International Business Machines Corporation

Kimiko Wilson

Jorge Andres Moros Ortiz

Khoi-Nguyen Dao Tran

John Michael Wagner

Suman Sedai

Lenin Mehedy

Filiz Isabell Kiral

Emily Jy Wong

Allison Irvin

In an approach to generating conversational image representations, one or more computer processors detect one or more utterances by a user, wherein utterances are either textual or acoustic. The one or more computer processors generate one or more image representations of the one or more detected utterances utilizing a generative adversarial network restricted by one or more user privacy parameters, wherein the generative adversarial network is fed with an extracted sentiment, a generated avatar, an identified topic, an extracted location, and one or more user preferences. The one or more computer processors display the generated one or more image representations on one or more devices associated with respective one or more recipients of the one or more utterances.

Autocreation of conversational image representation

Aspects of the present disclosure relate to managing the upload of media items to cloud storage. A model can be configured to distinguish between confidential and non-confidential media items. A media item to be uploaded to a cloud storage can be analyzed using the model to determine whether the media item is confidential. In response to determining that the media item is confidential, an upload control action can be issued on the media item.

Upload management

Method, apparatus, and computer program product are provided for verifying location using sound. In some embodiments, location data representing an unverified location of a first electronic device are received. Audio data generated based on sound detected by a sensor of the first electronic device during a predetermined time are received, as well as audio data generated based on trusted sound detected by a sensor of a second electronic device during the predetermined time, wherein the second electronic device is located near the unverified location of the first electronic device, and wherein the trusted sound includes one or more frequencies inaudible to humans (e.g., infrasonic and/or ultrasonic sound). The audio data generated by the first and second electronic devices are analyzed and a similarity score representing a similarity between the respective audio data is generated. The unverified location of the first electronic device may be verified based on the similarity score.

Using sound to verify location

Aspects of the invention include a computer-implemented method for quantifying tester sentiment. The computer-implemented method includes receiving a first feedback data from a first tester, where the first feedback data represents feedback generated by the first tester in connection with a first instance of a first software-under-development. The first feedback data is correlated to an aspect of the first instance of the first software-under-development to derive a tester sentiment data. The tester sentiment data is used to determine a tester sentiment rating of the first instance of the software-under-development. Based on the tester sentiment rating, a resource is applied to the first instance of the first software-under-development.

Growing community of inventors

Southbank, Australia

Kimiko Wilson