Abstract: Implementations of the present specification disclose a method and a system for recommending a target transaction code setting region. The method includes the following: dividing a target region to obtain multiple sub-regions, where the multiple sub-regions include one or more label sub-regions with known target transaction code setting effects and one or more sample sub-regions with unknown target transaction code setting effects; obtaining an association feature between the multiple sub-regions; obtaining predicted effect values of setting a target transaction code in the one or more sample sub-regions by using a prediction algorithm based on at least estimated effect values of setting a target transaction code in the one or more label sub-regions and the association feature; and determining at least one recommended region for setting a target transaction code from the one or more sample sub-regions based on at least the one or more predicted effect values.

Abstract: Disclosed are systems and methods for improving interactions with and between computers in content generating, searching, hosting and/or providing systems supported by or configured with personal computing devices, servers and/or platforms. The systems interact to identify and retrieve data within or across platforms, which can be used to improve the quality of data used in processing interactions between or among processors in such systems. The disclosed systems and methods automatically, in real-time, establish a network connection between two users based on one user's current situation and the other user's determined expertise in that situation. The user's situation can be based on his/her identity, location, activity, the time, date, and the like. The disclosed systems and methods provide a computerized, fully automated network environment that enables video conferencing between such geographically separated users, thereby enabling the expert user to advise the other user on his/her current situation.

Abstract: Various methods and systems are provided for conducting e-commerce. In one example, a method of conducting an e-commerce transaction includes a method of operating an online retail website. The method includes providing access to a computer interface for suppliers and presenting information to the suppliers through the computer interface regarding activity of the supplier's stock keeping unit (SKU). The suppliers are then enabled to directly modify at least one parameter associated with a presentation of the supplier's SKU on the retail website by way of the interface. The modification of the parameter may include, for example, modification of the presentation of the SKU including, for example, changing the title, adding video or photograph, or adding some other information. The modification of the parameter may also include, for example, modifying the price or entering into a bilateral agreement with the operator of the retail web site.

Abstract: Methods, computer program products, and systems are presented. The method computer program products, and systems can include, for instance: obtaining vocal utterance data representing vocal utterances of multiple users within a venue; processing the vocal utterance data to return metadata associated to the vocal utterance data; predicting using the metadata an item for acquisition by one or more user of the multiple users; and returning an action decision in dependence on the predicting.

Abstract: A work support device includes a first display control unit and a registration unit. The first display control unit performs control to display a label image having a message to a second user designated by a first user on a display screen relevant to the message. The registration unit takes the message as a task, and correlates and registers task information on the task with (i) display screen identification information to identify the display screen on which the label image is displayed and (ii) user identification information to identify the second user.

Abstract: Systems and associated methods are described for providing content recommendations. The system accesses content item consumption data for a plurality of users subscribed to a media service. Then, the system determines that a first subset of the plurality of users has unsubscribed from the media service and that a second subset of the plurality of users has not unsubscribed from the media service. The system identifies a time slot typical for the first subset of users and atypical for the second subset of users based on content item consumption data of the first subset of users and content item consumption data of the second subset of users. In response to determining that a user is consuming a first content item at the identified time slot, the system generates for display a recommendation for a second content item that is scheduled for a different time slot.

Abstract: A method identifies a plurality of product categories by applying a categorization model to product data that includes product names and product descriptions. The product data is obtained from internal sources and external sources. The method creates a knowledge graph for a plurality of business entities from inputs that include the plurality of product categories, published data that includes merchant categorizations, and geographical data. The method generates cohort clusters of similar business entities by applying a clustering algorithm to the knowledge graph. The method uses the cohort clusters to learn a first extrapolation model for predicting inventory. And the method provides access to the first extrapolation model to predict inventory level at a specific point in time. The access is provided via a merchant application that runs on an online merchant platform.

Abstract: A transportation company uses transportation vehicles. The transportation company receives a plurality of transportation needs. These transportation needs are received from user accounts. The transportation needs are based on states of users gathered without user intervention. Each transportation needs include time parameters and location parameters. The transportation company determines a probabilistic model for transportation needs. The probabilistic model is based on the plurality of transportation needs. The first probabilistic model relate to respective probabilities of transportation needs occurring at the locations and times of the plurality of transportation needs. The transportation company determines which transportation vehicles are currently available. The company then determines a plan which includes some of the vehicles going to some of the locations at some of the times. This plan is based on the probabilistic model.

