Provisional Application 62674170 · May 21, 2018
Related Publication 20240249816A1 · Jul 25, 2024
References Cited (56)
US 6478736B1 · Mault · 2002 [cited by applicant]
US 7966291B1 · Petrovic · 2011 [cited by applicant]
US 9311568B1 · Feller · 2016 [cited by applicant]
US 9797873B1 · Feller et al. · 2017 [cited by applicant]
US 9824152B1 · Feller et al. · 2017 [cited by applicant]
US 10480990B1 · Wallace · 2019 [cited by applicant]
US 10825567B1 · Wala et al. · 2020 [cited by applicant]
US 11062620B1 · Wallace · 2021 [cited by applicant]
US 20030132298A1 · Swartz et al. · 2003 [cited by applicant]
US 20040194141A1 · Sanders · 2004 [cited by applicant]
US 20070118405A1 · Campbell · 2007 [cited by applicant]
US 20080040313A1 · Schachter · 2008 [cited by applicant]
US 20080091705A1 · McBride · 2008 [cited by applicant]
US 20090099873A1 · Kurple · 2009 [cited by applicant]
US 20100161432A1 · Kumanov et al. · 2010 [cited by applicant]
US 20100169361A1 · Chen · 2010 [cited by applicant]
US 20110119161A1 · Van Treeck · 2011 [cited by applicant]
US 20110282861A1 · Bergstraesser et al. · 2011 [cited by applicant]
US 20110318717A1 · Adamowicz · 2011 [cited by applicant]
US 20120005222A1 · Bhagwan · 2012 [cited by applicant]
US 20120023107A1 · Nachnani · 2012 [cited by applicant]
US 20130216982A1 · Bennett · 2013 [cited by applicant]
US 20140081772A1 · Luke et al. · 2014 [cited by applicant]
US 20140147829A1 · Jerauld · 2014 [cited by applicant]
US 20140324607A1 · Frehn · 2014 [cited by applicant]
US 20150112843A1 · Pinel · 2015 [cited by examiner]
US 20150228062A1 · Joshi · 2015 [cited by applicant]
US 20150235136A1 · Dillon · 2015 [cited by applicant]
US 20150242468A1 · Shoemaker et al. · 2015 [cited by applicant]
US 20150276700A1 · Goel · 2015 [cited by applicant]
US 20160012749A1 · Connor · 2016 [cited by applicant]
US 20160103910A1 · Kim et al. · 2016 [cited by applicant]
US 20170046980A1 · Mehta et al. · 2017 [cited by applicant]
US 20170053362A1 · Galarraga · 2017 [cited by applicant]
US 20180075369A1 · Calmon · 2018 [cited by examiner]
US 20180240359A1 · Hujsak · 2018 [cited by applicant]
US 20190006040A1 · Fleming et al. · 2019 [cited by applicant]
US 20190103173A1 · Power et al. · 2019 [cited by applicant]
US 20190188776A1 · Hammond et al. · 2019 [cited by applicant]
US 20190228039A1 · Doble et al. · 2019 [cited by applicant]
US 20190286656A1 · Yerva et al. · 2019 [cited by applicant]
US 20200242964A1 · Wu · 2020 [cited by applicant]
US 20200365250A1 · Kim · 2020 [cited by applicant]
US 20220093234A1 · Shima et al. · 2022 [cited by applicant]
US 20240324911A1 · Hadad · 2024 [cited by examiner]
EP 1758038A1 · 2007 [cited by applicant]
WO 2007023619A1 · 2007 [cited by applicant]
WO 2013090768A2 · 2013 [cited by applicant]
WO 2016202274A1 · 2016 [cited by applicant]
WO 2017015612A1 · 2017 [cited by applicant]
WO 2017085777A1 · 2017 [cited by applicant]
Chen et al., “The Nutrients of Chronic Diet Recommended Based on Domain Ontology and Decision Tree,” TAAI2015 Tainan, Taiwan Nov. 20-22, 2015. (Year: 2015). [cited by examiner]
Ahire et al., “A Personalized Framework for Health Care Recommendation,” 2015 International Conference on Computing Communication Control and Automation; DOI 10.1109/ICCUBEA.2015.92. (Year: 2015). [cited by examiner]
Hochuli, Alexandra, Data Cleansing for Food Composition Data, Global Information Systems Group, 2014. [cited by applicant]
Schumer, Harleigh, Chioma Amadi, and Ashish Joshi. “Evaluating the dietary and nutritional apps in the google play store.” Healthcare informatics research 24.1 (2018): 38-45. [cited by applicant]
Franco, Rodrigo Zenun, et al. “Popular nutrition-related mobile apps: a feature assessment.” JMIR mHealth and uHealth 4.3 (2016): e5846. [cited by applicant]