Abstract: Computer-implemented techniques for repeatable and interpretable divisive analysis. In one embodiment, for example, a method comprises: identifying top-level cohorts of data items based on one or more characteristics of the data items in common; recursively or iteratively dividing a selected top-level cohort in a top-down manner resulting in a plurality of sub-level cohorts arranged in a hierarchy; detecting a particular data item that is a statistical outlier among data items of a leaf cohort in the hierarchy; and causing display of an indication in a computer user interface that the particular data item is an outlier.

Abstract: Computer-implemented methods for providing real-time customer, patient or accountability, security, consumer and employee metrics include: providing at least one strategic goal; providing at least one metric associated with the at least one strategic goal; providing at least one communication channel between a customer and a company; providing at least one communication code; utilizing the at least one communication code to access the at least one communication channel; providing a survey tool to the customer using the at least one communication channel; capturing data from the survey tool in a database; converting the captured data to the at least one metric; and providing the at least one metric on a dashboard application. An executable software application that implements the computer-implemented method disclosed is also contemplated.

Abstract: Computer-implemented systems and methods, trained through machine learning, score a sentiment expressed in a document. Individual sentences are scored and then overall document sentiment score is computed based on scores of individual sentences. Sentence scores can be computed with machine learning models. Digital matrix generator can generate N×M matrix for each sentence, where the matrix comprises vectors of word embeddings for the individual words of the sentence. A classifier computes a sentence sentiment score for each sentence based on the digital matrix for the sentence. Sentence sentiment scores computed by classifier can be adjusted based on a fuzzy matching of a phrase(s) in the sentence to key phrases in a lexicon that are labeled with a sentiment relevant to the context.

Abstract: Protected audience selection system. Media consumption histories of browsers which have converted are received at a modeling system where targeting of browsers is prohibity. A model is built by determining a frequency of each respective media consumption event among the histories and comparing each determined frequency of a respective media consumption event to a frequency of the respective media consumption event among a population of browsers without the conversion event. The model is sent to a targeting system which excludes conversion events. A description of the conversion event is received at the targeting system. A history of a targetable browser is received at the targeting system. The model is applied to the history of the targetable browser at the targeting system, where conversion events have been excluded from the history. Advertising content is sent to the targetable browser according to a result of applying the model.

Abstract: A method for testing medical data is provided. Each medical datum includes a plurality of information units and a plurality of separators, and the method includes the following steps: a. matching the medical data against a standard library including a plurality of patterns, a matching expression being: [\s\S][number/sequence/relation]&[\b|\B] (S101); and b. determining, based on a matching result of the step a, whether the medical datum is qualified (S102). A standardized standard library is first established, a matching result is obtained by matching the medical datum and the standard library for a non-initial boundary, an initial boundary, an information quantity, information sequences, a semantic relationship quantity, a character boundary, and a non-character boundary, and whether the medical datum meets a requirement is further determined according to the matching result.

Abstract: A method including determining a zip code of a user using a website that displays items. The method also can include receiving a selection by the user to display information about an item of the items. The method additionally can include retrieving first information including a predetermined geo-classification for the item. The method further can include retrieving second information including a list of fulfillment nodes that can currently deliver to the zip code of the user within a first shipping speed via ground shipping. The method additionally can include retrieving third information including a node-level inventory for the item. The method further can include determining a shipping speed to display to the user for the item based on (a) the predetermined geo-classification for the item, (b) the list of fulfillment nodes that can currently deliver to the zip code of the user within the first shipping speed, and (c) the node-level inventory for the item.

Abstract: A computer system, computer-implemented method, and computer program product include a processor(s) (executing code) that obtains a data set(s) related to a patient population diagnosed with a medical condition a database(s). The processor(s) identifies common features, generates patterns of the common features, and generates machine learning algorithms based on the patterns to identify presence or absence of the given medical condition in an undiagnosed patient. The processor(s) compiles a training set of data and tunes the machine learning algorithms with the training set of data. The processor(s) integrates the machine learning algorithms into a graphical user interface.

