# US 12,008,065 B2 · Utilizing machine-learning models to generate identifier embeddings and determine digital connections between digital content items > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,008,065 B2 - Document ID: US12008065B2 - Status: Granted - Kind: B2 - Application number: 18/153,960 - Filed: 2023-01-12 - Published: 2023-06-01 - Granted: 2024-06-11 - Earliest claimed: 2020-12-22 - Assignees: Dropbox, Inc. - Applicants: Dropbox, Inc. - Inventors: Jongmin Baek; Jiarui Ding; Ermo Wei; Scott McCrae - Web page: https://patentgrep.com/patent/US12008065B2 ## CPC - G06F 16/958: Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking - G06F 16/14: Details of searching files based on file metadata - G06F 40/284: Lexical analysis, e.g. tokenisation or collocates - G06F 40/30: Semantic analysis - G06N 3/044: Recurrent networks, e.g. Hopfield networks - G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] - G06N 3/045: Combinations of networks - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/084: Backpropagation, e.g. using gradient descent - G06N 3/09: Supervised learning - G06N 20/00: Machine learning - G06N 5/02: Knowledge representation; Symbolic representation - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract The present disclosure relates to systems, methods, and non-transitory computer-readable media that utilize machine learning models to generate identifier embeddings from digital content identifiers and then leverage these identifier embeddings to determine digital connections between digital content items. In particular, the disclosed systems can utilize an embedding machine-learning model that comprises a character-level embedding machine-learning model and a word-level embedding machine-learning model. For example, the disclosed systems can combine a character embedding from the character-level embedding machine-learning model and a token embedding from the word-level embedding machine-learning model. The disclosed systems can determine digital connections between the plurality of digital content items by processing these identifier embeddings for a plurality of digital content items utilizing a content management model. Based on the digital connections, the disclosed systems can surface one or more digital content suggestions to a user interface of a client device. ## Claims ### Claim 1 A system comprising: at least one processor; and at least one non-transitory computer-readable storage medium storing instructions that, when executed by the at least one processor, cause the system to: identify a plurality of identifiers corresponding to a plurality of digital content items; generate a plurality of identifier embeddings corresponding to the plurality of identifiers by utilizing one or more embedding machine-learning models; generate digital similarity predictions between the plurality of digital content items by processing the plurality of identifier embeddings utilizing a content management model; and determine a digital connection between a subset of digital content items of the plurality of digital content items based on the digital similarity predictions. ### Claim 2 (depends on 1) The system of claim 1, wherein generating the plurality of identifier embeddings comprises generating at least one token representing a subset of individual characters within a given identifier of the plurality of identifiers. ### Claim 3 (depends on 2) The system of claim 2, wherein the subset of individual characters represents a word within the given identifier. ### Claim 4 (depends on 1) The system of claim 1, further comprising instructions that, when executed by the at least one processor, cause the system to: determine, utilizing the content management model, a digital connection between a first identifier embedding from the plurality of identifier embeddings associated with a first digital content item and a second identifier embedding from the plurality of identifier embeddings associated with a second digital content item; and based on the digital connection, generate a suggestion related to at least one of the first digital content item or the second digital content item. ### Claim 5 (depends on 1) The system of claim 1, further comprising instructions that, when executed by the at least one processor, cause the system to generate, based on the digital connection between the subset of digital content items of the plurality of digital content items, a suggestion comprising at least one of a suggested team workspace, a suggested digital content item, or a suggested access privilege. ### Claim 6 (depends on 1) The system of claim 1, further comprising instructions that, when executed by the at least one processor, cause the system to generate the plurality of identifier embeddings by utilizing a word-level embedding machine-learning model and a character-level embedding machine-learning model. ### Claim 7 (depends on 1) The system of claim 1, further comprising instructions that, when executed by the at least one processor, cause the system to generate the plurality of identifier embeddings by: generating a word-level embedding utilizing a first embedding layer of a first neural network; and generating a character-level embedding utilizing a second embedding layer of a second neural network. ### Claim 8 (depends on 1) The system of claim 1, further comprising instructions that, when executed by the at least one processor, cause the system to generate a storage organization