Method and apparatus for generating recommendations based on user preferences and environmental characteristics
DCFirst Claim
1. A method for recommending an item to a user, comprising the steps of:
- observing one or more environmental characteristics;
learning preferences of said user for each item to be recommended while exposed to and under said one or more observed environmental characteristics; and
generating a recommendation score for said item based on features of said item and said learned preferences of said user under said one or more observed environmental characteristics, wherein said one or more observed environmental characteristics includes at least one of a weather condition, a characteristic of motion of said user, a location, and one or more characteristics of said location and each of the one or more observed environmental characteristics is associated with a weight assigned by the user.
5 Assignments
Litigations
1 Petition
Accused Products
Abstract
A recommendation system is disclosed that generates recommendations for one or more items based on user preferences and one or more environmental factors. The user'"'"'s preferences are learned under various environmental conditions using an environmental data collection system. The observed environmental conditions may include, for example, location, characteristics of the location, weather or characteristics of the user'"'"'s motion, such as a rate of movement. For each positive and negative behavioral example, a number of attributes of the selected item are classified in the user profile together with the prevailing environmental conditions. When recommending an item, the disclosed recommender retrieves the user preferences and evaluates the current environmental conditions. A recommendation score can be generated for each available item based on the user'"'"'s demonstrated preferences under similar environmental conditions, such as in the same or a similar geographic area or under similar weather conditions.
86 Citations
35 Claims
-
1. A method for recommending an item to a user, comprising the steps of:
-
observing one or more environmental characteristics; learning preferences of said user for each item to be recommended while exposed to and under said one or more observed environmental characteristics; and generating a recommendation score for said item based on features of said item and said learned preferences of said user under said one or more observed environmental characteristics, wherein said one or more observed environmental characteristics includes at least one of a weather condition, a characteristic of motion of said user, a location, and one or more characteristics of said location and each of the one or more observed environmental characteristics is associated with a weight assigned by the user. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. A method for recommending an item to a user, comprising the steps of:
-
observing one or more environmental characteristics for obtaining information characterizing said one or more environmental characteristics for a given time; learning preferences of said user for each item to be recommended while said user is exposed to and affected by said one or more observed environmental characteristics; and generating a recommendation score for said item based on features of said item, and said learned preferences of said user under said one or more observed environmental characteristics for a given time, wherein said one or more observed environmental characteristics includes at least one of a weather condition and a characteristic of motion of said user and each of the one or more observed environmental characteristics is associated with a weight assigned by the user. - View Dependent Claims (8, 9, 10, 11, 12, 13, 14)
-
-
15. A system for recommending an item to a user, comprising:
-
a memory for storing computer readable code; and a processor operatively coupled to said memory, said processor configured to; observe one or more environmental characteristics for obtaining information characterizing said one or more environmental characteristics for a given time learn preferences of said user for each item to be recommended while exposed to and under said one or more observed environmental characteristics; and generate a recommendation score for said item based on features of said item and said learned preferences of said user under said one or more observed environmental characteristics, wherein said one or more observed environmental characteristics includes at least one of a weather condition and a characteristic of motion of said user and each of the one or more observed environmental characteristics is associated with a weight assigned by the user. - View Dependent Claims (16, 17, 18, 19, 20, 21, 22)
-
-
23. A system for recommending an item to a user, comprising:
-
a memory for storing computer readable code; and a processor operatively coupled to said memory, said processor configured to; observe at least one motion characteristic for obtaining information characterizing said one or more environmental characteristics for a given time; learn preferences of said user for each item to be recommended while exposed to and under said characteristic of motion; obtain information characterizing said characteristic of motion of said user for a given time; and generate a recommendation score for said item based on features of said item, and said learned preferences of said user under said characteristic of motion of said user and each of the one or more observed environmental characteristics is associated with a weight assigned by the user. - View Dependent Claims (24, 25)
-
-
26. A computer readable medium having computer readable code means embodied thereon for recommending an item to a user, said computer readable program code means comprising:
-
a step to learn preferences of said user for each item to be recommended while exposed to and under one or more observed environmental characteristics; and a step to generate a recommendation score for said item based on features of said item and said learned preferences of said user under said one or more observed environmental characteristics, wherein said one or more environmental characteristics includes at least one of a weather condition and a characteristic of motion of said user and each of the one or more observed environmental characteristics is associated with a weight assigned by the user. - View Dependent Claims (27, 28, 29, 30)
-
-
31. A computer readable medium having computer readable code means embodied thereon for recommending an item to a user, said computer readable program code means comprising:
-
a step to obtain information characterizing one or more observed environmental characteristics for a given time; a step to learn preferences of said user for each item to be recommended by observing said user'"'"'s personal exposure to one or more observed environmental characteristics; and a step to generate a recommendation score for said item based on features of said item, and said learned preferences of said user under said one or more observed environmental characteristics for a given time, wherein said one or more observed environmental characteristics includes at least one of a weather condition and a characteristic of motion of said user and each of the one or more observed environmental characteristics is associated with a weight assigned by the user. - View Dependent Claims (32, 33, 34, 35)
-
Specification