Abstract: Techniques described herein include providing payment and access infrastructure for an array of transportation services, such as a set of transit or mobility services that might be provided by one or more governments, public agencies, and/or other public entities. In one example, this disclosure describes a method that includes enabling, by a computing system, a user to register for mobility benefits using a verification system, wherein the mobility benefits are provided by a provider entity; receiving, by the computing system and from the verification system, information about the user; establishing, by the computing system, an account linked to the provider entity; detecting, by the computing system, a request to access mobility benefits; allocating, by the computing system, funds from the account to pay for the mobility benefits.

Abstract: Systems and methods for providing a merchant-customer engagement system include a physical merchant location in which a customer may be tracked to determine products within the physical merchant location that the customer is interested in. A merchant may use a wearable merchant device that is configured to identify the customer via a camera that captures an image of the customer, and that image may be used to retrieve customer account information for that customer. Using the customer account information and the products that the customer is showing interest in, the wearable merchant device may be used to display merchant-customer engagement information next to a view of the customer to allow the merchant to help the customer while utilizing a variety of displayed information about the customer including, for example, past purchases, products browsed in-store and previously browsed online, time spent in an area of the physical merchant location, etc.

Abstract: A system may receive, from a client device, a user input indicating a product that is to be listed for sale via an online marketplace, and may transmit an instruction for the client device to capture a video of the product from a set of multiple perspectives including a reference perspective. The system may receive the video of the product, where the video includes a set of multiple image frames depicting the product from the set of multiple of perspectives. The system may extract a subset of image frames of the set of multiple of image frames that depict the product from one or more cardinal views, where the one or more cardinal views are determined relative to the reference perspective. The system may then generate an item listing for listing the product for sale via the online marketplace, where the item listing includes the subset of image frames.

Abstract: An online concierge system generates an item graph connecting item nodes with attribute nodes of the items. When the online concierge system receives a search query to identify one or more items from a customer, the online concierge system parses the search query into combinations of terms and identifies item nodes and attribute nodes related to the search query. The online concierge system may determine that no item nodes meet presentation criteria. The online concierge system may determine that a reformulated search query has a higher conversion probability than the search query received from the customer. The online concierge system reformulates the search query. The online concierge system selects item nodes as search results. The online concierge system transmits the search results to the customer.

Abstract: Techniques are disclosed relating to item representations. A computer system may access information identifying a first set of items and generate a representation of the first set of items that positions them in an embedding space. The computer system may send a request to another computer system for information pertaining to an item selected from the first set of items and receive correlation information that identifies recorded user behavior indicative of correlations between a second set of items and the selected item. The computer system may update the representation based on the correlation information, such that at least one of the first set of items that is included in the second set is moved closer to the selected item in the embedding space and at least one of the first set of items that is not included in the second set is moved farther away from the selected item.

Abstract: The technology involves a personalized recommender system that can be used with an e-commerce platform. It employs a contrastive learning based cross-domain recommendation approach. The approach balances the learning of user behaviors within each domain, as well as user behaviors across multiple domains. To achieve robust user representations and to improve knowledge transfer between the source and target domains, multi-task intra-domain contrastive regularizations may be employed along with multiple branches of sequential attentive encoders in a model for cross-domain sequential recommendation. Different data augmentation approaches can be used to generate augmented data for contrastive learning. For instance, different data augmentation methods may be combined with recommendation optimization in a multi-task learning paradigm. An optimized sequence representation may be fine-tuned in a next-value prediction task for recommendation in a target domain.

Abstract: Methods, systems, and apparatuses are described herein for providing purchase recommendations by analyzing social networks using machine learning. A machine learning model may be trained to select one or more of the first plurality of users. Purchase intention data that indicates an intention of a first user to acquire a type of asset may be received. Social networking data that comprises a plurality of associations between a second plurality of users may be received. Purchase history data indicating one or more purchases, of one or more assets associated with the type of asset, made by the second plurality of users may be received. The trained machine learning model may be provided the data. In return, the trained machine learning model may provide an indication of a second user. A notification may be sent to the second user.

