View source for 18484661. TEXT EMBEDDING GENERATION AND APPLICATIONS (GOOGLE LLC)

=TEXT EMBEDDING GENERATION AND APPLICATIONS=


==Organization Name==

[[:Category:GOOGLE LLC|GOOGLE LLC]]


[[Category:GOOGLE LLC]]

==Inventor(s)==

[[:Category:Xi Cheng of Kirkland WA US|Xi Cheng of Kirkland WA US]][[Category:Xi Cheng of Kirkland WA US]]

[[:Category:Wen Zhang of Bellevue WA US|Wen Zhang of Bellevue WA US]][[Category:Wen Zhang of Bellevue WA US]]

[[:Category:Jiashang Liu of Kirkland WA US|Jiashang Liu of Kirkland WA US]][[Category:Jiashang Liu of Kirkland WA US]]

[[:Category:Mingge Deng of Kirkland WA US|Mingge Deng of Kirkland WA US]][[Category:Mingge Deng of Kirkland WA US]]

[[:Category:Amir Hormati of Mountain View CA US|Amir Hormati of Mountain View CA US]][[Category:Amir Hormati of Mountain View CA US]]

[[:Category:Omid Fatemieh of Bellevue WA US|Omid Fatemieh of Bellevue WA US]][[Category:Omid Fatemieh of Bellevue WA US]]

==TEXT EMBEDDING GENERATION AND APPLICATIONS==


This abstract first appeared for US patent application 18484661 titled 'TEXT EMBEDDING GENERATION AND APPLICATIONS

==Original Abstract Submitted==

A method includes receiving a text embedding generation query from a user requesting generation of a text embedding for one or more data elements stored at a data warehouse. In response, the method includes selecting, using the text embedding generation query, a text embedding model from a plurality of different text embedding models. The method includes generating, using the selected text embedding model, the text embedding for the one or more data elements and storing the text embeddings at the data warehouse. The method includes receiving a machine learning model training query from the user device requesting training of a machine learning model using the text embeddings. In response to receiving the machine learning model training query, the method includes training the machine learning model using the text embeddings. The method includes providing, to the user device, a notification indicating that training of the machine learning model is complete.



[[Category:G06F16/2452]]
[[Category:G06F16/242]]
[[Category:G06F40/40]]
[[Category:CPC_G06F16/24522]]