Granted Patent B2

US 12,475,159 · App. 18/172,438 · Granted Nov 18, 2025

Inventors: Mohammad Ali Abbasi (Culver City, CA); Shervin Shahryari (Culver City, CA)

Assignee: Lemon Inc.

G06F16/435G06F16/34G06F21/6245

Abstract

Claims (47)

1 . A method of providing media content using a private interactive mode on a media platform, the method comprising:

providing the media platform having a user interface and a recommendation engine, the media platform being configured to provide a first interactive mode and the private interactive mode;

receiving, via the user interface, an instruction to enter the private interactive mode;

generating in the private interactive mode, via the recommendation engine, one or more recommendations of media content based on one or more predetermined parameters;

receiving in the private interactive mode, via the user interface, one or more indications of a user request, the user request comprising a user interaction corresponding to the one or more recommendations of media content;

providing the one or more indications of the user request to a second machine learning model to produce a trained machine learning model, the second machine learning model associated with the private interactive mode and configured to learn a user's preferences based on the one or more indications of the user request;

generating in the private interactive mode, via the recommendation engine using the trained machine learning model, additional recommendations of media content based on the received one or more indications of the user request; and

in response to receiving an indication to exit the private interactive mode:

deleting the one or more indications of the user request; and

deleting the trained machine learning model.

2 . The method of claim 1 , wherein the one or more predetermined parameters include one or more of a device type, a language setting, and a location setting.

3 . The method of claim 1 , further comprising presenting, via the user interface, a list of selectable categories of user interest.

4 . The method of claim 3 , further comprising receiving, via the user interface, an indication of user selection of one or more of the selectable categories of user interest.

5 . The method of claim 4 , wherein the generating of the one or more recommendations is further based on the received indication of user selection.

6 . The method of claim 1 , further comprising:

in response to receiving the instruction to enter the private interactive mode:

ceasing providing indications of the user request to a first machine learning model associated with the first interactive mode.

7 . The method of claim 6 , wherein the second machine learning model is pre-trained to provide relatively more recommendations of media content than the first machine learning model.

8 . The method of claim 1 , further comprising presenting in the private interactive mode, via the user interface, a notification of the private interactive mode.

9 . The method of claim 1 , wherein the recommendation engine operating in the first interactive mode is independent of information associated with the private interactive mode.

10 . The method of claim 1 , wherein the one or more predetermined parameters comprise local cookie information from the user's terminal device.

11 . The method of claim 10 , wherein the local cookie information from the user's terminal device is not updated by the one or more indications of the user request.

12 . A method of obtaining media content using a private interactive mode on a media platform, the method comprising:

providing, via a user interface of the media platform, an indication to enter the private interactive mode from a first interactive mode on the media platform;

receive in the private interactive mode, via the user interface, one or more recommendations of media content based on one or more predetermined parameters;

providing in the private interactive mode, via the user interface, one or more indications of a user request, the user request comprising a user interaction corresponding to the one or more recommendations of media content;

receiving in the private interactive mode, via the user interface, additional recommendations of media content based on the one or more indications of the user request, wherein the additional recommendations are provided by a second machine learning model associated with the private interactive mode and configured to learn a user's preferences based on the one or more indications of the user request, and wherein the second machine learning model is trained on the one or more indication of the user request; and

providing an indication to exit the private interactive mode, wherein in response to the user request the media platform will delete the one or more indications of the user request and the second machine learning model.

13 . The method of claim 12 , further comprising receiving in the private interactive mode, via the user interface, a list of selectable categories of user interest.

14 . The method of claim 13 , further comprising providing in the private interactive mode, via the user interface, an indication of user selection of one or more of the selectable categories of user interest.

15 . The method of claim 14 , wherein the one or more recommendations are further based on the indication of user selection.

16 . The method of claim 12 , further comprising receiving in the private interactive mode, via the user interface, a notification of the private interactive mode.

17 . A system to provide media content using a private interactive mode on a media platform, the system comprising:

a memory configured to store data; and

a processor configured to read the data from the memory and further configured to: provide the media platform having a user interface and a recommendation engine,

the media platform being configured to provide a first interactive mode and the private interactive mode;

receive, via the user interface, an instruction to enter the private interactive mode;

generate in the private interactive mode, via the recommendation engine, one or more recommendations of media content based on one or more predetermined parameters;

receive in the private interactive mode, via the user interface, one or more indications of a user request, comprising a user interaction corresponding to the one or more recommendations of media content;

provide the one or more indications of the user request to a second machine learning model to produce a trained machine learning model, the second machine learning model associated with the private interactive mode and configured to learn a user's preferences based on the one or more indications of the user request;

generate in the private interactive mode, via the recommendation engine using the trained machine learning model, additional recommendations of media content based on the received one or more indications of the user request; and

in response to receiving an indication to exit the private interactive mode:

delete the one or more indications of the user request; and

delete the trained machine learning model.

18 . The system of claim 17 , wherein the processor is further configured to modify a first machine learning model associated with the first interactive mode to operate in the private interactive mode.

19 . The system of claim 18 , wherein the processor is further configured to provide the one or more indications of the user request, as input data, to the modified first machine learning model.

20 . The system of claim 18 , wherein the processor is further configured to permanently delete data associated with the modified first machine learning model from the memory, when receiving the indication to exit the private interactive mode.

Assignments (2)

Continuity (1)

References Cited (9)