Patents.

Privacy-preserving system for machine-learning training data

Automated segmentation utilizing fully convolutional networks

Systems and methods for automated segmentation of anatomical structures (e.g., heart). Convolutional neural networks (CNNs) may be employed to autonomously segment parts of an anatomical structure represented by image data, such as 3D MRI data. The CNN utilizes two paths, a contracting path and an expanding path. In at least some implementations, the expanding path includes fewer convolution operations than the contracting path. Systems and methods also autonomously calculate an image intensity threshold that differentiates blood from papillary and trabeculae muscles in the interior of an endocardium contour, and autonomously apply the image intensity threshold to define a contour or mask that describes the boundary of the papillary and trabeculae muscles. Systems and methods also calculate contours or masks delineating the endocardium and epicardium using the trained CNN model, and anatomically localize pathologies or functional characteristics of the myocardial muscle using the calculated contours or masks.

Forming self-aligned contacts on pillar structures

Machine translation optimization for queries executed in a different language

A user query for items is received in a first language and translated from the first language to a second language. A result set in the second language that meets the query is obtained and is translated into the first language for presentation to the user. User feedback is used to build an ontology for optimizing the translation from the first language to the second language based on query context and the feedback.

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.

Template-driven multi-tenant workflow processing

Methods, systems, and devices for multi-tenant workflow processing are described. In some cases, a cloud platform may utilize a set of pre-defined batch processes (e.g., workflow templates) and tenant-specific configurations for instantiating and executing tenant-specific batch processes for each tenant.

Differentially Private Processing and Database Storage

A hardware database privacy device is communicatively coupled to a private database system. The hardware database privacy device receives a request from a client device to perform a query of the private database system and identifies a level of differential privacy corresponding to the request.

Analyzing writing using pressure sensing touchscreens

The present invention provides a computer implemented method, a system, and a computer program product for verifying a writing of a user. In an exemplary embodiment, the present invention includes in response to receiving a writing on a pressure sensing touchpad logically coupled a computer system ...

Methods and system for fast, adaptive correction of misspells

Embodiments are directed to a spellcheck module for an enterprise search engine. The spellcheck module includes a candidate suggestion generation module that generates a number of candidate words that may be the correction of the misspelled word.

Load balancing deterministically-subsetted processing resources using fractional loads

Systems and methods for load balancing between a set of servers, where subsets of servers are assigned to respective clients via deterministic subsetting and fractional loads are used rather than whole-server assignment.

Contextual chat message generation in online environments

A computer-implemented method for facilitating user communication in an online environment, the method comprising: associating a first user with a group profile, wherein the group profile is derived from monitoring interaction behavior of a plurality of users interacting with the online environment.

Content categorization

Control method for autonomous vehicles

Control systems and methods for an autonomous vehicle. A control method includes obtaining data indicative of a motion plan for the autonomous vehicle, upsampling the data indicative of the motion plan to determine a desired vehicle state, obtaining data indicative of a current vehicle state, and determining a control command for the autonomous vehicle based at least in part on the desired vehicle state and the current vehicle state.

Pointer Sentinel Mixture Architecture

The technology disclosed provides a so-called “pointer sentinel mixture architecture” for neural network sequence models that has the ability to either reproduce a token from a recent context or produce a token from a predefined vocabulary. In one implementation, a pointer sentinel-LSTM architecture achieves state of the art language modeling performance of 70.9 perplexity on the Penn Treebank dataset, while using far fewer parameters than a standard softmax LSTM.

Managing incrementally applied system updates

According to one embodiment of the present invention, a computer system updates a system including a plurality of sever instances, and includes at least one processor. The computer system determines a level of configuration for each operating server instance. One or more sets of operational features are added to the system based on a comparison between the determined levels of configuration of the operating server instances and minimum levels of configuration associated with the one or more sets of operational features. Server operations are performed and one or more corresponding sets of operational features are applied to the server operations in response to the addition of those corresponding sets of operational features to the system. Embodiments of the present invention further include a method and computer program product for updating a system including a plurality of server instances in substantially the same manner described above.

Unsupervised template extraction

An approach is provided that improves a question answering (QA) computer system by automatically generating relationship templates. Event patterns are extracted from data in a corpus utilized by the QA computer system.

Structured Cluster Execution for Data Streams

A system for executing a streaming query includes an interface and a processor. The interface is configured to receive a logical query plan. The processor is configured to determine a physical query plan based at least in part on the logical query plan. The physical query plan comprises an ordered set of operators. Each operator of the ordered set of operators comprises an operator input mode and an operator output mode. The processor is further configured to execute the physical query plan using the operator input mode and the operator output mode for each operator of the query.

