Context-based recommendations for robotic process automation design
Systems and methods for adding process actions to the design of a robotic software process. A context-recognition module recognizes a current state of a process being designed, and passes information on that current state to a recommendation module. The recommendation module evaluates the current state and identifies at least one suitable process action to recommend in response to that current state. The recommendation module then recommends the at least one process action to the human designer. If the designer accepts the recommendation, a design module adds the process action to the process design. The recommendation module may also use information about previous actions in the process and in other processes when identifying suitable process actions. The context-recognition module and the recommendation module may each comprise at least one machine learning module, which may or may not be neural network based.
1. A method for adding at least one process action to a design of a software process, the software process comprising a plurality of process steps, the software process corresponding to a software file, the method being executed by a processor, the processor being operatively connected to a user interface, the method comprising:
recognizing a current state in said software process, said current state being associated with contextual information;
encoding, by a first trained neural network, contextual information of said current state to obtain an encoded context, said encoded context being a single numerical representation;
evaluating, based on said encoded context, by a second trained neural network, suitability of at least one process action relative to the current state;
making a recommendation of said at least one process action based on said evaluated suitability;
transmitting, to the user interface, said recommendation to a designer of said software process;
receiving, from the user interface, a response to said recommendation from said designer; and
adding said at least one process action to said design of said software process when said response is an acceptance of said at least one process action, said adding comprising adding a section of software code corresponding to said at least one process action in the software file.
2. The method according to claim 1 , further comprising a plurality of process actions, wherein all of said plurality of process actions are recommended to said user simultaneously.
3. The method according to claim 1 , further comprising a plurality of process actions, wherein each of said plurality of process actions is recommended to said user sequentially.
4. The method according to claim 1 , wherein said at least one process action comprises multiple sub-actions.
5. The method according to claim 1 , wherein said current state is related to a current action in said software process.
6. The method according to claim 1 , wherein said recommending in step (b) is further based on at least one previous action in said software process.
7. The method according to claim 1 , wherein said at least one process action is at least one of:
a data manipulation action;
an action related to an interaction between systems;
a communication-related action; and
a storage-related action.
8. The method of claim 1 , further comprising the steps of:
collecting data related to: said current state; said at least one process action; and said response; and
using machine learning with said data to refine future recommendations.
9. A system for adding at least one process action to a design of a software process, the software process comprising a plurality of process steps, the software process corresponding to a software file, the system comprising:
a processor;
a non-transitory storage medium operatively connected to the processor, the non-transitory storage medium comprising computer-readable instructions;
the processor being operatively connected to a user interface,
the processor, upon executing the instructions, being configured to:
recognize a current state of said software process, said current state being associated with contextual information;
encode, by a first trained neural network, contextual information of said current state to obtain an encoded context, said encoded context being a single numerical representation;
evaluate, based on said encoded context, by a second trained neural network, suitability of at least one process action relative to the current state;
make a recommendation of said at least one process action based on said evaluated suitability;
transmit, to the user interface, said recommendation to a designer of said software process;
receive, from the user interface, a response to said recommendation from said designer; and
add said at least one process action to said design of said software process by adding a section of software code corresponding to said at least one process action in the software file when said response is an acceptance of said process action.
10. The system according to claim 9 , wherein said at least one process action comprises a plurality of process actions, wherein all of said plurality of process actions are recommended to said user simultaneously.
11. The system according to claim 9 , wherein said at least one process action comprises a plurality of process actions, wherein each of said plurality of process actions are recommended to said user sequentially.
12. The system according to claim 9 , wherein said current state is related to a current action in said software process.
13. The system according to claim 9 , wherein the processor is further configured to store information related to a previous action in said software process, and said information is used in determining said at least one process action to recommend.
14. The system according to claim 13 , wherein the processor is further configured to store other information related to other software processes, and wherein said other information is used in determining said at least one process action to recommend.
15. The system according to claim 9 , wherein said at least one process action is at least one of:
a data manipulation action;
an action related to an interaction between systems;
a communication-related action; and
a storage-related action.
16. The system of claim 13 , wherein the processor is further configured to store data related to: said current state; said at least one process action; and said response, and wherein said data is used to refine future recommendations.
17. A non-transitory computer-readable media having encoded thereon computer-readable and computer-executable instructions that, when executed by a processor, implement a method for adding at least one process action to a design of a software process, the software process comprising a plurality of process steps, the software process corresponding to a software file, the processor being operatively connected to a user interface, the method comprising:
recognizing a current state in said software process, said current state being associated with contextual information;
encoding, by a first trained neural network, contextual information of said current state to obtain an encoded context, said encoded context being a single numerical representation;
evaluating, based on said encoded context, by a second trained neural network, suitability of at least one process action relative to the current state;
making a recommendation of said at least one process action based on said evaluated suitability;
transmitting said recommendation to a designer of said software process to the user interface;
receiving, from the user interface, a response to said recommendation from said designer; and
adding said at least one process action to said design of said software process when said response is an acceptance of said at least one process action, said adding comprising adding a section of software code corresponding to said at least one process action in the software file.