Myfitnesspal, Inc.

Under Armour, Inc.

Hesamoddin Salehian

Chul Lee

Patrick Howell

Surender Reddy Yerva

Iman Barjasteh

Layla Martin

Joohyun Kim

Poojit Sharma

Wenzhe Xue

Kyler Eastman

Mark Allen

Jeff Knight

Yi Qiang

Sebastian Johnck

Mirela Spasova

Vaibhav Aggarwal

Hannah O'Neal

Kent Frazier

Marlene Mayfield

Jiaqi Sun

A method and system for providing more relevant search results and recommendation from a food database is disclosed. The method includes receiving a query, a first candidate food, and a second candidate food. The method includes generating vectors based on the query and food names of the first and second candidate foods using at least one embedding function of a machine learning model. The method includes determining nutrition content vectors from the nutritional data of the first and second candidate foods. The method includes generating a nutrition content vector based on the query using another embedding function of the machine learning model. The method includes determining which of the first and second candidate food is more relevant to the query based at least in part on the nutrition content vectors. The method includes providing search results or recommendation based on the determined relevance.

Deep multi-modal pairwise ranking model for crowdsourced food data

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.

Food knowledge graph for a health tracking system

A method for operating a health tracking system, a health tracking system, and non-transitory computer-readable medium for operating a health tracking system are disclosed. The method comprises receiving a data record comprising at least a descriptive string and nutritional data regarding a consumable item to which the data record corresponds; determining a taste associated to the consumable item based on an evaluation of at least one of: (i) the descriptive string, and (ii) the nutritional data; and associating the determined taste with the data record in a database.

Method, system, and non-transitory computer-readable medium for associating taste with consumable records

A health tracking system and method of operation is disclosed herein. The method of operating the health tracking system comprises: receiving a first data record comprising at least a first descriptive string regarding a consumable item, the first descriptive string having at least one word thereof incorrectly spelled; generating a vector using the first descriptive string using a machine learning model; identifying a second descriptive string which corresponds to the consumable item and which has a correct spelling of the at least one incorrectly spelled word by applying the machine learning model to the generated vector; calculating a confidence factor regarding the identified second descriptive string using the machine learning model; and when it is determined that the confidence factor exceeds a predetermined threshold, (i) modifying the first data record by replacing the first descriptive string with the second descriptive string, and (ii) storing the modified first data record in the database.

Context and domain sensitive spelling correction in a database

A method for decreasing a number of individual entries in a database of user-created records which describe a single item by: receiving a plurality of user-created records, each of said records comprising at least a descriptive string; placing individual ones of the plurality of user-created records having a sufficiently similar descriptive string into one of a plurality of first groups; hashing the descriptive string of each of the plurality of first groups in order to place two or more groups into a single bin; performing a pair-wise comparison of the descriptive strings of the two or more groups in each bin; and when the comparison of the descriptive strings of the two or more groups in a bin results in a distance below a first threshold, merging the two or more groups into a combined group.

Health tracking system with verification of nutrition information

System and method for associating user-entered consumable item description to an entry in a consumable item database. In one embodiment, formally structured restaurant menu item is matched to a large database of food items that has been constructed via crowd-sourcing. A novel, practical, and scalable machine learning solution architecture, consisting of two major steps is utilized. First a query generation approach is applied, based on a Markov Decision Process algorithm, to reduce the time complexity of searching for matching candidates. That is then followed by a re-ranking step, using deep learning techniques, to ensure matching quality goals are met.

System and method for associating user-entered text to database entries

A method of operating a health tracking system is disclosed. The method comprises: receiving a first data record comprising at least a first descriptive string regarding a consumable item, the first descriptive string having at least one word thereof incorrectly spelled; generating a vector using the first descriptive string using a machine learning model; identifying a second descriptive string which corresponds to the consumable item and which has a correct spelling of the at least one incorrectly spelled word by applying the machine learning model to the generated vector; calculating a confidence factor regarding the identified second descriptive string using the machine learning model; and when it is determined that the confidence factor exceeds a predetermined threshold, (i) modifying the first data record by replacing the first descriptive string with the second descriptive string, and (ii) storing the modified first data record in the database.

A method of providing gait coaching is disclosed. Run data is received and stored regarding runs of a broad and diverse population of users, as well as a more narrow set of expert users. A gait metric model is developed for determining an ideal stride length or cadence based on pace and at least one physiological characteristic. Regression coefficients for at the model are determined based on a regression of the run data from the broad and diverse population of users. In contrast, a regression constant for the model is determined based on a regression of the run data from expert users. Using the model, an ideal stride length or cadence for a particular user on a particular run can be determined and utilized to provide useful monitoring, comparison, and feedback to the user regarding his or her stride length or cadence.

Gait coaching in fitness tracking systems

A method and system for providing more relevant search results and recommendation from a food database is disclosed. The method includes receiving a query, a first candidate food, and a second candidate food. The method includes generating text feature vectors based on the query and food names of the first and second candidate foods using at least one first embedding function of a machine learning model. The method includes determining nutrition content vectors from the nutritional data of the first and second candidate foods. The method includes generating a nutrition content vector based on the query using a second embedding function of the machine learning model. The method includes determining which of the first and second candidate food is more relevant to the query based on the text feature vectors and the nutrition content vectors. The method includes providing search results or recommendation based on the determined relevance.

Growing community of inventors

San Francisco, CA, United States of America

Hesamoddin Salehian