Abstract: The present invention provides a hierarchy-based search system and method primarily used to shop for products (including services as well). The system includes either multiple rows or multiple columns arranged as user-selectable tiles (including buttons) that together incorporate hierarchies of product abstraction which include, from a broadest meta (large) product categories, to one or more granular (specific) product categories. Then, as a user searches for a product or service, that search and the results of the search are augmented by user-selectable tiles that further limit/filter the displayed search results such that only results consistent with the category selection are displayed to the user. Accordingly, a natural sequence of purchasing choice selection decisions is presented to the user so that they can more naturally narrow shopping choices and make faster, better purchasing decisions.

Abstract: A method for generating a related product interface portion in an electronic user interface based on user-generated text includes identifying, for each product of a plurality of products, one or more respective characteristics from end user-generated text associated with the product, whereby a plurality of characteristics are identified for the plurality of products. The method further includes determining a plurality of characteristic groups, each group comprising two or more of the plurality of characteristics, wherein the characteristics within a group are similar to each other; receiving, from a user through the electronic user interface, an input related to a product category; and in response to receiving the user input, generating and presenting the related product interface portion that includes a respective product from each of the two or more of the characteristic groups related to the category.

Abstract: In some implementations, a device may obtain an input that identifies a device type. The device may obtain, based on the input, information indicating a configuration associated with the device type. The device may determine, using a plurality of machine learning models respectively associated with a plurality of memory types, compatibilities between the plurality of memory types and the device type based on the configuration associated with the device type. Each of the plurality of machine learning models may be trained to determine a compatibility of a respective memory type, of the plurality of memory types, with a given configuration. The device may determine a recommendation of one or more memory types for the device type based on the compatibilities between the plurality of memory types and the device type. The device may transmit an indication of the recommendation of the one or more memory types.

Abstract: An information processing apparatus for determining a specification of a vehicle ordered by a user, comprises a controller unit configured to execute: receiving designation of a body color of the vehicle from the user; and proposing to the user to overcoat the vehicle with a second body color by an easily peelable paint after ordering the vehicle having any of a plurality of first body colors when the second body color that is not included in the plurality of first body colors set as a base color of the vehicle is designated by the user.

Abstract: Aspects described herein may relate to methods, systems, and apparatuses that provide new capabilities for recommending purchases to a user based on the user's past purchasing history and the purchase history of others. A new descriptor referred to as “purchase embeddings” is disclosed, which are data records in a new multi-dimensional space for describing and tracking purchases of goods and services.

Abstract: An information pushing method and apparatus. The method includes extracting preference attributes of a user from user dialogue information in the current dialogue scene; determining effective attribute nodes corresponding to the preference attributes in a preconstructed knowledge graph; arranging the effective attribute nodes according to a dialogue time sequence to generate a dialogue path; determining a candidate attribute set and a candidate commodity set on the basis of the dialogue path; using a pretrained strategy prediction model to predict the current pushing strategy on the basis of the current state vector; determining, on the basis of the current pushing strategy, an object to be pushed from the candidate attribute set or the candidate commodity set, and generating, on the basis of said object, information to be pushed; and pushing the information to be pushed.

Abstract: A system and method for providing payments is disclosed. A method can include establishing a wireless link between a mobile device and a merchant device. After an instruction is displayed on the mobile device, a combination of a first type of input and a second type of input are received on the mobile device, first type of input including at least one button press of a physical button and the second type of input received from a user to confirm a payment for the purchase. Based on the inputs, payment data is retrieved from a memory of the mobile device. The method includes receiving the payment data at the merchant device to make the purchase, wherein receiving the payment data, via the wireless link, at the merchant device to make the purchase is performed according to a protocol for communicating the payment data to the merchant device.

Abstract: A system, method, and computer program product for automatically diagnosing a condition of a case of a resource planning system using at least one operating parameter, the case including one or more new activities to order one or more new items, substitute one or more items, restock one or more items, replace one or more damaged items, or recall one or more items in a plurality of accounts of a resource planning system, correlating at least one operating parameter with at least one critical parameter of the resource planning system, comparing the at least one critical parameter with a predefined threshold value to identify at least one deviation including one or more discrepancies when a critical parameter falls, and controlling an supplier management activity by generating a response, communication, or action and adapting the prediction engine to eliminate the at least one deviation by correcting the discrepancy.

