# US 12,602,609 B2 · Updating machine learning training data using graphical inputs > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,602,609 B2 - Document ID: US12602609B2 - Status: Granted - Kind: B2 - Application number: 17/178,360 - Filed: 2021-02-18 - Published: 2022-08-18 - Granted: 2026-04-14 - Earliest claimed: 2021-02-18 - Assignees: Oracle International Corporation - Applicants: Oracle International Corporation - Inventors: Ketakee Kishorkumar Nimavat; Rajiv Kumar - Web page: https://patentgrep.com/patent/US12602609B2 ## CPC - G06N 20/00: Machine learning - G06Q 10/047: Optimisation of routes or paths, e.g. travelling salesman problem - G06F 3/0482: Interaction with lists of selectable items, e.g. menus - G06F 3/0486: Drag-and-drop - G06N 5/04: Inference or reasoning models - G06Q 50/40: Business processes related to the transportation industry (shipping G06Q10/083) - 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 - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Techniques are disclosed for using a machine learning model to identify and present a ranked array of interface elements representing entities. The location of individual interface elements within the ranked array of interface elements is based on a level of match between entity attributes and a set of requirements established by a user. The machine learning model may be further trained by receiving a user input that changes a location of a particular user interface element within a graphical user interface displaying the ranked array. Upon receiving the user input, the trained machine learning model may update training data to include an updated match score for the particular user interface element that reflects the new location. ## Claims ### Claim 1 One or more non-transitory computer-readable media storing instructions, which when executed by one or more hardware processors, cause performance of operations comprising: training a machine learning model to compute match scores representing a match between entities and sets of requirements at least by: obtaining training data sets, each training data set comprising: attribute values for a set of entity attributes; a set of requirements; a match score representing the match between the attribute values for the set of entity attributes and the set of requirements; training the machine learning model based on the training data sets; applying the machine learning model to a plurality of entities to determine a match score for each of the plurality of entities in relation to a particular set of requirements; generating a Graphical User Interface (GUI) that presents a plurality of interface elements respectively representing the plurality of entities, wherein a location of each particular interface element, of the plurality of interface elements, within the GUI is based at least in part on a match score of a corresponding particular entity of the plurality of entities that is represented by the corresponding particular interface element; receiving user input moving a first interface element of the plurality of interface elements from a first location in the GUI to a second location in the GUI, wherein the first location in the GUI is associated with a first match score computed for a first entity corresponding to the first interface element; responsive to receiving the user input moving the first interface element to the second location in the GUI: determining a second match score for the first entity, based at least in part on (a) the second location of the first interface element in the GUI and (b) two or more match scores associated respectively with two or more interface elements, in the plurality of interface elements, that neighbor the second location in the GUI; generating a new training data set comprising the first entity, the particular set of requirements, and the second match score; and re-training the machine learning model based at least on the new training data set. ### Claim 2 (depends on 1) The media of claim 1, wherein at least some of the interface elements of the plurality of interface elements comprise one or both of a color or a shading value indicating an evaluation status of a corresponding entity. ### Claim 3 (depends on 2) The media of claim 2, wherein the evaluation status of the corresponding entity comprises rejected, pending, or accepted. ### Claim 4 (depends on 1) The media of claim 1, wherein at least one interface element further comprises a display of a first requirement and a corresponding entity attribute value. ### Claim 5 (depends on 1) The media of claim 1, wherein generating the new training data set comprises changing weights of requirements corresponding to entity attributes having corresponding match scores above a threshold. ### Claim 6 (depends on 1) The media of claim 1, wherein at least some of the interface elements of the plurality of interface elements comprise one or both of a color or a shading value indicating one of the first match score or the second match score. ### Claim 7 (depends on 6) The media of claim 6, further comprising updating one or both of the color or the shading value indicating one of the first match score or the second match score based on the re-trained machine learning model. ### Claim 8 A method comprising: training a machine learning model to compute match scores representing a match between entities and sets of requirements at least by: obtaining training data sets, each training data set comprising: attribute values for a set of entity attributes; a set of requirements; a match score representing the match between the attribute values for the set of entity attributes and the set of requirements; training the machine learning model based on the training data sets; applying the machine learning model to a plurality of entities to determine a match score for each of the plurality of entities in relation to a particular set of requirements; generating a Graphical