Abstract: A method including: receiving a user report dataset indicating fraudulent activity corresponding to a phone number; responsive to receiving the user report dataset, identifying a record in a database corresponding to the phone number; and tagging the record to identify the phone number as being associated with fraudulent activity.

Abstract: A content moderation system analyzes speech, or characteristics thereof, and determines a toxicity score representing the likelihood that a given clip of speech is toxic. A user interface displays a timeline with various instances of toxicity by one or more users for a give session. The user interface is optimized for moderation interaction, and shows how the conversation containing toxicity evolves over the time domain of a conversation.

Abstract: A method including: receiving a user report dataset indicating fraudulent activity corresponding to a phone number; responsive to receiving the user report dataset, identifying a record in a database corresponding to the phone number; and tagging the record to identify the phone number as being associated with fraudulent activity.

Abstract: A method including: receiving one or more datasets indicating call activity corresponding to a phone number; analyzing the one or more datasets to identify unusual call activity; and generating a fraud prediction, based at least in part on the identified unusual call activity, that the phone number will be used for fraud.

Abstract: Described are systems and methods for natively generating a first protocol, including receiving, via a user device, a first transmission and first transmission data, wherein the first transmission is at least one of a call, a voicemail, a text message, an audio message, or a video message, determining, via a first trained machine learning model, the first protocol based on the first transmission and the first transmission data, the first trained machine learning model having been trained to determine one or more protocols using training transmissions and training transmission data, generating, via the first trained machine learning model, a first responsive output based on the first protocol, and transmitting, via the user device, the first responsive output to a third-party device.

Abstract: An Internet of Things device registry display that includes a user input processing circuit structured to interpret one or more user input command values, an Internet of Things Universal Identification (IoT UID) identification circuit structured to determine one or more IoT UIDs, based at least in part on the one or more user input command values, a device lookup circuit structured to: generate a query that includes the one or more IoT UIDs, and retrieve device property data corresponding to the one or more IoT UIDs, a query provisioning circuit structured to transmit the query to an IoT device registrar server, a device property processing circuit structured to interpret the device property data generated by the IoT device registrar server in response to the query, and a display circuit structured to display the device property data with the corresponding one or more IoT UIDs.

Abstract: This disclosure describes a mounting platform comprising a retainer plate opening that includes a first opening profile at a top platform surface of the mounting platform and a second opening profile at a bottom platform surface of the mounting platform. the top platform surface first receives a retainer plate when nested within the mounting platform, and the bottom platform surface abuts the retainer plate when the retainer plate is nested within the mounting platform. The first opening profile matches a planform profile of the retainer plate and is etched into the top platform surface through to the bottom platform surface, and the second opening profile is etched from midway between the top platform surface and the bottom platform surface through to the bottom platform surface. The second opening profile corresponding to a rotational offset of the first opening profile by a predetermined angle.

Abstract: A toxicity moderation system has an input configured to receive speech from a speaker. The system includes a multi-stage toxicity machine learning system having a first stage and a second stage. The first stage is trained to analyze the received speech to determine whether a toxicity level of the speech meets a toxicity threshold. The first stage is also configured to filter-through, to the second stage, speech that meets the toxicity threshold, and is further configured to filter-out speech that does not meet the toxicity threshold.

Abstract: A toxicity moderation system has an input configured to receive speech from a speaker. The system includes a multi-stage toxicity machine learning system having a first stage and a second stage. The first stage is trained to analyze the received speech to determine whether a toxicity level of the speech meets a toxicity threshold. The first stage is also configured to filter-through, to the second stage, speech that meets the toxicity threshold, and is further configured to filter-out speech that does not meet the toxicity threshold.

Abstract: A method of building a new voice having a new timbre using a timbre vector space includes receiving timbre data filtered using a temporal receptive field. The timbre data is mapped in the timbre vector space. The timbre data is related to a plurality of different voices. Each of the plurality of different voices has respective timbre data in the timbre vector space. The method builds the new timbre using the timbre data of the plurality of different voices using a machine learning system.