Abstract: A method includes obtaining data corresponding to a plurality of candidate wireless sites, and processing the data for at least a subset of the candidate wireless sites, to identify one or more line items of a purchase order (PO) to recommend for cancellation. Processing the data includes determining that the PO corresponding to at least one candidate wireless site has been approved, determining that at least one line item of the PO has not been cancelled, determining that no invoice has been received that corresponds to the at least one line item of the PO, and determining that the at least one candidate wireless site is not actively being pursued for development. The method also includes generating one or more alerts including an identification of the at least one line item of the PO and a recommendation to cancel the at least one line item of the PO; and presenting, on a graphical user interface, the one or more alerts to the user.

Abstract: Disclosed techniques enable cluster-based dynamic content with multi-dimensional vectors for video content analysis. User-specific data vectors on a plurality of users are accessed, which include shopping history and video consumption behavior. A plurality of clusters, based on the user-specific data vectors, is developed. A user, from the plurality of users, is associated with one or more clusters from the plurality of clusters. The user is identified as viewing media content. A container unit is inserted into the media content that is being viewed and is populated with at least one short-form video from a library of short-form videos. The populating is based on the identifying. An ecommerce purchase of a product for sale to the user is enabled. The product for sale is relevant to the one or more clusters and the at least one short-form video. The ecommerce purchase is accomplished within a short-form video window.

Abstract: A computer-implemented method of creating and changing one or more non-fungible tokens (NFTs) is disclosed. The method comprising steps of setting a time frame for NFT creation after receiving the time frame from a user; creating one or more storylines about the one or more NFTs within the time frame; associating the storylines with the one or more NFTs; receiving approval information from the user; displaying the one or more NFTs for public purchase, wherein the one or more NFTs includes one or more plots; receiving purchase information from a buyer; receiving bidding information from one or more fans; determining a purchased NFT that received the highest number of fans; retrieving at least one coded manuscript; and changing the at least coded manuscript according to the purchased NFT that received the highest number of fans.

Abstract: Implementing extended reality (XR) storefronts is described. A server(s) may access catalogue data associated with items offered for sale by a merchant via an existing online storefront or an existing brick-and-mortar store. The server(s) may generate digital representations of the items, and generate a XR storefront including the digital representations of the items positioned within a virtual space. The server(s) may store storefront data representing the XR storefront in a datastore(s). At runtime, the server(s) may receive, from an electronic device of a customer, a request to access the XR storefront. In response, the server(s) may access the storefront data and cause the electronic device to display the XR storefront based at least in part on the storefront data.

Abstract: The subject technology receives image data including a representation of a physical item. The subject technology analyzes the image data to determine an object corresponding to the physical item. The subject technology extracts product metadata based on the determined object. The subject technology sends, to a server, the product metadata to determine second product metadata associated with the product metadata. The subject technology receives, from the server, the second product metadata, the second product metadata including additional information related to the physical item. The subject technology causes display, at a client device, the additional information related to the physical item based at least in part on the second product metadata.

Abstract: Methods and systems for connecting short term rental with distributed infrastructure are provided. According to one example, a server maintains access to a plurality of property data contracts on a decentralized blockchain ledger, each property data contract associated with a real property in a locale and a cancellation policy data contract. The server receives a booking data operation including a cryptocurrency transaction and a cryptocurrency address and verifies the booking data operation relative to the cancellation policy contract. Responsive to the verifying, the server approves the booking data operation, processes the cryptocurrency transaction, and updates the decentralized blockchain ledger. After the booking data operation has been approved, the server runs a token data operation to provide a token to the cryptocurrency address associated with the user electronic device.

Abstract: Information related to apparently successful matches between two entities is collected, and culled based on a later indication that the match failed. Matches between two entities may be generated based on comparative information with other entities who appear to share some characteristics or preferences. Matches may be based on actual actions, in contrast to expressed preferences. Actual actions may be taken into account in addition to expressed preferences. Generation of matches may take into account geographical and/or temporal proximity and/or likelihood of receiving a response, in addition to other attributes of an entity. Matching algorithms may be updated based on entity input. Potential matches may be presented to third party entities for evaluation.

