Configurable machine learning systems through graphical user interfaces
Uloženo v:
| Název: | Configurable machine learning systems through graphical user interfaces |
|---|---|
| Patent Number: | 12039,177 |
| Datum vydání: | July 16, 2024 |
| Appl. No: | 17/836928 |
| Application Filed: | June 09, 2022 |
| Abstrakt: | Systems and methods for presenting configurable machine learning systems through graphical user interfaces are disclosed. In an embodiment, a machine learning server computer stores one or more machine learning configuration files. A particular machine learning configuration file of the one or more machine learning configuration files comprises instructions for configuring a machine learning system of a particular machine learning type with one or more first machine learning parameters. The machine learning server computer displays through a graphical user interface, a plurality of selectable parameter options, each of which defining a value for a machine learning parameter. The machine learning server computer receives a particular input dataset. The machine learning server computer additionally receives, through the graphical user interface, a selection of one or more selectable parameter options corresponding to one or more second machine learning parameters different from the one or more first machine learning parameters. The machine learning server computer replaces in the particular machine learning configuration file, the one or more first machine learning parameters with the one or more second machine learning parameters. Using the particular machine learning configuration file, the machine learning server computer configures a particular machine learning system. Using the particular machine learning system and the particular input dataset, the machine learning server computer computes a particular output dataset. |
| Inventors: | Coupa Software Incorporated (San Mateo, CA, US) |
| Assignees: | Coupa Software Incorporated (San Mateo, CA, US) |
| Claim: | 1. A computer-implemented method comprising: storing, at a machine learning server computer, one or more machine learning configuration files, a particular machine learning configuration file of the one or more machine learning configuration files comprising instructions for configuring a machine learning system of a particular machine learning type with one or more first machine learning parameters; displaying, through a graphical user interface, a plurality of selectable neural network type options and a plurality of selectable parameter options, each of which defines a value for a machine learning parameter, wherein the plurality of selectable neural network type options each defines a type of machine learning system; receiving, at the machine learning server computer, a particular input dataset; receiving, through the graphical user interface, a selection of a first selectable neural network type option and a selection of one or more selectable parameter options corresponding to one or more second machine learning parameters different from the one or more first machine learning parameters; configuring a particular machine learning system based, at least in part, on the selection of the first selectable neural network type option; replacing, in the particular machine learning configuration file, the one or more first machine learning parameters with the one or more second machine learning parameters; using the particular machine learning configuration file, configuring the particular machine learning system; using the particular machine learning system and the particular input dataset, computing a particular output dataset; receiving, through the graphical user interface, a selection of a particular selectable training option corresponding to a particular machine learning training dataset, wherein the particular machine learning training dataset is different from the particular input dataset; in response to configuring the particular machine learning system, training the particular machine learning system using the particular machine learning training dataset; wherein the plurality of selectable neural network type options comprises: Naive Bayes, Encoder Decoder, and Long Short Term Memory; storing, at the machine learning server computer, a confidence score threshold value; the particular output dataset comprising, for each of a plurality of data items in the particular output dataset, an output confidence score; determining that a subset of the plurality of data items in the particular output dataset comprise confidence scores below the confidence score threshold value; in response to determining that the subset of the plurality of data items in the particular output dataset comprise confidence scores below the confidence score threshold value; computing a second output dataset; replacing one or more data items in the subset of the particular output dataset with one or more corresponding items in the second output dataset. |
| Claim: | 2. The computer-implemented method of claim 1 , a second machine learning configuration file of the one or more machine learning configuration files comprising instructions for configuring a machine learning system of a second machine learning type with one or more third machine learning parameters, the method further comprising: receiving, at the machine learning server computer, a second input dataset; receiving, through the graphical user interface, a selection of a second selectable neural network type option corresponding to a machine learning system of the second machine learning type; based, at least in part, on the selection of the second selectable neural network type option, using the second machine learning configuration file, configuring a second machine learning system; computing the second output dataset using the second machine learning system and the second input dataset. |
| Claim: | 3. The computer-implemented method of claim 1 , further comprising: storing, at the machine learning server computer, a plurality of machine learning training datasets; displaying, through the graphical user interface, a plurality of selectable training options, each of which corresponds to a machine learning training dataset of the plurality of machine learning training datasets. |
| Claim: | 4. The computer-implemented method of claim 3 , further comprising: storing, for each machine learning training dataset of the plurality of machine learning training datasets, category data identifying a data category for the machine learning training dataset; receiving, through the graphical user interface, input categorization data identifying a particular data category for the particular input dataset; determining that each of the plurality of machine learning training datasets corresponds to the particular data category and, in response, displaying the plurality of selectable training options. |