Lung screening assessment system

A lung screening assessment system is operable to receive a chest computed tomography (CT) scan that includes a plurality of cross sectional images. Nodule classification data is generated by a computer vision model trained to identify a nodule and determine an assessment score, and a lung screening report is generated for display.

Hierarchical information visualizer and editor

Inferred identity

Techniques for inferring the identity (e.g., member profile attributes) of members of an online social network service are described. According to various embodiments, a member profile attribute missing from a member profile page associated with a particular member of an online social network service is identified. Member profile data and behavioral log data associated with a plurality of members of the online social network service is then accessed. Thereafter, a prediction modeling process is performed, based on a prediction model and feature data including the member profile data and the behavioral log data, to generate a confidence score associated with the particular member and the missing member profile attribute, the confidence score indicating a likelihood that the missing member profile attribute corresponds to a candidate value.

Replication of content to one or more servers

An approach is provided to automatically replicate content to certain servers in a networking environment based on, amongst other metrics, location of third parties accessing information in a social networking environment. The approach includes obtaining content from a user within a networked environment and analyzing information of one or more third parties that have access to the networked environment and who have an association with the user. The approach further includes replicating the content to one or more servers within the networked environment based on the analyzed information of the one or more third parties.

Predictive analytics work lists for healthcare

A mechanism is provided in a data processing system for generating healthcare work item recommendations based on predictive analytics. An analytics engine performs analytics to discover patterns in patient records data and to generate one or more risk scores using one or more predictive models... A decision system generates a healthcare recommendation for a given patient based on the risk score, the predictive model used, and the contributing factors.

Automatic ontology generation

An ontology is automatically generated for a set of data from multiple data sources. A semantic network of known concepts serves as an ontology template for a target domain of knowledge with known concepts defined as base entity types. Logical groupings of data and associated technical metadata are read from the data sources. Data discovery techniques are applied to detect semantic and/or syntactic classification of data attributes in the logical groupings of data. For each of the logical groupings of data, an entity type with properties for the data attributes are generated and the generated entity type is added to the semantic network with classifications of the properties as derived from the applied data discovery techniques. Semantic meanings of the generated entity types are generated and associated with other entity types within the semantic network and the semantic network is output as a resultant ontology for the set of data.

Platform-agnostic predictive models based on database management system instructions

Platform-agnostic predictive models based on database management system instructions are described. A system identifies a representation of data transformations associated with a first predictive model that executes on a first computing platform. The system parses the representation of data transformations. The system generates database management system instructions that correspond to the parsed representation of data transformations. The system sends the database management system instructions to a second predictive model that executes on a second computing platform, thereby enabling the second predictive model to execute at least some of the database management system instructions to generate a prediction. The first computing platform and the second computing platform are different types of computing platforms.

Vehicle braking system and method

A system for vehicle braking includes: a pedal actuated valve, including a first vent outlet in fluid communication with a fluid sink, a first supply inlet in fluid communication with a fluid source, and a first control outlet; and an autonomous braking subsystem for retrofit control of a heavy vehicle's air brakes.

Forecasting requests based on context data for a network-based service

Systems and methods for managing assets in a geographical location

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for managing or tracking assets in a geographical area. One method includes receiving one or more first messages from a plurality of assets on one or more first channels of a plurality of channels. (abstract excerpt from Google Patents)

Typeahead using messages of a messaging platform

Entity classification and/or relationship identification

Wholesale/trade-in pricing system, method and computer program product therefor

Enhanced coercivity in MTJ devices by contact depth control

Secondary battery management system

Differentially private density plots

Techniques are described for responding to queries of a private database system. A request is received from a client device to perform a query of the private database system. A level of differential privacy corresponding to the request is identified comprising privacy parameters epsilon and delta.

Distributed message queue stream verification

A stream verification system for a distributed message queue system with metric collectors on each producer and consumer. A producer time stamp allows correlation of sent and received messages. Verification reports are organized by a message topic. A cumulative checksum allows detection of missing or corrupted messages. Verification messages are used to determine if a zero message report means no messages were sent, or rather that the messages weren't received.

