Methods and apparatuses for deep learning-based recommendation, electronic devices, and media
AssigneeBeijing Sensetime Technology Development Co., Ltd.
InventorsZhiyu Min, Dahua Lin
Life of this patent
Estimating the term…
Abstract
Methods and apparatuses for deep learning-based recommendation, electronic devices, and media include: respectively obtaining related information of a target user and related information of a target item; respectively using at least two sub-models in an integrated model to obtain, based on the related information of the target user and the related information of the target item, operating probabilities corresponding to the at least two sub-models; obtaining, based on the operating probabilities corresponding to the at least two sub-models, a target probability about the target user operating the target item; and recommending the target item to the target user based on the target probability.
Claims18
A method for deep learning-based recommendation, comprising:
- obtaining related information of a target user and related information of a target item;
- respectively using at least two sub-models in an integrated model to obtain, based on the related information of the target user and the related information of the target item, operating probabilities corresponding to the at least two sub-models, wherein the operating probability is used for indicating a probability, obtained based on one sub-model, about the target user operating the target item, and the integrated model comprises at least two sub-models;
- obtaining, based on the operating probabilities corresponding to the at least two sub-models, a target probability about the target user operating the target item;
- and
- recommending the target item to the target user based on the target probability,
- wherein the obtaining, based on the operating probabilities corresponding to the at least two sub-models, a target probability about the target user operating the target item comprises:
- respectively calculating products of the operating probabilities and model weight values of the sub-models corresponding to the operating probabilities, each model weight value corresponding to one sub-model;
- and
- adding the products corresponding to the at least two operating probabilities to obtain the target probability about the target user operating the target item.
An apparatus for deep learning-based recommendation, comprising:
- a processor;
- and
- a memory for storing instructions executable by the processor,
- wherein the processor is configured to:
- obtain related information of a target user and related information of a target item;
- respectively use at least two sub-models in an integrated model to obtain, based on the related information of the target user and the related information of the target item, operating probabilities corresponding to the at least two sub-models, wherein the operating probability is used for indicating a probability, obtained based on one sub-model, about the target user operating the target item, and the integrated model comprises at least two sub-models;
- obtain, based on the operating probabilities corresponding to the at least two sub-models, a target probability about the target user operating the target item;
- and
- recommend the target item to the target user based on the target probability,
- wherein the processor is further configured to:
- respectively calculate products of the operating probabilities and model weight values of the sub-models corresponding to the operating probabilities, each model weight value corresponding to one sub-model, and
- add the products corresponding to the at least two operating probabilities to obtain the target probability about the target user operating the target item.
A non-transitory computer storage medium having stored thereon instructions that, when executed by a processor, cause the processor to perform operations of:
- obtaining related information of a target user and related information of a target item;
- respectively using at least two sub-models in an integrated model to obtain, based on the related information of the target user and the related information of the target item, operating probabilities corresponding to the at least two sub-models, wherein the operating probability is used for indicating a probability, obtained based on one sub-model, about the target user operating the target item, and the integrated model comprises at least two sub-models;
- obtaining, based on the operating probabilities corresponding to the at least two sub-models, a target probability about the target user operates the target item;
- and
- recommending the target item to the target user based on the target probability,
- wherein the obtaining, based on the operating probabilities corresponding to the at least two sub-models, a target probability about the target user operating the target item, the instructions when executed by the processor, cause the processor to perform operations of:
- respectively calculating products of the operating probabilities and model weight values of the sub-models corresponding to the operating probabilities, each model weight value corresponding to one sub-model;
- and
- adding the products corresponding to the at least two operating probabilities to obtain the target probability about the target user operating the target item.
Dependencies are inferred from the claim text.