Abstract:
A computer-implemented method includes identifying a first set of utterances from a plurality of utterances. The plurality of utterances is associated with a conversation and transmitted via a plurality of audio signals. The computer-implemented method further includes mining the first set of utterances for a first context. The computer-implemented method further includes determining that the first context associated with the first set of utterances is not relevant to a second context associated with the conversation. The computer-implemented method further includes dynamically muting, for at least a first period of time, a first audio signal in the plurality of audio signals corresponding to the first set of utterances. A corresponding computer system and computer program product are also disclosed.
Abstract:
A method and system for analyzing captured vehicle parts alteration data and correlating with vehicle service procedures to identify service completion and anomalies is disclosed. The method and system includes loading captured vehicle parts alteration data for a particular vehicle from a vehicle history module, the vehicle parts alteration data being captured by one or more sensors and stored in the vehicle history module, identifying predefined service procedure events and corresponding procedural steps for the particular vehicle, analyzing the captured vehicle parts alteration data for one or more events that match the predefined service procedure events; and for each service procedure event matched, automatically identifying anomalies by one or more of: identify procedural steps that have been completed and procedural steps that have not been completed and identifying procedural steps that were done that are not in one of the predefined service procedure events.
Abstract:
An approach is provided for pooling bandwidth provided by mobile devices in an ad hoc group. Based on information in data plans provided by wireless carriers to the mobile devices, amounts of data that will be unused at the end of respective billing cycles are estimated. Based on the estimated amounts, contributions of data from the mobile devices are determined. Based on capabilities of the mobile devices, time periods during which the respective mobile devices are subscripted for providing at least some of the respective contributions of data are determined. Hand-offs among the mobile devices are coordinated to provide a cooperative usage of the bandwidth among the mobile devices which minimizes redundant streaming or downloading of content to more than one of the mobile devices. The streamed or downloaded content is presented to the ad hoc group of mobile devices.
Abstract:
An embodiment of the invention provides a method for non-intrusive cloud services billing, including storing service log files in a data store, wherein each of the service log files include a lifecycle event of a resource in a service produced by an instance of the service. A log transformer connected to the data store converts the service log files into a standardized format. A metering descriptor describing billable entities for each offering of the service is obtained, wherein each offering of the service has a different metering descriptor, and wherein the billable entities include multiple categories of billing. A billing record generator connected to the log transformer is programmed, wherein the billing record generator converts standardized log records into metering records. The billing record generator generates a metering record with one or more of the service log files in the standardized format and the metering descriptor.
Abstract:
An approach for querying and managing/manipulating network computing resources (e.g., cloud computing resources) is provided. Typically, an interpreter component may be implemented so that a language describing such computing resources may be interpreted. The interpreter component may include other components such as a request processor, a provisioning queue, an execution engine, a results store, and response marshaller/handler that collaborate to manage the computing resources. Such computing resources may, for example, include virtual machine instances, virtual machine images, storage volumes, network resources, files, software bundles, etc.
Abstract:
A system including at least one memory having a plurality of individual contributions forming a compilation stored in the at least one memory; and at least one processor connected to the at least one memory, where the processor is configured to use provenance data associated with a catalog item to track an individual contribution in a compilation of contributions, where the compilation is stored in the at least one memory; and dynamically compute a royalty distribution for the individual contribution based, at least partially, upon at least one metric related to the contributions which form the compilation.
Abstract:
Provided is a method, system, and computer program product for assessing user engagement during playback of multimedia content. A processor may analyze user audio engagement during playback of audio content of the multimedia content. The analyzing may be based on comparing a distance of a user from a speaker transmitting the audio content and comparing the distance of the user from the speaker transmitting the audio content to a volume setting of the speaker. The processor may analyze user video engagement during playback of video content of the multimedia content. The analyzing may be based on using eye-tracking software to compare a particular video content the user is actively viewing to the audio content being presented. The processor may generate a user engagement score during the playback of the multimedia content based on a time averaged value for each metric analyzed during playback of the audio content and video content.
Abstract:
Mechanisms are provided for bulk product processing. Product data and customer data are obtained which specify characteristics of products and customer choice characteristics. A knowledge corpus is created based on a historical learning analysis of the product data and customer data, where the knowledge corpus comprises data specifying customer buying patterns, patterns in growing or waning customer interest in products, and patterns in customer choice of products for purchase. An artificial intelligence (AI) computer pipeline executes an AI computer model on the knowledge corpus to predict, for a customer segment of the customer data, a product that customers will purchase in bulk. A bulk product recommendation is generated based on results of executing the AI computer model and output to a product provider computing system.
Abstract:
According to one embodiment, a method, computer system, and computer program product for a personalized, point-of-sale graphical user interface is provided. The embodiment may include detecting an object for purchase that requires additional user input on a point-of-sale (POS) device. The embodiment may also include generating a custom user interface display on the POS device based, at least in part, on the detected object and historical purchase information associated with a user purchasing the detected object.
Abstract:
A method, computer system, and a computer program product for masking identifying traits contained in response text is provided. Embodiments may include receiving a request to anonymize response text in response to a predefined respondent interaction, wherein the response text is generated by the respondent and then obtaining the response text, wherein the obtained response text has semantic characteristics. Next, the obtained response text may be input into a natural language processing (NLP) algorithm and thereafter receiving an alternative masking text as output from the NLP algorithm, wherein the received alternative masking text maintains the semantic characteristics of the obtained response text. Finally, the response text may be replaced with the received alternative masking text.