Go Daddy Operating Company, LLC

Go Daddy Operating, LLC

Yu Tian

Wei-Cheng Lai

Wenbo Wang

Tapan Kamdar

Chungwei Yen

Grace Wardhana

Xiang Mao

David A Kellogg

Tejas Prakash Bajaj

Salvador Celis

Jyothiprakash Trishuleshwar

Methods are taught for creating training data for a learning algorithm, training the learning algorithm with the training data and using the trained learning algorithm to suggest domain names to users. A domain name registrar may store activities of a user on a registrar website. Preferably, domain name searches, selected suggested domain names and domain names registered to the user are stored as the training data in a training database. The training data may be stored so that earlier activities act as inputs to the learning algorithm while later activities are the expected outputs of the learning algorithm. Once trained, the learning algorithm may receive activities of other users and suggest domain names to the other users based on their activities.

Using a learning algorithm to suggest domain names

Systems and methods of the present invention provide for one or more server computers communicatively coupled to a network and configured to: identify a business name within an aggregation of business names; tokenize the business name; match a resulting token to an industry related keyword; generate a template with placeholders replacing a prefix or a suffix appended to the token from a recognized pattern; identify a request to generate a name candidate, select a personalized data associated with the requesting user and an associated industry; and generate a list of name candidates, with the personalized data inserted into the placeholder; then determines the availability and ranks each name candidate in the list.

Data-driven online business name generator

Training a learning algorithm to suggest domain names

Methods for generating (also known as spinning) and displaying suggested domain names to a domain name registrant by a domain name registrar are presented. The methods generate and display suggested domain names based on one or more methods. The one or more methods include determining how frequently the generated domain names are displayed to the domain name registrant (the fewer the times the better), the value of the generated domain names and/or how well the generated domain names compliment a portfolio of domain names or products and services already registered to the domain name registrant.

Portfolio-based domain name recommendations

Systems and methods of the present invention provide for one or more server computers communicatively coupled to a network and configured to: receive a string used to search an available domain name, identify a token within the string, select a misspelled token in a misspelled token database matching the token, and generate a corrected search string with a corrected token replacing the misspelled token. If the corrected search string has a higher probability of representing the intent of the user, the server generates and transmits one or more available domain name candidates with the corrected token to the user's client computer.

Misspelling identification in domain names

Growing community of inventors

Sunnyvale, CA, United States of America

Yu Tian