Abstract: This disclosure relates to methods, non-transitory computer readable media, and systems that asynchronously train a machine learning model across client devices that implement local versions of the model while preserving client data privacy. To train the model across devices, in some embodiments, the disclosed systems send global parameters for a global machine learning model from a server device to client devices. A subset of the client devices uses local machine learning models corresponding to the global model and client training data to modify the global parameters. Based on those modifications, the subset of client devices sends modified parameter indicators to the server device for the server device to use in adjusting the global parameters. By utilizing the modified parameter indicators (and not client training data), in certain implementations, the disclosed systems accurately train a machine learning model without exposing training data from the client device.

Abstract: A plurality of personalized news feeds are generated from input feeds including digital content items based on a dynamic taxonomy data structure. Entities are extracted from the input feeds and relationship strengths are obtained for the extracted entities and the digital content items. The dynamic taxonomy data structure is updated with the extracted entities and entries for the digital content news items are included at the corresponding branches based on the relationship strengths. Attributes are obtained for the entities and those entities corresponding to the trending topics are identified. Personalized news feeds are generated including the digital content items listed under the entities. Digital content items are added or removed from the digital content feeds based on one or more entity attributes.

Abstract: Aspects of the present disclosure provide systems, methods, and computer-readable storage media that support automated account maintenance and fraud mitigation for secure accounts such as vendor master accounts or client master accounts. To illustrate, a system receives a request from a user to update an account. The system extracts request data from the request, for example using natural language processing and optical character recognition. The system performs validation operation(s) (e.g., entry validation, location validation, domain validation, etc.), in some implementations using one or more machine learning models. Upon successful validation, if the user is an authorized contact for the account, the system authenticates the request (e.g., via request of an authorization code) and updates the account.

Abstract: Examples for the baggage weight prediction system are provided. The system may create a baggage prediction model in response to a carrier baggage weight prediction requirement requesting a total baggage weight to be carried in a future transportation operation by a carrier. The baggage prediction model may be used to determine a predicted baggage to be carried by a plurality of future passengers associated with a future transportation operation. The system may determine a predicted weight for the predicted baggage. The system may sort the predicted baggage into checked baggage and a carry-on baggage. The system may determine a carry-on baggage weight associated with the carry-on baggage based on the baggage prediction model. The system may determine a baggage weight ratio associated with the predicted baggage. The system may generate a baggage prediction result for performing a baggage management action.

Abstract: Systems and techniques are described herein for updating a machine learning model on edge servers. Local parameters of the machine learning model are updated at a plurality of edge servers using fresh data on the edge servers, rather than waiting for the data to reach a global server to update the machine learning model. Hence, latency is significantly reduced, making the systems and techniques described herein suitable for real-time services that support streaming data. Moreover, by updating global parameters of the machine learning model at a global server in a deterministic manner based on parameter updates from the edge servers, rather than by including randomization steps, global parameters of the converge quickly to their optimal values. The global parameters are sent from the global server to the plurality of edge servers at each iteration, thereby synchronizing the machine learning model on the edge servers.

Abstract: A system for providing data quality management may include a processor configured to execute instructions to: extract a plurality of first data elements from a data source; generate a data profile based on the first data elements; automatically create a first set of rules based on the first data elements and the data profile, the first set of rules assessing data quality according to a threshold; generate a second set of rules based on the first data elements and the first set of rules; extract a plurality of second data elements; assess the second data elements based on a comparison of the second data elements to the second set of rules; detect defects based on the comparison; analyze data quality according to the detected defects; and transmit signals representing the data quality analysis to a client device for display to a user.

Abstract: In some embodiments, a computing system determines, based on stored user information retrieved from a mobile user device and associated with a particular user, a location-specific affinity of the particular user for a product at a particular geographical location. The location-specific affinity indicates an interest of the particular user in the product that increases when the particular user is positioned at the particular geographical location. The computing system designs a geo-fence targeted to the particular user based on the location-specific affinity, where messages are transmitted to the mobile user device if the particular user is within a boundary of the geo-fence. The geo-fence defines a geographical area that includes the particular geographical location and that is associated with a provider of the product. The computing system causes a telecommunication server to transmit the message to the user device when the user device is positioned within the designed geo-fence.

