Back to results
US 11,636,527 B2Granted
Personalization based on private profile models
AssigneeInternational Business Machines Corporation
InventorsAhamed Jalaldeen Shahul Hamid, Chenthilraj Lakshmikanthan
Life of this patent
Estimating the term…
Abstract
In an approach for constructing private profile machine learning models for recommending products to a user, a processor gathers user data associated with interactions of the user on an ecommerce website. A processor analyzes the user data using machine learning (ML) techniques. A processor trains a private profile ML model on the analyzed user data, wherein the private profile ML model is stored on a private storage of the user. A processor predicts a product recommendation using the private profile ML model. A processor outputs the product recommendation.
Claims17
A computer-implemented method for constructing private profile machine learning models for recommending products to a user, the computer-implemented method comprising:
- responsive to the user during a registration to an ecommerce website providing an application program interface (API) and location of a private storage of the user for storing user data, enabling, by one or more processors, the ecommerce website to invoke the API to gather the user data associated with interactions of the user on the ecommerce website, wherein the private storage of the user is a local storage of the user or a cloud storage of the user;
- analyzing, by the one or more processors, the user data stored on the private storage using machine learning (ML) techniques;
- training, by the one or more processors, a private profile ML model that is stored on the private storage of the user using the analyzed user data to predict product recommendations for the user;
- responsive to the user browsing the ecommerce website, enabling, by the one or more processors, the ecommerce website to activate the trained private profile ML model to provide the predicted product recommendations for the user;
- responsive to the user during a second registration to a different ecommerce website providing the API and the location of the private storage of the user for storing second user data, enabling, by the one or more processors, the different ecommerce website to invoke the API to gather the second user data associated with interactions of the user on the different ecommerce website;
- updating, by the one or more processors, the private profile ML model using the second user data to predict second product recommendations associated with the different ecommerce website for the user;
- and
- responsive to the user browsing the different ecommerce website, enabling, by the one or more processors, the different ecommerce website to activate the private profile ML model to provide the second product recommendations to the user.
5 more elements
A computer program product for constructing private profile machine learning models for recommending products to a user, the computer program product comprising:
- one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the program instructions comprising:
- program instructions to, responsive to the user during a registration to an ecommerce website providing an application program interface (API) and location of a private storage of the user for storing user data, enable the ecommerce website to invoke the API to gather the user data associated with interactions of the user on the ecommerce website, wherein the private storage of the user is a local storage of the user or a cloud storage of the user;
- program instructions to analyze the user data stored on the private storage using machine learning (ML) techniques;
- program instructions to train a private profile ML model that is stored on a private storage of the user using the analyzed user data to predict product recommendations for the user;
- responsive to the user browsing the ecommerce website, enabling, by the one or more processors, the ecommerce website to activate the trained private profile ML model to provide the predicted product recommendations for the user;
- program instructions to, responsive to the user during a second registration to a different ecommerce website providing the API and the location of the private storage of the user for storing second user data, enable the different ecommerce website to invoke the API to gather the second user data associated with interactions of the user on the different ecommerce website;
- program instructions to update the private profile ML model using the second user data to predict second product recommendations associated with the different ecommerce website for the user;
- and
- program instructions to, responsive to the user browsing the different ecommerce website, enable the different ecommerce website to activate the private profile ML model to provide the second product recommendations to the user.
6 more elements
A computer system for constructing private profile machine learning models for recommending products to a user, the computer system comprising:
- one or more computer processors;
- one or more computer readable storage media;
- program instructions stored on the computer readable storage media for execution by at least one of the one or more processors, the program instructions comprising:
- program instructions to, responsive to the user during a registration to an ecommerce website providing an application program interface (API) and location of a private storage of the user for storing user data, enable the ecommerce website to invoke the API to gather the user data associated with interactions of the user on the ecommerce website, wherein the private storage of the user is a local storage of the user or a cloud storage of the user;
- program instructions to analyze the user data stored on the private storage using machine learning (ML) techniques;
- program instructions to train a private profile ML model that is stored on a private storage of the user using the analyzed user data to predict product recommendations for the user;
- responsive to the user browsing the ecommerce website, enabling, by the one or more processors, the ecommerce website to activate the trained private profile ML model to provide the predicted product recommendations for the user;
- program instructions to, responsive to the user during a second registration to a different ecommerce website providing the API and the location of the private storage of the user for storing second user data, enable the different ecommerce website to invoke the API to gather the second user data associated with interactions of the user on the different ecommerce website;
- program instructions to update the private profile ML model using the second user data to predict second product recommendations associated with the different ecommerce website for the user;
- and
- program instructions to, responsive to the user browsing the different ecommerce website, enable the different ecommerce website to activate the private profile ML model to provide the second product recommendations to the user.
8 more elements
Dependencies are inferred from the claim text.