Abstract: A system for retrieving products in response to a customer query includes a computing device configured to obtain query information characterizing a query initiated by the customer on an ecommerce marketplace and to determine embedding-based search results comprising a first list of items. The computing device is also configured to obtain legacy search results comprising a second list of items and to blend the embedding-based search results with the legacy search results to obtain blended search results. The computing device is also configured to send the blended search results to the customer.

Abstract: Systems and methods for generating dynamically definable gift objects are provided. A gift service may train a gift object algorithm and a gift selection algorithm using sample datasets. A gift request may be received and the gift service may generate a gift object with an undefined set of gift object using the gift object algorithm. A redemption request may be received and the gift service may generate a custom set of gift selection options using the gift selection algorithm in response to the redemption request. A selection from the custom set of gift selection options may be received and the gift object algorithm and the gift selection algorithm may be updated based on the redemption request, the custom set of gift selection options, and the selection.

Abstract: Techniques described herein are directed to e-commerce tags in multimedia content. In an example, multimedia content is received that includes a representation of an item offered for sale by a merchant. A user profile of the viewer is determined. Identifying information including customized item details are generated based on the user profile. The identifying information is sent to a different application (on a same device or different device as the device that is playing the multimedia content), which allows for linkage of a merchant profile and user profile and enables payment for the item.

Abstract: Techniques described herein include systems and methods for utilizing a shopping list generated by a user in one or more shopping list features. A list of items including keywords not associated with specific items may be received. A user interface may be updated to present the list of items, with a first area of the user interface corresponding to uncompleted tasks associated with a keyword of the list, and a second area corresponding to completed tasks associated with a keyword of the list. One or more sensors may receive information about an item. Input about an interaction with the user interface and a keyword of the list may be received. The user interface may be updated to move the keyword of the list from the first area to the second area. A mapping of the keyword to the item may be updated by a computer system.

Abstract: Purchase history data is used to automatically create links within a data repository between product sold via an electronic vendor system and a plurality of shopping carts. When a customer performs a search for product, the vendor system queries the data repository to retrieve the plurality of shopping carts that have been linked to the product that is associated within the data repository to the search request. A plurality of customer interface elements, each corresponding to a one of the plurality of shopping carts, is then presented as a result to the search query. A selection of a one of the customer interface elements causes the vendor system to add one or more of the product to the corresponding one of the plurality of shopping carts.

Abstract: A computer-implemented method, comprising receiving an order associated with a user, and capturing information associated with a physical attribute of the user; for the order being completed, performing a matching operation on the physical attribute of the user and information associated with a region of the user that includes the physical attribute of the user and respective physical attributes of other users, to determine a closest match; and generating an output that identifies the user associated with the closest match in the information associated with the region of the user, and providing the output to a server to deliver the order to the user.

Abstract: Various embodiments are directed to a system for automatically and dynamically facilitating various transactions via a hyperlocal marketplace. A smart home system, for example, may track all perishable items within the home. Any items expected to have a surplus may be offered for sale to other homes in the hyperlocal marketplace. Any items expected to have a shortage may be identified and made known to the other homes in the hyperlocal marketplace. Bids may be made on the shortage items that may be offered for sale by the marketplace.

Abstract: A client device obtains a request from a user to retrieve makeup information from a cloud server and obtains a digital image of a facial region of the user. The client device transmits the digital image to initiate a communication session with the cloud server without obtaining login credentials from the user, wherein the cloud server retrieves a makeup session packet by matching the transmitted digital image with one of a plurality of digital images in the cloud server and transmits the makeup session packet comprising a corresponding selection of cosmetic products. The client device receives the makeup session packet and extracts the selection of cosmetic products by the client device and generates a user interface displaying the selection of cosmetic products. The client device performs virtual application of the selection of cosmetic products onto the facial region of the user.

Abstract: Provided herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for using computer technology to automate the creation of consistent, high quality listings for selling “for sale objects” (FSO) on an ecommerce site. Some embodiments are configured to or operate by: identifying a category of a FSO; accessing templates for the category from a template database; navigating a user through a computer generated augmented reality (AR) environment using the templates to generate images of the FSO; analyzing one or more of the images to determine characteristics of the FSO; and generating a listing for the FSO using the images and the characteristics.