Abstract: Techniques configuring a machine learning model include receiving, via a user interface configured to communicate with a machine learning model hosted on a collaborative computing platform, a selection of a file for input to the machine learning model, a selection of content in the file for input to the machine learning model, and instructions for applying the selected content to the machine learning model, which are sent to the machine learning model. As new files are uploaded to the selected directories of the collaborative computing platform, the machine learning model is applied to the uploaded files to classify the files and extract metadata. The extracted metadata and associated classification data are stored in data structures associated with the new files. The data structures are existing data structures of the collaborative computing platform.

Abstract: In a method for communicating information about a service or product, a record can be retrieved from a database storing records of communications related to a second entity. The record can include information related to an identity of a first entity. The first entity can be defined, at a processor and based upon content of the record, as a member of a set designated to be sent the information about the product or service. The first entity can have previously engaged in a first communication related to the second entity. The second entity can be associated with the product or service. A second communication, which can include the information related to the identity of the first identity, can be sent from the processor to an advertising platform. A third communication, which can include the information about the product or service, can be sent from the processor to the advertising platform.

Abstract: An exception-resolution monitoring system determines an exception error is detected corresponding to a failed transmission of a message between servers of a distributed network. Changes are monitored that are tested and implemented to correct the detected exception errors. An executable corrective action is determined based on the monitored changes. The executable action is stored for future use and linked to a root cause of the exception error and properties of the distributed network at the time of the exception error.

Abstract: A behavior pattern search system and method is disclosed. A change in a behavior pattern contributing to improving a Key Performance Indicator (KPI) is discovered from among changes in the behavior pattern arising in common among customers having a specific characteristic. The behavior pattern search system classifies transfiguration candidates that are customers satisfying transfiguration result information. The transfiguration result information indicates a characteristic purchase behavior predicted to occur by a change in a behavior pattern of each of the customers.

Abstract: An image processing method, an electronic device, and a storage medium for processing an image dynamically. The image processing method includes obtaining a three-dimensional image of a first facial image based on a plurality of first feature points of the first facial image, the plurality of first feature points being used to identify a first face in the first facial image; obtaining a plurality of second feature points in each of a plurality of frames of second facial images in real time, the plurality of second feature points being used to identify an expression change of a second face; and synchronizing the three-dimensional image of the first facial image based on changes of the plurality of second feature points in each of the plurality of frames of second facial images, to simulate the expression change of the second face.

Abstract: The disclosed system and method enhances security of people, organizations, and other entities that use what has been termed “social media.” Recent trends have shown that information posted to social media may cause tremendous damage to individuals and other entities. This includes information that was posted deliberately or unintentionally, including social security numbers, financial data and other sensitive information. Further, information that previously may have been viewed as innocuous, such as location data, has caused harm on certain occasions and may need to be protected. The disclosed system provides a novel method of screening, identifying, and preventing certain information from being posted on social media and other public locations. In addition, the disclosed system and method improves security by motivating people to use security software by offering rewards for its use.

Abstract: Modifying operation of an intelligent agent in response to facial expressions and/or emotions.

Abstract: Devices and techniques are generally described for non-textual topic modeling. In some examples, a first item of a plurality of items may be identified. A first ranked list of items from the plurality of items may be generated for the first item using collaborative filtering. Topic modeling input data representing associations between the first item and each item in the first ranked list may be generated. Second data may be generated by inputting the topic modeling input data into a topic modeling algorithm. The second data may comprise one or more topics for the first ranked list of items.

Abstract: Systems and methods for designing an information processing system are described. In one embodiment, a design space is partitioned into a plurality of independent partitions based on a defined set of rules. A unique processing core is assigned to each partition. A plurality of starting points is generated for each partition, where each starting point is associated with a machine learning algorithm. The starting points for each partition may include a performance driven seed and an area-driven seed. A set of feasible designs associated with the information processing system are determined.

Abstract: Systems and methods can include one or more processing modules and one or more non-transitory storage modules storing computing instructions configured to run on the one or more processing modules and perform acts of: estimating demand for one or more items in an electronic basket of items using one or more different demand models; estimating elasticity for the one or more items in the electronic basket of items using a multi-armed bandit model; determining a price using the demand and the elasticity; and facilitating display of the price on a video screen of a device. Other embodiments are disclosed herein.

