# US 12,008,448 B2 · Documentation file-embedded machine learning models > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,008,448 B2 - Document ID: US12008448B2 - Status: Granted - Kind: B2 - Application number: 18/183,120 - Filed: 2023-03-13 - Published: 2023-07-13 - Granted: 2024-06-11 - Earliest claimed: 2019-07-23 - Assignees: AT&T Intellect al P Property I, L.P. - Applicants: AT&T Intellectual Property I, L.P. - Inventors: Changchuan Yin - Web page: https://patentgrep.com/patent/US12008448B2 ## CPC - G06N 20/00: Machine learning - G06F 40/103: Formatting, i.e. changing of presentation of documents (automatic justification G06F40/189; automatic line break hyphenation G06F40/191) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract A processing system including at least one processor may obtain a machine learning model, serialize the machine learning model into a serialized format, and embed a delimiter indicator into a documentation file comprising information regarding the use of the machine learning model, where the delimiter indicator is in a file position that is after an end-of-file indicator of the documentation file. The processing system may further embed the machine learning model in the serialized format into the documentation file in a file position that is after the delimiter indicator. The processing system may then store the documentation file with the delimiter indicator and the machine learning model in the serialized format that are embedded. ## Claims ### Claim 1 A method comprising: obtaining, by a processing system including at least one processor, a documentation file comprising information regarding a use of a machine learning model, wherein the documentation file is in comprises a byte array, wherein the documentation file includes a delimiter indicator that is embedded, wherein the delimiter indicator is in a file position that is after an end-of-file indicator of the documentation file, wherein the end-of-file indicator indicates an end of a documentation file content, wherein the end-of-file indicator is in an intermediate position in the byte array, wherein the machine learning model is embedded in the documentation file, wherein the machine learning model is in a serialized format, and wherein the machine learning model is in a file position of the documentation file that is after the delimiter indicator; determining, by the processing system, the file position of the delimiter indicator; extracting, by the processing system, the machine learning model in the serialized format from the documentation file in accordance with the delimiter indicator; and storing, by the processing system, the machine learning model that is extracted in a separate file from the documentation file. ### Claim 2 (depends on 1) The method of claim 1, wherein the machine learning model comprises: a trained machine learning model; or an untrained machine learning model. ### Claim 3 (depends on 2) The method of claim 2, wherein the machine learning model comprises the untrained machine learning model, the method further comprising: training the untrained machine learning model in accordance with a set of input data to create a newly trained machine learning model; and storing the newly trained machine learning model. ### Claim 4 (depends on 1) The method of claim 1, wherein the delimiter indicator is a byte sequence that is associated with a text code. ### Claim 5 (depends on 4) The method of claim 4, wherein the text code is included in a portion of the documentation file that is accessible via a user application. ### Claim 6 (depends on 5) The method of claim 5, wherein the text code is included in a metadata field of the documentation file. ### Claim 7 (depends on 1) The method of claim 1, wherein the documentation file comprises: a text document file; a portable document format file; an image file; or a video file. ### Claim 8 (depends on 1) The method of claim 1, wherein the information regarding the use of the machine learning model is accessible via a user application, wherein the information regarding the use of the machine learning model comprises at least one of: text-based information; image-based information; or video-based information. ### Claim 9 An apparatus comprising: a processing system including at least one processor; and a non-transitory computer-readable storage medium storing instructions which, when executed by the processing system, cause the processing system to perform operations, the operations comprising: a documentation file comprising information regarding a use of a machine learning model, wherein the documentation file comprises a byte array, wherein the documentation file includes a delimiter indicator that is embedded, wherein the delimiter indicator is in a file position that is after an end-of-file indicator of the documentation file, wherein the end-of-file indicator indicates an end of a documentation file content, wherein the end-of-file indicator is in an intermediate position in the byte array, wherein the machine learning model is embedded in the documentation file, wherein the machine learning model is in a serialized format, and wherein the machine learning model is in a file position of the documentation file that is after the delimiter indicator; determining the file position of the delimiter indicator; extracting the machine learning model in the serialized format from the documentation file in accordance with the delimiter indicator; and storing the machine learning model that is extracted in a separate file from the documentation file. ### Claim 10 (depends on 9) The apparatus of claim 9, wherein the machine learning model comprises: a trained machine learning model; or an untrained machine learning model. ### Claim 11 (depends on 10) The apparatus of claim 10, wherein the machine learning model comprises the untrained machine learning model, the operations further comprising: training the untrained machine learning model in accordance with a set of input data to create a newly trained machine learning model; and storing the newly trained machine learning model. ### Claim 12 (depends on 9) The apparatus of claim 9, wherein the delimiter indicator is a byte sequence that is associated with a text code. ### Claim 13 (depends on 12) The apparatus of claim 12, wherein the text code is included in a portion of the documentation file that is accessible via a user application. ### Claim 14 (depends on 13) The apparatus of claim 13, wherein the text code is included in a metadata field of the documentation file. ### Claim 15 (depends on 9) The apparatus of claim 9, wherein the documentation file comprises: a text document file; a portable document format file; an image file; or a video file. ### Claim 16 (depends on 9) The apparatus of claim 9, wherein the information regarding the use of the machine learning model is accessible via a user application, wherein the information regarding the use of the machine learning model comprises at least one of: text-based information; image-based information; or video-based information. ### Claim 17 A non-transitory computer-readable storage medium storing instructions which, when executed by a processing system including at least one processor, cause the processing system to perform operations, the operations comprising: a documentation file comprising information regarding a use of a machine learning model, wherein the documentation file comprises a byte array, wherein the documentation file includes a delimiter indicator that is embedded, wherein the delimiter indicator is in a file position that is after an end-of-file indicator of the documentation file, wherein the end-of-file indicator indicates an end of a documentation file content, wherein the end-of-file indicator is in an intermediate position in the byte array, wherein the machine learning model is embedded in the documentation file, wherein the machine learning model is in a serialized format, and wherein the machine learning model is in a file position of the documentation file that is after the delimiter indicator; determining the file position of the delimiter indicator; extracting the machine learning model in the serialized format from the documentation file in accordance with the delimiter indicator; and storing the machine learning model that is extracted in a separate file from the documentation file. ### Claim 18 (depends on 17) The non-transitory computer-readable storage medium of claim 17, wherein the machine learning model comprises: a trained machine learning model; or an untrained machine learning model. ### Claim 19 (depends on 18) The non-transitory computer-readable storage medium of claim 18, wherein the machine learning model comprises the untrained machine learning model, the method further comprising: training the untrained machine learning model in accordance with a set of input data to create a newly trained machine learning model; and storing the newly trained machine learning model. ### Claim 20 (depends on 17) The non-transitory computer-readable storage medium of claim 17, wherein the delimiter indicator is a byte sequence that is associated with a text code.