Abstract: Techniques are disclosed for generating explanatory data for predictions generated by a machine learning model. An explanatory engine receives a trained machine learning model and a plurality of predictions generated by the machine learning model. The explanatory engine calculates a predictive strength for the trained machine learning model based on the plurality of predictions. The explanatory engine further determines one or more features having at least a threshold influence on the plurality of predictions and displays, via a graphical user interface, one or more of the influential features and an indication of the predictive strength of the trained model.

Abstract: Techniques are disclosed for specifying a predictive goal that describes an action that a customer of an organization may take or a behavior that a customer of the organization may exhibit. A training engine receives the predictive goal from a user via a Graphical User Interface (GUI). The user specifies the predictive goal by entering one or more customizable logical or comparative statements. A training engine divides historical data into training data and testing data, selects useful and relevant features from the historical data as inputs to a machine learning model, and trains the machine learning model. The training engine transmits the trained machine learning model to an inference engine that generates, for each customer in a historical data set, a probability that the customer will satisfy the predictive goal within a specified time frame. The disclosed techniques further generate explanatory data associated with the trained machine learning model.

Abstract: The embodiments of the present disclosure are capable of capturing a user's movement using inertial measurement units (IMUs) that are embedded in, or otherwise attached to, clothing. In one embodiment, a wearable system for capturing a user's bodily movements includes a wearable item mechanically coupled to an inertial measurement unit (IMU). The wearable item, when worn by a user, positions the IMU proximate to a body part of the user. The system further includes a processor communicatively coupled to the IMU and configured to receive the sensor data from the IMU, generate movement data based on the sensor data, and transmit the movement data to a device.

Abstract: A device for storing, mixing and applying skincare, cosmetic, food and pharmaceutical products includes a tubular housing which is used to hold a plurality of dispensing canisters, a plurality of plungers, and a dispensing actuation hub. The plurality of dispensing canisters is used to store various types of skincare, cosmetic, food, and pharmaceutical products. Each of the plurality of plungers is used to dispense products from a corresponding dispensing canister. Each of the plurality of plungers is controlled by the dispensing actuation hub. The device includes a microprocessor housed within the tubular housing and used to control which products are dispensed by the dispensing actuation hub. The device is powered by power supply which is also housed within the tubular housing. A mixing chamber is included within the tubular housing and provides a space for multiple products to be blended.

Abstract: The present disclosure describes dynamically adjusting linguistic models for automatic speech recognition based on biometric information to produce a more reliable speech recognition experience. Embodiments include receiving a speech signal, receiving a biometric signal from a biometric sensor implemented at least partially in hardware, determining a linguistic model based on the biometric signal, and processing the speech signal for speech recognition using the linguistic model based on the biometric signal.

Abstract: A device for storing, mixing and applying skincare, cosmetic, food and pharmaceutical products includes a tubular housing which is used to hold a plurality of dispensing canisters, a plurality of plungers, and a dispensing actuation hub. The plurality of dispensing canisters is used to store various types of skincare, cosmetic, food, and pharmaceutical products. Each of the plurality of plungers is used to dispense products from a corresponding dispensing canister. Each of the plurality of plungers is controlled by the dispensing actuation hub. The device includes a microprocessor housed within the tubular housing and used to control which products are dispensed by the dispensing actuation hub. The device is powered by power supply which is also housed within the tubular housing. A mixing chamber is included within the tubular housing and provides a space for multiple products to be blended.

Abstract: The present disclosure relates to the identification of video content. In one aspect, a method includes generating a query based on bibliographic data. The method also includes obtaining a collection of resources responsive to the query, wherein one or more of the resources include text and video content. The method further includes calculating occurrence scores for the resources. A particular occurrence score for a particular resource is based at least in part on the bibliographic data matching text included in the particular resource and the text being associated with video content. The method further includes selecting one or more resources as including video content identified by the bibliographic data using the occurrence scores. The method further includes storing data associating the selected resources with the bibliographic data.

Abstract: A system to add metadata to downstream broadcasts to devices such as smart phones, MP3 music players, tablet computers, etc. equipped with receivers to receive said downstream broadcasts and a full time or part time upstream digital data communication path. The devices are controlled to display or playback advertisements, images etc. in the metadata, detect click events indicating interest by a user in something in the metadata and communicate that click event upstream over a full time or part time internet or an SMS data path connection. Upstream communications to implement user interest such as visit web pages, make a phone call, start an e-commerce transaction are implemented by the client devices. The Transmitters have structure to insert metadata in band or out of band with the broadcast program content and can be coupled to ad servers.

Abstract: A preferred embodiment of the inventive fluid delivery system comprises a vertical liquid/vapor separator and riser assembly that comprises a multi-phase separator inlet, a vapor outlet and riser, and a liquid outlet port connected to a hydraulically-driven centrifugal pump. By controlling the operational speed of the pump, the level of the separated liquid within the separator can be controlled without the need for control valves. The vertical separator is capable of low pressure operation and large variations in controlled liquid levels within the separator, allowing the relatively slow reaction time pump to control the liquid level from low pressure wells penetrating low pressure reservoirs.

Abstract: A preferred embodiment of the inventive fluid delivery system comprises a vertical liquid/vapor separator and riser assembly that comprises a multi-phase separator inlet, a vapor outlet and riser, and a liquid outlet port connected to a hydraulically-driven centrifugal pump. By controlling the operational speed of the pump, the level of the separated liquid within the separator can be controlled without the need for control valves. The vertical separator is capable of low pressure operation and large variations in controlled liquid levels within the separator, allowing the relatively slow reaction time pump to control the liquid level from low pressure wells penetrating low pressure reservoirs.

Abstract: A preferred embodiment of the inventive fluid delivery system comprises a vertical liquid/vapor separator and riser assembly that comprises a multi-phase separator inlet, a vapor outlet and riser, and a liquid outlet port connected to a hydraulically-driven centrifugal pump. By controlling the operational speed of the pump, the level of the separated liquid within the separator can be controlled without the need for control valves. The vertical separator is capable of low pressure operation and large variations in controlled liquid levels within the separator, allowing the relatively slow reaction time pump to control the liquid level from low pressure wells penetrating low pressure reservoirs.

Abstract: A preferred embodiment of the inventive fluid delivery system comprises a vertical liquid/vapor separator and riser assembly that comprises a multi-phase separator inlet, a vapor outlet and riser, and a liquid outlet port connected to a hydraulically-driven centrifugal pump. By controlling the operational speed of the pump, the level of the separated liquid within the separator can be controlled without the need for control valves. The vertical separator is capable of low pressure operation and large variations in controlled liquid levels within the separator, allowing the relatively slow reaction time pump to control the liquid level from low pressure wells penetrating low pressure reservoirs.