Abstract: Cardinality-based activity pattern detection is described herein. Events on a computing system are monitored to detect patterns matching defined activity patterns. A cardinality-based activity pattern query is executed over data representing detected activity patterns to identify multiple, distinct defined activity patterns that have occurred during a particular time period.

Abstract: Embodiments described herein are directed to computer-implemented methods, systems, and computer program products for calculating a metric using natural language processing tokens. A non-limiting example of the computer-implemented method includes parsing, by a processing device, user content using a natural language processing technique to extract tokens. The method further includes filtering, by the processing device, the tokens relating to a natural language processing criterion. The method further includes calculating, by the processing device, a metric based at least in part on the filtered tokens. The method further includes determining, by the processing device, whether to take an action by applying the metric to a set of rules. The method further includes taking the action responsive to determining to take the action.

Abstract: Systems and methods for analyzing product exposure to one or more shoppers in a shopping environment are disclosed herein. One method may include developing a three-dimensional model of the shopping environment indicating a product location of each of a plurality of products, capturing a plurality of images of shoppers using an overhead camera, and computing an estimated field of view of each shopper captured in the plurality of images. Computer vision techniques may be used to determine a location of a facial feature in the plurality of images, determine a head pose, and then assign the estimated field of view. The method may further include, based on the three-dimensional model, computing that a product location exists within the estimated field of view for each shopper, and generating a visibility metric based on an extent to which the product location exists within each estimated field of view.

Abstract: Methods and systems for clustering objects using Geohash grids. The clusters are typically displayed on an interactive map. A clustering module receives multiple objects having respective geo-information and derives clusters for the objects in respective grid cells of a given resolution level. The clustering is based on the geo-information of the objects at one or more resolution levels that are finer than the given resolution level. Clustering based on finer-resolution levels provides spatial information at a granularity that is unavailable at the given resolution level and therefore achieves clustering with improved accuracy. The geo-information may comprise a Geohash spatial index that specifies the geographic location in accordance with the Geohash system.

Abstract: Example implementations described herein are directed to systems and methods for predictive maintenance with health indicators using reinforcement learning. An example implementation includes a method to receive sensor data, operational condition data, and failure event data and generate a model to determine health indicators that indicate equipment performance based on learned policies, state values, and rewards. The model is applied to external sensor readings and operating data for a piece of equipment to output a recommendation based on the model.

Abstract: A device may obtain, from a collection of data sources, personal information and activity information for a group of individuals. The device may generate profile information by associating the personal information and the activity information for each individual in the group of individuals. The device may determine a set of features capable of being used to train a set of machine learning models by using one or more feature identification techniques to analyze the profile information. The set of features may include generic features and contextualized features associated with the group of individuals. The device may train the set of machine learning models using one or more subsets of features of the set of features. The device may use the set of machine learning models to process a request from a client device for a list of prospective targets for a campaign.

Abstract: An information output device includes: a first output unit that outputs acquired information acquired by a sensor; and a second output unit that converts personal information included in the acquired information into attribute information from which identification of an individual is impossible, and outputs the attribute information.

Abstract: A computer-implemented method for proactive fraudster exposure in a customer service center having multiple service channels is provided herein. The computer-implemented method may collect call interactions based on predefined rules by a calls collection engine and store the collected call interactions. The computer-implemented method may further analyze the call interactions by a Proactive Fraud Exposure engine by: (i) generating a voiceprint for each call interaction; (ii) using machine learning technique to group the call interactions into one or more clusters based on respective voiceprints in the voiceprints database; (iii) storing the one or more clusters; and (iv) ranking and classifying the one or more clusters to yield a list of potential fraudsters. The computer-implemented method may further transmit the list of potential fraudsters to a user to enable the user to review said list of potential fraudsters and to add fraudsters from the list to a watchlist database.

Abstract: Systems, methods, and other embodiments are disclosed that are configured to characterize an effect on sales of a retail item due to a sales promotion. In one embodiment, first sales data for the retail item is retrieved from a plurality of stores that have applied the sales promotion for the retail item. Second sales data for the retail item is retrieved from a single store that has applied the sales promotion for the retail item. A combined promotion effect value is generated based on the first sales data and the second sales data. The combined promotion effect value characterizes an effect on sales of the retail item as sold by the single store due to the sales promotion.