Abstract: In one embodiment a finite rank deep kernel learning method includes: receiving a training dataset; forming a plurality of training data subsets from the training dataset; for each respective training data subset of the plurality of training data subsets: calculating a subset-specific loss based on a loss function and the respective training data subset; and optimizing a model based on the subset-specific loss; determining a set of embeddings based on the optimized model; determining, based on the set of embeddings, a plurality of dot kernels; combining the plurality of dot kernels to form a composite kernel for a Gaussian process; receiving live data from an application; and predicting a plurality of values and a plurality of uncertainties associated with the plurality of values simultaneously using the composite kernel.

Abstract: Systems and techniques are disclosed for accessing accounts associated with a user and estimating a value of an attribute associated with the user based upon the retrieved account information. Transaction data associated with an account at an external user account system is received. The transactions are categorized into transaction groups. For each transaction group, a confidence value that the group is associated with the attribute is estimated, based at least in part upon a distribution of transaction amounts for the transactions of the group over a time period associated with the group. An attribute value is estimated for each group, based at least in part upon the transaction amounts of the transaction of the group. In addition a value of the attribute for a future time period may be predicted based upon the transaction groups.

Abstract: A computer-implemented data processing system comprises account management logic, workflow logic, and interface logic. The account management logic is configured to manage financial accounts associated with a plurality of users. The workflow logic is configured to identify workflow items to be acted upon by users in connection with financial transactions relating to the financial accounts. The interface logic cooperates with the workflow logic to generate a plurality of display screens to be displayed by wireless handheld mobile devices. The display screens comprise a home page screen that is provided to the user upon login and that includes a link to a workflow screen where the user may act upon one or more of the workflow items.

Abstract: Work support system and method with screen sharing and development system for multi-platform application disclosed. The work support system with screen sharing includes a customer terminal in which a service application is installed and executed, an employee terminal configured of sharing and displaying a designated area of an execution screen of the service application, and a work support server configured of communicating with the customer terminal and the employee terminal, and supporting a customer work by setting a screen of the customer terminal to be shared in the employee terminal under a specified condition.

Abstract: A computer-implemented method includes providing an electronic loan application form to the graphical user interface displayed in the client device, receiving loan application data from the client device, and pre-approving a user for a lending product to form a pre-approved lending product. The loan application data includes user inputs provided via the electronic loan application form. The computer-implemented method further includes providing selectable lending product features via the graphical user interface displayed in the client device, where each of the selectable lending product features relates to one or more lending products. At least one of the one or more lending products is the pre-approved lending product.

Abstract: System, apparatus, user equipment, and associated computer program and computing methods are provided for facilitating efficient decision-making with respect to a subject entity. In one aspect, a labeled training dataset containing N records respectively corresponding to N entities is provided for training a decision engine based on performing supervised learning. Responsive to receiving a plurality of attribute values for the subject entity requiring a decision relative to an estimate of a performance variable based on at least a portion of the attribute values, the trained decision engine is configured to determine a decision score as a function obtained as a set of linearly decomposed constituent components corresponding to the attribute values of the subject entity, thereby effectuating an objective determination of which attributes contribute to what portions of the decision score in a computationally efficient manner.

Abstract: Systems and methods for processing items in a queue, a system including one or more memory devices storing instructions and one or more processors configured to execute the instructions to perform operations including: analyzing training data to build a predictive model; applying the predictive model to items in a queue to determine scores of the items based on respective probabilities of an entity completing an action for each item; listing the items, sorted by the scores, in a first display view; identifying a first and a second item, respectively having highest and next highest scores; grouping, with each of the first and second items, items that satisfy a grouping condition based on characteristic information of the items; and listing the groups of items including the first and second items, sorted based on the scores of the first and second items, in a second display view.

Abstract: A system and method are provided for presenting trading information. One example method includes displaying a plurality of effective trade indicators corresponding to price levels at which effective trades have been initiated, and displaying trading information corresponding to each effective trade. The effective trades can be determined based on user-configured trade definitions. The trading information can include a traded quantity and profit/loss corresponding to each effective trade. In addition to the trading information, current market information could be displayed as well in relation to the plurality of effective trades.

