Computer-based domain name recommendation system utilizing personalized generative artificial intelligence engines and methods of use thereof

1 . A method, comprising:

instructing, by a server computing device via an endpoint thereof, a client computing device of a first user to display a domain search interface;

receiving, via the endpoint of the server computing device, a domain search query from the domain search interface of the client computing device;

tokenizing, by the server computing device, the domain search query;

generating, by the server computing device, a first plurality of vector embeddings from the tokenized domain search query;

generating, by the server computing device, based on the domain search query and user profile information associated with the first user, a prompt comprising a temperature hyperparameter to provide to a first machine learning model, the prompt instructing the first machine learning model to provide at least one domain name recommendation, wherein

the temperature hyperparameter controls predictability of the at least one domain name recommendation,

in a case where the temperature hyperparameter is less than a threshold value, the at least one domain name recommendation is predictable,

in a case where the temperature hyperparameter is greater than the threshold value, the at least one domain name recommendation is random, and

the first machine learning model is trained by utilizing at least one dataset comprising:

first data reflecting interactions of a plurality of users, including the first user, with a plurality of domain portfolios,

second data reflecting a plurality of domain-related actions, performed by the plurality of users, comprising at least one first domain-related action with at least one top-level domain (TLD) and at least one second domain-related action with at least one second-level domain (SLD),

third data reflecting a behavior of a second user of the plurality of users, different from the first user, during a current domain search session,

fourth data reflecting a plurality of behaviors, excluding the behavior, of the second user over a predetermined period of time covering a plurality of search sessions, excluding the current domain search session, of the second user, and

fifth data reflecting a plurality of search scenarios of the plurality of users;

fine-tuning, in real-time, based on the prompt and one or more real-time interactions of the first user with the plurality of domain portfolios during the current domain search session, the first machine learning model to generate the at least one domain name recommendation, wherein the fine-tuning of the first machine learning model comprises:

optimizing the first machine learning model based on a Low-Rank Adaptation (LoRA) technique and the temperature hyperparameter, wherein the LoRA technique comprises modifying a subset of a plurality of internal parameters of the first machine learning model;

predicting the at least one domain name recommendation based on the optimized first machine learning model;

determining, by the server computing device, the predicted at least one domain name recommendation against at least one predetermined rule to form at least one sanitized domain name recommendation;

verifying, by the server computing device, an availability to register the at least one sanitized domain name recommendation to form at least one available domain name recommendation;

tokenizing, by the server computing device, the at least one available domain name recommendation;

generating, by the server computing device, a second plurality of vector embeddings from the tokenized at least one available domain name recommendation;

performing, by the server computing device, a vector space search on the first plurality of vector embeddings and the second plurality of vector embeddings to form at least one vector-based domain name recommendation;

adding, by the server computing device, industry information to the at least one vector-based domain name recommendation to form at least one enriched domain name recommendation, wherein the industry information is generated by a second machine learning model based at least in part on the at least one available domain name recommendation; and

transmitting, by the server computing device via the endpoint, at least one computer instruction configured for the client computing device to present the at least one enriched domain name recommendation to the first user in association with an action-enable graphical user element.

2 . The method of claim 1 , wherein the prompt is generated based at least in part on at least one customer signal associated with the domain search query.

3 . The method of claim 2 , wherein the at least one customer signal is obtained through at least one cookie stored in the client computing device.

4 . The method of claim 1 , wherein the domain search query comprises an identification of the client computing device.

5 . The method of claim 1 , wherein the user profile information is retrieved based on an identification of the client computing device.

6 . The method of claim 1 , wherein the user profile information comprises aggregated patterns of search behavior, purchase histories, and preferences of the first user.

7 . The method of claim 1 , wherein the prompt is selected from the group consisting of: at least one prompt payload and at least one diversity parameter.

8 . The method of claim 1 , wherein

the predetermined rule comprises a list of undesirable items for the predicted at least one domain name recommendation, and

the undesirable items are selected from the group consisting of: at least one taboo token, at least one exclusion word, and at least one unsellable TLD.