Abstract: Systems and methods for setting up a telephony communication include an operating system of a user telephony device diverting a call setup request made via a native dialer of the user telephony device to a telephony software application on the user telephony device. The telephony software application then sets up the requested telephony communication using a telephony communication application programming interface (API).

Abstract: Input data comprises a particular quantity of one or more finished goods to be produced over a time period. Software is programmed for: accessing infrastructure data that defines an infrastructure of a particular production facility; generating one or more sequence-dependent production plans comprising a particular sequence of one or more production process steps; calculating one or more optimized production plans for the time period by: determining a sub-period optimization plan for a first sub-period by adjusting one or more of a plurality of binary variables; generating a neighborhood optimization plan by adjusting one or more of the plurality of binary variables for a predefined neighborhood; and generating a particular optimized production plan for the time period by adjusting one or more of the plurality of binary variables; filtering the one or more optimized production plans based on one or more filtering criteria; and outputting the optimized production plans for display.

Abstract: In some implementations, a computing device can be configured to perform impact-based fraud detection. For example, a computing device (e.g., a network server) can receive user submissions from user devices corresponding to traffic incident reports, point of interest (POI) ratings, product ratings, vendor ratings, and/or other crowd-sourced information. The computing device can identify groups of users based on the user submissions and various grouping criteria. The computing device can determine the impact of these user groups with respect to the targets (e.g., traffic in an area, ratings of a business, etc.) of their user submissions. The computing device can prioritize high impact user groups when attempting to detect fraudulent user group activity (e.g., fraud rings).

Abstract: An automated system for detecting risky entity behavior using an efficient frequent behavior-sorted list is disclosed. From these lists, fingerprints and distance measures can be constructed to enable comparison to known risky entities. The lists also facilitate efficient linking of entities to each other, such that risk information propagates through entity associations. These behavior sorted lists, in combination with other profiling techniques, which efficiently summarize information about the entity within a data store, can be used to create threat scores. These threat scores may be applied within the context of anti-money laundering (AML) and retail banking fraud detection systems. A particular instantiation of these scores elaborated here is the AML Threat Score, which is trained to identify behavior for a banking customer that is suspicious and indicates high likelihood of money laundering activity.

Abstract: A system for triggering based on analytics comprises a storage device and a processor. The storage device is configured to store customer adoption data. A processor is configured to receive the customer adoption data; determine an under-used product feature based at least in part on the customer adoption data, wherein the customer adoption data is stored in the storage device; and determine and set a trigger for training the under-used product feature based at least in part on the customer adoption data.

Abstract: In some examples, personality trait-based customer behavior prediction may include extracting personality features from images associated with a user. Social style features may be extracted from social data associated with the user. Consumer demographics features may be extracted from consumer demographics data associated with the user. Based on a probability analysis of the extracted features, relevant features may be selected from the images, the social data, and the consumer demographics data. Historical purchase features may be extracted from historical purchase data associated with the user. At least one machine learning model may be trained based on the extracted features, and used to generate a next best offer for the user for purchase of a product or a service. A purchase of the product or the service may be performed based on the generated offer.

Abstract: In accordance with embodiments, there are provided mechanisms and methods for managing business deals. The mechanisms and methods for managing business deals may enable embodiments to provide a dynamic and interactive user-interface including any combination of contacts, accounts, opportunities, allowing users to create tasks, events, leads (e.g., from Data.com), reports, dashboards, instant messenger, external deal spaces, email service (e.g., Outlook), a cloud-based productivity suite for businesses that allows work on any device (e.g., Google apps), mobile access, private messaging, lead management, mass email templates, social media monitoring (e.g., from Radian6), role-based sharing and security, and/or additional storage, for example. In an embodiment, the number of contacts may be unlimited.

Abstract: The application relates to a computer-implemented method for calculating a reference sales price for industrial product, in particular a complex industrial product, to be manufactured at industrial level. The method of the present invention is particularly suitable for being implemented in the context of the design activities of an industrial product to be manufactured, in particular once the industrial product to be manufactured has been configured according to the technical specifications provided by a client.

