Abstract: Digital photograph filters and associated settings are recommended by an image classification model. A plurality of images and metadata associated with each of the plurality of images are received. Human interaction scores for each of the images are received. Training data is generated classifying the images using the associated metadata and human interaction scores. The training data is used to derive an image classification model for predicting a human interaction score for an image having an unknown human interaction score. At least one recommended image capture setting using the image classification model is determined in response to determining that a user is preparing to capture an image with a device. The recommended image capture setting is displayed on a display of the device.

Abstract: An example method of determining operational health of a virtualized computing system includes: monitoring, at a service executing in the virtualized computing system, a current configuration of a software-defined data center (SDDC) with respect to a desired state, the desired state including: a host cluster having hosts executing a virtualization layer thereon; a software-defined (SD) network deployed in the host cluster; shared storage accessible by the host cluster; a virtual infrastructure (VI) control plane managing the host cluster, the SD network, and the shared storage; and an orchestration control plane integrated with the virtualization layer and the VI control plane; determining a configuration status for the current configuration of the SDDC; monitoring, at the service, operational status of an application management system executing on the SDDC having the current configuration; and determining at least one measure of the operational health in response to the configuration status and the operation

Abstract: Digital photograph filters and associated settings are recommended by an image classification model. A plurality of images and metadata associated with each of the plurality of images are received. Human interaction scores for each of the images are received. Training data is generated classifying the images using the associated metadata and human interaction scores. The training data is used to derive an image classification model for predicting a human interaction score for an image having an unknown human interaction score. At least one recommended image capture setting using the image classification model is determined in response to determining that a user is preparing to capture an image with a device. The recommended image capture setting is displayed on a display of the device.

Abstract: Managing user access to data of a social media account, by providing a first user with access to data of a social media account of a second user based on determining that a first data access request by the first user conforms to an expected data access pattern.

Abstract: An example method of determining operational health of a virtualized computing system includes: monitoring, at a service executing in the virtualized computing system, a current configuration of a software-defined data center (SDDC) with respect to a desired state, the desired state including: a host cluster having hosts executing a virtualization layer thereon; a software-defined (SD) network deployed in the host cluster; shared storage accessible by the host cluster; a virtual infrastructure (VI) control plane managing the host cluster, the SD network, and the shared storage; and an orchestration control plane integrated with the virtualization layer and the VI control plane; determining a configuration status for the current configuration of the SDDC; monitoring, at the service, operational status of an application management system executing on the SDDC having the current configuration; and determining at least one measure of the operational health in response to the configuration status and the operation

Abstract: Managing user access to data of a social media account, by providing a first user with access to data of a social media account of a second user based on determining that a first data access request by the first user conforms to an expected data access pattern.

Abstract: Systems and methods are provided for enabling communication, without breaching the engine firewall, between a datalogger located on one side of the firewall and one or more sensor devices that are located on the opposite side of the firewall. The systems and methods described herein can allow a transmitting node (i.e., a transmitting datalogger) to transmit collected data (from an auxiliary sensor) to a receiving node (i.e., a receiving datalogger) while reducing or minimizing various difficulties associated with addition of an auxiliary sensor in the engine environment. The transmission of data from the transmitting node to the receiving node can correspond to wired data communication or wireless data communication.

Abstract: According to a computer-implemented method, a visual component and an audio component of an electronic presentation are analyzed. The electronic presentation is classified based on the analysis of the visual component and the analysis of the audio component. A number of transition points for the electronic presentation are identified based on the analysis of the visual component and the analysis of the audio component. Reference markers are inserted into the electronic presentation at certain identified transition points.

Abstract: Techniques for medical coding include applying a natural language understanding (NLU) engine to a free-form text documenting a clinical patient encounter, to derive a first set of one or more medical billing codes for the clinical patient encounter and a link between each code in the first set and a corresponding portion of the free-form text. The first set of codes may be compared to a second set of one or more medical billing codes approved by one or more human users for the patient encounter, to identify at least one code in the first set that overlaps with at least one code in the second set. The code in the second set approved by the one or more human users may be retained instead of the overlapping code in the first set derived by the NLU engine.

Abstract: A method for improving fuel efficiency testing precision in on-road vehicles. The method comprises: installing one or more dataloggers in one or more vehicles, each datalogger configured to receive fuel consumption data broadcast by an on-road vehicle's engine control unit (ECU); transmitting the fuel consumption data from the one or more dataloggers in the one or more on-road vehicles to a processor; and analyzing, using the processor, the fuel consumption data from the one or more dataloggers in the one or more on-road vehicles to determine fuel efficiency of the one or more on-road vehicles. The fuel consumption data comprises fuel rate data from the ECU which is transmitted through the one or more dataloggers, engine speed and other operating parameters from the ECU that are transmitted through the one or more dataloggers, torque sensor data which is transmitted through the one or more dataloggers, and traditional fuel log data.