Abstract: Aspects of the disclosure describe systems and methods for handling a loss involving an insured vehicle. A total loss evaluation and handling system receives vehicle telematics data from a vehicle telematics device that monitors the vehicle. The total loss evaluation and handling system determines that a loss involving the vehicle has occurred, and a total loss evaluator selects a set of total loss rules configured to determine whether the loss is a total loss. The total loss evaluator applies the total loss rules selected to the vehicle telematics data received and determines whether the loss is a total loss based on the total loss rules applied. A total loss handler obtains an estimated value of the vehicle and generates a settlement amount based on the estimated value. The total loss handler initiates a payment corresponding to the settlement amount as settlement for the total loss.

Abstract: According to various embodiments, trades may be filled based at in part on order price and fill rates determined for providers of orders. In some embodiments, orders at a given price in an order book may be ordered in order of decreasing fill rate, such that orders associated with a higher fill rate (or higher probability of fill) are preferenced above orders associated with a lower fill rate. In some embodiments, order books may also be ordered based in part on response times from order providers. For example, orders in an order book may be ordered according to an algorithm that preferences higher fill rates and shorter response times ahead of orders with lower fill rates and longer response times. Order book ordering algorithms may also consider order quantity and interdependence and duplication of order quantity.

Abstract: The Multiple Modular Asset Class Constructor Apparatuses, Methods and Systems (“MMACC”) transforms collateralized equity obligation structure parameters, asset search, tranche selections inputs via MMACC components into asset income distribution message, principal distribution message outputs. In one embodiment, the MMACC is an apparatus, with a memory having a component collection, including: a capital structure component, a preferred share class component, and a common share class component. The MMACC also has a processor to issue instructions from the component collection including instructions to obtain a capital structure input via said capital structure component from a system user and determine a preferred share class allocation via said capital structure input and said preferred share class component.

Abstract: A structural analysis computing device may generate a proposed insurance claim and/or generate a proposed insurance quote for an object pictured in a three-dimensional (3D) image. The structural analysis computing device may be coupled to a drone configured to capture exterior images of the object. The structural analysis computing device may include a memory, a user interface, an object sensor configured to capture the 3D image, and a processor in communication with the memory and the object sensor. The processor may access the 3D image including the object, and analyze the 3D images to identify features of the object—such as by inputting the 3D image into a trained machine learning or pattern recognition program. The processor may generate a proposed claim form for a damaged object and/or a proposed quote for an uninsured object, and display the form to a user for their review and/or approval.

Abstract: A system for generating and managing usage-based insurance contracts configured to (i) store a plurality of offers for sharing transactions, where each of the plurality of offers includes an item being offered and an associated offerer; (ii) receive a selection from a buyer of an offer that is accepted by the buyer of the plurality of offers; (iii) automatically generate a usage-based insurance contract for the sharing transaction based on the offer; and (iv) transmit the insurance contract to at least one of the buyer and the associated offerer.

Abstract: Systems and methods are disclosed with respect to using a blockchain for managing the subrogation claim process related to a vehicle collision, in particular, utilizing evidence oracles as part of the subrogation process. An exemplary embodiment includes receiving recorded data from one or more connected devices at a geographic location; analyzing the recorded data, wherein analyzing the recorded data includes determining that an collision has occurred involving one or more vehicles; generating a transaction including the data indicative of the collision based upon the analysis; and transmitting the transaction to at least one other participant in the distributed ledger network.

Abstract: A method and system for handling data field tasks, the system comprising a database containing records and data fields associated with real estate ownership expense insurance policies that reimburses for increases in property ownership expenses including increases in maintenance fees and assessments from non-covered losses, an underwriting server communicatively coupled to one or more client devices and data sources over a communications network, the underwriting server comprising a processor that configures processes to the data sources and generates data source connections to receive information from the data sources, and a scheduler that allocates threads within the processes to at least one of the data fields associated with premium for coverage, expenses, and reimbursement of the real estate ownership expense insurance policies, and assigns the threads to tasks for performing operations on the at least one of the data fields based on the information from the data sources.

