US 12,229,585 B2
Back-end task fulfillment for dialog-driven applications
Vikram Sathyanarayana Anbazhagan, Seattle, WA (US); Swaminathan Sivasubramanian, Sammamish, WA (US); Stefano Stefani, Issaquah, WA (US); and Vladimir Zhukov, Seattle, WA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Jan. 8, 2021, as Appl. No. 17/145,133.
Application 17/145,133 is a continuation of application No. 15/360,818, filed on Nov. 23, 2016, granted, now 10,891,152.
Prior Publication US 2021/0132986 A1, May 6, 2021
Int. Cl. G06F 9/48 (2006.01); G06F 40/35 (2020.01)
CPC G06F 9/4843 (2013.01) [G06F 40/35 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
prior to depolying an application to make it available for a user:
obtaining, via one or more programmatic interfaces of a dialog-driven-application management service of a cloud computing environment, a request to define a first intent of the application, wherein the first intent corresponds to a first task to be initiated on behalf of the user in response to one or more dialog inputs obtained from the user via on or more end user-related programmatic interfaces;
storing an indication of one or more parameters of the first intent; wherein the first task is to be performed based on the one or more parameters of the first internet;
provisioning, in the cloud computing environment, one or more computer resources to perform a least a first portion of the first task wherein the one or more compute resources includes one or more virtual machines allocated for the application, and
generating integration code to integrate the application with a fulfillment resource external to the cloud computing environment, wherein the fulfillment resource is configured to perform a least a second portion of the first task; and
after the application is deployed:
receiving, from the application, one or more respective values of the one or more parameters of the first intent determined based at least in part on processing of a dialog input from the user using one or more machine learning models, wherein the one or more machine learning models generates a match score of the dialog input with respect to the first intent and the match score exceeds a match threshold,
causing the one or more compute resources of the cloud computing environment to perform the first portion of the first task based on the respective values of the one or more parameters; and
causing the second portion of the first task to be performed at by the fulfillment resource external to the cloud computing environment.