9 . The method of claim 1 , wherein the second machine learning model is trained based on industry data collected by at least one online service provider.

10 . The method of claim 1 , wherein the industry information comprises information on ways of utilizing the at least one sanitized domain name recommendation by at least one industry pertaining to the at least one sanitized domain name recommendation.

11 . The method of claim 1 , further comprising streaming, by the server computing device, the at least one enriched domain name recommendation into at least one log group.

12 . The method of claim 11 , further comprising transforming the at least one log group from a first format to a second format.

13 . The method of claim 1 , further comprising:

augmenting the at least one enriched domain name recommendation with at least one keyword-based domain name suggestion to form at least one augmented domain name recommendation; and

transmitting the at least one augmented domain name recommendation to the client computing device.

14 . A system, comprising:

at least one processor; and

at least one memory storing a plurality of computing instructions configured to instruct the at least one processor to:

instruct, via an endpoint of the system, a client computing device to display a domain search interface;

receive, via the endpoint, a domain search query from the domain search interface of the client computing device of a first user;

tokenize the domain search query;

generate a first plurality of vector embeddings from the tokenized domain search query;

generate, based on the domain search query and user profile information associated with the first user, a prompt comprising a temperature hyperparameter to provide to a first machine learning model, the prompt instructing the first machine learning model to provide at least one domain name recommendation, wherein

the temperature hyperparameter controls predictability of the at least one domain name recommendation,

in a case where the temperature hyperparameter is less than a threshold value, the at least one domain name recommendation is predictable,

in a case where the temperature hyperparameter is greater than the threshold value, the at least one domain name recommendation is random, and

the first machine learning model is trained by utilizing at least one dataset comprising:

first data reflecting interactions of a plurality of users, including the first user, with a plurality of domain portfolios,

second data reflecting a plurality of domain-related actions performed by the plurality of users, comprising at least one first domain-related action with at least one top-level domain (TLD) and at least one second domain-related action with at least one second-level domain (SLD),

third data reflecting a behavior of a second user of the plurality of users, different from the first user, during a current domain search session,

fourth data reflecting a plurality of behaviors, excluding the behavior, of the second user over a predetermined period of time covering a plurality of search sessions, excluding the current domain search session, of the second user, and

fifth data reflecting a plurality of search scenarios of the plurality of users;

fine-tune, in real-time, based on the prompt and one or more real-time interactions of the first user with the plurality of domain portfolios during the current domain search session, the first machine learning model to generate the at least one domain name recommendation, wherein the fine-tuning of the first machine learning model comprises:

optimize the first machine learning model based on a Low-Rank Adaptation (LoRA) technique and the temperature hyperparameter, wherein the LoRA technique modifies a smaller subset of a plurality of internal parameters of the first machine learning model;

predict the at least one domain name recommendation based on the optimized first machine learning model;

determine the predicted at least one domain name recommendation against a predetermined rule to form at least one sanitized domain name recommendation;

verify an availability to register the at least one sanitized domain name recommendation to form at least one available domain name recommendation;

tokenize the at least one available domain name recommendation;

generate a second plurality of vector embeddings from the tokenized at least one available domain name recommendation;

perform a vector space search on the first plurality of vector embeddings and the second plurality of vector embeddings to form at least one vector-based domain name recommendation;

add industry information to the at least one vector-based domain name recommendation to form at least one enriched domain name recommendation, wherein the industry information is generated by a second machine learning model based at least in part on the at least one available domain name recommendation; and

transmit, via the endpoint, at least one computer instruction configured for the client computing device to present the at least one enriched domain name recommendation to the first user in association with an action-enable graphical user element.

15 . The system of claim 14 , wherein the prompt is generated based at least in part on at least one customer signal associated with the domain search query.

16 . The system of claim 14 , wherein the user profile information is retrieved based on an identification contained in the domain search query.

17 . The system of claim 14 , wherein the second machine learning model is trained based on industry data collected by at least one online service provider.