Dynamic adjustment of recommendations using a conversation assistant

摘要

Usage data associated with a user of a telephonic device is accessed by a remote learning engine. A first service or a first product is identified by the remote learning engine based on the accessed usage data. A first recommended voice bundle application is determined by the remote learning engine. A recommendation associated with the first recommended voice bundle application is transmitted to the telephonic device. The recommendation is presented by the telephonic device to the user through voice communications. A response from the user associated with the recommendation is received. In response to determining that the user has not accepted the recommendation, a second service or a second product is determined based on the received response. A second recommended voice bundle application is determined based on the second service. The second recommended voice bundle application 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; identifying, by the remote learning engine based on the accessed usage data, a first service or a first product that is likely to be of interest to the user; determining, by the remote learning engine based on the accessed usage data, a first recommended voice bundle application for the user, the first 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 first service or the first product; transmitting a recommendation associated with the first recommended voice bundle application from the remote learning engine to the telephonic device; presenting through voice communications, by the telephonic device to the user, the recommendation; receiving a response from the user associated with the recommendation; determining, by the telephonic device and based on the received response, whether the user through voice communications has accepted the recommendation; and in response to determining that the user has not accepted the recommendation:
identifying, based on the received response, a second service or a second product that is of interest to the user;determining, by the remote learning engine, a second recommended voice bundle application based on the second service or the second product, the second recommended voice bundle application being a voice application that is different from the first recommended voice bundle application, and 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 second service or the second product;installing, by the telephonic device, the second recommended voice bundle application on the telephonic device; andexecuting, by the telephonic device, the second recommended voice bundle application on the telephonic device.