| Claim: | 5. The computer-implemented method of claim 3 , further comprising: identifying a subset of the particular input dataset that corresponds to the subset of the plurality of data items in the particular output dataset; receiving, through the graphical user interface, a selection of a second selectable training option corresponding to a second machine learning training dataset of the plurality of machine learning training datasets; using the particular machine learning configuration file, configuring a second machine learning system; training the second machine learning system using the second machine learning training dataset; computing the second output dataset using the second machine learning system and the subset of the particular input dataset. |
| Claim: | 6. The computer-implemented method of claim 5 , further comprising: storing, for each machine learning training dataset of the plurality of machine learning training datasets, category data identifying a data category for the machine learning training dataset, the particular machine learning training dataset corresponding to a particular data category; in response to determining that the subset of the plurality of data items in the particular output dataset comprise confidence scores below the confidence score threshold value, displaying, through the graphical user interface, a subset of the plurality of selectable training options, wherein each of the subsets of the plurality of selectable training options corresponds to the particular data category; receiving the selection of the second selectable training option from the subset of the plurality of selectable training options. |
| Claim: | 7. The computer-implemented method of claim 3 , further comprising: storing, for each machine learning training dataset of the plurality of machine learning training datasets, category data identifying a data category for the machine learning training dataset; the particular machine learning training dataset corresponding to a particular data category; identifying one or more machine learning training datasets corresponding to the particular data category; automatically selecting, from the one or more machine learning training datasets, a second machine learning training dataset; using the particular machine learning configuration file, configuring a second machine learning system; training the second machine learning system using the second machine learning training dataset of the plurality of machine learning training datasets; computing the second output dataset using the second machine learning system and the subset of the particular input dataset. |
| Claim: | 8. The computer-implemented method of claim 1 , a second machine learning configuration file of the one or more machine learning configuration files comprising instructions for configuring a machine learning system of a second machine learning type with one or more third machine learning parameters, and wherein the method further comprises: displaying, through the graphical user interface, a plurality of selectable network type options, each of which defines a type of machine learning system; receiving, through the graphical user interface, a selection of both a first selectable network type option corresponding to a machine learning system of the particular machine learning type and a second selectable network type option corresponding to a machine learning system of the second machine learning type; configuring the particular machine learning system based, at least in part, on the selection of the first selectable network type option; based, at least in part, on the selection of the second selectable network type option, using the second machine learning configuration file, configuring a second machine learning system; computing the second output dataset using the second machine learning system and the particular input dataset. |
| Claim: | 9. The computer-implemented method of claim 1 , further comprising: storing, at the machine learning server computer, a plurality of machine learning training datasets; displaying, through the graphical user interface, a plurality of selectable training options, each of which corresponds to a machine learning training dataset of the plurality of machine learning training datasets; receiving, through the graphical user interface, a selection of both a particular selectable training option corresponding to a particular machine learning training dataset and a second selectable option corresponding to a second machine learning training dataset; using the particular machine learning configuration file, configuring a second machine learning system; in response to configuring the particular machine learning system, training the particular machine learning system using the particular machine learning training dataset; in response to configuring the second machine learning system, training the second machine learning system using the second machine learning training dataset; computing the second output dataset using the second machine learning system and the particular input dataset. |
| Claim: | 10. The computer-implemented method of claim 1 , further comprising: configuring a plurality of test machine learning systems of the particular machine learning type, each of which comprising different machine learning parameters; using a test input dataset and the plurality of test machine learning systems, computing a plurality of test output datasets; determining that an output of a particular test machine learning system of the plurality of test machine learning systems is more accurate than outputs of each other test machine learning system of the plurality of test machine learning systems, the particular test machine learning system comprising the one or more first machine learning parameters; in response to determining that the output of the particular test machine learning system is more accurate than each other test machine learning system, storing the particular machine learning configuration file with the one or more first machine learning parameters. |
| Claim: | 11. The computer-implemented method of claim 1 , further comprising: storing, at the machine learning server computer, a plurality of machine learning training datasets; displaying, through the graphical user interface, a plurality of selectable training options, each of which corresponds to a machine learning training dataset of the plurality of machine learning training datasets; receiving, through the graphical user interface, a selection of a particular selectable training option corresponding to a particular machine learning training dataset; in response to computing the particular output dataset, updating the particular machine learning training dataset using the particular input dataset and the particular output dataset. |