Transaction management in distributed ledger systems

Zero-knowledge databases

Serverless Execution of Code Using Cluster Resources

A system for cluster resource allocation includes an interface and a processor. The interface is configured to receive a process and input data. The processor is configured to determine an estimate for resources required for the process to process the input data; determine existing available resources in a cluster for running the process; determine whether the existing available resources are sufficient for running the process; in the event it is determined that the existing available resources are not sufficient for running the process, indicate to add new resources; determine an allocated share of resources in the cluster for running the process; and cause execution of the process using the share of resources.

Techniques and architectures for managing disparate heterogeneous cloud-based resources

Techniques and architectures for data modeling and management. Data modeling services are provided to agents within multiple different operating environments of a computing environment having at least one database stored on one or more physical memory devices communicatively coupled with one or more hardware processors the one or physical memory devices. Building and versioning of data modeling projects is coordinated and data utilized for the data modeling projects with the one or more hardware processors.

Differentially private database queries involving rank statistics

A differentially private security system is communicatively coupled to a database. The differentially private security system receives a request from a client device to perform a query of the database and identifies a level of differential privacy corresponding to the request.

Systems and methods of multispectral blood measurement

An exemplary system comprises an energy transmitter, an energy receiver, and an analyzer. The energy transmitter may project energy at a first wavelength and a second wavelength into tissue of a user, the first wavelength and the second wavelength being associated with at least one nutrient of a set of nutrients in blood of the user. The energy receiver may generate a composite signal based on a fraction of the energy at the first wavelength and the second wavelength, the fraction of the energy being received through the tissue of the user.

Ranking network anomalies in an anomaly cluster

Applied essentia dunning

Filter chains for exploring large data sets

A multipath explorer may allow a user to quickly visualize an entire population of data hierarchically in a tree-like structure. For example, a user can select a first filter to be applied to a data set, and the multipath explorer can display data in the data set that satisfies the first filter requirements and data in the data set that does not satisfy the first filter requirements. A second filter can be applied to the data in the data set, and the multipath explorer can display data in the data set that satisfies the first and second filter requirements, data in the data set that satisfies the first filter requirements and not the second filter requirements, data in the data set that satisfies the second filter requirements and not the first filter requirements, and data in the data set that does not satisfy the first or second filter requirements.

Confidentiality management of e-mail users in redistributed e-mail messages

Embodiments of the present invention address deficiencies of the art in respect to instant messaging and provide a novel and non-obvious method, system and computer program product for managing e-mail user confidentiality. In one embodiment of the invention, a method for managing e-mail user confidentiality can be provided. The method can include transmitting an e-mail message for delivery to multiple e-mail users and corresponding e-mail addresses, identifying a privacy preference for a particular one of the e-mail users; and, concealing a display within the e-mail message of an e-mail address associated with the particular one of the e-mail users responsive to the privacy preference.

Computer-implemented system and method for facilitating interactions via automatic agent responses

A computer-implemented system and method for facilitating interactions via automatic agent responses is provided. A request for information for an agent is received from a user during an interaction with the agent. A list of candidate responses to the request is generated and one of the candidate responses is automatically selected when the agent fails to respond to the request within a predetermined time period. The selected response is provided to the user on behalf of the agent.

Systems and methods for intelligent peer-to-peer fundraising campaign management

An intelligent peer-to-peer fundraising campaign platform is provided for managing charitable and for profit campaigns. The platform includes capabilities for creating and managing campaigns by supporters, retrieving person data for supporters and leads for the campaign, relationship data and other attributes including affinity data, donation history data, potential and financial data and storing such data in the form of social graph. The campaign platform also helps supporters of a campaign to identify leads, send personalized communication to the leads for enlisting support to the campaign, determine donor outcomes with respect to each personalized communication sent to the lead; and updating or reinforcing a donor prediction model based on the donor outcome.

Access control system for enterprise cloud storage

Systems and corresponding computer-implemented methods for context-based rule evaluation in an electronic data storage system are described. A request to perform an operation with respect to a resource is received from a client device, with the request including various attributes associated with the client device. At least one set of rules applicable to the operation is identified. The rules can be formed from a combination of primitives arranged to dynamically evaluate attributes associated with the resource and attributes associated with the client device. Based on the evaluation of the rule set(s), an action is identified to be performed with respect to the resource.

Automatic updating of real estate database

Determining descriptive attributes for listing locations

Response effectiveness determination in a question/answer system

Answer effectiveness evaluations include providing, by a computing device, an answer to a search query received from a user, and in response to receiving a subsequent search query from the user, determining by the computing device a level of effectiveness of the answer.