# US 12,223,403 B2 · Machine learning model publishing systems and methods > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,223,403 B2 - Document ID: US12223403B2 - Status: Granted - Kind: B2 - Application number: 17/977,839 - Filed: 2022-10-31 - Published: 2023-03-09 - Granted: 2025-02-11 - Earliest claimed: 2019-01-30 - Assignees: Open Text SA ULC - Applicants: Open Text SA Ulc - Inventors: Isidre Royo Bonnin; Mariano Fernandez Garrido - Web page: https://patentgrep.com/patent/US12223403B2 ## CPC - G06N 20/00: Machine learning - G06F 16/182: Distributed file systems - G06N 5/04: Inference or reasoning models - G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract A machine learning (ML) model publisher can, responsive to an indication that a ML model is ready for publication, generate a publication request form or page on a user device. The ML model publisher can be invoked from within a ML modeling application. Responsive to an instruction received through the publication request form or page, the ML model publisher can access a data structure in memory used in training the ML model and populate the publication request form or page with attributes required by the ML model to run. Responsive to activation of a single-click publication actuator, the ML model publisher can publish the ML model directly from the ML modeling application to a target computing system by providing, to the target computing system, a path to a repository location where the ML model is stored and information on the attributes required by the ML model to run. ## Claims ### Claim 1 A method, comprising: responsive to an indication that a machine learning (ML) model has been trained and is ready for publication, generating, by a computer, a model publication request form or window within a ML modeling application on a user device, the ML model publication request form or window containing input fields and a publication button; accessing, by the computer, a data structure in memory, the data structure containing an attribute used in training the ML model; populating, by the computer, the input fields of the publication request form or window with a path to a repository location where the ML model is stored and with information from the data structure describing the attribute used in training the ML model; receiving, by the computer, an indication that the publication button has been selected for single-click publication of the ML model; and performing, by the computer, the single-click publication of the ML model to a target computing system, including providing the target computing system with the path to the repository location where the ML model is stored and the information describing the attribute used in training the ML model. ### Claim 2 (depends on 1) The method according to claim 1, wherein the ML modeling application runs in a development environment and wherein the target system runs in a production environment. ### Claim 3 (depends on 1) The method according to claim 1, wherein the data structure comprises a table, a data frame, or a two-dimensional data structure for organizing a dataset into named columns. ### Claim 4 (depends on 1) The method according to claim 1, wherein the publication request form or window comprises a schema definition section and wherein the populating comprises automatically filing out the schema definition section with attributes from the data structure. ### Claim 5 (depends on 1) The method according to claim 1, wherein the ML model is stored in a distributed file system. ### Claim 6 (depends on 1) The method according to claim 1, wherein the single-click publication of the ML model comprises publication of a minimal set of information needed to run the ML model and wherein the minimal set of information comprises the path to where the ML model is stored in a distributed file system and what data is needed for running the ML model. ### Claim 7 (depends on 1) The method according to claim 1, wherein the target system comprises an enterprise application running on an artificial intelligence platform. ### Claim 8 A system, comprising: a processor; a non-transitory computer-readable medium; and instructions stored on the non-transitory computer-readable medium and translatable by the processor for: responsive to an indication that a machine learning (ML) model has been trained and is ready for publication, generating a model publication request form or window within a ML modeling application on a user device, the ML model publication request form or window containing input fields and a publication button; accessing a data structure in memory, the data structure containing an attribute used in training the ML model; populating the input fields of the publication request form or window with a path to a repository location where the ML model is stored and with information from the data structure describing the attribute used in training the ML model; receiving an indication that the publication button has been selected for single-click publication of the ML model; and performing the single-click publication of the ML model to a target computing system, including providing the target computing system with the path to the repository location where the ML model is stored and the information describing the attribute used in training the ML model. ### Claim 9 (depends on 8) The system of claim 8, wherein the ML modeling application runs in a development environment and wherein the target system runs in a production environment. ### Claim 10 (depends on 8) The system of claim 8, wherein the data structure comprises a table, a data frame, or a two-dimensional data structure for organizing a dataset into named columns. ### Claim 11 (depends on 8) The system of claim 8, wherein the publication request form or window comprises a schema definition section and wherein the populating comprises automatically filing out the schema definition section with attributes from the data structure. ### Claim 12 (depends on 8) The system of claim 8, wherein the ML model is stored in a distributed file system. ### Claim 13 (depends on 8) The system of claim 8, wherein the single-click publication of the ML model comprises publication of a minimal set of information needed to run the ML model and wherein the minimal set of information comprises the path to where the ML model is stored in a distributed file system and what data is needed for running the ML model. ### Claim 14 (depends on 8) The system of claim 8, wherein the target system comprises an enterprise application running on an artificial intelligence platform. ### Claim 15 A computer program product comprising a non-transitory computer-readable medium storing instructions translatable by a processor for: responsive to an indication that a machine learning (ML) model has been trained and is ready for publication, generating a model publication request form or window within a ML modeling application on a user device, the ML model publication request form or window containing input fields and a publication button; accessing a data structure in memory, the data structure containing an attribute used in training the ML model; populating the input fields of the publication request form or window with a path to a repository location where the ML model is stored and with information from the data structure describing the attribute used in training the ML model; receiving an indication that the publication button has been selected for single-click publication of the ML model; and performing the single-click publication of the ML model to a target computing system, including providing the target computing system with the path to the repository location where the ML model is stored and the information describing the attribute used in training the ML model. ### Claim 16 (depends on 15) The computer program product of claim 15, wherein the ML modeling application runs in a development environment and wherein the target system runs in a production environment. ### Claim 17 (depends on 15) The computer program product of claim 15, wherein the data structure comprises a table, a data frame, or a two-dimensional data structure for organizing a dataset into named columns. ### Claim 18 (depends on 15) The computer program product of claim 15, wherein the publication request form or window comprises a schema definition section and wherein the populating comprises automatically filing out the schema definition section with attributes from the data structure. ### Claim 19 (depends on 15) The computer program product of claim 15, wherein the ML model is stored in a distributed file system. ### Claim 20 (depends on 15) The computer program product of claim 15, wherein the single-click publication of the ML model comprises publication of a minimal set of information needed to run the ML model and wherein the minimal set of information comprises the path to where the ML model is stored in a distributed file system and what data is needed for running the ML model.