Abstract: A backup manager for providing backup services to clients includes storage for storing a priority list. The backup manager also includes a processor programmed to obtain a request to generate a backup for a client of the clients; make a determination that the client is a high restoration priority client using the priority list; in response to the determination: obtain a raw disk backup for the client; and store the raw disk backup in backup storage in raw disk format.

Abstract: Aspects of the subject disclosure may include, for example, a method in which a processing system obtains physical and social environmental data for a communication device user, and provides content for presentation at the device. First reaction data, obtained via sensors associated with the user, indicate the user's reaction to presentation of the content; the data is analyzed to determine user affinity for the content in a context of the physical and social environments. The content is modified during the presentation; second reaction data is obtained and analyzed to determine a second user affinity for the modified content. If the affinity is enhanced, the modified content is sent to other users' equipment via a social network. Affinity responses regarding the modified content are analyzed, and a set of users is identified as an affinity group; additional content is transmitted to equipment of the affinity group. Other embodiments are disclosed.

Abstract: A system, method, and computer-readable storage medium are disclosed that execute machine vision operations to categorize a locality. At least one embodiment accesses a map image of a locality, where the map image includes geographical artefacts corresponding to entities within the locality; analyzes the map image to detect the entities in the locality using the geographical artefacts; assigns entity classes to detected entities in the locality; assigns a locality score to the locality based on entity classes included in the locality; retrieves street view images for one or more of the detected entities in the locality; and analyzes street view images of the detected entities to assign one or more further classifications to the detected entities. Other embodiments include corresponding computer systems, apparatus, and computer programs recorded on one or more computer storage devices, each configured to perform the actions of the method.

Abstract: The invention relates to systems and methods for automated insight curation and alerting. The system generates insights from time-series data at scale using unsupervised machine learning algorithms. The system can further automate the suggested actions by signaling the actuators or middleware which ultimately executes the action.

Abstract: Systems and methods for generating and presenting a clinical workforce management interface to assign staff in a clinical setting. The interface may present components including an aggregate patient population profile listing individual patients in a unit, the projected workload capacity the care for those patients represents, and an assignment bar depicting provider assignments for that patient over a designated time period. The interface may likewise present a provider population profile which lists available care providers in a unit, as well as their capacity ratings, skill sets, shifts, or other schedule data characterizing available clinical staff. A charge nurse or other staff manager may view and manipulate the provider-to-patient assignments, for instance by dragging and dropping visual elements to perform assignments. Compliance monitoring functions such as maintaining provider ratios may be automatically performed, and the staff manager may be alerted when ratios or criteria violate limits.

Abstract: A network computer system that determines metrics related to effort and cost on the part of deliverers who deliverer items for delivery orders. The network computer system can implement operations to facilitate or mitigate features that cause deliverers to expend effort or cost when completing delivery tasks.

Abstract: A browsing history associated with a user of a client device is received from the client device. One or more keywords associated with a target audience for a variant of a web page are received from a content provider system. A score is determined for the user based on the browsing history for the user and the one or more keywords associated with the target audience. The user is identified as part of the target audience based on the score for the user satisfying a score threshold. The variant of the web page is caused to be presented at the client device associated with the user.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to monitor auditing devices. An example apparatus includes a workload analyzer to obtain alert data related to a potential new product from an auditing device, and a product analyzer to identify a product within the alert data to determine if the product has been previously identified by another auditing device. In response to determining that the product has not been previously identified, the example apparatus includes an alert analyzer to cluster the alert data based on characteristics associated with an auditor profile of the auditing device, and determine a probability of transmitting the alert data to other auditing devices based on the clustered alert data. The example apparatus also includes an alert authorizer to suppress the alert data from being transmitted to the other auditing devices to reduce an amount of network resources required for subsequent processing when the probability does not satisfy a threshold.

Abstract: Methods and systems for providing accounting services and corporate strategic planning services that comprise processing and aggregating financial transaction data and a plurality of input variables for maintaining a subscriber's general ledger, outputting audit ready financial reports, providing strategic planning inputs and by using at least one of semi-automated and machine learning algorithms are disclosed.