relationship suggestion for one or more digital content items from the subset of digital content items based on the digital connection between the subset of digital content items. ### Claim 9 A non-transitory computer readable medium comprising instructions that, when executed by at least one processor, cause a computing device to: identify a plurality of identifiers corresponding to a plurality of digital content items, wherein the plurality of identifiers comprise a plurality of filenames associated with the plurality of digital content items; generate a plurality of identifier embeddings corresponding to the plurality of identifiers by utilizing one or more embedding machine-learning models; generate digital similarity predictions between the plurality of digital content items by processing the plurality of identifier embeddings utilizing a content management model; and determine a digital connection between a first digital content item and a second digital content item from the plurality of digital content items based on the digital similarity predictions. ### Claim 10 (depends on 9) The non-transitory computer readable medium as recited in claim 9, wherein generating the plurality of identifier embeddings comprises generating a first token representing a word within a first filename associated with the first digital content item. ### Claim 11 (depends on 9) The non-transitory computer readable medium as recited in claim 9, further comprising instructions that, when executed by the at least one processor, cause the computing device to: generate a suggestion related to the first digital content item or the second digital content item based on the digital connection between the first digital content item and the second digital content item; and provide the suggestion to a client device having access to the plurality of digital content items. ### Claim 12 (depends on 9) The non-transitory computer readable medium as recited in claim 9, further comprising instructions that, when executed by the at least one processor, cause the computing device to generate, based on the digital connection between the first digital content item and the second digital content item, a suggestion comprising at least one of a suggested team workspace, a suggested digital content item, or a suggested access privilege. ### Claim 13 (depends on 9) The non-transitory computer readable medium as recited in claim 9, further comprising instructions that, when executed by the at least one processor, cause the computing device to generate the plurality of identifier embeddings by utilizing a word-level embedding machine-learning model to process words within the plurality of filenames and a character-level embedding machine-learning model to process characters within the plurality of filenames. ### Claim 14 (depends on 9) The non-transitory computer readable medium as recited in claim 9, further comprising instructions that, when executed by the at least one processor, cause the computing device to generate a suggestion for the first digital content item based on at least one of: a file extension embedding corresponding to the first digital content item; or a user activity embedding corresponding to user activity with respect to the first digital content item. ### Claim 15 A computer-implemented method comprising: identifying a plurality of identifiers corresponding to a plurality of digital content items; generating a plurality of identifier embeddings corresponding to the plurality of identifiers by utilizing one or more embedding machine-learning models; generating digital similarity predictions between the plurality of digital content items by processing the plurality of identifier embeddings utilizing a content management model; and determining a digital connection between a subset of digital content items of the plurality of digital content items based on the digital similarity predictions. ### Claim 16 (depends on 15) The computer-implemented method of claim 15, wherein generating the plurality of identifier embeddings comprises generating a token representing a subset of individual characters within a given identifier of the plurality of identifiers. ### Claim 17 (depends on 15) The computer-implemented method of claim 15, further comprising providing, for display on a client device and based on the digital connection between the subset of digital content items of the plurality of digital content items, a suggestion comprising at least one of a suggested team workspace, a suggested digital content item, or a suggested access privilege. ### Claim 18 (depends on 15) The computer-implemented method of claim 15, further comprising generating the plurality of identifier embeddings by utilizing a word-level embedding machine-learning model and a character-level embedding machine-learning model. ### Claim 19 (depends on 15) The computer-implemented method of claim 15, wherein generating the plurality of identifier embeddings comprises: generating a word-level embedding utilizing a first embedding layer of a first neural network; and generating a character-level embedding utilizing a second embedding layer of a second neural network. ### Claim 20 (depends on 15) The computer-implemented method of claim 15, further comprising generating a storage organization relationship suggestion for one or more digital content items from the subset of digital content items based on the digital connection between the subset of digital content items.