# US 12,596,467 B2 · Advanced application of model operations in energy > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,596,467 B2 - Document ID: US12596467B2 - Status: Granted - Kind: B2 - Application number: 18/553,146 - Filed: 2022-03-30 - Published: 2024-05-30 - Granted: 2026-04-07 - Earliest claimed: 2021-03-30 - Assignees: Schlumberger Technology Corporation - Applicants: Schlumberger Technology Corporation - Inventors: Charu Hans; Babu Sai Sampath Reddy Vinta; Yongdong Zeng; Lan Lu; Jimin Zhang - Web page: https://patentgrep.com/patent/US12596467B2 ## CPC - G06F 3/0484: for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range - G06F 3/04842: Selection of displayed objects or displayed text elements (G06F3/0482 takes precedence) - G06F 3/04817: using icons (graphical or visual programming using iconic symbols G06F8/34) - G06F 3/0482: Interaction with lists of selectable items, e.g. menus - G06F 9/451: Execution arrangements for user interfaces - G06F 16/29: Geographical information databases - G06N 20/00: Machine learning - G06Q 10/10: Office automation; Time management - G06Q 50/06: Energy or water supply - G06F 2203/04806: Zoom, i.e. interaction techniques or interactors for controlling the zooming operation - 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 A method implements advanced application of model operations in energy. The method includes presenting an inspection view with a model list. The method further includes receiving a selection of a list entry, corresponding to a model, from the model list, wherein the model of the list entry is a champion model selected from multiple challenger models corresponding to the list entry. The method further receiving deployment settings of the model, presenting a deployment view with a deployment list with the model, and updating a deployment status of the model in the deployment view. ## Claims ### Claim 1 A method, comprising: presenting an inspection view with a model list, the model list comprising a plurality of list entries, each list entry corresponding to a respective data analysis project, each list entry comprising: a plurality of challenger models corresponding to the respective data analysis project for the list entry; and a selected model comprising a champion model for the respective data analysis project, the champion model being automatically selected from among the plurality of challenger models periodically after retraining of the plurality of challenger models is performed; receiving a selection of a selected list entry from among the plurality of list entries in the model list; receiving deployment settings of the selected model of the selected list entry; presenting a deployment view with a deployment list with the selected model; and updating a deployment status of the selected model in the deployment view, wherein the retraining of the plurality of challenger models is performed periodically after a deployment of the selected model based on at least a performance metric monitored during the deployment. ### Claim 2 (depends on 1) The method of claim 1, further comprising: storing a model lineage, of the selected model, identifying a version of the selected model, a training time of the selected model, training data the selected model was trained with, metadata of the selected model, algorithms of the selected model, parameters of the selected model, and validation accuracies of the selected model. ### Claim 3 (depends on 1) The method of claim 1, further comprising: for each list entry in the model list, designating the champion model over the plurality of challenger models based on a metric corresponding to the respective data analysis project for the list entry. ### Claim 4 (depends on 1) The method of claim 1, further comprising: presenting the list entry with a validation accuracy of the selected model. ### Claim 5 (depends on 1) The method of claim 1, further comprising: presenting the plurality of challenger models with corresponding validation accuracies. ### Claim 6 (depends on 1) The method of claim 1, further comprising: deploying the selected model using the deployment settings and a procedure call standard selected from among a plurality of procedure call standards. ### Claim 7 (depends on 1) The method of claim 1, further comprising: deploying the selected model using continuous deployment and continuous delivery using an automated pipeline to train, test, deploy, and continuously improve the selected model in production. ### Claim 8 (depends on 1) The method of claim 1, further comprising: monitoring deployment of the selected model with performance metrics, audit logs, and relevant performance indicators. ### Claim 9 (depends on 1) The method of claim 1, further comprising: identifying degradation of the selected model over time using a model drift alert. ### Claim 10 (depends on 1) The method of claim 1, further comprising: monitoring deployment of the selected model to auto-scale compute resources allocated to the selected model. ### Claim 11 (depends on 1) The method of claim 1, further comprising: presenting the deployment status of the selected model with a link to the selected model. ### Claim 12 (depends on 1) The