Abstract: An interactive algorithm and sequential methodology dynamically that pulls numerous organic data sets from online social, search, sentiment and paid media sources against a weighted formulation to determine with statistical significance a brand's market performance and characterization defined as a “Brand Attraction Score” in real time against key competitors. Consumer and media behaviors are measured using billions of data signals from multiple API sources distributed downstream through a series of influence (I) and exposure (E) weighted formulations to a master algorithm to determine the net performance and attraction scores and ranking. These statistical sets are then conformed into a series of scores and rankings in a predetermined competitive set in an Exposure to Attraction coordinate system, thereby allowing a Brand to easily visualize their comparative Attraction among their competitor brands.

Abstract: Systems and methods for simulating behavior of agents in a virtual environment are described. Observed customer behavior data for a retail space may be received. A model for customer behavior in the retail space is generated, the model including probabilities for customer responses to a plurality of stimuli. A virtual customer agent is built based on the model for customer behavior. A virtual retail space is built and modified, the modified virtual retail space including at least one different design feature from the virtual retail space. In the modified virtual retail space, the virtual customer agent is simulated performing a predetermined list of tasks based on the probabilities for the customer responses. Simulated customer behavior data, including responses of the virtual customer agent to the modified virtual retail space, may be generated based on the simulation.

Abstract: Provided is a process of coordinating dynamic on-demand logistics to deliver goods or services between geographically distributed heterogeneous sources of inventory and geographically distributed consumers at scales exceeding metropolitan areas of more than one million residents, with more than 10,000 users, more than 1,000 vehicle operators, and more than 10 geographically distributed sources of inventory.

Abstract: Techniques and arrangements for industry vertical classification of merchants using merchant signals, based, in part, on data obtained from payment activity. The techniques can include identifying one or more clusters using the data associated with the merchant and classifying and/or reclassifying the merchant within a cluster and then a class using the one or more identified clusters.

Abstract: A person's behavior monitoring device includes a processor for acquiring a captured image of each of a plurality of cameras, acquiring information relating to a person requiring special attention by analyzing the captured image, and generating a monitoring image including the information, in which the processor determines, for each of the cameras, whether or not a person detected from the captured image is a long-time stayer who stays for a long-time in a capturing area of one of the cameras based on a result of tracking the person, and superimposes and displays a person rectangle that enables identification of a degree of stay on the captured image in correspondence with a person corresponding to the long-time stayer.

Abstract: A data center information retrieval system includes a computer-executed device information retrieval application in communication with first and second devices configured in a data center. Each device includes one or more elements that provide a service for the data center. The application obtains and stores one or more first element records associated with one or more of the elements of the first device in a database, and communicates with a modular software component to obtain information associated with the corresponding one or more second elements of the second device, the modular software component translating information obtained about the second elements to a format similar to that of the first element records.

Abstract: Some embodiments provide a non-transitory machine-readable medium that stores a program. The program provides a client device a tool for configuring computational models. The program further receives, from the client device and through the tool, a selection of a set of external data sources. The program also receives, from the client device and through the tool, a plurality of weight values for a plurality of categories. The program further receives, from the client device and through the tool, a plurality of threshold values for the plurality of categories. The program also generates a plurality of computational models based on the set of external data sources, the plurality of weight values for the plurality of categories, and the plurality of threshold values for the plurality of categories.

Abstract: Systems, methods, and computer-readable media are disclosed for determining product attribute sequences using quantitative values and predicting product performance.

Abstract: At a network-accessible artificial intelligence service for time series predictions, a recurrent neural network model is trained using a plurality of time series of demand observations to generate demand forecasts for various items. A probabilistic demand forecast is generated for a target item using multiple executions of the trained model. Within the training set used for the model, the count of demand observations of the target item may differ from the count of demand observations of other items. A representation of the probabilistic demand forecast may be provided via a programmatic interface.

