SYSTEM AND METHOD FOR DYNAMIC CREATIVE OPTIMIZATION VIA GENERATIVE AI

1 . A method, comprising:

obtaining, via machine learning, generative artificial intelligence (AI) models for creating advertisement assets based on training data generated based on online feedback information on previously displayed advertisements;

receiving base advertisement information associated with an advertisement for a product, wherein the base advertisement information specifies a base image to characterize features of the product; and

modifying at least one of the features exhibited in the base image to create different image assets of the product based on the generative AI models, wherein

the different image assets of the product used to form different asset combinations each of which can be used to display the advertisement for the product via an online platform.

2 . The method of claim 1 , further comprising:

receiving a request for a recommendation of an advertisement for a display advertisement opportunity associated with a user;

accessing information related to a plurality of advertisements and different asset combinations associated each of the plurality of advertisements;

selecting one of the plurality of advertisements based on the request;

selecting one of the different asset combinations associated with the selected advertisement according to performance metrics estimated for the different asset combinations;

generating an advertisement recommendation based on the selected asset combination; and

sending the advertisement recommendation in response to the request.

3 . The method of claim 1 , wherein the online feedback information includes user activities with respect to the previously displayed advertisements, wherein the user activities include at least one of:

clicks on the previously displayed advertisements; or

conversions related to the previously displayed advertisements.

4 . The method of claim 1 , wherein

the base advertisement information further specifies at least one of a base title and a base description of the product;

the method further comprising modifying at least one of a base title and a base description of the product to create

different title assets for the product, and/or

different description assets for the product.

5 . The method of claim 4 , wherein

the different title assets are created based on the base title;

and

the different description assets are created based on the base description.

6 . The method of claim 1 , wherein the obtaining the generative AI models comprises:

analyzing the online feedback information to identify user activities with respect to the previously displayed advertisements;

determining performance metrics of the previously displayed advertisements based on the identified user activities;

detecting features of advertisement assets used in the previously displayed advertisements;

generating the training data based on the features of advertisements and performance metrics of the previously displayed advertisements; and

training the generative AI models using the training data.

7 . The method of claim 1 , wherein the creating the plurality of advertisement assets comprises:

determining an asset creation range based on the base advertisement information; and

generating the plurality of advertisement assets within the asset creation range, wherein

the base advertisement information specifies geo-regions and/or a target audience intended for the advertisement, and

the asset creation range specifies one or more segments for which the advertisement assets are to be generated which are determined based on at least one of the geo-regions, the target audience, and some modifying variables defining allowable modifications to be applied to the base advertisement information to create advertisement assets.

8 . A non-transitory machine-readable medium having information recorded thereon, wherein the information, when read by a machine, causes the machine to perform the following steps:

obtaining, via machine learning, generative artificial intelligence (AI) models for creating advertisement assets based on training data generated based on online feedback information on previously displayed advertisements;

receiving base advertisement information associated with an advertisement for a product, wherein the base advertisement information specifies a base to characterize features of the product; and

modifying at least one of the features exhibited in the base image to create different image assets of the product based on the generative AI models, wherein

the different image assets of the product are used to form different asset combinations each of which can be used to display the advertisement for the product via an online platform.

9 . The medium of claim 8 , wherein the information, when read by the machine, further causes the machine to perform the following steps:

receiving a request for a recommendation of an advertisement for a display advertisement opportunity associated with a user;

accessing information related to a plurality of advertisements and different asset combinations associated each of the plurality of advertisements;

selecting one of the plurality of advertisements based on the request;

selecting one of the different asset combinations associated with the selected advertisement according to performance metrics estimated for the different asset combinations;

generating an advertisement recommendation based on the selected asset combination; and

sending the advertisement recommendation in response to the request.

10 . The medium of claim 8 , wherein the online feedback information includes user activities with respect to the previously displayed advertisements, wherein the user activities include at least one of:

clicks on the previously displayed advertisements; or

conversions related to the previously displayed advertisements.