Abstract: A system for providing data quality management may include a processor configured to execute instructions to: extract a plurality of first data elements from a data source; generate a data profile based on the first data elements; automatically create a first set of rules based on the first data elements and the data profile, the first set of rules assessing data quality according to a threshold; generate a second set of rules based on the first data elements and the first set of rules; extract a plurality of second data elements; assess the second data elements based on a comparison of the second data elements to the second set of rules; detect defects based on the comparison; analyze data quality according to the detected defects; and transmit signals representing the data quality analysis to a client device for display to a user.

Abstract: Embodiments of the present disclosure provide systems and methods for recognizing a masked face. According to the present disclosure, the disclosed systems and methods include features that provide augmentation of existing face recognition databases, real-time mask detection, and real-time masked face recognition. In embodiments, masked face recognition includes a multi-layered approach, which includes finding matching simulated masked faces in the database that match the masked face being analyzed, comparing the unmasked portion of the masked face to stored unmasked faces in a database to identify any matches, and executing face restoration algorithms in which the masked portion is reconstructed to generate an unmasked representation which may then be matched against unmasked faces in the database.

Abstract: In implementations of a recommendation system based on individualized privacy settings, a computing device maintains user profiles of information and recommendations associated with users of the recommendation system. The computing device includes a recommendation module that is implemented to receive a privacy level selection for a type of items corresponding to a user profile in the system. The recommendation module can determine a privacy setting for a user associated with the user profile, where the privacy setting is individualized for the user in context of the type of items with an algorithmic noise function utilized to obfuscate a proportional level of the information associated with the user and the type of items based on the received privacy level selection. The recommendation module can also generate recommendations of relevant items for the user based on the determined privacy setting as individualized for the user in context of the type of items.

Abstract: Systems and techniques are described herein for updating a machine learning model on edge servers. Local parameters of the machine learning model are updated at a plurality of edge servers using fresh data on the edge servers, rather than waiting for the data to reach a global server to update the machine learning model. Hence, latency is significantly reduced, making the systems and techniques described herein suitable for real-time services that support streaming data. Moreover, by updating global parameters of the machine learning model at a global server in a deterministic manner based on parameter updates from the edge servers, rather than by including randomization steps, global parameters of the converge quickly to their optimal values. The global parameters are sent from the global server to the plurality of edge servers at each iteration, thereby synchronizing the machine learning model on the edge servers.

Abstract: In implementations of a recommendation system based on individualized privacy settings, a computing device maintains user profiles of information and recommendations associated with users of the recommendation system. The computing device includes a recommendation module that is implemented to receive a privacy level selection for a type of items corresponding to a user profile in the system. The recommendation module can determine a privacy setting for a user associated with the user profile, where the privacy setting is individualized for the user in context of the type of items with an algorithmic noise function utilized to obfuscate a proportional level of the information associated with the user and the type of items based on the received privacy level selection. The recommendation module can also generate recommendations of relevant items for the user based on the determined privacy setting as individualized for the user in context of the type of items.

Abstract: This disclosure relates to methods, non-transitory computer readable media, and systems that asynchronously train a machine learning model across client devices that implement local versions of the model while preserving client data privacy. To train the model across devices, in some embodiments, the disclosed systems send global parameters for a global machine learning model from a server device to client devices. A subset of the client devices uses local machine learning models corresponding to the global model and client training data to modify the global parameters. Based on those modifications, the subset of client devices sends modified parameter indicators to the server device for the server device to use in adjusting the global parameters. By utilizing the modified parameter indicators (and not client training data), in certain implementations, the disclosed systems accurately train a machine learning model without exposing training data from the client device.

