Feature space management
AssigneeLemon Inc.
InventorsMeng Xin, Silun Wang, Huang Zou, Yu Zhang
Life of this patent
Estimating the term…
Abstract
There are proposed methods, devices, and computer program products for extending a feature space of a data sample. In the method, a global representation is obtained for a feature in a plurality of features of the data sample. A local representation is obtained for the feature based on a classifying criterion for classifying the data sample into one of a plurality of predefined domains. A representation is generated for the feature of the data sample based on the global representation and the local representation. With these implementations, an exclusive feature space may be created for each domain identified by the classifying criterion, which is dedicated to capturing domain-specific knowledge and characteristics.
Claims18
A computer-implemented method for video recommendation based on an extended feature space of a data sample of a machine learning model, the data sample comprising any of user data of a user or video data of a video in a recommendation system for recommending videos to users, the method comprising:
- obtaining, by a computing device, a global representation for a feature in a plurality of features of the data sample, wherein a global dimension size for the global representation for the feature is determined based on a predefined dimension size for the representation for the feature;
- obtaining, by the computing device, a local representation for the feature based on a classifying criterion for classifying the data sample into one of a plurality of predefined domains;
- generating, by the computing device, a representation for the feature of the data sample based on the global representation and the local representation;
- and
- recommending, by the computing device and the machine learning model, the video to the user based on the generated representation for the feature of the data sample.
An electronic device, comprising a computer processor coupled to a computer-readable memory unit, the memory unit comprising instructions that when executed by the computer processor implements a method for video recommendation based on an extended feature space of a data sample of a machine learning model, the data sample comprising any of user data of a user or video data of a video in a recommendation system for recommending videos to users, the method comprising:
- obtaining a global representation for a feature in a plurality of features of the data sample, wherein a global dimension size for the global representation for the feature is determined based on a predefined dimension size for the representation for the feature;
- obtaining a local representation for the feature based on a classifying criterion for classifying the data sample into one of a plurality of predefined domains;
- generating a representation for the feature of the data sample based on the global representation and the local representation;
- and
- recommending, by the computing device and the machine learning model, the video to the user based on the generated representation for the feature of the data sample.
A non-transitory computer program product, the non-transitory computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by an electronic device to cause the electronic device to perform a method for video recommendation based on an extended feature space of a data sample of a machine learning model, the data sample comprising any of user data of a user or video data of a video in a recommendation system for recommending videos to users, the method comprising:
- obtaining a global representation for a feature in a plurality of features of the data sample, wherein a global dimension size for the global representation for the feature is determined based on a predefined dimension size for the representation for the feature;
- obtaining a local representation for the feature based on a classifying criterion for classifying the data sample into one of a plurality of predefined domains;
- generating a representation for the feature of the data sample based on the global representation and the local representation;
- and
- recommending, by the computing device and the machine learning model, the video to the user based on the generated representation for the feature of the data sample.
Dependencies are inferred from the claim text.