Abstract: A computer-implemented system and method for managing and visualizing financial transaction data is disclosed. Rows of financial data are managed as data objects with a reorganizable node tree hierarchy. A user interface visualization system supports an interactive user interface with a client device. In some implementations, a user may reorganize the node hierarchy, define dimension, communicate on a node-based basis, and assign directly responsible individuals to nodes.

Abstract: A method begins by a drive unit affiliated with farm equipment receiving data from the farm equipment to produce agricultural data. The method continues with the drive unit determining a filtering constraint based on one or more parameters selected from a plurality of lists of agricultural parameters and filtering the agricultural data based on the filtering constraint to produce filtered agricultural data. The method continues with the drive unit determining processing of the filtered agricultural data and executing the processing of the filtered agricultural data.

Abstract: A distributed ledger based utility system architecture may be configured to enable secure payments, data transmission, and meter configuration of smart sensors. The utility system architecture may be a tiered architecture including multiple nodes at different levels of the architecture where each level may contain a different portion of the distributed ledger. As information is added to the distributed ledger, each portion of the distributed ledger may be updated based on whether the information is relevant to that node. The information may include rate contract transactions, meter configuration data transactions, payment transactions, or the like.

Abstract: In general, intelligent fuel dispensers are provided. In at least some implementations, an intelligent fuel dispenser can determine customer identities and/or other characteristics and provide customized fueling sessions based on the determined customer identities and/or other characteristics. In at least some implementations, the fuel dispenser includes a touchless interface allowing customers to complete fueling sessions with minimal physical contact with the fuel dispenser.

Abstract: In general, intelligent fuel dispensers are provided. In at least some implementations, an intelligent fuel dispenser can determine customer identities and/or other characteristics and provide customized fueling sessions based on the determined customer identities and/or other characteristics. In at least some implementations, the fuel dispenser includes a touchless interface allowing customers to complete fueling sessions with minimal physical contact with the fuel dispenser.

Abstract: Some embodiments include a computer-implemented method of providing a computer system including a processor and access to at least one coupled source of real estate records. A storage medium includes program logic that when executed by a coupled processor, causes the computer system to access or exchange data with a realty database of real estate property data. The execution of program logic by an application programming interface results in upload and/or download of real estate property data to or from a realty database. An event engine is executed to manage an open house event of property including scheduling of a date and time of the open house event, and the scheduling of a prospective buyer. A statistics engine is executed to record open house real estate data including attribute data of the prospective buyer prior to and/or during an open house event.

Abstract: A method for agricultural land parcel valuation includes: accessing data for parcels within a prescribed region, the data comprising management practices, historical weather conditions, locations and topography, remote sense images, soil types, and crop types; assessing and ranking the management practices for each of the parcels; generating simulation inputs for the each of the parcels, where the simulation inputs comprise highest ranked management practices, the historical weather conditions, the locations and topography, the soil types, and the crop types; simulating crop growth for the each of the parcels over a prescribed number of previous years, where the simulating employs the simulation inputs provided by the generating; and employing selected outputs from the simulating to calculate agricultural metrics and a valuation corresponding to the each of the parcels, where the agricultural metrics include a stability metric.

Abstract: Systems, methods, and graphical user interfaces for the management and coordination of patent infringement-related analyses, such as freedom-to-operate, patent clearance, and enforcement, are provided. Patent claim information is extracted and presented to users along with purpose-specific workflows that facilitate the capture and presentation of work product on both a claim-by-claim level as well as on a document level. Integrated data management facilitates access to historical work product by interconnecting the various record entities of the system including product information, patent document information, review information, and work product information.

Abstract: A platform receives transaction information for an entity, where the transaction information identifies a plurality of transactions associated with the entity, and receives entity information associated with the entity. The platform identifies, using a first model, a selected set of transactions based on the transaction information and the entity information, where the first model outputs information identifying the selected set of transactions based on the selected set of transactions being associated with an event, a theme, or a transaction parameter. The platform determines, using a second model, potential modifications to a document based on the selected set of transactions, where the second model receives the information identifying the selected set of transactions or information identifying the event, the theme, or the transaction parameter, and where the second model outputs information identifying the potential modifications.

