Back to results
US 12,743,361 B2Granted
Automatic generation of process instructions from log files
AssigneeWells Fargo Bank, N.A.
InventorsManesh Saini, Carleton Jay Lindgren, Jr., James Hubbard, Ronald Sobey, Winthrop Treynor Smith
Life of this patent
Estimating the term…
Abstract
A computing system may access log files that log data associated with prior performances of a process by users. Such data may be recorded by one or more computing systems based on tracking user interactions with the one or more computing systems to perform the process. The computing system may generate, using an instructions generation model that is trained using machine learning, the process instructions for performing the process based on the data associated with the prior performances of the process. The process instructions may be human-readable written instructions.
Claims20
A method comprising:
- accessing, by one or more processors, log files that log data associated with a plurality of prior performances of a process by users, wherein the data are recorded by one or more computing systems based on tracking user interactions with the one or more computing systems to perform the process during each performance of the plurality of prior performances of the process;
- and
- generating, by the one or more processors and using an instructions generation model that is trained using machine learning, process instructions for performing the process based on inputting the data associated with each of the plurality of prior performances of the process into the instructions generation model at inference time and synthesizing, by the instructions generation model, the data associated with each of the plurality of prior performances of the process, including different actions taken by different users across the plurality of prior performances of the process, to generate the process instructions, wherein the process instructions specify a sequence of actions to perform the process based on an ordering of two or more of the different actions taken to perform the process during the plurality of prior performances, and wherein the process instructions are human-readable written instructions.
A computing system comprising:
- memory configured to store log files that log data associated with a plurality of prior performances of a process by users, wherein the data are recorded by one or more computing systems based on tracking user interactions with the one or more computing systems to perform the process during each performance of the plurality of prior performances of the process;
- and
- one or more processors configured to:
- access the log files;
- and
- generate, using an instructions generation model that is trained using machine learning, process instructions for performing the process based on inputting the data associated with each of the plurality of prior performances of the process into the instructions generation model at inference time and synthesizing, by the instructions generation model, the data associated with each of the plurality of prior performances of the process, including different actions taken by different users across the plurality of prior performances of the process, to generate the process instructions, wherein the process instructions specify a sequence of actions to perform the process based on an ordering of two or more of the different actions taken to perform the process during the plurality of prior performances, and wherein the process instructions are human-readable written instructions.
3 more elements
A non-transitory computer-readable medium comprising instructions that, when executed, cause one or more processors of a computing system to:
- access log files that log data associated with a plurality of prior performances of a process by users, wherein the data are recorded by one or more computing systems based on tracking user interactions with the one or more computing systems to perform the process during each performance of the plurality of prior performances of the process;
- and
- generate, using an instructions generation model that is trained using machine learning, the process instructions for performing the process based on inputting the data associated with each of the plurality of prior performances of the process into the instructions generation model at inference time and synthesizing, by the instructions generation model, the data associated with each of the plurality of prior performances of the process, including different actions taken by different users across the plurality of prior performances of the process, to generate the process instructions, wherein the process instructions specify a sequence of actions to perform the process based on an ordering of two or more of the different actions taken to perform the process during the plurality of prior performances, and wherein the process instructions are human-readable written instructions.
Dependencies are inferred from the claim text.