Abstract: An online system predicts, using a first targeting model, a first group of users as candidates to be in a targeting cluster, and predicts, using a second targeting model, a second group of users as candidates to be in the targeting cluster. The online system determines a first set of users that are not part of the first group of users, and a second set of users that are not part of the second group of users, and provides surveys to the first and second set of users. The online system determines a first subgroup of the first group of users and a second subgroup of the second group of users, and provides an ad preferences tool to the first subgroup and the second subgroup. The online system scores the first and second targeting models based in part on responses to the surveys and/or the ad preferences tools.

Abstract: A system for producing a customized beverage or beverage concentrate is disclosed. The system comprises a personalization server and a distribution machine communicatively coupled to the personalization server. The personalization server is configured to receive need and want information associated with a consumer, analyze the need and want information, apply a plurality of rules to the analyzed need and want information, and produce one or more customized beverage or beverage concentrate recipes based on the analysis of the need and want information and the application of the plurality of rules. The distribution machine is configured to receive the one or more customized beverage or beverage concentrate recipes from the personalization server and produce and deliver at least one customized beverage or beverage concentrate based on the one or more customized beverage or beverage concentrate recipes to the consumer by combining one or more beverage ingredients.

Abstract: A framework for improving user interfaces, and in particular for improving user interfaces for displaying and interacting with predictive analytics, is described herein. In one embodiment, a user interface template renders predictive models and enables visually interacting with data to discover hidden insights and relationships in the data. The user interface template determines, based on the metadata and data annotations, how to display the supplied data. By encapsulating complex code necessary to render predictive models and enable visually interacting with data, the amount of frontend code required to implement predictive analytic functionality is reduced, defect rates are reduced, while design consistency is improved.

Abstract: A computer system analyzes user sentiment to dynamically modify a communication session. One or more user interactions are captured during a communication session, wherein a machine learning model is updated based on the captured user interactions. A likelihood score of a user terminating the communication session before performing one or more desired actions is calculated. In response to determining that the likelihood score is above a threshold value, one or more queries are presented, during the communication session, to the user, wherein the one or more queries are selected using the machine learning model. Received user feedback is analyzed to determine a user sentiment. The communication session is dynamically modified based on to the user feedback and the user sentiment. Embodiments of the present invention further include a method and program product for analyzing user sentiment to dynamically modify a communication session in substantially the same manner described above.

Abstract: A method includes storing, at one or more data storage devices, a design in a platform-independent format. The method also includes generating, at a web front end, a GUI including a publish option associated with the design. The method includes sending the GUI to a client device. The method also includes receiving a user request indicating a selection of the publish option, and, in response to receiving the user request, generating first output based on the design, the first output having a HTML format. The method includes identifying a rendering engine based on browser information associated with the client device and generating second output by rendering the first output at the rendering engine, the second output having an image format. The method includes sending the second output to at least one of a data storage device of the data storage devices, a publishing endpoint, or the client device.

Abstract: The present disclosure relates to methods and associated systems for managing a plurality of device-exchange stations. The method includes, for example, (1) receiving empirical information regarding exchanges of energy storage devices from each of the plurality of device-exchange stations in an initial time period; (2) determining a target time period; (3) identifying a plurality of reference factors and associated weighting values based on empirical information regarding exchanges of energy storage devices; (4) determining demand information during the target time period for each of the plurality of device-exchange stations during the target time period for each of the device-exchange stations; and (5) forming a plurality of charging plans for each of the plurality of device-exchange stations according to demand information during the target time period.

Abstract: To promote a merchant's products on a social networking system, a promotion engine receives data from a merchant site regarding the merchant site's users' activities. The users' purchases of a promoted product are correlated with the user's activities performed in connection with a related product. An automated process running on a computer system then determines promotion criteria for the promoted product, based at least in part on the activities performed in connection with the related product. A promotion for the promoted product is generated and communicated to a social networking system, which displays the promotion to one or more users of the social networking system based on the determined promotion criteria.

Abstract: A method is provided that includes receiving a tenant identifier. The method also includes identifying a quality of service (QoS) policy associated with a tenant identified by the tenant identifier, by looking up the tenant identifier in a memory data structure. The QoS policy includes a threshold value of a performance parameter. The threshold value is a minimum or a maximum threshold value. The method also includes receiving a service request from the tenant. The method also includes determining an estimated value of the performance parameter in view of the request. The method also includes, responsive to successfully evaluating a validity condition with respect to the estimated value in view of the threshold value, forwarding the request to a servicing component for execution. The validity condition is provided by the estimated value not exceeding the maximum threshold value or the estimated value not falling below the minimum threshold value.

