Patents.

Systems and methods for prioritizing data for autonomous mobility on demand

A system and method that enables autonomous mobility implementations to prioritize, offload, and process data in an efficient manner includes generating a prioritization model, training the prioritization model on a data corpus to generate a prioritization schedule, deploying the prioritization schedule to one or more autonomous vehicles, offloading data at a local content absorption node, processing data at the local content absorption node, and optionally transmitting data results from the processed data.

Rapid deployment of dialogue system

End-to-end speech recognition

Medical scan comparison system

Continuation of the medical scan comparison system: similar-scan data is generated for a received medical scan by comparing it against a medical scan database over a network.

Providing reminders based on voice recognition

Methods, systems, and computer program products for providing reminders to users based on voice recognition are provided. Aspects include monitoring, via a microphone of a user device, a communication of a user. Aspects also include determining an identity of a person communicating with the user based on a voice signature of the person. Aspects further include providing a notification to the user based on a determination that the user has a reminder event for the person.

Using multiple natural language classifiers to associate a generic query with a structured question type

A natural language query (NLQ) is translated to a structured data query (e.g., a SQL statement) by extracting entities from the NLQ and replacing them with generic variables to form a generic query. The generic query is associated with a structured question type.

Systems and methods for searching property listings

Medical scan image analysis system

Continuation of the medical scan image analysis system: medical scans representing a three-dimensional anatomical region are processed by a trained computer vision model to produce abnormality and classification data for the scan.

Transaction execution commitment without updating of data row transaction status

Real-time search and validation of phrases using linguistic phrase components

A method and system is disclosed for evaluating a chat message sent between users of an online environment. The method may include receiving a chat message and parsing the message into words. The method determines the acceptability of the message by matching the message to a plurality of linguistic phrase components.

Metal/air battery with gas separations unit and load-leveling oxygen storage system

Method and system for characterizing and/or treating poor sleep behavior

Representing enterprise data in a knowledge graph

System maintenance using unified cognitive root cause analysis for multiple domains

A computer-implemented method, system, and non-transitory computer program product for maintaining a system. A domain of the system is identified. Problem information identifying a problem in the system is captured. Key performance indicators are obtained from a historical model database for the identified domain. An unsupervised model is applied to the key performance indicators to identify historical solutions to historical problems that are similar to the problem in the system. A linear complexity model is used to identify potential solutions for the problem as an historical solution for each historical problem that has the lowest combination of time-cost complexity, resource-cost complexity, and recurrence frequency for the historical problem. A real-time objective function is used to select a solution to the problem from the potential solutions. A maintenance operation to be performed on the system to implement the solution and fix the problem is identified.

Systems and methods for biological metrics measurement

A wearable member may include a plurality of energy transmitters arranged on a surface of the wearable member, each configured to project energy into tissue of a user, and a plurality of energy receivers each of which generates a signal based on a received portion of the energy reflected by the tissue, where the transmitters and receivers are multi-dimensionally arranged on the wearable member.

Template-Based Key-Value Extraction for Inferring OCR Key Values Within Form Images

The system has a form analysis module that receives an image of a form into which values have been filled for the possible fields of information on the form, such as first name, address, age, and the like. By using a library of form templates, a form analysis module allows both flexibility of form processing and simplicity for the user. That is, the techniques used by the form analysis module allow the processing of any form image for which the library has a form template example. The form image need not precisely match any form template, but rather may be scaled or shifted relative to a corresponding template. Additionally, the user need only provide the form image itself, without providing any additional exemplars, metadata for training, or the like.

Magnetic field sensor based on topological insulator and insulating coupler materials

Automated tasking and accuracy assessment systems and methods for assigning and assessing individuals and tasks

Disclosed is a tasking system to assign individuals to tasks. The tasking system targets a user for the task based information in a user profile such as demographics, background and reputation of the user to perform a task. The tasking system predicts if a user will do a given task well based on a user's background, user's skill, and applied predictive algorithms. The tasking system manages the workflow of the task, assesses the probability of the user's answer being accurate, and continuously optimizes assignment and assessment of the task to improve data quality.

