Intelligent agent
A computing system aggregates information from a plurality of information channels associated with a computing device and a user of the computing device. A user configures the access for the computing system to specific information channels at a user interface. Based on a knowledge base and by machine learning techniques, the computing system analyzes the aggregated information to identify information relevant to an intelligent action for execution on behalf of the user. The computing system identifies the intelligent action in the context of the user's preferences and permissions granted to the computing system. The computing system initiates execution of the intelligent action based on a confidence level derived from analysis of information contained the knowledge base and historical decisioning information. The computing system receives feedback for an executed action and incorporates the feedback in the knowledge base for future decisioning based on aggregated information.
1. A computing platform, comprising:
at least one processor;
a communication interface communicatively coupled to the at least one processor; and
memory storing computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
receive, by an aggregation module and via the communication interface, aggregated information from a plurality of information channels;
analyze, automatically by a machine learning module and based on a knowledge base, the aggregated information to identify relevant information for automatic decisioning;
analyze, by the machine learning module and based on the knowledge base, the relevant information to identify an executable action to be performed by an application associated with the computing platform;
generate, based on the knowledge base and historical decisioning information, a confidence level associated with initiating the executable action by the application, wherein the confidence level corresponds to a user satisfaction with performance of the executable action by the application;
cause execution, by a decision processing module and based on the confidence level, a decision threshold, and user permission information, of the executable action at a system of the computing platform associated with the executable action; and
update the historical decisioning information with decisioning information associated with the executable action initiated at the system of the computing platform, wherein the decisioning information comprises a description of the executable action, the confidence level, the decision threshold, and user feedback associated with the executable action.
2. The computing platform of claim 1 , wherein the instructions, when executed by the one or more processors, cause the computing platform to:
compare, by the decision processing module, the confidence level to the decision threshold associated with the executable action, wherein the decision threshold is determined based on analysis of the knowledge base, the historical decisioning information, and the user feedback.
3. The computing platform of claim 1 , wherein the instructions, when executed by the one or more processors, cause the computing platform to:
identify, based on the executable action and at the knowledge base, the user permission information associated with the executable action.
4. The computing platform of claim 1 , wherein the instructions, when executed by the one or more processors, cause the computing platform to:
cause display, by the decision processing module and at a user interface of the computing platform, a notification comprising a request for user permission information associated with the executable action.
5. The computing platform of claim 4 , wherein the instructions, when executed by the one or more processors, cause the computing platform to:
receive, by a user interface of the computing platform, a permission response for the request for user permission information associated with the executable action, wherein the permission response comprises information indicating approval or disapproval of the executable action; and
store, at the knowledge base, the permission response.
6. The computing platform of claim 1 , wherein the instructions, when executed by the one or more processors, cause the computing platform to:
configure, by a user interface of the computing platform, accessibility settings for the aggregation module to deny or allow the aggregation module to access an information channel of the plurality of information channels.
7. The computing platform of claim 1 , wherein the instructions, when executed by the one or more processors, cause the computing platform to:
receive, by a user interface of the computing platform, the user feedback associated with the executable action, wherein the user feedback comprises information indicating the user satisfaction level with the executable action; and
store, at the knowledge base and with the historical decisioning information, the user feedback associated with the executable action.
8. The computing platform of claim 1 , wherein the plurality of information channels comprises account information, applications, systems associated with the computing platform, and data gathered from peripherals of the computing platform.
9. A method, comprising:
at a computing platform comprising one or more processors, memory, and a communication interface:
receiving, by an aggregation module and via the communication interface, aggregated information from a plurality of information channels;
analyzing, automatically by a machine learning module and based on a knowledge base, the aggregated information to identify relevant information for automatic decisioning;
analyzing, by the machine learning module and based on the knowledge base, the relevant information to identify an executable action to be performed by an application associated with the computing platform;
generating, based on the knowledge base and historical decisioning information, a confidence level associated with initiating the executable action by the application, wherein the confidence level corresponds to a user satisfaction with performance of the executable action by the application;
causing execution, by a decision processing module and based on the confidence level, a decision threshold, and user permission information, of the executable action at a system of the computing platform associated with the executable action; and
updating the historical decisioning information with decisioning information associated with the executable action initiated at the system of the computing platform, wherein the decisioning information comprises a description of the executable action, the confidence level, the decision threshold, and user feedback associated with the executable action.