Abstract: A method of building a new voice having a new timbre using a timbre vector space includes receiving timbre data filtered using a temporal receptive field. The timbre data is mapped in the timbre vector space. The timbre data is related to a plurality of different voices. Each of the plurality of different voices has respective timbre data in the timbre vector space. The method builds the new timbre using the timbre data of the plurality of different voices using a machine learning system.

Abstract: A method for online voice content moderation provides a multi-stage voice content analysis system. The system includes a pre-moderator stage having a toxicity scorer configured to provide a toxicity score for a given toxic speech content from a user. The toxicity score is a function of a platform content policy. The method generates a toxicity score for the given toxic speech content. The toxic speech content is provided to a moderator as a function of the toxicity score.

Abstract: A content moderation system analyzes speech, or characteristics thereof, and determines a toxicity score representing the likelihood that a given clip of speech is toxic. A user interface displays a timeline with various instances of toxicity by one or more users for a give session. The user interface is optimized for moderation interaction, and shows how the conversation containing toxicity evolves over the time domain of a conversation.

Abstract: Illustrative embodiments employ trained artificial intelligence to provide real-time (e.g., zero introduced latency), or near-real-time (e.g., less than 500 ms of introduced latency), moderation of a verbal communication, without the need for human moderators. By using predictive technology with pre-defined knowledge of undesirable content (e.g., speech to be redacted from a verbal communication), undesirable content of a verbal communication (e.g., human speech or text-to-speech communication) may be censored, as the verbal communication is created. Prediction of undesirable content may be based on context of the initial audio communication (e.g., words preceding the offensive language) and/or the phonetic content of the verbal communication preceding the undesirable content, and/or the phonetic content of the undesirable content itself (e.g., the first sounds of offensive language).

Abstract: Devices associated with on-body analyte sensor units are disclosed. These devices include any of packaging and/or loading systems, applicators and elements of the on-body sensor units themselves. Also, various approaches to connecting electrochemical analyte sensors to and/or within associated on-body analyte sensor units are disclosed. The connector approaches variously involve the use of unique sensor and ancillary element arrangements to facilitate assembly of separate electronics assemblies and sensor elements that are kept apart until the end user brings them together.

Abstract: This disclosure describes a mounting platform comprising a retainer plate opening that includes a first opening profile at a top platform surface of the mounting platform and a second opening profile at a bottom platform surface of the mounting platform. the top platform surface first receives a retainer plate when nested within the mounting platform, and the bottom platform surface abuts the retainer plate when the retainer plate is nested within the mounting platform. The first opening profile matches a planform profile of the retainer plate and is etched into the top platform surface through to the bottom platform surface, and the second opening profile is etched from midway between the top platform surface and the bottom platform surface through to the bottom platform surface. The second opening profile corresponding to a rotational offset of the first opening profile by a predetermined angle.

Abstract: A method including: receiving one or more datasets indicating call activity corresponding to a phone number; analyzing the one or more datasets to identify unusual call activity; and generating a fraud prediction, based at least in part on the identified unusual call activity, that the phone number will be used for fraud.

Abstract: A method including: receiving a user report dataset indicating fraudulent activity corresponding to a phone number; responsive to receiving the user report dataset, identifying a record in a database corresponding to the phone number; and tagging the record to identify the phone number as being associated with fraudulent activity.

Abstract: A method of manufacturing three-dimensional (3D) objects is provided. The method includes generating a plan for printing a plurality of 3D objects in a 3D printing medium at least in part by identifying an unprinted area of the 3D printing medium for insertion of a cooling device and determining where at least some of the plurality of 3D objects are to be printed in the 3D printing medium such that none of the at least some of the plurality of 3D objects, when printed, intersect the identified unprinted area for the insertion of the cooling device. The method further includes printing, using a 3D printer, the at least some of the plurality of 3D objects in accordance with the plan and, after the printing, inserting the cooling device into the unprinted area of the 3D printing medium and cooling the 3D printing medium using the cooling device.