Back to results
US 11,080,775 B2Granted
Recommending meals for a selected group
AssigneeInternational Business Machines Corporation
InventorsOznur Alkan, Adi I. Botea, Akihiro Kishimoto, Radu Marinescu
Life of this patent
Estimating the term…
Abstract
Embodiments for recommending meals by a processor. A collaboration of data capturing a plurality of factors of a group user profile for each user in a group of users may be received for aiding in recommending one or more meals. The one or more meals may be recommended for the group of users according to the group user profile such that the recommending balances a satisfaction level for the one or more meals for the group of users.
Claims20
A method, by a processor, for recommending meals in a computing environment, comprising:
- receiving a collaboration of data capturing a plurality of factors of a group user profile for each user in a group of users for aiding in recommending one or more meals, wherein the plurality of factors are implicitly derived from automated analyses of historical data of one or more meals consumed by each user in the group of users, the plurality of factors including nutritional constraints, one or more meal types, time constraints of each user, and a preparation time to prepare the one or more meals consumed by each user;
- determining a level of satisfaction according to real-time physiological data monitored by sensory devices associated with each user and the historical data associated with the one or more meals consumed by each user in the group of users, wherein the level of satisfaction is identified, at least in part, according to reviews and one or more communication messages posted to a social media network by respective users of the group of users, wherein determining the level of satisfaction includes correlating types of cuisine and characteristics of recipes used in the types of cuisine to a psychological disposition of the respective users according to a semantic analysis performed on at least a portion of the physiological data, and wherein the correlation identifies a root cause of the determined level of satisfaction for the respective users with respect to the characteristics of recipes used in the types of cuisine;
- training a machine learning model utilizing the collaboration of data, wherein training the machine learning model includes training a classifier to correlate the real-time physiological data and the historical data with the level of satisfaction associated with the one or more meals consumed by each user in the group of users;
- and
- responsive to an analysis of the machine learning model, recommending the one or more meals for the group of users according to the group user profile such that the recommending balances the satisfaction level for the one or more meals recommended for the group of users.
2 more elements
A system for recommending meals, comprising:
- one or more computers with executable instructions that when executed cause the system to:
- receive a collaboration of data capturing a plurality of factors of a group user profile for each user in a group of users for aiding in recommending one or more meals, wherein the plurality of factors are implicitly derived from automated analyses of historical data of one or more meals consumed by each user in the group of users, the plurality of factors including nutritional constraints, one or more meal types, time constraints of each user, and a preparation time to prepare the one or more meals consumed by each user;
- determine a level of satisfaction according to real-time physiological data monitored by sensory devices associated with each user and the historical data associated with the one or more meals consumed by each user in the group of users, wherein the level of satisfaction is identified, at least in part, according to reviews and one or more communication messages posted to a social media network by respective users of the group of users, wherein determining the level of satisfaction includes correlating types of cuisine and characteristics of recipes used in the types of cuisine to a psychological disposition of the respective users according to a semantic analysis performed on at least a portion of the physiological data, and wherein the correlation identifies a root cause of the determined level of satisfaction for the respective users with respect to the characteristics of recipes used in the types of cuisine;
- train a machine learning model utilizing the collaboration of data, wherein training the machine learning model includes training a classifier to correlate the historical data with the level of satisfaction associated with the one or more meals consumed by each user in the group of users;
- and
- responsive to an analysis of the machine learning model, recommend the one or more meals for the group of users according to the group user profile such that the recommending balances the satisfaction level for the one or more meals recommended for the group of users.
3 more elements
A computer program product for recommending meals by a processor, the computer program product comprising a non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:
- an executable portion that receives a collaboration of data capturing a plurality of factors of a group user profile for each user in a group of users for aiding in recommending one or more meals, wherein the plurality of factors are implicitly derived from automated analyses of historical data of one or more meals consumed by each user in the group of users, the plurality of factors including nutritional constraints, one or more meal types, time constraints of each user, and a preparation time to prepare the one or more meals consumed by each user;
- an executable portion that determines a level of satisfaction according to real-time physiological data monitored by sensory devices associated with each user and the historical data associated with the one or more meals consumed by each user in the group of users, wherein the level of satisfaction is identified, at least in part, according to reviews and one or more communication messages posted to a social media network by respective users of the group of users, wherein determining the level of satisfaction includes correlating types of cuisine and characteristics of recipes used in the types of cuisine to a psychological disposition of the respective users according to a semantic analysis performed on at least a portion of the physiological data, and wherein the correlation identifies a root cause of the determined level of satisfaction for the respective users with respect to the characteristics of recipes used in the types of cuisine;
- an executable portion that trains a machine learning model utilizing the collaboration of data, wherein training the machine learning model includes training a classifier to correlate the historical data with the level of satisfaction associated with the one or more meals consumed by each user in the group of users;
- and
- an executable portion that, responsive to an analysis of the machine learning model, recommends the one or more meals for the group of users according to the group user profile such that the recommending balances the satisfaction level for the one or more meals recommended for the group of users.
2 more elements
Dependencies are inferred from the claim text.