# US 2019/0171972 A1 · Quick path to train, score, and operationalize a machine learning project > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0171972 A1 - Document ID: US20190171972A1 - Status: Published application - Kind: A1 - Application number: 16/272,769 - Filed: 2019-02-11 - Published: 2019-06-06 - Earliest claimed: 2014-12-05 - Assignees: Microsoft Technology Licensing, LLC - Applicants: Microsoft Technology Licensing, LLC - Inventors: Pedro Ardila; Christina Storm; Mohan Krishna Bulusu; Raymond Ramin Laghaeian - Web page: https://patentgrep.com/patent/US20190171972A1 ## CPC - G06N 20/00: Machine learning - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Automatically detecting and anticipating that an additional machine learning experiment may be needed. A method includes after successfully running a first experiment workflow, automatically prompting a user that an additional experiment workflow may be needed based on specific criteria associated with the first experiment workflow. The method further includes receiving input from the user confirming the additional experiment workflow. As a result of receiving input from the user confirming the additional experiment workflow, the method further includes the system automatically reconfiguring the first experiment workflow, including automatically identifying all necessary modules for the additional experiment workflow and connecting them properly to perform the intended second experiment workflow. The method further includes displaying to the user the first experimental workflow transitioning from the first experiment workflow to the additional experiment workflow. ## Claims ### Claim 1 A system comprising: one or more processor; and one or more storage device having stored executable instructions which are executable by the one or more processor for causing the system to implement a method for automatically detecting and anticipating that an additional machine learning experiment may be needed after a first experiment workflow is executed, wherein the method includes: automatically prompting a user that an additional experiment workflow may be needed, based on specific criteria associated with a first experiment workflow; receiving input from the user confirming the additional experiment workflow; as a result of receiving input from the user confirming the additional experiment workflow, reconfiguring the first experiment workflow, including automatically identifying and connecting modules for the additional experiment workflow; and displaying to the user the first experimental workflow transitioning from the first experiment workflow to the additional experiment workflow. ### Claim 2 (depends on 1) The system of claim 1, wherein automatically reconfiguring the first experiment workflow comprises identifying and removing irrelevant portions of the first experiment workflow. ### Claim 3 (depends on 1) The system of claim 1, wherein the first experiment workflow is a training experiment workflow and wherein the additional experiment workflow is a scoring experiment workflow that comprises a fully trained experiment workflow, such that the fully trained experiment workflow is created only upon receiving the input from the user confirming that the additional experiment workflow is to be created. ### Claim 4 (depends on 1) The system of claim 1, wherein the specific criteria associated with the first experiment comprises the existence of both an algorithm and a training module. ### Claim 5 (depends on 1) The system of claim 1, wherein the method further includes populating and creating elements for web service deployment in the second experiment workflow. ### Claim 6 (depends on 1) The system of claim 1, wherein the method further includes receiving user input approving the second experiment workflow and as a result, automatically deploying the workflow to a live web operation. ### Claim 7 (depends on 1) The system of claim 1, wherein the method further includes displaying a user interface element that allows a user to toggle the additional experiment workflow between an connected mode and a disconnected mode. ### Claim 8 (depends on 1) The system of claim 1, wherein displaying to the user the first experimental workflow transitioning from the first experiment workflow to the additional experiment workflow comprises displaying an animation highlighting the transition. ### Claim 9 (depends on 1) The system of claim 1, wherein the method further includes displaying addition visual cues indicating what has happened to transition the first experiment workflow to the additional experiment workflow. ### Claim 10 (depends on 1) The system of claim 1, further comprising: a filter module, wherein prior to running the first experiment workflow, the filter module transforms a data set to be used during the first experiment by applying one or more of an Apply, FIR, IIR, Median, Moving Average, Threshold, or User Defined filter. ### Claim 11 (depends on 1) The system of claim 1, further comprising: a manipulation module, wherein prior to running the first experiment workflow, the manipulation module transforms a data set to be used during the first experiment by applying one or more of an Add Column, Add Row, Group Categorical Values, Indicator Value, Join, Metadata Editor, Missing Values Scrubber, Project Columns, or Remove Duplicate Rows function. ### Claim 12 (depends on 11) The system of claim 11, wherein the manipulation module applies the Missing Values Scrubber. ### Claim 13 (depends on 1) The system of claim 1, wherein the additional experiment workflow is a consolidation of the first experiment workflow that omits at least some elements from the first experiment workflow. ### Claim 14 (depends on 1) The system of claim 1, wherein displaying to the user the first experimental workflow transitioning from the first experiment workflow to the additional experiment workflow comprises displaying an animation with unnecessary elements from the first experiment workflow being shown floating off screen. ### Claim 15 (depends on 1) The system of claim 1, the specific criteria being first specific criteria, the automatic user prompt being a first automatic user prompt, input from the user being first input from the user, and the additional experiment workflow being a first additional experiment workflow, wherein after successfully running a third experiment workflow, and in response to detecting the second specific criteria associated with the first experiment workflow, the method further includes: automatically prompting a user with a second automatic user prompt that creation of a second additional experiment workflow may be needed; receiving input from the user denying that the second additional experiment workflow is to be created; and as a result of input from the user denying that the second additional experiment workflow is to be created, refraining from creating the second additional experiment workflow. ### Claim 16 A system for creating a scoring experiment from a training experiment, the system comprising: one or more processors; and one or more computer-readable media, wherein the one or more computer-readable media comprise computer-executable instructions that when executed by at least one of the one or more processors cause the system to perform a method that includes: in response to detecting specific criteria associated with a first experiment workflow, identifying specific elements of the training experiment; automatically prompting a user with an automatic user prompt that creation of scoring experiment may be needed, based at least in part on detecting the identified specific elements associated with the training experiment workflow, wherein the automatic user prompt is presented at a user interface concurrently with at least a portion of the first experiment workflow; identifying components in the training experiment for a scoring experiment; and using the components to create the scoring experiment. ### Claim 17 (depends on 16) The system of claim 16, wherein the method further includes presenting a graphical representation of consolidation and/or elimination of the identified components. ### Claim 18 (depends on 17) The system of claim 17, wherein the graphical representation is an animation. ### Claim 19 (depends on 16) The system of claim 16, wherein the method further includes adding components to the scoring experiment for web service deployment. ### Claim 20 (depends on 19) The system of claim 19, wherein the method further includes automatically deploying the web service deployment with the components.