Hybrid cognitive system for AI/ML data privacy
Systems, methods, and devices are disclosed for cognitive collaboration systems on a hybrid node. A query is received by a virtual assistant running on a public cloud, and it is determined whether the query pertains to data available on a public cloud resource, or the query pertains to data available on a private cloud resource. When it is determined that the query pertains to the data available on the public cloud resource, the query is interpreted by using a first model trained on at least one machine learning technique on data from the public cloud. When it is determined that the query pertains to the data available on the private cloud resource, the query is interpreted by using a second model trained on at least one machine learning technique on the data from the private cloud.
1. A method comprising:
receiving, at a virtual assistant at a public cloud having access to public data of the public cloud, a query;
determining whether the query is requesting to access the public data of the public cloud by processing the query through a first machine learning model trained using the public data of the public cloud;
in response to determining that the query is not requesting to access the public data of the public cloud, determining whether the query is a request to access private data of a private cloud;
in response to determining that the query is requesting to access the private data of the private cloud, transmitting the query to a virtual assistant at the private cloud;
in response to transmitting the query to the virtual assistant of the private cloud, interpreting the query by using a second machine learning model trained on at least one machine learning technique using the private data of the private cloud; and
receiving, at the virtual assistant of the public cloud from the virtual assistant of the private cloud, a response to the query.
2. The method of claim 1 , further comprising:
in response to determining that the query is requesting to access the public data of the public cloud, responding to the query with the public data of the public cloud.
3. The method of claim 1 , wherein the determining whether the query is requesting to access the public data of the public cloud or the private data of the private cloud comprises:
parsing, at the virtual assistant of the public cloud, the query to determine one or more domains; and
determining whether the one or more domains is in the public cloud or in the private cloud.
4. The method of claim 3 , further comprising:
determining, at the virtual assistant of the public cloud, whether the one or more domains has one or more intents; and
determining whether the one or more intents is in the public cloud or in the private cloud.
5. The method of claim 4 , further comprising:
determining, at the virtual assistant of the public cloud, whether the one or more intents has one or more entities; and
determining whether the one or more entities is in the public cloud or in the private cloud.
6. The method of claim 1 , wherein determining whether the query is requesting to access private data of a private cloud comprises:
receiving, at the virtual assistant of the public cloud, one or more domains, one or more intents, or one or more entities of the private cloud; and
determining whether the one or more domains, the one or more intents, or the one or more entities are related to the query.
7. The method of claim 1 , further comprising:
in response to determining that the query is requesting to access the public data of the public cloud, interpreting the query by using a first model trained on at least one machine learning technique on data from the public cloud.
8. The method of claim 1 , wherein the query is generated from natural language processing.
9. The method of claim 1 , wherein the virtual assistant at the public cloud includes customizable content based on domains of the public cloud and the private cloud.
10. A virtual assistant at a public cloud having access to public data of the public cloud, the virtual assistant comprising: at least one processor; and at least one memory storing instructions, which when executed by the at least one processor, causes the at least one processor to:
receive a query;
determine whether the query is requesting to access the public data of the public cloud by processing the query through a first machine learning model trained using the public data of the public cloud;
in response to determining that the query is not requesting to access the public data of the public cloud, determine whether the query is a request to access private data of a private cloud;
in response to determining that the query is requesting to access the private data of the private cloud, transmit the query to a virtual assistant at the private cloud;
in response to transmitting the query to the virtual assistant of the private cloud, interpret the query by using a second machine learning model trained on at least one machine learning technique using the private data of the private cloud; and
receive, from the virtual assistant of the private cloud, a response to the query.
11. The virtual assistant of claim 10 , further comprising instructions which when executed causes the at least one processor to:
parse the query to determine one or more domains; and
determine whether the one or more domains is in the public cloud or in the private cloud.
12. The virtual assistant of claim 11 , further comprising instructions which when executed causes the at least one processor to:
determine whether the one or more domains has one or more intents; and
determine whether the one or more intents is in the public cloud or in the private cloud.
13. The virtual assistant of claim 12 , further comprising instructions which when executed causes the at least one processor to:
determine whether the one or more intents has one or more entities; and
determine whether the one or more entities is in the public cloud or in the private cloud.
14. The virtual assistant of claim 10 , further comprising instructions which when executed causes the at least one processor to:
receive one or more domains, one or more intents, or one or more entities of the private cloud; and
determine whether the one or more domains, the one or more intents, or the one or more entities are related to the query.
15. The virtual assistant of claim 10 , wherein the virtual assistant at the public cloud includes customizable content based on domains of the public cloud and the private cloud.
16. At least one non-transitory computer readable medium storing instructions, which when executed by at least one processor of a virtual assistant at a public cloud having access to public data of the public, causes the at least one processor to:
receive a query;
determine whether the query is requesting to access the public data of the public cloud by processing the query through a first machine learning model trained using the public data of the public cloud;
in response to determining that the query is not requesting to access the public data of the public cloud, determine whether the query is a request to access private data of a private cloud;
in response to determining that the query is requesting to access the private data of the private cloud, transmit the query to a virtual assistant at the private cloud;
in response to transmitting the query to the virtual assistant of the private cloud, interpret the query by using a second machine learning model trained on at least one machine learning technique using the private data of the private cloud; and
receive, from the virtual assistant of the private cloud, a response to the query.
17. The at least one non-transitory computer readable medium of claim 16 , further comprising instructions which when executed causes the at least one processor to:
parse the query to determine one or more domains; and
determine whether the one or more domains is in the public cloud or in the private cloud.
18. The at least one non-transitory computer readable medium of claim 17 , further comprising instructions which when executed causes the at least one processor to:
determine whether the one or more domains has one or more intents; and
determine whether the one or more intents is in the public cloud or in the private cloud.
19. The at least one non-transitory computer readable medium of claim 18 , further comprising instructions which when executed causes the at least one processor to:
determine whether the one or more intents has one or more entities; and
determine whether the one or more entities is in the public cloud or in the private cloud.
20. The at least one non-transitory computer readable medium of claim 18 , wherein the query is generated from natural language processing.