Dataset distinctiveness modeling

1. A method, comprising:

receiving first data representing a trademark associated with at least one of a good or service;

receiving second data representing a description of the at least one of the good or the service;

querying a set of databases to determine a first language associated with the trademark, individual ones of the set of databases including words in a given language;

determining that the description of the at least one of the good or the service is in a second language that differs from the first language;

translating the trademark from the first language to the second language;

generating, based at least in part on a translated version of the trademark to the second language, third data including a first vector representation of the first data;

generating fourth data including a second vector representation of the second data;

generating, via a machine learning model trained on feedback and based at least in part on the third data and the fourth data, fifth data indicating a distance between the first vector representation and the second vector representation in a vector space and quantifying a degree of distinctiveness of the trademark in association with the at least one of the good or the service; and

sending, via a network protocol over a network to a user device, a command configured to cause an application on the user device to enable and to display, without user input, a recommendation to change the description of the at least one of the good or the service based on the distance satisfying a threshold distance indicating that the trademark is similar to the description of the at least one of the good or the service.

2. The method of claim 1 , further comprising:

determining context data associated with the trademark, wherein the context data includes at least one of a first indication that the trademark is associated with a first declaration that the trademark has been in use continuously for at least a first period of time, a second indication that the trademark is associated with a second declaration that an owner of a registration for the trademark has claimed incontestable rights in the trademark, or a third indication that a disclaimer has been associated with the trademark; and

weighting the fifth data based at least in part on the context data.

3. The method of claim 1 , further comprising:

generating, utilizing text data representing a text portion of the trademark, metadata indicating syllables of the text portion of the trademark;

determining that the syllables of the text portion correspond to a word in a reference database of words; and

wherein generating the third data including the first vector representation is based at least in part on the syllables corresponding to the word.

4. The method of claim 1 , further comprising:

generating, utilizing text data representing a text portion of the trademark, metadata indicating syllables of the text portion of the trademark;

determining that the syllables of the text portion do not correspond to a word in a reference database of other trademarks; and

wherein the fifth data is based at least in part on the syllables of the text portion not corresponding to the word.

5. The method of claim 1 , further comprising:

generating a machine learning model configured to determine a correlation between trademarks and related descriptions of goods and services;

generating a training dataset based at least in part on feedback data associated with prior correlations between the trademarks and the related descriptions of goods and services;

training the machine learning model utilizing the training dataset such that a trained machine learning model is generated; and

wherein generating the fifth data is performing utilizing the trained machine learning model.

6. The method of claim 1 , further comprising:

determining that the distance satisfies a threshold distance indicating that the trademark is similar to the description of the at least one of the good or the service; and

generating, based at least in part on the distance satisfying the threshold distance, a recommendation to change the description of the at least one of the good or the service, the recommendation including an alternative description of the at least one of the good or the service, the alternative description associated with a third vector representation having a greater distance from the first vector representation than the distance.

7. The method of claim 1 , further comprising:

determining, from text data associated with a text portion of the trademark, that the text portion corresponds to an acronym listed in a database of acronyms;

determining, utilizing the database, a phrase that corresponds to the acronym; and

wherein generating the third data including the first vector representation is based at least in part on the phrase that corresponds to the acronym.

8. The method of claim 5 , wherein training the machine learning model comprises identifying a new feature that the trained machine learning model will utilize when determining the correlation between the trademarks and the related descriptions of goods and services, the new feature being unutilized by the machine learning model prior to training the machine learning model.

9. The method of claim 5 , wherein training the machine learning model comprises applying a first weighting to a feature that the trained machine learning model will utilize when determining the correlation between the trademarks and the related description of goods and services, the first weighting differing from a second weighting of the feature utilized by the machine learning model prior to training the machine learning model.

10. A system, comprising:

one or more processors; and

non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:

receiving first data representing a trademark associated with at least one of a good or service;

receiving second data representing a description of the at least one of the good or the service;

determining that the description of the at least one of the good or the service is in a first language that differs from a second language that the trademark is in;

translating the trademark from the second language to the first language; generating, based at least in part on a translated version of the trademark to the first language, third data including a first vector representation of the first data;

generating fourth data including a second vector representation of the second data;

generating, via a machine learning model trained on feedback and based at least in part on the third data and the fourth data, a value indicating a distance between the first vector representation and the second vector representation in a vector space and quantifying a degree of distinctiveness of the trademark in association with the at least one of the good or the service; and

sending, via a network protocol over a network to a user device, a command configured to cause an application on the user device to enable and to display, without user input, a recommendation to change the description of the at least one of the good or the service based on the value indicating the distance between the first vector representation and the second vector representation in the vector space and quantifying the degree of distinctiveness of the trademark in association with the at least one of the good or the service.

11. The system of claim 10 , the operations further comprising:

determining context data associated with the trademark, wherein the context data includes an indication that a disclaimer has been associated with the trademark; and

weighting the value based at least in part on the context data.

12. The system of claim 10 , the operations further comprising:

generating metadata indicating syllables of a text portion of the trademark;

determining that the syllables of the text portion correspond to a word in a reference database of words; and

wherein generating the third data including the first vector representation is based at least in part on the syllables corresponding to the word.

13. The system of claim 10 , the operations further comprising:

generating metadata indicating syllables of a text portion of the trademark;

determining that the syllables of the text portion do not correspond to from a word in a reference database of other trademarks; and

wherein the value is based at least in part on the syllables of the text portion not corresponding to the word.

14. The system of claim 10 , the operations further comprising:

generating a machine learning model configured to determine a correlation between trademarks and related descriptions of goods and services;

generating a training dataset based at least in part on prior feedback data associated with prior correlations between the trademarks and the related descriptions of goods and services;

training the machine learning model utilizing the training dataset such that a trained machine learning model is generated; and

wherein generating the value is performing utilizing the trained machine learning model.

15. The system of claim 10 , the operations further comprising:

determining that a text portion of the trademark corresponds to an acronym listed in a database of acronyms;

determining, utilizing the database, a phrase that corresponds to the acronym; and

wherein generating the third data including the first vector representation is based at least in part on the phrase that corresponds to the acronym.

16. The system of claim 14 , wherein training the machine learning model comprises identifying a new feature that the trained machine learning model will utilize when determining the correlation between the trademarks and the related descriptions of goods and services, the new feature being unutilized by the machine learning model prior to training the machine learning model.

17. The system of claim 14 , wherein training the machine learning model comprises applying a first weighting to a feature that the trained machine learning model will utilize when determining the correlation between the trademarks and the related description of goods and services, the first weighting differing from a second weighting of the feature utilized by the machine learning model prior to training the machine learning model.