Abstract: A provider institution computing system includes a customer database structured to retrievably store information relating to a customer of an originator institution associated with an originator computing system and a transaction processing circuit coupled to the customer database.

Abstract: Logic may receive one or more questions from a customer in a chat. The logic may associate the one or more questions with one or more categories of subjects. The logic may store indications of the one or more categories of the subjects with a customer profile. The logic may select questions for a quiz for the customer based on the one or more categories of the subjects in the customer profile from a set of questions. The logic may present the one or more questions to the customer. And, in some embodiments, the logic may receive answers to the one or more questions from the customer.

Abstract: An example operation may include one or more of receiving a loan application of a user, extracting a plurality of personal attributes about the user from the loan application, querying a machine learning model via an application programming interface (API) based on the plurality of attributes about the user to identify one or more rules for auto-adjudicating the loan application, determining whether or not to approve the loan application based on the one or more rules identified via the machine learning model, and transmitting notice of the determination to a device associated with the user.

Abstract: An example operation may include one or more of assigning different criteria to a plurality of nodes of a decision tree model, respectively, iteratively executing the decision tree model on a plurality of training data which causes the plurality of training data to be assigned to the plurality of nodes of the decision tree model based on the different criteria assigned to the plurality of nodes, identifying nodes among the plurality of nodes within the decision tree model which have a purity above a predetermined purity threshold, generating a set of rules based on the identified nodes which have the purity above the predetermined purity threshold, and embedding the set of rules within the decision tree model and storing the decision tree model within a storage device.

Abstract: A system and method for facilitating loan reconciliation for multiple organizations of organizations is disclosed. The method includes receiving one or more proof sheet templates, one or more proof sheet rulebooks and one or more proof sheet configurations of a loan settlement process from one or more electronic devices, creating the one or more proof sheets, and obtaining financial data defined in a rulebook. Further, the method includes creating a dynamic workbook, and loading workbook data as additional sheets. The method includes generating an interim fee for one or more partners, detecting one or more exceptions in the loan reconciliation, and outputting the generated interim fee, the created one or more proof sheets and the detected one or more exceptions on graphical user interface screen of the one or more electronic devices.

Abstract: Systems and methods are provided for facilitating and managing unsecured loan products that utilize borrower's existing credit accounts as a modified collateral. In some embodiments, a lender can provide lending products by using customer's existing credit account as a modified collateral. A first machine learning model trained on data sets not presently utilized by financial industry to determine interest rates without increasing the lender's financial risk. A second machine learning model may be used to optimize the distribution of the pre-authorization hold amounts between revolving credit accounts using a second machine learning model that would determine weighted decision that combines the categorization and the confidence score based on the output calculated by the first machine learning model.

Abstract: A fast clock domain crossing architecture for high frequency trading includes a receiver that recovers data and a clock of a first clock domain from a communication from an exchange, functional circuitry that generates and a buy/sell command based on the recovered data and the recovered clock, format circuitry that formats the command in a second clock domain, and a transmitter that transmits the formatted command to the exchange. The architecture further includes error detection circuitry that detects bit errors that arise from an asynchronous boundary of the clock domains without increasing a round-trip latency, and/or synchronization circuitry that synchronizes the clock domains, where the synchronization circuitry includes a cleanup PLL that filters input jitter and a phase detector and variable delay line that compensate for latency within the architecture.

Abstract: An embodiment relates to a system comprising: a processor, a memory, and a database; wherein the processor configured to: receive a real-time data along with a real-time performance of the athlete; determine a recommendation, using a machine learning model comprising artificial intelligence of a recommendation engine, to a user of a stock of the athlete for a future period; determine, a stock price associated with the stock of the athlete in real-time based on a computation metric comprising the real-time performance of the athlete in the game and the historical performance of the athlete, wherein the stock price of the athlete is computed using a blockchain technology; wherein the blockchain technology is configured to facilitate at least one of a creation of transaction of the stock; and wherein a cyber security module is configured for providing security to the system.

Abstract: An energy trading method and system for supporting environmental, social and governance (ESG) management are provided. More specifically, the method and the system enhance environmental, social and governance (ESG) management of a factory by evaluating utility through energy trading between a main grid and a factory having a distributed resource.