Abstract: Systems and methods are provided for recommending price of benefit items offered through a membership platform. Exemplary implementations may: obtain benefit information for content creators of a membership platform; obtain consumption information, the consumption information describing acceptance of offers for the benefit items at the requested amounts by the subscribers of the content creators; train a machine learning model on input/output pairs to generate a trained machine learning model, the individual input/output pairs including training input information and training output information; store the trained machine learning model; determine, using the trained machine learning model, recommended amounts of consideration for the benefit items that correspond to greater acceptance; generate recommendations for individual content creators conveying the recommended amounts for the benefit items offered by the individual content creators; and/or perform other operations.

Abstract: System and methods for generating a product recommendation based on reactions such as bio-feedback of a subject during a virtual try-on session are described herein. A recommendation engine captures bio-feedback and determines whether the subject has a positive or negative attitude towards a certain feature of a product that is being virtually “tried on” with the subject. The recommendation engine can then provide a product recommendation based on the actual sentiment of the subject towards a product feature.

Abstract: Provided herein are systems, methods and computer readable media for forecasting demand. An example method comprises generating a virtual offer for one or more combinations of a category or sub-category, location, and price range, accessing consumer data comprising one or more users and user data related to each of the one or more users, calculating a probability that a particular user would buy a particular offer in a particular time frame for at least a portion of the plurality of users and for each of the virtual offers, and determining an estimated number of units of to be sold for at least a portion of the one or more virtual offers as a function of at least the probability associated with each of the one or more virtual offers.

Abstract: The systems may include receiving, by a processor, transaction information for a transaction, wherein the transaction information comprises a transaction amount; matching, by the processor, the transaction information with a transaction type; retrieving, by the processor, a plurality of possible charge types associated with the transaction type; comparing, by the processor, the transaction information with the plurality of possible charge types; separating, by the processor, the transaction amount of the transaction information into at least one individual charge amount; and/or identifying, by the processor, a charge type of the plurality of possible charge types associated with the at least one individual charge amount.

Abstract: Systems, methods, and computer-readable media are provided to assist users to locate content of interest based on viewer ratings. First information enabling unique identification of a first user may be processed. Indications of ratings of television programming may be processed, the indications being received from a first media device associated with the first user. Ratings information associated with the first user may be retained in repositories, the ratings information being based on the indications. The first user may be matched to a category that represents a classification of a set of viewers and/or of a set of content based on a set of attributes. Descriptive content indicative of the first user and/or content rated by the first user may be selected and may be transmitted via the network to a second media device associated with a second user.

Abstract: A graphical user interface (GUI) may be provided by a computing system that implements a database system for presentation at a client device. The GUI may display a designated one or more criteria for selecting one of a plurality of recommendations for a target object instance associated with a designated object definition. A predictive model for determining a propensity score for selected ones of the plurality of recommendations in association with the target object instance may be configured. The propensity score may be a function of one or more data field values associated with the target object instance and may be configured based on user input received via the graphical user interface. The predictive model may be stored on a storage medium for retrieval when selecting recommendations in response to requests received to access instances of the designated object definition.

Abstract: Technologies for audiovisual communication include an audiovisual server and a number of audiovisual client devices, including a presenter device and a number of audience devices. Each audience device captures an audiovisual stream and transmits the audiovisual stream to the audiovisual server. Each audience device also captures sensor input data such as eye tracking data or facial expression data and transmits abstracted sensor input data to the audiovisual server. The abstracted sensor input data may be based on the captured audiovisual stream. The audiovisual server determines an interestingness rating associated with each audience device based on the sensor input data, and selects one or more audiovisual streams based on the interestingness ratings. The audiovisual server transmits the selected audiovisual streams to the presenter device. The audiovisual server may update the interestingness rating algorithm based on feedback from the presenter device or the audience devices.

Abstract: Apparatus and methods of instruction presentations to a ‘virtual’ audience or students including real-time information formed from observable audience reactions as they receive the presentation material, and further includes apparatus and methods to correlate the detected or missing audience reactions in relation to specific presented material, rapidly prompting the presenter and/or the audience with specific, timely, low-latency feedback. The presenter is alerted (possibly before an audience question can be formulated), and the audience member is prompted that there may be questions or contributions regarding a specific matter as it is presented, whereupon the audience member is given the freedom to join or question (or not).