| Claim: | 12. A computer system comprising: one or more processors; one or more non-transitory computer-readable storage media storing one or more sequences of instructions which, when executed by the one or more processors, cause the one or more processors to execute: storing one or more machine learning configuration files, a particular machine learning configuration file of the one or more machine learning configuration files comprising instructions for configuring a machine learning system of a particular machine learning type with one or more first machine learning parameters; displaying, through a graphical user interface, a plurality of selectable neural network type options and a plurality of selectable parameter options, each of which defines a value for a machine learning parameter, wherein the plurality of selectable neural network type options each defines a type of machine learning system; receiving a particular input dataset; receiving, through the graphical user interface, a selection of a first selectable neural network type option and a selection of one or more selectable parameter options corresponding to one or more second machine learning parameters different from the one or more first machine learning parameters; configuring a particular machine learning system based, at least in part, on the selection of the first selectable neural network type option; replacing, in the particular machine learning configuration file, the one or more first machine learning parameters with the one or more second machine learning parameters; using the particular machine learning configuration file, configuring the particular machine learning system; using the particular machine learning system and the particular input dataset, computing a particular output dataset; receiving, through the graphical user interface, a selection of a particular selectable training option corresponding to a particular machine learning training dataset, wherein the particular machine learning training dataset is different from the particular input dataset; in response to configuring the particular machine learning system, training the particular machine learning system using the particular machine learning training dataset; wherein the plurality of selectable neural network type options comprises: Naive Bayes, Encoder Decoder, and Long Short Term Memory; storing a confidence score threshold value; the particular output dataset comprising, for each of a plurality of data items in the particular output dataset, an output confidence score; determining that a subset of the plurality of data items in the particular output dataset comprise confidence scores below the confidence score threshold value; in response to determining that the subset of the plurality of data items in the particular output dataset comprise confidence scores below the confidence score threshold value; computing a second output dataset; replacing one or more data items in the subset of the particular output dataset with one or more corresponding items in the second output dataset. |
| Claim: | 13. The computer system of claim 12 , a second machine learning configuration file of the one or more machine learning configuration files comprising one or more second sequences of instructions for configuring a machine learning system of a second machine learning type with one or more third machine learning parameters and which second sequences of instructions, when executed by the one or more processors, cause the one or more processors to execute: receiving, a second input dataset; receiving, through the graphical user interface, a selection of a second selectable neural network type option corresponding to a machine learning system of the second machine learning type; based, at least in part, on the selection of the second selectable neural network type option, using the second machine learning configuration file, configuring a second machine learning system; computing the second output dataset using the second machine learning system and the second input dataset. |
| Claim: | 14. The computer system of claim 12 , further comprising sequences of instructions which when executed by the one or more processors cause the one or more processors to execute: storing a plurality of machine learning training datasets; displaying, through the graphical user interface, a plurality of selectable training options, each of which corresponds to a machine learning training dataset of the plurality of machine learning training datasets. |
| Claim: | 15. The computer system of claim 14 , further comprising sequences of instructions which when executed by the one or more processors cause the one or more processors to execute: storing, for each machine learning training dataset of the plurality of machine learning training datasets, category data identifying a data category for the machine learning training dataset; receiving, through the graphical user interface, input categorization data identifying a particular data category for the particular input dataset; determining that each of the plurality of machine learning training datasets corresponds to the particular data category and, in response, displaying the plurality of selectable training options. |
| Claim: | 16. The computer system of claim 14 , further comprising sequences of instructions which when executed by the one or more processors cause the one or more processors to execute: identifying a subset of the particular input dataset that corresponds to the subset of the plurality of data items in the particular output dataset; receiving, through the graphical user interface, a selection of a second selectable training option corresponding to a second machine learning training dataset of the plurality of machine learning training datasets; using the particular machine learning configuration file, configuring a second machine learning system; training the second machine learning system using the second machine learning training dataset; computing the second output dataset using the second machine learning system and the subset of the particular input dataset. |
| Claim: | 17. The computer system of claim 16 , further comprising sequences of instructions which when executed by the one or more processors cause the one or more processors to execute: storing, for each machine learning training dataset of the plurality of machine learning training datasets, category data identifying a data category for the machine learning training dataset, the particular machine learning training dataset corresponding to a particular data category; in response to determining that the subset of the plurality of data items in the particular output dataset comprise confidence scores below the confidence score threshold value, displaying, through the graphical user interface, a subset of the plurality of selectable training options, wherein each of the subsets of the plurality of selectable training options corresponds to the particular data category; receiving the selection of the second selectable training option from the subset of the plurality of selectable training options. |