Abstract: Techniques for training a natural language understanding (NLU) engine may include generating a first annotation of free-form text documenting a healthcare patient encounter and a link between the first annotation and a corresponding portion of the text, using the NLU engine. A second annotation of the text and a link between the second annotation and a corresponding portion of the text may be received from a human user. The first annotation and its corresponding link may be merged with the second annotation and its corresponding link. Training data may be provided to the engine in the form of the text and the merged annotations and links.

Abstract: Techniques for medical coding include applying a natural language understanding (NLU) engine to a free-form text documenting a clinical patient encounter, to derive a first set of one or more medical billing codes for the clinical patient encounter and a link between each code in the first set and a corresponding portion of the free-form text. The first set of codes may be compared to a second set of one or more medical billing codes approved by one or more human users for the patient encounter, to identify at least one code in the first set that overlaps with at least one code in the second set. The code in the second set approved by the one or more human users may be retained instead of the overlapping code in the first set derived by the NLU engine.

Abstract: A method for managing an e-mail response based on the e-mail domains of the recipients is provided. The method receives a first e-mail sent to a plurality of e-mail addresses that includes e-mails with different domain names, provides a list of different domain names associated with a plurality of e-mail addresses and an e-mail address of a sender of the first e-mail, generates, based on a selection of one or more of the different domain names, a distribution list including one or more e-mail addresses limited to e-mail addresses having a selected domain name, and providing the distribution list in an addressee field associated with the e-mail response.

Abstract: Systems and methods are provided for enabling communication, without breaching the engine firewall, between a datalogger located on one side of the firewall and one or more sensor devices that are located on the opposite side of the firewall. The systems and methods described herein can allow a transmitting node (i.e., a transmitting datalogger) to transmit collected data (from an auxiliary sensor) to a receiving node (i.e., a receiving datalogger) while reducing or minimizing various difficulties associated with addition of an auxiliary sensor in the engine environment. The transmission of data from the transmitting node to the receiving node can correspond to wired data communication or wireless data communication.

Abstract: A method for improving fuel efficiency testing precision in on-road vehicles. The method comprises: installing one or more dataloggers in one or more vehicles, each datalogger configured to receive fuel consumption data broadcast by an on-road vehicle's engine control unit (ECU); transmitting the fuel consumption data from the one or more dataloggers in the one or more on-road vehicles to a processor; and analyzing, using the processor, the fuel consumption data from the one or more dataloggers in the one or more on-road vehicles to determine fuel efficiency of the one or more on-road vehicles. The fuel consumption data comprises fuel rate data from the ECU which is transmitted through the one or more dataloggers, engine speed and other operating parameters from the ECU that are transmitted through the one or more dataloggers, torque sensor data which is transmitted through the one or more dataloggers, and traditional fuel log data.

Abstract: A method for managing an e-mail response based on the e-mail domains of the recipients is provided. The method receives a first e-mail sent to a plurality of e-mail addresses that includes e-mails with different domain names, provides a list of different domain names associated with a plurality of e-mail addresses and an e-mail address of a sender of the first e-mail, generates, based on a selection of one or more of the different domain names, a distribution list including one or more e-mail addresses limited to e-mail addresses having a selected domain name, and providing the distribution list in an addressee field associated with the e-mail response.

Abstract: A method for managing an e-mail response based on the e-mail domains of the recipients is provided. The method receives a first e-mail sent to a plurality of e-mail addresses that includes e-mails with different domain names, provides a list of different domain names associated with a plurality of e-mail addresses and an e-mail address of a sender of the first e-mail, generates, based on a selection of one or more of the different domain names, a distribution list including one or more e-mail addresses limited to e-mail addresses having a selected domain name, and providing the distribution list in an addressee field associated with the e-mail response.

Abstract: A method for managing an e-mail response based on the e-mail domains of the recipients is provided. The method receives a first e-mail sent to a plurality of e-mail addresses that includes e-mails with different domain names, provides a list of different domain names associated with a plurality of e-mail addresses and an e-mail address of a sender of the first e-mail, generates, based on a selection of one or more of the different domain names, a distribution list including one or more e-mail addresses limited to e-mail addresses having a selected domain name, and providing the distribution list in an addressee field associated with the e-mail response.

Abstract: A method for managing an e-mail response based on the e-mail domains of the recipients is provided. The method receives a first e-mail sent to a plurality of e-mail addresses that includes e-mails with different domain names, provides a list of different domain names associated with a plurality of e-mail addresses and an e-mail address of a sender of the first e-mail, generates, based on a selection of one or more of the different domain names, a distribution list including one or more e-mail addresses limited to e-mail addresses having a selected domain name, and providing the distribution list in an addressee field associated with the e-mail response.

Abstract: Techniques for medical coding include applying a natural language understanding (NLU) engine to a free-form text documenting a clinical patient encounter, to derive a first set of one or more medical billing codes for the clinical patient encounter and a link between each code in the first set and a corresponding portion of the free-form text. The first set of codes may be compared to a second set of one or more medical billing codes approved by one or more human users for the patient encounter, to identify at least one code in the first set that overlaps with at least one code in the second set. The code in the second set approved by the one or more human users may be retained instead of the overlapping code in the first set derived by the NLU engine.