11 . The medium of claim 8 , wherein

the base advertisement information further specifies at least one of a base title and a base description of the product;

the method further comprising modifying at least one of a base title and a base description of the product to create

different title assets for the product, and/or

different description assets for the product.

12 . The medium of claim 11 , wherein

the different title assets are created based on the base title;

and

the different description assets are created based on the base description.

13 . The medium of claim 8 , wherein the obtaining the generative AI models comprises:

analyzing the online feedback information to identify user activities with respect to the previously displayed advertisements;

determining performance metrics of the previously displayed advertisements based on the identified user activities;

detecting features of advertisement assets used in the previously displayed advertisements;

generating the training data based on the features of advertisements and performance metrics of the previously displayed advertisements; and

training the generative AI models using the training data.

14 . The medium of claim 8 , wherein the creating the plurality of advertisement assets comprises:

determining an asset creation range based on the base advertisement information; and

generating the plurality of advertisement assets within the asset creation range, wherein

the base advertisement information specifies geo-regions and/or a target audience intended for the advertisement, and

the asset creation range specifies one or more segments for which the advertisement assets are to be generated which are determined based on at least one of the geo-regions, the target audience, and some modifying variables defining allowable modifications to be applied to the base advertisement information to create advertisement assets.

15 . A system, comprising:

a processor;

a machine learning engine implemented by the processor and configured for obtaining, via machine learning, generative artificial intelligence (AI) models for creating advertisement assets based on training data generated based on online feedback information on previously displayed advertisements; and

an AI-assisted ad asset generator implemented by the processor and configured for

receiving base advertisement information associated with an advertisement for a product, wherein the base advertisement information specifies a base image to characterize features of the product, and

modifying at least one of the features exhibited in the base image to create different image assets of the product based on the generative AI models, wherein

the different image assets of the product are used to form different asset combinations each of which can be used to display the advertisement for the product via an online platform.

16 . The system of claim 15 , further comprising an ad recommendation server implemented by the processor and configured for:

receiving a request for a recommendation of an advertisement for a display advertisement opportunity associated with a user;

accessing information related to a plurality of advertisements and different asset combinations associated each of the plurality of advertisements;

selecting one of the plurality of advertisements based on the request;

selecting one of the different asset combinations associated with the selected advertisement according to performance metrics estimated for the different asset combinations;

generating an advertisement recommendation based on the selected asset combination; and

sending the advertisement recommendation in response to the request.

17 . The system of claim 15 , wherein the online feedback information includes user activities with respect to the previously displayed advertisements, wherein the user activities include at least one of:

clicks on the previously displayed advertisements; or

conversions related to the previously displayed advertisements.

18 . The system of claim 15 , wherein

the base advertisement information further specifies at least one of a base title and a base description of the product;

the method further comprising modifying at least one of a base title and a base description of the product to create

different title assets for the product created based on the base title, and/or

different description assets for the product created based on the base description.

19 . The system of claim 15 , wherein the obtaining the generative AI models comprises:

analyzing the online feedback information to identify user activities with respect to the previously displayed advertisements;

determining performance metrics of the previously displayed advertisements based on the identified user activities;

detecting features of advertisement assets used in the previously displayed advertisements;

generating the training data based on the features of advertisements and performance metrics of the previously displayed advertisements; and

training the generative AI models using the training data.

20 . The system of claim 15 , wherein the creating the plurality of advertisement assets comprises:

determining an asset creation range based on the base advertisement information; and

generating the plurality of advertisement assets within the asset creation range, wherein the base advertisement information specifies geo-regions and/or a target audience intended for the advertisement, and

the asset creation range specifies one or more segments for which the advertisement assets are to be generated which are determined based on at least one of the geo-regions, the target audience, and some modifying variables defining allowable modifications to be applied to the base advertisement information to create advertisement assets.