Fast entity linking in noisy text environments

A system for disambiguation of noisy text includes an interface and processor. The interface is configured to receive a set of words. The processor is configured to determine a token from the set of words, wherein the token includes a subset of the set of words; determine candidates for the token; determine a ranking for the candidates based at least in part on a semantic similarity between the token and each of the candidates; determine whether to select a top ranked candidate or to abstain; and in response to a select determination to select the top ranked candidate, indicate the top ranked candidate is selected.

Indexing structured data with security information

A system for indexing and searching includes an input interface and a processor. The interface is to receive a request to search for a term. The processor is to determine a search response based at least in part on a security associated with an index field and the term.

Differentially private machine learning using a random forest classifier

A request from a client is received to generate a differentially private random forest classifier trained using a set of restricted data. The differentially private random forest classifier is generated in response to the request.

Systems, methods, and apparatuses for implementing machine learning model training and deployment with a rollback mechanism

Systems, methods, and apparatuses for implementing machine learning model training and deployment with a rollback mechanism within a computing environment.

Natural language content generator

Constrained optimization for provider groups

Redirecting blocked media content

A method includes determining, using a processor system, that a portion of media content is objectionable to an audience based at least on a comparison between an identified aspect of the portion of media content and a first set of preferences associated with the audience. The first set of ...

Decentralized discovery across different networks

Dynamic discovery of peers or services in different networks, where few or no servers may be required for the discovering process, is provided. Broadcasting used for the peer or service discovery may serve to reduce centralized bottlenecks and may serve to increase scalability.

Annealed seed layer for magnetic random access memory

Drone-based smoke detector

One embodiment provides a method comprising receiving a request to release a utility holder detachably mounted to a surface mount. The utility holder maintains a utility payload. A set of rotatable holding brackets is coupled to the surface mount in a pivotable fashion to engage the holding brackets with the utility holder in order to mount the utility holder to the surface mount. The method further comprises, in response to receiving the request, powering on a drone attached to the utility holder, and releasing the utility holder from the surface mount by actuating rotation of the holding brackets to disengage the holding brackets from the utility holder, enabling the drone to transport the utility holder from the surface mount to a desired location.

Secure storage decryption system

A system for secure retrieval of stored data includes an encrypted key database and a processor. The encrypted key database is configured to store an encrypted tenant service key and an encrypted tenant master key. The processor is configured to request decryption of the encrypted tenant master key into an unencrypted tenant master key. The decryption of the encrypted master key is approved by a key release system. The processor is further configured to decrypt the encrypted tenant service key using the unencrypted tenant master key into an unencrypted tenant service key and authorize a response to a request using the unencrypted tenant service key.

Secondary battery management

Media selection and display based on conversation topics

Technical solutions are described for selecting and retrieving, by a media retrieval system, media items for displaying. An example method for selecting and retrieving the media items includes monitoring a conversation of a user via a user device, and extracting a conversation topic from the conversation. The method further includes determining that a metadata database of a media storage associated with the user includes the conversation topic. The method further includes adding, in response, to a topic match database, from the media storage, an identity of a media item matching with the conversation topic, and adding, to a list of media items to be played back by a media display device, the topic match database. Further yet, the method includes playing back, by the media display device, the media item.

Enhanced managed runtime environments that support deterministic record and replay

Techniques for providing visual translation cards including contextually relevant definitions and examples

Computer-implemented techniques can include receiving a selected word in a source language, obtaining one or more parts of speech for the selected word, and for each of the one or more parts-of-speech, obtaining candidate translations of the selected word to a different target language, each candidate translation corresponding to a particular semantic meaning of the selected word. The techniques can include for each semantic meaning of the selected word: obtaining an image corresponding to the semantic meaning of the selected word, and compiling translation information including (i) the semantic meaning, (ii) a corresponding part-of-speech, (iii) the image, and (iv) at least one corresponding candidate translation. The techniques can also include outputting the translation information.

Method and apparatus for combining an augmented reality object in a real-world image

A method including receiving a first depth image associated with a first frame at a first time of an augmented reality (AR) application, the first depth image representing at least a first portion of a real-world space; storing the first depth image; receiving a second depth image associated with a second frame at a second time; and combining an augmented reality object into the real-world image using the stored depth information, so that occlusion between virtual content and the real world is rendered correctly.