Abstract: Methods, systems and computer program products for identifying recurring series from transactional data are disclosed. An analytic server receives transactional data. The server reduces the transactional data to one or more series of transactions. The analytic server identifies one or more features in each series of transactions. The analytic server determines a respective recurrence score for each series of transactions based on training data. The recurrence score measures a likelihood that the series of transactions is a recurring series, in which transactions recur. The analytic server determines whether each series of transactions is a recurring series based on the respective recurrence score and a threshold. The analytic server predicts a future transaction based on the recurring series of transactions.

Abstract: A real-time fraud prevention system enables merchants and commercial organizations on-line to assess and protect themselves from high-risk users. A centralized database is configured to build and store dossiers of user devices and behaviors collected from subscriber websites in real-time. Real, low-risk users have webpage click navigation behaviors that are assumed to be very different than those of fraudsters. Individual user devices are distinguished from others by hundreds of points of user-device configuration data each independently maintains. A client agent provokes user devices to volunteer configuration data when a user visits respective webpages at independent websites. A collection of comprehensive dossiers of user devices is organized by their identifying information, and used calculating a fraud score in real-time. Each corresponding website is thereby assisted in deciding whether to allow a proposed transaction to be concluded with the particular user and their device.

Abstract: A system for enhancing speed and power operation of a sensor network is provided. The system includes an edge section disposed at an edge location and including a reservoir layer placed at the edge location. The reservoir layer has a set of reservoir nodes for performing edge computing by compressing time-series data by reducing a dimensionality of the time-series data using a random projection method. The compression of the time-series data reduces spatial redundancy and preserves a structure of the time-series data. The system further includes a datacenter section disposed at a datacenter location and including an output layer placed at the datacenter location. The output layer has a set of output nodes connected to the set of reservoir nodes for reconstructing the time-series data from the compressed time-series data, thereby enhancing speed and power operation of the sensor network.

Abstract: A method of enhancing a user interface of a network-based publication system based on seasonality scores associated with items featured in listings posted on the network-based publication system is disclosed. Seasonality data is generated for each of the items. The generating of the seasonality data includes identifying a season corresponding to transaction data pertaining to each of the items and storing the seasonality data in conjunction with the transaction data in a database. The season pertains to a selected user action that is to result in a presentation of a user interface on a device of the user. Seasonality scores are calculated and associated with the items featured in a subset of the listings that are candidates for inclusion in the presentation of the user interface. Relevancy scores are adjusted for each of the candidates and are incorporated into a presentation of the listings in the user interface.

Abstract: A charging station, such as, in particular, a charging column, includes an electrical connection for supplying current/voltage to the charging station, a charging connection for connecting at least one electrical energy store that is to be charged, and a thermal connection to a geothermal temperature control device for controlling the temperature of the charging station by geothermal energy.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to project ratings for future broadcasts of media. Disclosed example methods include normalizing, with a processor, audience measurement data corresponding to media exposure data, social media exposure data and programming information associated with a future quarter to determine normalized audience measurement data. Disclosed example methods also include classifying a media asset based on the programming information to determine a media asset classification.

Abstract: In one embodiment, a method includes generating a query based on a seed product offer that describes a product being offered for sale and executing the query, using a search engine that normalizes search terms in the query, on a plurality of product offers to determine candidate offers. The candidate offers are likely associated with the product. The method further includes determining one or more common attribute values across corresponding attributes of the candidate offers. The method additionally includes for each attribute value of each candidate offer, scoring the attribute value based on whether it matches one or more of the common attribute values, and updating a set of normalized attribute values for the product to include the attribute value based on whether the score is greater than a predetermined threshold.

Abstract: The system receives a set of load signals from an archive that contains historic load information gathered at various locations throughout an electrical grid, which distributes electrical power for the utility system. Next, the system applies a first difference function to the set of load signals to produce a set of difference signals. The system then performs a spike-detection operation on the set of difference signals to identify pairs of positive-negative and negative-positive spikes, which identify gaps in the set of load signals associated with periods of network disruption. Next, the system modifies the set of load signals by filling in each identified gap with projected load values determined by performing a localized loadshape forecasting operation based on the continuous load values immediately preceding the identified gap. Finally, the system forecasts electricity demand for the utility system based on the modified set of load signals.