Abstract: A device receives image data of a contractual document that includes an offer including terms of a proposed transaction, converts the image data to text data that identifies text within the contractual document, and receives preferences information for a recipient of the offer. The device identifies key terms within the contractual document by using term identification to analyze the text. The key terms may include a first key term that identifies subject matter of the proposed transaction and other key terms that are part of the offer. The device determines term scores that correspond to likelihoods of the other key terms being favorable to the recipient by using a data model to analyze the key terms and the preferences information. The device, based on the term scores, generates and provides another device with a recommendation to be used in determining whether the accept the offer.

Abstract: Systems and methods to process many power line-down reports. A number of power line-down reports are received from different devices operated by users that specify the location of its device. Based on locations of devices sending the reports, a related set of power line-down reports is determined that likely report a particular power line-down condition. Based on those locations and power line location information, a location of the particular power line-down condition is determined that is a location of a power line that is closest to all locations in the related reports. Based on the related set of reports, a consolidated power line-down report is created with data associated with the particular power line-down condition. The consolidated power line-down report is reported to a power grid trouble report system.

Abstract: Systems, apparatus, and methods for transacting, recording, validating and/or verifying agricultural products. The 2018 Farm Act rescinded industrial hemp from Schedule I of the Controlled Substances Act (CSA). Although industrial hemp has a variety of uses, the Government's biggest concern is the ingestion of tetrahydrocannabinol (THC) and cannabidiol (CBD). Commercial regulation typically balances a variety of factors: e.g., consumer protection, regulatory overhead, market competition, tax revenue, public policy, etc. In contrast, law enforcement has a singular purpose, and may go to extraordinary lengths to stop criminal activity. Various embodiments described herein provide a blockchain ledger-based supply chain that allows many commercial and regulatory entities to independently cooperate. Every transaction is permanently and transparently recorded within a chain-of-custody; the chain-of-custody enables a traceability. A variety of new applications are enabled by the blockchain ledger-based supply chain.

Abstract: Described is a digitized mail control system. The system may include a server having a memory storing mail data associated with a user and a user computing device coupled to the server. The server may be programmed to receive an access signal from the user computing device that has accessed the system. In response to receiving the access signal, the server may process the user data and locate the stored mail data associated with the user data. The server may then create and send for execution on the user computing device instruction to display mail data including sender information and action buttons associated with predetermined actions to take in response to the sender information. The server may receive a signal including a selected action associated with a selected action button with regard to a selected sender and automatically execute program code corresponding to the selected action.

Abstract: Feedback information is an important aspect in all machine learning systems. In robot systems that are picking objects from a plurality of objects this has been arranged by acquiring images of objects that have been picked. When images are acquired after picking they can be imaged accurately and the information about picking and also dropping success can be improved by using acquired images as a feedback in the machine learning arrangement being used for controlling the picking and dropping of objects.

Abstract: A generalizable and interpretable deep learning model for predicting biomarker status and biomarker metrics from histopathology slide images is provided.

Abstract: A hardware accelerator for computing integral image values of an image is provided that includes a plurality of row computation components configurable to operate in parallel to compute row sum values of respective rows of a row block of the image. The hardware accelerator is further configured to compute integral image values for the row block using the row sum values and block pivots.

Abstract: In various examples, a signal processing pipeline is dynamically generated or instantiated for a signal processing request. To generate the pipeline, a graph topology—including nodes and edges—may be created to represent features, functionality, and characteristics of a signal processing system. The nodes, representing processing tasks, may be connected via edges having associated costs for performing, by a node, a processing task on an output of a prior or edge-connected node. For a given signal processing request, the nodes or processing tasks to be included may be selected and, using a graph routing algorithm and the costs between and among the determined nodes, a path through the nodes may be determined—thereby defining, at least in part, the signal processing pipeline.

Abstract: A method that includes accessing a frame buffer of a graphics processing unit (GPU), analyzing, in the frame buffer of the GPU, a frame representing a section of a stream of displayed data that is being displayed by a first device, identifying a reference patch that includes a unique identifier associated with secondary digital content that is insertable in the displayed data, the unique identifier including encoded data that identifies the secondary digital content, retrieving the secondary digital content from the remote device via the data communication network based on the unique identifier and a device parameter of the first device, and overlaying the secondary digital content into the displayed data in accordance with the display parameters of the customized secondary digital content.