method of claim 1, wherein the deployment status comprises one of “pass”, “fail”, and “in progress”. ### Claim 13 (depends on 1) The method of claim 1, wherein the retraining of the plurality of challenger models is performed periodically on a schedule of at least one day between each retraining. ### Claim 14 (depends on 1) The method of claim 1, wherein the champion model is automatically selected from among the plurality of challenger models based on one or more model accuracy metrics that identify an accuracy of each model, the one or more model accuracy metrics comprising one or more of: a mean absolute value (MAV), a mean absolute error (MAE), a root mean squared error (RMS), or a Pearson correlation coefficient (PCC). ### Claim 15 (depends on 1) The method of claim 1, wherein the deployment status is indicated by displaying, on a user interface, at least two of: an image, text, or a link. ### Claim 16 (depends on 15) The method of claim 15, wherein, responsive to the deployment status being “pass”, the link is displayed on the user interface. ### Claim 17 A system, comprising: an inspection view; a deployment view; and a server application executing on one or more servers and configured for: presenting the inspection view with a model list, the model list comprising a plurality of list entries, each list entry corresponding to a respective data analysis project, each list entry comprising: a plurality of challenger models corresponding to the respective data analysis project for the list entry; and a selected model comprising a champion model for the respective data analysis project, the champion model being automatically selected from among the plurality of challenger models periodically after retraining of the plurality of challenger models is performed; receiving a selection of a selected list entry from among the plurality of list entries in the model list; receiving deployment settings of the selected model of the selected list entry; presenting the deployment view with a deployment list with the selected model; and updating a deployment status of the selected model in the deployment view, wherein the retraining of the plurality of challenger models is performed periodically after a deployment of the selected model based on at least a performance metric monitored during the deployment. ### Claim 18 (depends on 17) The system of claim 17, wherein the server application is further configured for: storing a model lineage, of the selected model, identifying a version of the selected model, a training time of the selected model, training data the selected model was trained with, metadata of the selected model, algorithms of the selected model, parameters of the selected model, and validation accuracies of the selected model. ### Claim 19 (depends on 17) The system of claim 17, wherein the server application is further configured for: for each list entry in the model list, designating the champion model over the plurality of challenger models based on a metric corresponding to the respective data analysis project for the list entry. ### Claim 20 (depends on 17) The system of claim 17, wherein the server application is further configured for: presenting the list entry with a validation accuracy of the selected model. ### Claim 21 (depends on 17) The system of claim 17, wherein the server application is further configured for: presenting the plurality of challenger models with corresponding validation accuracies. ### Claim 22 (depends on 17) The system of claim 17, wherein the server application is further configured for: deploying the selected model using the deployment settings and a procedure call standard selected from among a plurality of procedure call standards. ### Claim 23 (depends on 17) The system of claim 17, wherein the server application is further configured for: deploying the selected model using continuous deployment and continuous delivery using an automated pipeline to train, test, deploy, and continuously improve the selected model in production. ### Claim 24 A method, comprising: displaying, on a user interface, an inspection view with a list of models, the list of models comprising a plurality of list entries, each list entry corresponding to a respective data analysis project, each list entry comprising: a plurality of challenger models corresponding to the respective data analysis project for the list entry; and a selected model comprising a champion model for the respective data analysis project, the champion model being automatically selected from among the plurality of challenger models periodically after retraining of the plurality of challenger models is performed; receiving a selection of a selected list entry from among the plurality of list entries in the list of models; receiving deployment settings of the selected model of the selected list entry; displaying, on a user interface, a deployment view with the list of models; and updating a deployment status of the selected model in the deployment view, wherein the retraining of the plurality of challenger models is performed periodically after a deployment of the selected model based on at least a performance metric monitored during the deployment.