Abstract: Method, apparatus, and system may control chronological sequencing of data items received from a plurality of client computing devices, according to times of completion of transmission respectively from the client computing devices and distributing the data items according to the chronological sequencing to one or more destination computing devices with minimal latency. In an exemplary implementation, trade orders from participant computing devices may be distributed by an electronic trading platform with minimal latency to exchange gateways, based on time of transmission of the trade orders to the platform instead of time of receipt of the trade orders by the platform, thereby avoiding unfairness to those participants whose computing devices are located at greater distances from the platform than other computing devices respectively of other participants.

Abstract: A system and method for distributing market data in response to price level transitions is disclosed. The system and method provide a mechanism for detecting when a price level transition has occurred. Detection of a price level transition results in the distribution of market data and may include displaying the results.

Abstract: Various embodiments disclosed herein relate to order entry. In the electronic trading process, order entry involves setting one or more order entry parameters, sending one or more order entry parameters, or both setting and sending one or more order entry parameters. As will be described in more detail below, various order entry actions, such as moving a cursor across an order entry line, moving a cursor into an order entry region, pressing an order entry button, or performing a gesture, may be used to trigger the setting, sending, or both setting and sending of one or more order entry parameters. At least some embodiments relate to enabling an order entry action before the order entry action is able to set, send, or both set and send one or more order entry parameters.

Abstract: A retirement plan roadmap system that is comprised of a computer processing system, a display that is operatively connected to the computer processing system, and input device that is operatively connected to the computer processing system. The computer processing system uses an application that will run a Monte Carlo Simulation on a prospect's investments with or without an adjustment. The application is programmed to have a growth bucket and a volatility bucket. The growth bucket has financial products that are potentially exposed to volatility over the life of a retirement plan. The volatility bucket has financial products that cannot go down in value and are not correlated to the growth bucket. The application is programmed to only take distributions from the growth bucket during up market years, and to only take distributions from the volatility bucket during down market years.

Abstract: An platform for contingent fundraising includes a method, system, system architecture that efficiently allows businesses to establish milestones and offer a liability based on an offered interest rate and a target amount of funds to raise. Funders using the system can match the business' offer with funding to meet the target raise. Funds commensurate with the liability and a funder's offer are provided by participants and isolated by the system until the milestone is evaluated. Funds are distributed to the business or funders based on the milestone status.

Abstract: The present invention allocates node variables to resources held by respective entities, which are servers or computer systems through a network, sets a connection to the resources required for generating an investment signal, and allocates the connection relationship as an edge variable. In addition, the present invention allocates a distribution rate for distributing loss and profit to each node as a value of the edge variable, so that the loss and profit to be distributed to each node during loss and profit distribution after investment execution can be easily derived from the value of the edge variable.

Abstract: An on-demand insurance (ODI) server for generating dynamic user offerings may be provided. The ODI server may include at least one processor in communication with a memory device. The at least one processor may be programmed to (i) receive, from a user computing device associated with a user, an insurance policy request for a trip from a start location to an end location, (ii) determine at least one transportation mode available for the trip, (iii) access contextual data associated with the trip, (iv) assess a risk associated with the at least one transportation mode, (v) calculate a risk score associated with the at least one transportation mode based upon at least the contextual data, (vi) generate an insurance offering associated with the at least one transportation mode, and/or (vii) transmit the insurance offering in real time to the user computing device for purchase by the user.

Abstract: A technique of processing insurance data collected from a plurality of companies includes obtaining a company defined configuration that specifies how to extract a set of company generated data records from a data store and how the set of company generated data records is used by an application. The data store includes common data elements shared by the plurality of companies and company-specific data elements specified by a company. It further includes obtaining from the data store the set of company generated data records based on the company defined configuration. It further includes executing the application to process the company generated data records according to how the set of company generated data records is used by the application as specified by the company defined configuration.

Abstract: A property analyzer device may include (1) a receiver configured to receive property identification information from a mobile device, the received property identification information including a picture of the property and/or a property location; (2) a retriever configured to retrieve property-related information from multiple property sources (such as public record databases, websites, or an internal company database) based upon the received property identification information; (3) a processor configured to consolidate the retrieved property-related information into a consolidated property-related image of the property; and (4) a transmitter configured to transmit the consolidated property-related image to the mobile device for review by a user.