User Interface (GUI) that presents a plurality of interface elements respectively representing the plurality of entities, wherein a location of each particular interface element, of the plurality of interface elements, within the GUI is based at least in part on a match score of a corresponding particular entity of the plurality of entities that is represented by the corresponding particular interface element; receiving user input moving a first interface element of the plurality of interface elements from a first location in the GUI to a second location in the GUI, wherein the first location in the GUI is associated with a first match score computed for a first entity corresponding to the first interface element; responsive to receiving the user input moving the first interface element to the second location in the GUI: determining a second match score for the first entity, based at least in part on (a) the second location of the first interface element in the GUI and (b) two or more match scores associated respectively with two or more interface elements, in the plurality of interface elements, that neighbor the second location in the GUI; generating a new training data set comprising the first entity, the particular set of requirements, and the second match score; and re-training the machine learning model based at least on the new training data set, wherein the method is performed by at least one device including a hardware processor. ### Claim 9 (depends on 8) The method of claim 8, wherein at least some of the interface elements of the plurality of interface elements comprise one or both of a color or a shading value indicating an evaluation status of a corresponding entity. ### Claim 10 (depends on 8) The method of claim 8, wherein at least one interface element further comprises a display of a first requirement and a corresponding entity attribute value. ### Claim 11 (depends on 8) The method of claim 8, wherein generating the new training data set comprises changing weights of requirements corresponding to entity attributes having corresponding match scores above a threshold. ### Claim 12 (depends on 8) The method of claim 8, wherein at least some of the interface elements of the plurality of interface elements comprise one or both of a color or a shading value indicating one of the first match score or the second match score. ### Claim 13 (depends on 12) The method of claim 12, further comprising updating one or both of the color or the shading value indicating one of the first match score or the second match score based on the re-trained machine learning model. ### Claim 14 A system comprising: at least one device including a hardware processor; the system being configured to perform operations comprising: training a machine learning model to compute match scores representing a match between entities and sets of requirements at least by: obtaining training data sets, each training data set comprising: attribute values for a set of entity attributes; a set of requirements; a match score representing the match between the attribute values for the set of entity attributes and the set of requirements; training the machine learning model based on the training data sets; applying the machine learning model to a plurality of entities to determine a match score for each of the plurality of entities in relation to a particular set of requirements; generating a Graphical User Interface (GUI) that presents a plurality of interface elements respectively representing the plurality of entities, wherein a location of each particular interface element, of the plurality of interface elements, within the GUI is based at least in part on a match score of a corresponding particular entity of the plurality of entities that is represented by the corresponding particular interface element; receiving user input moving a first interface element of the plurality of interface elements from a first location in the GUI to a second location in the GUI, wherein the first location in the GUI is associated with a first match score computed for a first entity corresponding to the first interface element; responsive to receiving the user input moving the first interface element to the second location in the GUI: determining a second match score for the first entity, based at least in part on (a) the second location of the first interface element in the GUI and (b) two or more match scores associated respectively with two or more interface elements, in the plurality of interface elements, that neighbor the second location in the GUI; generating a new training data set comprising the first entity, the particular set of requirements, and the second match score; and re-training the machine learning model based at least on the new training data set. ### Claim 15 (depends on 14) The system of claim 14, wherein at least some of the interface elements of the plurality of interface elements comprise one or both of a color or a shading value indicating an evaluation status of a corresponding entity. ### Claim 16 (depends on 14) The system of claim 14, wherein at least one interface element further comprises a display of a first requirement and a corresponding entity attribute value. ### Claim 17 (depends on 14) The system of claim 14, wherein generating the new training data set comprises changing weights of requirements corresponding to entity attributes having corresponding match scores above a threshold. ### Claim 18 (depends on 14) The system of claim 14, wherein at least some of the interface elements of the plurality of interface elements comprise one or both of a color or a shading value indicating one of the first match score or the second match score. ### Claim 19 (depends on 18) The system of claim 18, further comprising updating one or both of the color or the shading value indicating one of the first match score or the second match score based on the re-trained machine learning model.