Dynamic access of artificial intelligence engine in a cloud computing architecture
A method and a cloud-computing architecture for enabling dynamic access of an artificial intelligence engine are described. A record that includes a set of one or more fields is stored in a database. A first field from the set of fields includes an identification of an artificial intelligence (AI) engine and one or more additional fields from the set of fields respectively include one or more parameters for the AI engine. The record is accesses causing the AI engine to run with the one or more parameters. As a result of the AI engine running with the one or more parameters upon access of the record, a desired predicted output is obtained.
1. A method in a cloud-computing architecture, the method comprising:
storing, in a database, a record that includes a set of one or more fields, wherein a first field from the set of fields includes an identification of an artificial intelligence (AI) engine and one or more additional fields from the set of fields respectively include one or more parameters for the AI engine, wherein the identification of the AI engine and the one or more parameters are entered when the record is created or modified by a user;
in response to a request to view or update the record, generating one or more query statements for accessing the record in the database, wherein the accessing the record causes the AI engine to run with the one or more parameters as inputs; and
dynamically obtaining, as a result of the AI engine running with the one or more parameters as inputs, a desired predicted output.
2. The method of claim 1 , wherein the dynamically obtaining the desired predicted output includes defining the desired predicted output as data from a data source that is external to the database.
3. The method of claim 1 , wherein a second field from the set of fields includes authentication credentials for authorizing access to the AI engine when the AI engine is run with the one or more parameters as inputs.
4. The method of claim 1 , wherein a third field from the set of fields includes a type of the desired predicted output.
5. The method of claim 1 , wherein the request to view the record is a request for view the record on a graphical user interface presented to a user of the cloud computing architecture.
6. The method of claim 5 further comprising:
displaying the desired predicted output on the graphical user interface as a related list of the record or as a second record.
7. The method of claim 1 , further comprising:
processing the desired predicted output.
8. The method of claim 1 , wherein the identification of the AI engine is a Uniform Resource Locator (URL) that specifies a location of the AI engine in a network.
9. The method of claim 1 , wherein the AI engine is included in the cloud-computing architecture and includes a sales AI engine, a marketing AI engine, a community AI engine, an analytics AI engine, a language AI engine, a sentiment analysis engine, or a vision AI engine.
10. A non-transitory machine-readable storage medium that provides instructions that, if executed by a processor in a cloud-computing architecture, will cause said processor to perform operations comprising:
storing, in a database, a record that includes a set of one or more fields, wherein a first field from the set of fields includes an identification of an artificial intelligence (AI) engine and one or more additional fields from the set of fields respectively include one or more parameters for the AI engine, wherein the identification of the AI engine and the one or more parameters are entered when the record is created or modified by a user;
in response to a request to view or update the record, generating one or more query statements for accessing the record in the database, wherein the accessing the record causes the AI engine to run with the one or more parameters as inputs; and
dynamically obtaining, as a result of the AI engine running with the one or more parameters as inputs, a desired predicted output.
11. The non-transitory machine-readable storage medium of claim 10 , wherein the dynamically obtaining the desired predicted output includes defining the desired predicted output as data from a data source that is external to the database.
12. The non-transitory machine-readable storage medium of claim 10 , wherein a second field from the set of fields includes authentication credentials for authorizing access to the AI engine when the AI engine is run with the one or more parameters as inputs.
13. The non-transitory machine-readable storage medium of claim 10 , wherein a third field from the set of fields includes a type of the desired predicted output.
14. The non-transitory machine-readable storage medium of claim 10 , wherein the request to view the record is a request to view the record on a graphical user interface presented to a user of the cloud computing architecture.
15. The non-transitory machine-readable storage medium of claim 14 , wherein the operations further comprise:
displaying the desired predicted output on the graphical user interface as a related list of the record or as a second record.
16. The non-transitory machine-readable storage medium of claim 10 , wherein the operations further comprise:
processing the desired predicted output.
17. The non-transitory machine-readable storage medium of claim 10 , wherein the identification of the AI engine is a Uniform Resource Locator (URL) that specifies a location of the AI engine in a network.
18. The non-transitory machine-readable storage medium of claim 10 , wherein the AI engine is included in the cloud-computing architecture and includes a sales AI engine, a marketing AI engine, a community AI engine, an analytics AI engine, a language AI engine, a sentiment analysis engine, or a vision AI engine.