Abstract: A server includes a session management device establishing a video call session between a first electronic apparatus of a first user and a second electronic apparatus of a second user, a communication device receiving match satisfaction calculated from the first electronic apparatus through the video call session, an image analysis device obtaining first feature point distribution information from a face image of the first user and obtaining second feature point distribution information from a face image of the second user, a processor training a machine learning model by using the first feature point distribution information, the second feature point distribution information, and the match satisfaction and estimating the match satisfaction of the first user for each of standby users by using the trained machine learning model when a video call connection between the first electronic apparatus and the second electronic apparatus is terminated, and a user management device selecting a third user, who becomes a

Abstract: System and method embodiments are described that enable generation of an electronic content schedule. In a method embodiment, one or more data files including TV viewing data and descriptive data of a plurality of individuals are received. Target audience criteria, target TV content, and criteria for key performance indicators (KPIs) are received. KPIs for a target segment are tracked. Spot watching probabilities for each individual in the target segment are calculated. A plurality of spot packages is generated based on the target TV content. For each spot package, a probabilistic segment is generated based on the spot watching probabilities and a plurality of KPIs are calculated. Scores corresponding to the spot packages are generated based on the plurality of KPIs and based on tracked KPIs of the target segment. The content schedule is generated by selecting a spot package selected from the plurality of spot packages based on the scores.

Abstract: Systems, apparatus, and methods for providing diversified promotions are discussed herein. Some embodiments may include a system including circuitry configured to provide diversified promotions within an impression or other communication including multiple promotions. For example, promotions may be associated with diversity characteristics to determine the diversity of promotional offerings within an impression and/or within a series of impressions over a period of time sent to a targeted consumer. When an impression is determined to lack diversity based on the diversity characteristics of the promotions, the system may be configured to take corrective action such as by replacing at least one promotion with a replacement promotion that provides greater diversity to the impression.

Abstract: Aspects of the disclosure relate to generating map data. For instance, data generated by a perception system of a vehicle may be received. This data corresponds to a plurality of observations including observed positions of a passenger of the vehicle as the passenger approached the vehicle at a first location. The data may be used to determine an observed distance traveled by a passenger to reach a vehicle. A road edge distance between an observed position of an observation of the plurality of observations and a nearest road edge to the observed position may be determined. An inconvenience value for the first location may be determined using the observed distance and the road edge distance. The map data is then generated using the inconvenience value.

Abstract: The embodiments of the disclosure disclose an intelligent playing method and apparatus based on preference feedback. An embodiment of the method comprises: receiving voice feedback on currently played multimedia from a user; analyzing a user intention based on the voice feedback; calculating, in response to the user intention indicating updating a currently played multimedia list, a similarity between multimedia in a multimedia database and the current multimedia; and updating the currently played multimedia list based on the voice feedback and the similarity. The embodiment improves the quality and pertinence in playing multimedia.

Abstract: A method for obtaining credit card pricing for a merchant includes obtaining a merchant category classification (MCC) code. A sales volume, a number of credit card transactions, an average dollar amount of the credit card transactions and a percentage of credit card transactions that are keyed are obtained. The MCC code, the average dollar amount of the of credit card transactions processed and the percentage of credit card transactions that are keyed are compared with corresponding data from a database of merchant credit card transactions. A matched merchant is identified whose transaction profile closely matches a combination of the MCC code, the average dollar amount of the credit card transactions processed and the percentage of credit card transactions that are keyed. Credit card processing pricing information for the matched merchant is obtained from the database. The credit card processing pricing information is used to calculate credit card processing pricing for the matched merchant.

Abstract: A common point of purchase (CPP) system for identifying a common point of purchases involved in fraudulent or unauthorized payment transactions is provided. The CPP system includes a common point of purchase (CPP) computing device that is configured to receive transaction data, store the transaction data in a database, and perform a look up within the database. The CPP computing device is also configured to build a merchant table, receive a card list, and compare a plurality of flagged account identifiers in the card list to account identifiers in the merchant table. The CPP computing device is further configured to retrieve a unique merchant identifier and/or a merchant name identifier associated with the merchant table account identifiers matched with the flagged account identifiers, aggregate the unique merchant identifier using the merchant name identifier, and determine a first number of the flagged account identifiers associated with the merchant name identifier.