| Claim: | 18. The computer system of claim 14 , further comprising sequences of instructions which when executed by the one or more processors cause the one or more processors to execute: storing, for each machine learning training dataset of the plurality of machine learning training datasets, category data identifying a data category for the machine learning training dataset; the particular machine learning training dataset corresponding to a particular data category; identifying one or more machine learning training datasets corresponding to the particular data category; automatically selecting, from the one or more machine learning training datasets, a second machine learning training dataset; using the particular machine learning configuration file, configuring a second machine learning system; training the second machine learning system using the second machine learning training dataset of the plurality of machine learning training datasets; computing the second output dataset using the second machine learning system and the subset of the particular input dataset. |
| Claim: | 19. The computer system of claim 12 , a second machine learning configuration file of the one or more machine learning configuration files comprising one or more second sequences of instructions for configuring a machine learning system of a second machine learning type with one or more third machine learning parameters, which second sequences of instructions, when executed by the one or more processors, cause the one or more processors to execute: displaying, through the graphical user interface, a plurality of selectable network type options, each of which defines a type of machine learning system; receiving, through the graphical user interface, a selection of both a first selectable network type option corresponding to a machine learning system of the particular machine learning type and a second selectable network type option corresponding to a machine learning system of the second machine learning type; configuring the particular machine learning system based, at least in part, on the selection of the first selectable network type option; based, at least in part, on the selection of the second selectable network type option, using the second machine learning configuration file, configuring a second machine learning system; computing the second output dataset using the second machine learning system and the particular input dataset, computing a second output dataset. |
| Claim: | 20. The computer system of claim 12 , further comprising sequences of instructions which when executed by the one or more processors cause the one or more processors to execute: storing a plurality of machine learning training datasets; displaying, through the graphical user interface, a plurality of selectable training options, each of which corresponds to a machine learning training dataset of the plurality of machine learning training datasets; receiving, through the graphical user interface, a selection of both a particular selectable training option corresponding to a particular machine learning training dataset and a second selectable option corresponding to a second machine learning training dataset; using the particular machine learning configuration file, configuring a second machine learning system; in response to configuring the particular machine learning system, training the particular machine learning system using the particular machine learning training dataset; in response to configuring the second machine learning system, training the second machine learning system using the second machine learning training dataset; computing the second output dataset using the second machine learning system and the particular input dataset. |
| Claim: | 21. The computer system of claim 12 , further comprising sequences of instructions which when executed by the one or more processors cause the one or more processors to execute: configuring a plurality of test machine learning systems of the particular machine learning type, each of which comprising different machine learning parameters; using a test input dataset and the plurality of test machine learning systems, computing a plurality of test output datasets; determining that an output of a particular test machine learning system of the plurality of test machine learning systems is more accurate than outputs of each other test machine learning system of the plurality of test machine learning systems, the particular test machine learning system comprising the one or more first machine learning parameters; in response to determining that the output of the particular test machine learning system is more accurate than each other test machine learning system, storing the particular machine learning configuration file with the one or more first machine learning parameters. |
| Claim: | 22. The computer system of claim 12 , further comprising sequences of instructions which when executed by the one or more processors cause the one or more processors to execute: storing a plurality of machine learning training datasets; displaying, through the graphical user interface, a plurality of selectable training options, each of which corresponds to a machine learning training dataset of the plurality of machine learning training datasets; receiving, through the graphical user interface, a selection of a particular selectable training option corresponding to a particular machine learning training dataset; in response to computing the particular output dataset, updating the particular machine learning training dataset using the particular input dataset and the particular output dataset. |
| Patent References Cited: | 20150379429 December 2015 Lee 20160110657 April 2016 Gibiansky 20170178020 June 2017 Duggan 20170243132 August 2017 Sainani 20180032862 February 2018 Oliner 20180089591 March 2018 Zeiler 20180253645 September 2018 Burr 20200050329 February 2020 Maclean |
| Primary Examiner: | Xia, Xuyang |
| Attorney, Agent or Firm: | Baker Botts L.L.P. |
| Přístupové číslo: | edspgr.12039177 |
| Databáze: | USPTO Patent Grants |
| Abstrakt: | Systems and methods for presenting configurable machine learning systems through graphical user interfaces are disclosed. In an embodiment, a machine learning server computer stores one or more machine learning configuration files. A particular machine learning configuration file of the one or more machine learning configuration files comprises instructions for configuring a machine learning system of a particular machine learning type with one or more first machine learning parameters. The machine learning server computer displays through a graphical user interface, a plurality of selectable parameter options, each of which defining a value for a machine learning parameter. The machine learning server computer receives a particular input dataset. The machine learning server computer additionally receives, through the graphical user interface, a selection of one or more selectable parameter options corresponding to one or more second machine learning parameters different from the one or more first machine learning parameters. The machine learning server computer replaces in the particular machine learning configuration file, the one or more first machine learning parameters with the one or more second machine learning parameters. Using the particular machine learning configuration file, the machine learning server computer configures a particular machine learning system. Using the particular machine learning system and the particular input dataset, the machine learning server computer computes a particular output dataset. |
|---|