Abstract: This specification relates to methods and systems for providing intuitive navigation of a set of entities. One of the methods includes determining n-dimensional embeddings representing entities; reducing the n-dimensional embeddings representing entities into a 2-dimensional representation of the entities; forwarding, for display on a user's computing device, the 2-dimensional representation of the entities; receiving an input from the user's computing device; responsive to the input, determining an additional 2-dimensional entity representation; and forwarding, for display on the user's computing device, the additional 2-dimensional entity representation.

Abstract: Provided is a method for automatically performing image alignment without a user input. An image alignment method performed by an image alignment device, according to one embodiment of the present invention, can comprise the steps of: recognizing at least one person in an inputted image; determining a person-of-interest among the recognized persons; and performing image alignment, on the basis of the person-of-interest, on the inputted image, wherein the image alignment is performed without an input of a user of the image alignment device for the image alignment.

Abstract: This application relates to apparatus and methods for automatically providing item reviews. In some examples, a website provides a widget on a website allowing a customer to request an item review for an item. In response to the customer requesting the item review, a computing device determine whether suitable reviews for the item are available. If suitable reviews are available, the reviews are provided to the customer requesting the item review. If suitable reviews are not available, the computing device determines a set of customers to request item reviews for the item from, and provides item review requests to the determined set of customers. The computing device receives responses to the item review requests received from the set of customers, and provides an item review based on the received item review requests. In some examples, the website provides the item review to the customer requesting the item review.

Abstract: Disclosed herein are systems and methods for managing access to data objects in cloud storage. In one aspect, an exemplary method comprises storing, by a processor, a data object in a storage device of a cloud storage service for a duration of time, wherein the data object is accessible to a plurality of user accounts. The method comprises extending the duration of time for retaining the data object on the storage device to a first extended duration when a degree of access of the data object by the plurality of user accounts meets a target threshold value during the duration of time. The method further comprises extending the duration of time for retaining the data object on the storage device to a second extended duration when the degree of access does not meet the target threshold value during the duration of time.

Abstract: A computer program, computer-implemented process, and/or an apparatus may detect an event in a webpage or an application, and adjust a lead score by comparing the event with implicit lead scoring rules, explicit lead scoring rules, lead state, or any combination thereof. Using the lead score, the event is assigned to a category or classification for purposes of identifying a positive or negative lead.

Abstract: A computer implemented method of access control for a restricted resource of a resource provider in a network connected computer system, wherein a blockchain data structure accessible via the network stores digitally signed records validated by network connected miner software components, the method including: identifying an access control role definition for access to the resource, the role including a specification of access permissions; defining a cryptocurrency for indicating authorization to access the resource, the cryptocurrency being formed of tradeable units of value associated with records in the blockchain and wherein transfer of the cryptocurrency between records in the blockchain is validated by the miners; receiving a request from an authenticated resource consumer for authorization to access the resource; and submitting a blockchain transaction to the miner components to transfer a quantity of cryptocurrency to a consumer record in the blockchain, the transaction including an identification of

Abstract: A system and method for facilitating a user to initiate and accept an assistance request through a chat session is disclosed. Controls may be provided in a graphical chat interface to enable the user to specify inputs to request assistance from other users participating in the chat session. An assistance request may be generated and communicated to those users through the chat session. Graphical representation for the assistance request and controls that facilitate the users to accept the assistance request may be provided in the graphical chat interface. Upon an acceptance to the assistance request by a responding user through the graphical chat interface, an assistance command may be generated and executed in the virtual space.

Abstract: An online host for conducting a promotion campaign is presented. Online behaviors of subscribers exposed by the promotion campaign are tracked for determining conversion counts for the promotion campaign. For exposed subscribers whose online behaviors are not sufficiently available to the online host to determine conversion counts (non-measurable subscribers), a machine learning model is trained to predict conversion counts based on online behaviors that are conducted on internet locations under control of the online service, and further trained to determine an estimated error rate regarding the predicted conversion counts.