Abstract: A method for predicting preliminary design load cases using an artificial neural network, the method including obtaining, with a processor, historical data corresponding to an existing structural component, the historical data including finite element modeling analysis data and measured test data for the existing structural component, designing the artificial neural network to include a plurality of neurons to form a numerical model for preliminary design load cases of a new structural component, training, with the processor and the historical data for the existing structural component, the artificial neural network to predict the preliminary design load cases for the new structural component, providing input design parameters for the new structural component to the artificial neural network, and predicting, with the artificial neural network, the preliminary design load cases for the new structural component.

Abstract: Embodiments for discovery and analysis of interpersonal relationships from a collection of unstructured text data by a processor. A relationship between one or more entities and extracted text data from a plurality of unstructured text data may be identified such that the relationship includes a sentiment of the relationship, a type of relationship, temporal information, or a combination thereof. The one or more entities may be associated with a knowledge graph based on an ontology of concepts representing a domain knowledge. The extracted information and the identified relationship may be automatically aggregated into a multi-graph representation.

Abstract: A system is provided for analyzing information collected by a plurality of wearable camera systems. In one implementation, the system may include a memory storing executable instructions and at least one processing device. The at least one processing device may be programmed to execute the instructions to receive information derived from image data captured by the wearable camera systems; analyze the derived information to identify a commonality related to the image data captured by at least two of the wearable camera systems; determine, based on the commonality, statistical data related to users of the at least two of the wearable camera systems; and select, based on the statistical data, at least one content item for at least one of the users of the wearable camera systems who share the commonality.

Abstract: A computing device computes a plurality of quantile regression solvers for a dataset at a plurality of quantile levels. Each observation vector includes an explanatory vector of a plurality of explanatory variable values and a response variable value. The read dataset is recursively divided into subsets of the plurality of observation vectors, a lower counterweight vector and an upper counterweight vector are computed for each of the subsets, and a quantile regression solver is fit to each of the subsets using the associated, computed lower counterweight vector and the associated, computed upper counterweight vector to describe a quantile function of the response variable values for a selected quantile level of the identified plurality of quantile level values. For each selected quantile level, a parameter estimate vector and a dual solution vector that describe the quantile function are output in association with the selected quantile level.

Abstract: Methods and systems are provided herein for calibrating subject data based on reference data, so that the calibrated subject data more closely represents a target population. The methods and systems include partitioning a reference data set into a plurality of reference data partitions using a data partitioning scheme, each reference data partition associated with a characteristic; and partitioning a subject data set into a plurality of subject data partitions using the data partitioning scheme, each subject data partition associated with a characteristic that corresponds to the characteristic associated with a reference data partition of the plurality of reference data partitions; identifying a variable present in the reference data set that is not present in the subject data set; and calculating a value of the variable for each reference data partition based on a rate of occurrence of the variable in each reference data partition.

Abstract: A method and apparatus of a device that re-rank a plurality of search results is described. In an exemplary embodiment, the device receives a search query from a user and generates the plurality of search results over a plurality of search domains, wherein the plurality of search results is ranked according to a first ranking. The device additionally generates a re-ranking model, where the re-ranking model includes a plurality of intra-domain models that are generated based on at least based on-device interactions of a plurality of users interacting with a plurality of other devices and each of the plurality of search domains corresponds to one of the plurality of intra-domain models. The device further re-ranks the plurality of search results using the re-ranking model and presents the plurality of search results using the second ranking.

Abstract: A method includes obtaining data related to a plurality of historical transactions, where each historical transaction is associated with a label based on a click stream created by the first user, generating a vector of features from the data related to each historical transaction, training, using the vectors and labels, a multinomial classifier to generate a probability that a specific transaction belongs to a specific classification with respect to income, obtaining data related to a new transaction from a financial stream for a second financial account of a second user of the financial service, generating a new vector of features from the data related to the new transaction, determining a classification with respect to income for the new transaction, and presenting the classification to the second user for review in a view of a graphical user interface.