Abstract: Disclosed herein are system, method, and computer program product embodiments for modifying graphics rendering by transcoding a serialized command stream. An embodiment operates by receiving a command configured to instruct an API to render a graphics element. The embodiment further operates by generating, based on the command, a transcoded command configured to instruct the API to render a modified graphics element by applying a set of modification factors to a portion of the command. Subsequently, the embodiment operates by transmitting the transcoded command to the API.

Abstract: Systems, computer-implemented methods, apparatus and/or computer program products are provided that facilitate improving the accuracy of global positioning system (GPS) coordinates of indoor photos. The disclosed subject matter further provides systems, computer-implemented methods, apparatus and/or computer program products that facilitate generating exterior photos of structures based on GPS coordinates of indoor photos.

Abstract: Provided is a display apparatus including an image forming optical system configured to form an image to be displayed, an eyepiece optical system configured to provide the image formed by the image forming optical system to a pupil of an observer, and an image shifting optical system disposed on an optical path between the image forming optical system and the eyepiece optical system, the image shifting optical system being configured to shift the image formed by the image forming optical system in a direction perpendicular to an optical axis, wherein the image shifting optical system includes a first optical member having a first focal length and a second optical member having a second focal length, and wherein a distance between the first optical member and the second optical member along the optical axis is equal to a sum of the first focal length and the second focal length.

Abstract: The technical problem of removing an object depicted in a selected region of an image to create a natural-looking edited image is addressed by providing systems, methods, and computer-readable storage media to perform automatic image inpainting. The method includes replacing the selected region using a color mask. A color mask can be generated using a mean color of pixels from a portion of the image that is distinct from and outside of the selected region.

Abstract: Examples disclosed herein obtain first image data and the second image data for a foveated image frame to be displayed on a display, the first image data to have a first resolution and the second image data to have a second resolution lower than the first resolution. Disclosed examples also up-sample the second image data based on first metadata to generate up-sampled second image data, the up-sampled second image data to have the first resolution, and combine the first image data and the up-sampled second image data based on second metadata. Disclosed examples further perform, based on third metadata, a combination of at least two different filter operations on an overlap region including a portion of the first image data and a portion of the up-sampled second image data to generate the foveated image frame, the third metadata to specify a width in pixels of the overlap region.

Abstract: An image capturing apparatus and a method for depth of filed (DOF) adjustment in images based on time of flight (TOF) depth maps is provided. The image capturing apparatus includes an image sensor and circuitry. The circuitry generates a TOF depth map of a scene that includes a plurality of objects. The TOF depth map includes information associated with distances between the image sensor and surfaces of the plurality of objects. The circuitry divides the TOF depth map into a plurality of regions that corresponds to at least one object of the plurality of objects. The circuitry determines a region of interest from the plurality of regions and adjusts the DOF of the at least one object associated with the determined region of interest. The circuitry further controls the image sensor to capture an image of the scene based on the adjusted DOF.

Abstract: This disclosure relates to various implementations that dynamically adjust one or more shallow depth of field (SDOF) parameters based on a designated, artificial aperture value. The implementations obtain a designated, artificial aperture value that modifies an initial aperture value for an image frame. The designated, artificial aperture value generates a determined amount of synthetically-produced blur within the image frame. The implementations determine an aperture adjustment factor based on the designated, artificial aperture value in relation to a default so-called “tuning aperture value” (for which the camera's operations may have been optimized). The implementations may then modify, based on the aperture adjustment factor, one or more SDOF parameters for an SDOF operation, which may, e.g., be configured to render a determined amount of synthetic bokeh within the image frame.

Abstract: This disclosure provides systems, devices, apparatus, and methods, including computer programs encoded on storage media, for configurable aprons for expanded binning. Aspects of the present disclosure include identifying one or more pixel tiles in at least one bin and determining edge information for each pixel tile of the one or more pixel tiles. The edge information may be associated with one or more pixels adjacent to each pixel tile. The present disclosure further describes determining whether at least one adjacent bin is visible based on the edge information for each pixel tile, where the at least one adjacent bin may be adjacent to the at least one bin.