Abstract: A property analyzer device may include (1) a receiver configured to receive property identification information from a mobile device, the received property identification information including a picture of the property and/or a property location; (2) a retriever configured to retrieve property-related information from multiple property sources (such as public record databases, websites, or an internal company database) based upon the received property identification information; (3) a processor configured to consolidate the retrieved property-related information into a consolidated property-related image of the property; and (4) a transmitter configured to transmit the consolidated property-related image to the mobile device for review by a user.

Abstract: A method for identifying a primary vehicle associated with a user of a mobile device includes receiving an indication of a vehicle entry event from a mobile device and retrieving sensor data from the mobile device. The method further includes receiving an indication of a vehicle exit event from the mobile device, generating a trip log including portions of the sensor data, and storing the trip log in a trip database. A server, or other suitable computing device, then analyzes the trip log and a plurality of previously stored trip logs in the trip database to determine a primary vehicle corresponding to the user of the mobile device. The method may allow a computing device to assign gathered mobile device data to a specific household vehicle.

Abstract: A method for determining vehicle insurance costs includes receiving a starting location and a destination location for a trip using a vehicle. One or more routes for the vehicle from the starting location to the destination location are received. A cost of insurance is determined for each of the one or more routes for the trip. The cost of insurance for each of the one or more routes for the trip is displayed. A selected route from the one or more routes is received. Operation of the vehicle for the trip is enabled along the selected route.

Abstract: Techniques including a system and method for processing insurance documents are provided. The techniques may involve the use of a system. The system may include a component configured to process a plurality of input document entities. The system may include a routing component configured to process the plurality of input document entities, wherein the routing component is configured to determine one or more workflows for processing at least one of the plurality of document entities. The system may include a workflow management component configured to process the at least one of the plurality of document entities.

Abstract: Techniques including a system and method for analyzing insurance claims. The techniques may involve the use of a system. The system may include a plurality of machine learning models trained on a plurality of insurance loss claim records, the plurality of machine learning models comprising: at least one machine learning model trained on open claims records; and at least one machine learning model trained on closed claims records. The system may include a component configured to predict a loss for a subject insurance claim based on outputs of the at least one machine learning model trained on open claims records and the at least one machine learning model trained on closed claims records.

Abstract: A computer implement method that assist healthcare payers in identifying potentially fraudulent claims and which requests confirmation preferably from a healthcare provider or patient of services rendered by the healthcare provider or products received by the patient. Confirmation of equipment and services can occur at different times in the settlement process including, but not limited to, prior to payments being made to health care providers.

Abstract: Technology is directed to tools for providing tax related services for virtual currency holdings, e.g., bitcoin holdings. The tax related services can include computation of taxes such as income tax, sales tax, and payroll tax for virtual currency holdings. The services can also include facilitating filing of the taxes with the concerned department. The tool can include a computing device configured to execute a tax application for computing the taxes on virtual currency holdings. The user provides information on a source of virtual currency transactions, e.g., an address of a bitcoin wallet, to the tax application, and the tax application retrieves the transactions from the source. The tax application categorizes the transactions into various transaction types and identifies the taxable and/or non-taxable transactions. The gain/loss and the associated tax are computed for the taxable transactions using one or more cost-basis methods.

Abstract: A system and method for creating and using a location-based augmented reality community platform is disclosed.

Abstract: A system includes a processor and an interface coupled to the processor. The processor determines that a first user takes a first action, and determines to pair the first user and a second user. The processor pairs the first user and the second user for an interaction, where the interaction lasts for a first time period. The interface receives an indication of a preference of the first user for the second user at a second time. The second time is after the first time period.

Abstract: A method for controlling application of agrichemical products, comprises acquiring remotely sensed digital image data; developing a prescription to apply at least one agrichemical product in a variable manner based on at least the digital image data, wherein the prescription describes a plurality of passes of a particular autonomous vehicle over a field to apply the at least one agrichemical product; applying the at least one agrichemical product to a crop in the variable manner by the particular autonomous vehicle according to the prescription.