Abstract: According to one embodiment of the present disclosure, a virtualized communication device dynamic provisioning system includes a computer-based set of instructions that are executed to generate a user interface for receiving selection of one or more virtualized communication devices. The instructions may then receive provisioning information associated with the selected virtualized communication devices from the user interface, and provision the virtualized communication devices in accordance with the received provisioning information to prepare and equip the virtualized communication devices according to the financial transaction.

Abstract: A computer system for remote interactive graphical display and data management includes a data storage device storing data records, a remote data acquisition computer configured to selectively trigger display actions for the data records based on at least a time-based rule and a time-independent rule; a classification engine configured to classify a response received from a remote display interface having user-selectable options arranged to define a scale of values, in one of two categories, a first category and a second category, being below a first threshold value being classified as being in the first category, and responses on the scale above a second threshold value being in the second category, and a display interface generator configured to selectively generate a supplemental interface or a conclusion message dependent on the category.

Abstract: Review data associated with a plurality of entities is received. Each of the entities is associated with a particular industry and the review data comprises review data obtained from a plurality of review sites. From at least a portion of the received review data, a review benchmark for the industry is determined. The benchmark is provided as output.

Abstract: There is provided a system having a memory for storing a software application, where the software application includes a product database. The product database includes a product history for a plurality of products. A processor is configured to execute the software application. The software application receives product requirements for a new product, determines at least one related product from the plurality of products based on the product requirements for the new product, evaluates the product history of the at least one related product to determine a linguistic corpus for the new product, and creates the linguistic corpus for the new product.

Abstract: Systems and methods are described for facilitating payments and transactions using social background checks. Such systems and methods may use social networks with both individual members communicating over a network to a social authentication computing system. The authentication of transactions associated financial institutions are determined through the use of relationship measures based on social media interactions. Transactions and services available to a user are determined based on a measure of social identity through the use of social media platforms. Available contact and interaction data from one or more social media platforms is leveraged to analyze a level of trust that a transaction is not a consequence of fraudulent activity. Transactions that have a low level of risk of being a consequence of fraudulent activity are benefited through faster transaction times and other improvements.

Abstract: Embodiments forecasting future demand for an item. Embodiments receive a regression based demand algorithm for the item that includes the set of features as regression variables and split the data points into a training set and a testing set. Embodiments assign each of the features of the set of features into one of a plurality of regularization categories and assign a penalty parameter to each of the features subject to regularization. Embodiments train the demand algorithm using the training set, the penalty parameters and the features to generate a trained demand model. Embodiments evaluate the trained demand model using the testing set to determine an early drop metric and repeat the assigning each of the features, the assigning the penalty parameter, the training the demand algorithm and the evaluating the trained demand model until the early drop metric meets a threshold.

Abstract: Systems and methods are provided for informing a user about the emotional response of the user to a presentation. Facial expressions of the user are monitored while the user is presented with the presentation. The facial expressions are analyzed to determine an emotion displayed at one or more specific times of the presentation. The user is provided with information about the emotion conveyed by the facial expressions of the user. The user is further provided with an opportunity to take a selected action that corresponds to the emotion conveyed.

Abstract: Systems and methods for providing search results based on time obtain an item are discussed. In an example, a method can include receiving a search query, generating search results, calculating a time to obtain for each listing in the search results, and arranging the search results for display. The search query can include a current location of a mobile device. The search results can include a plurality of listings, with each listing including a location. The locations representing either a physical location proximate the current location or a delivery time to the current location. The search results can be arranged for display in various manners according to the calculated time to obtain for each result.

Abstract: The innovation disclosed and claimed herein, in one aspect thereof, comprises systems and methods of providing trust recommendations. The innovation receives fidelity data of an advisor. The fidelity data can include audio or visual data of the advisor in which the advisor is providing advice. A trust score for the advisor is determined based on a biometric or other analysis of the fidelity data. The trust score is compared to a threshold trust score to determine a recommendation to the user. The recommendation can be to trust or distrust the advisor or the advice. The recommendation is communicated or otherwise provided to the user.

