# US 11,443,144 B2 · Storage and automated metadata extraction using machine teaching > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,443,144 B2 - Document ID: US11443144B2 - Status: Granted - Kind: B2 - Application number: 16/821,886 - Filed: 2020-03-17 - Published: 2021-09-23 - Granted: 2022-09-13 - Earliest claimed: 2020-03-17 - Assignees: Microsoft Technology Licensing, LLC - Applicants: Microsoft Technology Licensing, LLC - Inventors: Sean Squires; Mingquan Xue; Yuri Rychikhin; Liming Chen; Nicholas Anthony Buelich, II - Web page: https://patentgrep.com/patent/US11443144B2 ## CPC - G06F 16/35: Clustering; Classification - G06F 16/176: Support for shared access to files; File sharing support - G06F 16/367: {Ontology} - G06F 17/18: for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)} - G06F 18/2155: {characterised by the incorporation of unlabelled data, e.g. multiple instance learning [MIL], semi-supervised techniques using expectation-maximisation [EM] or naïve labelling} - G06N 20/00: Machine learning - G06Q 10/101: Collaborative creation, e.g. joint development of products or services - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR ## Abstract Techniques configuring a machine learning model include receiving, via a user interface configured to communicate with a machine learning model hosted on a collaborative computing platform, a selection of a file for input to the machine learning model, a selection of content in the file for input to the machine learning model, and instructions for applying the selected content to the machine learning model, which are sent to the machine learning model. As new files are uploaded to the selected directories of the collaborative computing platform, the machine learning model is applied to the uploaded files to classify the files and extract metadata. The extracted metadata and associated classification data are stored in data structures associated with the new files. The data structures are existing data structures of the collaborative computing platform. ## Claims ### Claim 1 A method for integrating a machine learning model with a collaborative computing platform, the method comprising: receiving, via a user interface configured to communicate with the machine learning model, a selection of one or more files for input to the machine learning model, wherein the files are stored on the collaborative computing platform; receiving, via the user interface, a selection of content in the files for input to the machine learning model, and one or more instructions for applying the selected content to the machine learning model; receiving a selection of one or more directories of the collaborative computing platform; in response to receiving an instruction to apply the machine learning model to the selected directories: as new files are uploaded to the selected directories of the collaborative computing platform, applying the machine learning model to the uploaded files to classify the files and extract metadata; storing the extracted metadata and associated classification data in data structures associated with the new files, wherein the data structures are existing data structures of the collaborative computing platform; and exposing the extracted metadata and associated classification data to applications executing on the collaborative computing platform; wherein the machine learning model is trained using the selected files, selected content, and instructions; and the trained machine learning model is operable to generate outputs based on the selected directories as input data. ### Claim 2 (depends on 1) The method of claim 1, wherein the machine learning model implements a machine teaching paradigm. ### Claim 3 (depends on 1) The method of claim 1, wherein the files comprise documents containing text. ### Claim 4 (depends on 1) The method of claim 1, wherein the selected directories are libraries configured to host files associated with selected users of the collaborative computing platform. ### Claim 5 (depends on 1) The method of claim 1, further comprising compiling the extracted metadata and associated classification data to maintain running statistics for the selected directories. ### Claim 6 (depends on 4) The method of claim 4, wherein the data structures comprise columns of the libraries. ### Claim 7 (depends on 1) The method of claim 1, wherein the applications comprise one or more of data discovery, business process, or compliance applications. ### Claim 8 (depends on 1) The method of claim 1, wherein the metadata comprises one or more of model, label, feature, or schema. ### Claim 9 A computing device comprising: one or more processors; a memory in communication with the one or more processors, the memory having computer-readable instructions stored thereupon which, when executed by the one or more processors, cause the computing device to: in response to receiving an instruction to apply a machine learning model to one or more directories of a collaborative computing platform: as new files are uploaded to the directories of the collaborative computing platform, apply the machine learning model to the uploaded files to classify the files and extract metadata; store the extracted metadata and associated classification data in data structures associated with the new files, wherein the data structures are existing data structures of the collaborative computing platform; and expose the extracted metadata and associated classification data to applications executing on the collaborative computing platform; wherein the machine learning model is trained using selected files stored on the collaborative computing platform; and the trained machine learning model is operable to generate outputs based on the selected files as input data. ### Claim 10 (depends on 9) The computing device of claim 9, wherein the machine learning model implements a machine teaching paradigm. ### Claim 11 (depends on 9) The computing device of claim 9, wherein the directories are libraries configured to host files associated with selected users of the collaborative computing platform. ### Claim 12 (depends on 9) The computing device of claim 9, further comprising computer-readable instructions stored thereupon which, when executed by the one or more processors, cause the computing device to: compile the extracted metadata and associated classification data to maintain running statistics for the directories. ### Claim 13 (depends on 11) The computing device of claim 11, wherein the data structures comprise columns of the libraries. ### Claim 14 (depends on 9) The computing device of claim 9, wherein the applications comprise one or more of data discovery, business process, or compliance applications. ### Claim 15 (depends on 9) The computing device of claim 9, wherein the metadata comprises one or more of model, label, feature, or schema. ### Claim 16 One or more non-transitory computer-readable media storing computer-executable instructions that, upon execution cause one or more processors of a computing device to cause the computing device to perform operations comprising: receiving a selection of one or more files for input to a machine learning model integrated with a collaborative computing platform, wherein the files are stored on the collaborative computing platform; receiving a selection of content in the files for input to the machine learning model, and one or more instructions for applying the selected content to the machine learning model; receiving a selection of one or more directories of the collaborative computing platform; in response to receiving an instruction to apply the machine learning model to the selected directories: applying the machine learning model to files that are uploaded to the selected directories to classify the files and extract metadata; storing the extracted metadata and associated classification data in data structures associated with the uploaded files, wherein the data structures are data structures of the collaborative computing platform; and exposing the extracted metadata and associated classification data to applications executing on the collaborative computing platform; wherein the machine learning model is trained using the selected files, selected content, and instructions; and the trained machine learning model is operable to generate outputs based on the selected directories as input data. ### Claim 17 (depends on 16) The non-transitory computer-readable media of claim 16 further comprising computer-executable instructions that, upon execution cause one or more processors of a computing device to cause the computing device to perform operations comprising: compiling the extracted metadata and associated classification data to maintain running statistics for the selected directories. ### Claim 18 (depends on 16) The non-transitory computer-readable media of claim 16, wherein the selected directories are libraries configured to host files associated with selected users of the collaborative computing platform. ### Claim 19 (depends on 16) The non-transitory computer-readable media of claim 16, wherein the applications comprise one or more of data discovery, business process, or compliance applications. ### Claim 20 (depends on 16) The non-transitory computer-readable media of claim 16, wherein the metadata comprises one or more of model, label, feature, or schema.