Abstract: A system for providing data quality management may include a processor configured to execute instructions to: extract a plurality of first data elements from a data source; generate a data profile based on the first data elements; automatically create a first set of rules based on the first data elements and the data profile, the first set of rules assessing data quality according to a threshold; generate a second set of rules based on the first data elements and the first set of rules; extract a plurality of second data elements; assess the second data elements based on a comparison of the second data elements to the second set of rules; detect defects based on the comparison; analyze data quality according to the detected defects; and transmit signals representing the data quality analysis to a client device for display to a user.

Abstract: A system for providing data quality management may include a processor configured to execute instructions to: extract a plurality of first data elements from a data source; generate a data profile based on the first data elements; automatically create a first set of rules based on the first data elements and the data profile, the first set of rules assessing data quality according to a threshold; generate a second set of rules based on the first data elements and the first set of rules; extract a plurality of second data elements; assess the second data elements based on a comparison of the second data elements to the second set of rules; detect defects based on the comparison; analyze data quality according to the detected defects; and transmit signals representing the data quality analysis to a client device for display to a user.

Abstract: Rules for triggering geo-notifications, such as push notifications to a mobile computing device based on its location, are automatically generated based on a user's location, dwell time, and browsing activity. In some embodiments, a geo-fence communication system determines an average dwell time for a group of users in a user segment. The average dwell time indicates an average time for each user to respond to a geo-notification for a product, within a geo-fence. The geo-fence communication system generates a rule for the user segment/product/geo-fence tuple based on the average dwell time. In some cases, semantic similarities between geo-fence locations are determined, and a rule for a geo-fence is generated based on average dwell times for other geo-fences in similar locations.

Abstract: In some embodiments, a computing system determines, based on stored user information retrieved from a mobile user device and associated with a particular user, a location-specific affinity of the particular user for a product at a particular geographical location. The location-specific affinity indicates an interest of the particular user in the product that increases when the particular user is positioned at the particular geographical location. The computing system designs a geo-fence targeted to the particular user based on the location-specific affinity, where messages are transmitted to the mobile user device if the particular user is within a boundary of the geo-fence. The geo-fence defines a geographical area that includes the particular geographical location and that is associated with a provider of the product. The computing system causes a telecommunication server to transmit the message to the user device when the user device is positioned within the designed geo-fence.

Abstract: A system for providing data quality management may include a processor configured to execute instructions to: extract a plurality of first data elements from a data source; generate a data profile based on the first data elements; automatically create a first set of rules based on the first data elements and the data profile, the first set of rules assessing data quality according to a threshold; generate a second set of rules based on the first data elements and the first set of rules; extract a plurality of second data elements; assess the second data elements based on a comparison of the second data elements to the second set of rules; detect defects based on the comparison; analyze data quality according to the detected defects; and transmit signals representing the data quality analysis to a client device for display to a user.

Abstract: Methods and systems for performing capture threshold tests are described. During an initialization procedure a capture detection interval and capture detection threshold are determined based on peak values of cardiac signals sensed following the supracapture threshold initialization pulses. Following initialization, a plurality of pacing pulses to the atrium are delivered and the peak values of the cardiac signals sensed following each of the plurality of pacing pulses are determined. The peak values are compared to the pacing artifact threshold and the capture detection threshold. A timing of each of the peak values is compared to the capture detection interval. For each pacing pulse, discrimination between a captured response, a noncaptured response, and a fusion response is based on the peak value and timing comparisons.

Abstract: Methods and systems for performing capture threshold tests are described. During an initialization procedure a capture detection interval and capture detection threshold are determined based on peak values of cardiac signals sensed following the supracapture threshold initialization pulses. Following initialization, a plurality of pacing pulses to the atrium are delivered and the peak values of the cardiac signals sensed following each of the plurality of pacing pulses are determined. The peak values are compared to the pacing artifact threshold and the capture detection threshold. A timing of each of the peak values is compared to the capture detection interval. For each pacing pulse, discrimination between a captured response, a noncaptured response, and a fusion response is based on the peak value and timing comparisons.