Abstract: A method includes receiving a first signal originating from a first communication device located in a vehicle, the first signal indicating a requested product or service, a receiving time for the requested product or service, and a moving route of the vehicle, determining a receiving location of the requested product or service based on the receiving time and the moving route indicated by the first signal, and transmitting a second signal to a second communication device associated with the determined receiving location, the second signal indicating an instruction to prepare the requested product or service.

Abstract: A method for providing purchased content is provided. Management data including the identification data of the purchased content data stored in the information processing apparatus is received. Backup data of a user identification associated with the information processing apparatus is updated based on the management data. A request with the user identification associated with the information processing apparatus is received. A determination is made as to whether the request is authorized based on an authentication process. A list of identification data of content data identified in the backup data is provided to the information processing apparatus in response to a determination that the request is authorized. Further, the purchased content data without the fee is provided to the information processing apparatus based on a user selection of the identification data of the purchased content data from the list of the identification data of the content data.

Abstract: The disclosed computer-implemented method may include identifying a region within a user's eye gaze and calculating a ranking for the identified region within the user's eye gaze. The ranking may indicate the user's level of interest in the identified region. The method may then determine how the identified region is to be presented according to the calculated ranking and present the identified region in the determined manner according to the calculated ranking. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: Disclosed are systems, methods, and computer-readable storage media to select content to present to a user are disclosed. In one aspect, a method includes determining a content consumption rate of the user, and selectively presenting content to the user based on the content consumption rate. The content consumption rate may be determined based on a number of media content presented to the user over a period of time. If the number is above a threshold, a first type of content may be presented, while if the number is below (or equal) to the threshold, a second type of content, or in some aspects, no content, may be presented. After the selective presentation, additional content may be presented regardless of the content consumption rate.

Abstract: Examples described herein generally relate to a computer device including a memory, and at least one processor configured to process a transaction. The computer device receives customer transaction information. The computer device evaluates the customer transaction information to determine a risk score for the transaction. The computer device assigns the transaction, based on the risk score, to one of a plurality of stratums including at least a first stratum and a second stratum. The computer device selects a merchant identifier (MID) from at least a first MID associated with the first stratum and a second MID associated with the second stratum based on at least the assigned stratum and a target chargeback rate for at least one of the first MID or the second MID. The computer device transmits the transaction information and the selected MID to an issuing bank.

Abstract: A system for monitoring a product on display includes a display pedestal configured to secure the product to a fixture to which the display pedestal is mounted. The display pedestal includes a tether to allow movement of the product relative to the fixture. The system includes a sensor system including a capacitive sensor pad. The capacitive sensor pad is supported by the fixture and configured to detect the movement of the product via the tether.

Abstract: One embodiment relates to a financial institution computing system. The financial institution computing system includes a network circuit enabling the financial institution computing system to exchange information over a network and a risk analysis circuit. The risk analysis circuit is configured to receive user information, simulate a plurality of investment outcomes for a first investment risk level based on the received user information, display at least one augmented reality or virtual reality depiction of at least one of the investment outcomes via a display device, monitor a reaction of the user to each displayed augmented reality or virtual reality depiction, and select an investment strategy for the user based on the reactions of the user.

Abstract: A device may receive, from a camera device, an image that includes a person. The device may provide the image to a user recognition device and receive, from the user recognition device, a user identifier based on the person included in the image. In addition, the device may obtain user data based on the user identifier, the user data relating to prior activity relating to the person associated with the user identifier. The device may identify a user device based on a first physical location associated with the camera device and a second physical location associated with the user device, and provide the user data to the user device.

Abstract: Taught is a search engine for science tools which dynamically evaluates search rank of said science tools through Natural Language Processing and machine learning. The search engine accepts into a corpus of public and private materials, which references individual science tools. Each item of the corpus is evaluated both as to how much that given item should be trusted, and what that item says about individual science tools. Each science tool is evaluated based on what the whole corpus of input data contains concerning those science tools, taking into account how valuable the source of the data is in order to render an overall score and search rank. The search engine generates a judgement of each individual science tool, which is dynamically updated as new information becomes available in the corpus of input data.

