Server and method for generating digital content for users of a recommendation system
AssigneeCommunaute Woopen Inc.
InventorsEdwin Grappin, Jerome Verdier
Life of this patent
Estimating the term…
Abstract
A method and server for generating content for a user are disclosed. The method includes generating, via a first model, a first output for the user. The first output is representative of a predicted item of a first type. The method includes ranking, via a second model, the items of the second type into a ranked list based on the first output. A rank of an item is indicative of a likelihood of that the user interacts with the given item of the second type if the user performs an event of the pre-determined type on the given predicted item of the first type. Content is then selected from the ranked list and transmitted to a user device.
Claims20
A computer-implemented method of generating content for a user, the content to be displayed by an electronic device executing an application, the electronic device being communicatively coupled to a server by a communication network, the server hosting a recommendation system, the method executable by the server, the method comprising:
- acquiring, by the server from the electronic device over the communication network, a request for providing the content to the user;
- acquiring, by the server, user data associated with the user indicative of previous user interactions of the user with content items of the recommendation system;
- generating, by the server using a first model, a first output for the user based on the user data, the first output being representative of a synthesized content item of a first type,
- content items of the first type having a frequency ratio below a threshold ratio, the frequency ratio being a number of events of a pre-determined type that have been performed on a given content item by users of the recommendation system over a number of times that users have been presented with an indication of the events of the pre-determined type having been performed on the given content item;
- acquiring, by the server, item data associated with a plurality of content items of a second type, the first type being distinct from the second type, content items of the second type having a frequency ratio above the threshold ratio;
- ranking, by the server using a second model, the content items of the second type into a ranked list based on the first output, the user data, and the item data,
- a rank of a given content item of the second type being indicative of a likelihood of that the user interacts with the given content item of the second type if the user performs an event of the pre-determined type on the given content item of the first type;
- selecting, by the server, a set of content items from the ranked list of content items as the content for the user;
- transmitting, by the server to the electronic device over the communication network, the content for display to the user in the application.
A server for generating content for a user, the content to be displayed by an electronic device executing an application, the electronic device being communicatively coupled to the server by a communication network, the server hosting a recommendation system, the server being configured to:
- acquire, from the electronic device over the communication network, a request for providing the content to the user;
- acquire user data associated with the user indicative of previous user interactions of the user with content items of the recommendation system;
- generate, using a first model, a first output for the user based on the user data, the first output being representative of a synthesized content item of a first type,
- content items of the first type having a frequency ratio below a threshold ratio, the frequency ratio being a number of events of a pre-determined type that have been performed on a given content item by users of the recommendation system over a number of times that users have been presented with an indication of the events of the pre-determined type having been performed on the given content item;
- acquire item data associated with a plurality of content items of a second type, the first type being distinct from the second type, content items of the second type having a frequency ratio above the threshold ratio;
- rank, using a second model, the content items of the second type into a ranked list based on the first output, the user data, and the item data,
- a rank of a given content item of the second type being indicative of a likelihood of that the user interacts with the given content item of the second type if the user performs an event of the pre-determined type on the given content item of the first type;
- select a set of content items from the ranked list of content items as the content for the user;
- transmit, to the electronic device over the communication network, the content for display to the user in the application.
Dependencies are inferred from the claim text.