Dynamically changing message classification and priority based on IOT device publication

Approaches for automatically and dynamically changing message classification and priority based on Internet-Of-Things (IOT) device publication are provided. A computer-implemented method includes: receiving, by a computer device, a device status message from an Internet-of-Things (IOT) device; receiving, by the computer device, a message from a message server; assigning, by the computer device, a priority to the message based on the device status message from the IOT device; and communicating, by the computer device, the assigned priority of the message to the message server.

Systems and methods for principled bias reduction in production speech models

Described herein are systems and methods to identify and address sources of bias in an end-to-end speech model. In one or more embodiments, the end-to-end model may be a recurrent neural network with two 2D-convolutional input layers, followed by multiple bidirectional recurrent layers and one fully connected layer before a softmax layer. In one or more embodiments, the network is trained end-to-end using the CTC loss function to directly predict sequences of characters from log spectrograms of audio. With optimized recurrent layers and training together with alignment information, some unwanted bias induced by using purely forward only recurrences may be removed in a deployed model.

Bot-based data collection for detecting phone solicitations

One embodiment provides a method comprising answering one or more incoming phone calls received at one or more pre-specified phone numbers utilizing a bot. The bot is configured to engage in a conversation with a caller initiating an incoming phone call utilizing a voice recording that impersonates a human being. The method further comprises recording each conversation the bot engages in, and classifying each recorded conversation as one of poison data or truthful training data based on content of the recorded conversation and one or more learned detection models for detecting poisoned data.

Method and system for improving care determination

Method for providing therapy to an individual

Cognitive traffic light pattern analysis and notification

Methods, systems and computer program products providing traffic light status notifications to drivers are provided. Aspects include determining that a first vehicle, operated by the driver, is approaching a traffic light and receiving, by the first vehicle, traffic light status data from one or ...

Multi-tenancy management within a distributed database

Embodiments are provided for enabling dynamic reallocation of resources in a multi-tenant distributed database.

Computer storage deduplication

A data center comprising plural computer hosts and a storage system external to said hosts is disclosed. The storage system includes storage blocks for storing tangibly encoded data blocks. Each of said hosts includes a deduplicating file system for identifying and merging identical data blocks

Systems and methods for non-invasive blood pressure measurement

Systems and methods for non-invasive blood pressure measurement are disclosed. In some embodiments, a system comprises a wearable member configured to generate first and second signals (e.g., PPG signals), and a blood pressure calculation system that calculates an arterial blood pressure value based on sets of feature vectors and an empirical model.

Automatic detection and alert of an emergency from social media communication

A computer monitors a plurality of social media communications. The computer identifies a first social media communication of the plurality of social media communications. The computer evaluates the first social media communication for a first communication emergency level. The computer identifies ...

Cryogenic patterning of magnetic tunnel junctions

Formation and manipulation of test data in a database system

Dynamically detecting abnormalities in otherwise legitimate emails containing uniform resource locators (URLs)

Dynamically changing message classification and priority based on IOT device publication

Approaches for automatically and dynamically changing message classification and priority based on Internet-Of-Things (IOT) device publication are provided. A system includes: a CPU, a computer readable memory, and a computer readable storage medium; program instructions to receive a device status message from an Internet-of-Things (IOT) device; program instructions to determine a categorization of the device status message; program instructions to determine a classification of an email message; program instructions to compare the categorization of the device status message to the classification of the email message; and program instructions to assign a priority to the email message based on the comparing. The program instructions are stored on the computer readable storage medium for execution by the CPU via the computer readable memory.

System and method for performing caller identity verification using multi-step voice analysis

Caller identity verification can be improved by employing a multi-step verification that leverages speech features that are obtained from multiple interactions with a caller. An enrollment is performed in which customer speech features and customer information are collected. When a caller calls into the call center, an attempt is made to verify the caller's identity by requesting the caller to speak a predefined phrase, extracting speech features from the spoken phrase, and comparing the phrase. If the match cannot be made with a high enough degree of confidence, the customer is asked to speak any phrase that is not predefined.

Server failure predictive model

A failure prediction subsystem may obtain metrics information from a set of servers, the metrics information including measurements of the operation of the set of servers. The failure prediction subsystem may then determine a mean time between failures for at least one server of the set of servers.