Conversation assistant

摘要

Usage data associated with a user of a telephonic device is accessed by a remote learning engine. A service or a product that is likely to be of interest to the user is identified by the remote learning engine based on the accessed usage data. A recommended voice bundle application for the user is determined by the remote learning engine based on the accessed usage data, the recommended voice bundle application being a voice application that, when executed by the telephonic device, results in a simulated multi-step spoken conversation between the telephonic device and the user to enable the user to receive the identified service or the identified product. A recommendation associated with the recommended voice bundle application is transmitted from the remote learning engine to the telephonic device. The recommendation is presented by the telephonic device to the user through voice communications. The user through voice communications has accepted the recommendation determining is determined by the telephonic device. In response to determining that the user has accepted the recommendation, the recommended voice bundle application on the telephonic device is executed by the telephonic device.

主权项

1. A computer-implemented method comprising:
accessing, by a remote learning engine, usage data associated with a user of a telephonic device for determining a recommended voice bundle application for the user; identifying, by the remote learning engine based on the accessed usage data, a service or a product that is likely to be of interest to the user; determining, by the remote learning engine based on the accessed usage data and before the user requests to initiate the recommended voice bundle application, the recommended voice bundle application for the user, the recommended voice bundle application being a voice application that, when executed by the telephonic device, results in a simulated multi-step spoken interaction between the telephonic device and the user to enable the user to receive the identified service or the identified product; transmitting a recommendation that is based on the usage data and associated with the recommended voice bundle application, from the remote learning engine to the telephonic device; presenting through a voice communication, by the telephonic device to the user, the recommendation without executing the recommended voice bundle application; determining, by the telephonic device, whether the user through a voice communication has accepted the recommendation; in response to determining that the user has accepted the recommendation: determining whether the recommended voice bundle application is installed on the telephonic device; in response to determining that the recommended voice bundle application is installed on the telephonic device, executing, by the telephonic device, the recommended voice bundle application on the telephonic device; and in response to determining that the recommended voice bundle application is not installed on the telephonic device: (i) transmitting, from the remote learning engine to the telephonic device, the recommended voice bundle application; and (ii) executing, by the telephonic device, the recommended voice bundle application on the telephonic device; and in response to determining that the user has not accepted the recommendation, not executing the recommended voice bundle application on the telephonic device.