Abstract: Systems and methods relating to generated printed products are provided. One system includes a transceiver configured to transmit commands to a printing press, the commands used by the printing press to execute print operations to generate printed products. The system further includes a processing circuit configured to receive data indicating a first amount of a printed product for a print operation. The processing circuit is further configured to determine a second amount of the printed product to be printed by modifying the first amount using a characteristic of the printed product. The processing circuit is further configured to transmit, using the transceiver, a first command to the printing press configured to cause the printing press to print the second amount of the printed product. In some implementations, a plant selection system determines where to print the product based on the amount to be printed and/or characteristics of the product.

Abstract: Some implementations may provide a method for conducting a marketing campaign, including: providing a user interface to a marketing professional; receiving, via the interface, input from the marketing professional prescribing a sequence of at least three steps for engaging at least one target customer, the sequence comprising: a start step corresponding to a beginning point for the at least one target customer to enter into the sequence, at least one end step corresponding to a finishing line for the at least one target customer to complete the sequence, at least one step for communicating information to the at least one target customer for the at least one target customer to progress through the sequence; subsequent to determining that the sequence of steps is valid, receiving an instruction from the marketing professional to launch the sequence; and in response to the received instruction, launching the sequence to conduct the marketing campaign.

Abstract: A dynamic supply chain planning system for analysis of historical lead time data that uses machine learning algorithms to forecast future lead times based on historical lead time data, weather data and financial data related to locations and dates within the supply chain.

Abstract: Disclosed are systems and methods for identifying location-based information associated with a product on a web page. The method may include: detecting user navigation by the user of the web page; detecting the at least one product on the web page; identifying one or more merchants having the detected at least one product in stock; determining a user location of the user; determining the identified one or more merchants having the detected at least one product in stock and having a location within a predetermined distance of the user location; generating a list of merchants, the list including the determined one or more merchants having the detected at least one product in stock and having the location within the predetermined distance of the user location; and executing a browser extension to display, on the web page associated with the at least one product, the generated list of merchants.

Abstract: For modeling consumer activity, a plurality of processor computational resources generates potential model types. In addition, the plurality of processor computational resources divides activity data into a training data set, a test data set, and a validation data set. The plurality of processor computational resources further trains the potential model types with the training set data. In addition, the plurality of processor computational resources selects a model type with the test data set. The plurality of processor computational resources calculates algorithmic parameters with the validation data set.

Abstract: A system and method for optimizing at least one of a promotion, a targeting of the promotion, and a campaign associated with the promotion. Acceptances of the promotion are received following each user's selection of the promotion. Information representing users is received from publisher computing devices. Thereafter, respective match keys are generated that are usable to access information representing transaction accounts of each of the users. The match keys are transmitted computing device(s) having access to information representing transaction accounts. Information representing a selected one account is received. For users who redeemed the promotion, the promotion is associated with the selected one transaction account.

Abstract: The amount and variety of data being generated is becoming too extreme for many computing systems to process, and is even more difficult for information systems to provide relevant data to users. A distributed computing system is provided that includes server machines that form a data enablement platform. The platform includes: a plurality of data collectors that stream data over a message bus to a streaming analytics and machine learning engine; a data lake and a massive indexing repository for respectively storing and indexing data; a behavioral analytics and machine learning module; and multiple application programming interfaces (APIs) to interact with the data lake and the massive indexing repository, and to interact with multiple applications. The multiple applications are command cards, and each command card includes a directive module, a memory module, search bots, and behavior bots that operate at least within the data enablement platform.

Abstract: A method and system determining node order fulfillment performance considering cancelation costs. The method includes receiving a current order for fulfillment node assignment and calculating a cancelation ratio of a node of a plurality of nodes by dividing orders canceled due to back order from the node by orders scheduled from the node collected from a pre-assigned time period. The method also includes determining a cancelation cost of the node based on the cancelation ratio of said node. The method then includes automatically generating a node order assignment based on the determined cancelation cost for fulfillment of a current order.