Abstract: This application describes apparatus and methods for using edge-computing to control resource distribution among access channels, such as a retail banking center. Edge-nodes may be configured to move a product display in response to detected or expected customer traffic flow in or near a retail location. Edge-nodes may be configured to redirect resources provided by a cloud computing environment to or away from the retail location. Based on customer traffic flow, edge-nodes may direct customers/resources to a retail location and ensure the retail location provides a predetermined quality of service.

Abstract: A user's historical service data of a first time period and a second time period is obtained. Means and variances of a plurality of users' historical service data of the first time period and the second period are calculated. A risk model is generated based on at least one type of the plurality of users' historical behavioral data. The user's service data is obtained. At least one type of the user's behavior data is introduced to the risk model. A determination is made whether the at least one type of the user's behavior data is outside of the safety threshold. A service corresponding to the service data is rejected when the at least one type of the user's behavior data is outside of the safety threshold.

Abstract: Disclosed are apparatus and method for facilitating a purchase in conjunction with media content information. The apparatus includes a receiver configured to receive a transmission of media content, information regarding the content, and information for facilitating a purchase of at least one of a copy of the content, a good, and/or a service. The content may include broadcast media content and entertainment media content. The apparatus also includes a processor configured to process the information regarding the content and the information for facilitating a purchase of the copy of the content, the good, and/or the service. The apparatus also includes a display device for displaying information.

Abstract: A contract generation system that automatically generates cost models for new business contracts is provided. The system receives a new contract comprising a set of key-value pairs, each key-value pair comprising a question and an answer that correspond to a field of information in a document for the new contract. The system computes a similarity measure between the new contract and an existing contract based on a set of variance definitions for determining differences between the set of key-value pairs of the new contract and a corresponding set of key-value pairs of the existing contract. The system generates a cost model of the new contract based on the similarity measure and a cost model of the existing contract.

Abstract: Systems, methods, and non-transitory computer-readable media can collect past user information and churn data for a plurality of users. A churn prediction model is trained using the past user information and churn data. A churn propensity score is calculated for a present user based on the churn prediction model, the churn propensity score indicative of the likelihood of the present user to churn.

Abstract: A system and method determines the creditworthiness of a consumer and issues a loan and generates a behavioral profile for that consumer. An initial set of data is acquired from the consumer that includes non-identification attributes without obtaining a full name, a credit card number, a passport number, or a government issued ID number that allows identification of the consumer. A user ID number matches the initial set of data to a physical user in a transaction database. A credit score based on the average credit among a plurality of user profiles is matched to determine a maximum credit for the consumer. A loan is credited and a behavioral profile is generated based on the consumer check-ins and location and correlating periodic location patterns to loan and transactional activities.

Abstract: A method of assigning numbers to flights includes displaying, in a first window that is displayed on a GUI, a slideable scale that receives a pairing preference input that indicates a user preference relating to the classification of flights as thru flights relative to the classification of flights as out-and-back flights. The method also includes: after displaying the first window, receiving by a processor the pairing preference input; in response to the receipt of the pairing preference input, classifying, using a flight number optimization model, each flight as one of: a thru flight, an out-and-back flight, and a stand-alone flight based on the pairing preference input; assigning, using the flight number optimization model, a number to each flight; and displaying, in a second window that is displayed on the GUI, at least a portion of an output schedule that comprises assigned numbers for each flight.

Abstract: A device may determine a plurality of components for a development project. The device may determine a blueprint template based on the plurality of components of the development project. The device may generate a blueprint for the development project based on the blueprint template. The device may generate a package for the development project based on the blueprint for the development project. The device may provide output associated with the blueprint and the package based on generating the blueprint and generating the package.

Abstract: A 5G-based communication method for an industrial apparatus can be implemented in industrial apparatus during manufacturing operations, and a microprocessor. The industrial apparatus can collect data sets concerning itself, generate a 5G signal containing the data sets, and send the 5G signal to the microprocessor. The microprocessor determines a communication channel for the microprocessor according to the identification of the industrial apparatus in the data set, and can find a data processing rule, a data storage rule, and a data emission rule corresponding to the communication channel in a relationship table. The data is processed accordingly enabling a safe, efficient, and convenient transmission of data sets between the microprocessor and the industrial apparatus.