AUTOMATIC GENERATION OF PROCESS INSTRUCTIONS FROM LOG FILES
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.
1 . A method comprising:
accessing, by one or more processors, log files that log data associated with 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; 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 the data associated with the prior performances of the process, wherein the process instructions are human-readable written instructions.
2 . The method of claim 1 , wherein generating the process instructions further comprises:
selecting, by the one or more processors, a procedural template for the process; and
mapping, by the one or more processors and using the instructions generation model, the data associated with the prior performances of the process by the users onto the procedural template to generate a process map for performing the process.
3 . The method of claim 1 , further comprising:
training, by the one or more processors, a foundational large language model to be the instructions generation model that generates, from the data associated with the prior performances of the process by the users, the process instructions for performing the process.
4 . The method of claim 1 , wherein accessing the log files that log the data associated with the prior performances of the process by the users further comprises:
parsing, by the one or more processors, the log files to determine log entries associated with the same unique identifier as data associated with an instance of a prior performance of the process by a user; and
including, by the one or more processors, the data associated with the instance of the prior performance of the process by the user in the data associated with the prior performances of the process by the users.
5 . The method of claim 1 , further comprising:
generating, by the one or more processors and using a process refinement model trained using machine learning to refine the process instructions, an ideal process workflow for the process.
6 . The method of claim 1 , further comprising:
generating, by the one or more processors, operational intelligence associated with the prior performances of the process that includes at least one of conformance information associated with the prior performances of the process or efficiency information associated with the prior performance of the process.
7 . The method of claim 1 , further comprising:
generating, by the one or more processors and using an instructions comparison model that is trained using machine learning to compare the process instructions and official process documents for the process, a procedural report that indicates inconsistencies between the process instructions and the official process documents for the process.
8 . The method of claim 7 , further comprising:
training, by the one or more processors, a foundational large language model to be the instructions comparison model that compares the process instructions and official process documents for the process to generate a procedural report that indicates inconsistencies between the process instructions and the official process documents for the process.
9 . The method of claim 8 , wherein the instructions comparison model includes one or more reasoning engines implemented using a LangChain framework to perform attribution analysis of why actions taken by the users to perform the process would enable the process to meet an efficiency goal, and wherein the procedural report includes the attribution analysis.
10 . The method of claim 7 , wherein the procedural report categorizes differences between the process instructions and the official process documents as add, modify, counter, or no change.
11 . The method of claim 7 , wherein the procedural report indicates that the inconsistencies between the process instructions and the official process documents for the process are due to malicious behavior by at least one of the users.
12 . The method of claim 7 , wherein the procedural report indicates that the inconsistencies between the process instructions and the official process documents for the process are due to compliance with recent regulation changes.
13 . A computing system comprising:
memory configured to store log files that log data associated with 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; 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 the data associated with the prior performances of the process, wherein the process instructions are human-readable written instructions.
14 . The computing system of claim 13 , wherein to generate the process instructions, the one or more processors are further configured to:
select a procedural template for the process; and
map, using the instructions generation model, the data associated with the prior performances of the process by the users onto the procedural template to generate a process map for performing the process.
15 . The computing system of claim 13 , the one or more processors are further configured to:
train a foundational large language model to be the instructions generation model that generates, from the data associated with the prior performances of the process by the users, the process instructions for performing the process.
16 . The computing system of claim 13 , wherein to access the log files that log the data associated with the prior performances of the process by the users, the one or more processors are further configured to:
parse the log files to determine log entries associated with the same unique identifier as data associated with an instance of a prior performance of the process by a user; and
include the data associated with the instance of the prior performance of the process by the user in the data associated with the prior performances of the process by the users.
17 . The computing system of claim 13 , wherein the one or more processors are further configured to:
generate, using a process refinement model trained using machine learning to refine the process instructions, an ideal process workflow for the process.
18 . The computing system of claim 13 , wherein the one or more processors are further configured to:
generate operational intelligence associated with the prior performances of the process that includes at least one of conformance information associated with the prior performances of the process or efficiency information associated with the prior performance of the process.
19 . The computing system of claim 13 , wherein the one or more processors are further configured to:
generate, using an instructions comparison model that is trained using machine learning to compare the process instructions and official process documents for the process, a procedural report that indicates inconsistencies between the process instructions and the official process documents for the process.
20 . 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 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; and
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, wherein the process instructions are human-readable written instructions.