10. The method of claim 9 , comprising:
comparing, by the decision processing module, the confidence level to the decision threshold associated with the executable action, wherein the decision threshold is determined based on analysis of the knowledge base, the historical decisioning information, and the user feedback.
11. The method of claim 9 , comprising:
identifying, based on the executable action and the knowledge base, the user permission information associated with the executable action.
12. The method of claim 9 , comprising:
generating, by the decision processing module and at a user interface of the computing platform, a notification comprising a request for user permission information associated with the executable action.
13. The method of claim 12 , comprising:
receiving, at a user interface of the computing platform, a permission response associated with the request for user permission information associated with the executable action, wherein the permission response comprises information indicating approval or disapproval of the executable action; and
storing, at the knowledge base, the permission response.
14. The method of claim 9 , comprising:
configuring, by a user interface of the computing platform, accessibility settings to an information channel of the plurality of information channels for the aggregation module.
15. One or more non-transitory computer-readable media storing instructions that, when executed by a computing platform comprising at least one processor, memory, and a communication interface, cause the computing platform to:
receive, by an aggregation module and via the communication interface, aggregated information from a plurality of information channels;
analyze, automatically by a machine learning module and based on a knowledge base, the aggregated information to identify relevant information for automatic decisioning;
analyze, by the machine learning module and based on the knowledge base, the relevant information to identify an executable action to be performed by an application associated with the computing platform;
generate, based on the knowledge base and historical decisioning information, a confidence level associated with initiating the executable action by the application, wherein the confidence level corresponds to a user satisfaction with performance of the executable action by the application;
cause execution, by a decision processing module and based on the confidence level, a decision threshold, and user permission information, of the executable action at a system of the computing platform associated with the executable action; and
update the historical decisioning information with decisioning information associated with the executable action initiated at the system of the computing platform, wherein the decisioning information comprises a description of the executable action, the confidence level, the decision threshold, and user feedback associated with the executable action.
16. The one or more non-transitory computer-readable media of claim 15 , wherein the instructions, when executed by the one or more processors, cause the computing platform to:
compare, by the decision processing module, the confidence level to the decision threshold associated with the executable action, wherein the decision threshold is determined based on analysis of the knowledge base, the historical decisioning information, and the user feedback.
17. The one or more non-transitory computer-readable media of claim 15 , wherein the instructions, when executed by the one or more processors, cause the computing platform to:
identify, based on the executable action and the knowledge base, the user permission information associated with the executable action.
18. The one or more non-transitory computer-readable media of claim 15 , wherein the instructions, when executed by the one or more processors, cause the computing platform to:
generate, by the decision processing module and at a user interface of the computing platform, a notification comprising a request for user permission information associated with the executable action;
receive, at a user interface of the computing platform, a permission response associated with the request for user permission information associated with the executable action, wherein the permission response comprises information indicating approval or disapproval of the executable action; and
store, at the knowledge base, the permission response.
19. The one or more non-transitory computer-readable media of claim 15 , wherein the instructions, when executed by the one or more processors, cause the computing platform to:
configure, by a user interface of the computing platform, accessibility settings to an information channel of the plurality of information channels for the aggregation module.
20. The one or more non-transitory computer-readable media of claim 15 , wherein the instructions, when executed by the one or more processors, cause the computing platform to:
receive, by a user interface of the computing platform, the user feedback associated with the executable action, wherein the user feedback comprises information indicating a user satisfaction level with the executable action; and
store, at the knowledge base and with the historical decisioning information, the user feedback associated with the executable action.