Abstract: Virtualization methods and systems for optimizing the availability of items in an inventory of items in a reservation system. The items are classified into item types and an item type is defined by a requestable set of at least one characteristic. Reservations may be received for a set of at least one characteristic that is a subset of an item type. After a reservation has been accepted, all the availabilities of the requestable sets of at least one characteristic in the inventory are updated. The reservation system may be a hotel reservation system and item types may be hotel room types or other bookable products. The reservation system may be a flight reservation system and item types may be bookable places on flights.

Abstract: A system for fulfillment & optimization. The system includes an optimization engine that executes scenario simulations, wherein the scenario simulations generate pick information. The optimization engine selects a best scenario from at least two scenarios based on the scenario information. In response to the selection of the best scenario, the optimization engine configures a computing system to execute a zoning policy, a routing policy, and a base algorithm policy associated with the best scenario. The computing system executes the zoning policy, the routing policy, and the base algorithm policy to fulfill orders.

Abstract: The present invention provides a method for forecasting load and managing a control plan for households having electric appliances wherein the control plan determines the activation of the electric appliances at pre-defined control periods.

Abstract: A method for selectively providing a learned model using a learned model providing device includes saving various learned models and model information associated with a generation environment in a database of the learned model providing device. The generation environment indicates an environment where sensing data used for generating each of the learned models is sensed. The method further includes acquiring needs information associated with a use environment of a user side device, and selecting one of the learned model suitable for the needs information by referring to the model information by a processor of the learned model providing device.

Abstract: In one embodiment, a method is provided. The method includes receiving forecast information from sales people in a computer. The method further includes receiving comments on specific entries of the forecast information from non-sales people in the computer. The method also includes receiving changes of the forecast information from the non-sales people in the computer. The method additionally includes providing a display of the comments and the changes to the sales people in an interface to the computer.

Abstract: A method and system for evaluating node fulfillment capacity in node order assignment. The method includes receiving by a network average capacity utilization cost module an electronic record of a current order. The method includes retrieving data of a plurality of nodes, calculating an actual capacity utilization on an expected date, and determining a probability of backlog on the expected date. The method includes generating a network average capacity utilization cost model, automatically converting a regular labor cost or a overtime labor cost into a capacity utilization cost, and transmitting the capacity utilization cost of each node to an order fulfillment engine. The method includes receiving by the engine the current order, the processing cost data, and the capacity utilization cost. The method includes automatically calculating a fulfillment cost and identifying a node with the lowest fulfillment cost for assignment.

Abstract: An onboard vehicle communication system includes a first ECU configured to manage charge information of a vehicle, a gateway connected to the first ECU, a second ECU connected to the gateway, an onboard vehicle communication device configured to communicate with the outside of the vehicle, and a local bus that connects the first ECU and the onboard vehicle communication device. The first ECU is configured to transmit charge information of the vehicle to the onboard vehicle communication device via the local bus when an external charge device is charging a vehicle.

Abstract: Techniques described herein include a method and system for item demand forecasting that utilizes machine learning techniques to generate a set of quantiles. In some embodiments, several item features may be identified as being relevant to an item forecast and may be provided as inputs to a regression module, which may calculate a set of quantiles for each item. A set of quantiles may comprise a number of confidence levels or probabilities associated with calculated demand values for an item. In some embodiments, costs associated with the item may be used to select an appropriate quantile associated (e.g., based on a corresponding confidence level). In some embodiments, an item demand forecast may be generated based on the calculated demand value associated with the selected quantile. In some embodiments, one or more of the item may be automatically ordered based on that item demand forecast.

Abstract: A method and system for evaluating node fulfillment capacity in node order assignment. The method includes receiving by a network average capacity utilization cost module an electronic record of a current order. The method includes retrieving data of a plurality of nodes, calculating an actual capacity utilization on an expected date, and determining a probability of backlog on the expected date. The method includes generating a network average capacity utilization cost model, automatically converting one or more of a plurality of costs and capacity utilization into a capacity utilization cost, and transmitting the capacity utilization cost of each node to an order fulfillment engine. The method includes receiving by the engine the current order, the processing cost data, and the capacity utilization cost. The method includes automatically calculating a fulfillment cost and identifying a node with the lowest fulfillment cost for assignment.