US 2023/0412888 A1Published application

Methods and systems for recommendations based on user-supplied criteria

AssigneeMarketX LLC

InventorsMichael Joseph KARLIN, Daniel Z. ZANGER, Ariel Mikhael KATZ

Life of this patent

Estimating the term…

Loading patent…

Abstract

Methods and systems are proposed herein to address the inefficiencies in the recommendation schemes available. More specifically, the embodiments disclosed herein provide a new recommendation scheme, whereby a user enters various criteria for what he/she would like to be recommended. For example, the system may receive a user preference for content recommendations from a user. The system may retrieve a user profile for the user. The system may compare the user preference to the user profile to determine a criterion for content recommendations for the user. The system may receive a content attribute for content provided by a content provider. The system may match the criterion to the content attribute. The system may, in response to matching the criterion to the content attribute, generate for display a recommendation to the user for the content.

Claims20

Dependent claims

A system of providing recommendations based on user-supplied criteria using artificial intelligence models, the system comprising:

memory;
and
non-transitory computer-readable memory comprising instructions that cause a processor to perform operations comprising:
receiving, from a user, a prompt, via a user interface, for content;
retrieving a user profile for the user;
in response to receiving the prompt, receiving, via the user interface, a user preference for content recommendations from a user;
comparing the user preference to the user profile to determine a criterion for content recommendations for the user by generating a first feature input for a first model based on the user preference and the user profile and inputting the first feature input into the first model to receive the criterion, wherein the first model comprises a first content-based filtering component and a first collaborative filtering component;
receiving a content attribute for content provided by a content provider;
retrieving a content provider profile for the content provider;
comparing the content attribute to the content provider profile to determine a normalized content attribute for content recommendations for the content provider by generating a second feature input for a second model based on the content attribute and the content provider profile and inputting the second feature input into the second model to receive the normalized content attribute, wherein the second model comprises a second content-based filtering component and a second collaborative filtering component;
matching the criterion to the normalized content attribute;
and
in response to matching the criterion to the normalized content attribute, generating for display, on the user interface, a recommendation to the user for the content.

10 more elements

A method of providing recommendations based on user-supplied criteria, the method comprising:

receiving, from a user, a prompt, via a user interface, for content;
retrieving a user profile for the user;
determining a user preference for content recommendations;
in response to receiving the prompt, receiving, via the user interface, a user preference for content recommendations;
inputting the user preference and the user profile into a first model to determine a criterion for content recommendations for the user, wherein the first model comprises a first content-based filtering component and a first collaborative filtering component;
receiving a content attribute for content provided by a content provider;
retrieving a content provider profile for the content provider;
inputting the content attribute and the content provider profile into a second model to determine a normalized content attribute for content recommendations for the content provider, wherein the second model comprises a second content-based filtering component and a second collaborative filtering component;
matching the criterion to the normalized content attribute;
and
in response to matching the criterion to the normalized content attribute, generating for display, on the user interface, a recommendation to the user for the content.

8 more elements

A non-transitory, computer-readable medium comprising instructions embedded thereon that when executed by one or more processors causes operations comprising:

receiving, from a user, a prompt for content;
retrieving a user profile for the user;
in response to receiving the prompt, receiving a user preference for content recommendations from a user;
comparing the user preference to the user profile to determine a criterion for content recommendations for the user by generating a first feature input for a first model based on the user preference and the user profile and inputting the first feature input into the first model to receive the criterion, wherein the first model comprises a first content-based filtering component and a first collaborative filtering component;
receiving a content attribute for content provided by a content provider;
retrieving a content provider profile for the content provider;
comparing the content attribute to the content provider profile to determine a normalized content attribute for content recommendations for the content provider by generating a second feature input for a second model based on the content attribute and the content provider profile and inputting the second feature input into the second model to receive the normalized content attribute, wherein the second model comprises a second content-based filtering component and a second collaborative filtering component;
matching the criterion to the normalized content attribute;
and
in response to matching the criterion to the normalized content attribute, generating for display a recommendation to the user for the content.

7 more elements

Dependencies are inferred from the claim text.

Facts

Application: 18/458,618Filed 30 Aug 2023
Priority: 10 Feb 2020
Published: 21 Dec 2023
Term ends: Not estimatedThe source records don’t support an estimate.

Classification16 codes

H04N 21/4668
Learning process for intelligent management, e.g. learning user preferences for recommending movies: for recommending content, e.g. movies
G06N 3/0442
Recurrent networks, e.g. Hopfield networks: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
G06N 3/045
Architecture, e.g. interconnection topology: combinations of networks
G06N 3/0455
Combinations of networks: auto-encoder networks; Encoder-decoder networks

Family

Application62/972,430Us provisional application · filed 10 Feb 2020
Application17/759,029Continuation · filed 18 Jul 2022
Application18/458,618Continuation
US 11,838,591 B2Related patent
US 12,177,521 B2Related patent
US 2023/0040678 A1Published application
US 2023/0412888 A1This patent

From the US filing history. Foreign family members aren’t listed.

Timeline

Citations

Open elsewhere

Building an agent or pulling many patents? Use the API or MCP server instead of scraping pages. Get an API key