Abstract: Aspects described herein may relate to methods, systems, and apparatuses that provide new capabilities for recommending purchases to a user based on a new descriptor referred to as “purchase embeddings.” The purchase embedding may include a tuple in a new multi-dimensional search space for describing and tracking purchases of goods and services. Recommendations may be based on a distance between tuples in the search space, which provides a measure of similarity between items represented by the tuples.

Abstract: In some embodiments, a computer-implemented method comprises: using a client application executing on a user device, generating a user interface configured to receive one or more user characteristics; wherein the one or more user characteristics have been associated with one or more corresponding graph of transform invariant features product-tokens (GTIF product-tokens); receiving, by the client application executing on the user device, via the user interface, a particular characteristic of the one or more user characteristics; determining, by the client application, a particular GTIF product-token associated with the particular characteristic of the one or more user characteristics; determining whether the particular GTIF product-token, associated with the particular characteristic, matches a particular pair of a set of GTIF product-token pairs; in response to determining that the particular GTIF product-token matches the particular pair, determining particular additional content based on the particular pair

Abstract: A system, for example, an online system uses a machine learning based language model, for example, a large language model (LLM) to process crowd-sourced information provided by users. The crowd-sourced information may include comments from users represented as unstructured text. The system further receives queries from users and answers the queries based on the crowd-sourced information collected by the system. The system generates a prompt for input to a machine-learned language model based on the query. The system provides the prompt to the machine-learned language model for execution and receives a response from the machine-learned language model. The response comprises the insight on the topic and evidence for the insight. The evidence identifies one or more comments used to obtain the insight.

Abstract: A system, for example, an online system uses a machine learning based language model, for example, a large language model (LLM) to process high-level natural language queries received from users. The system receives a natural language query from a user of a client device. The system determines contextual information associated with the query. Based on this information, the system generates a prompt for the machine learning based language model. The system receives a response from the machine learning based language model. The system uses the response to generate a search query for a database. The system obtains results returned by the database in response to the search query and provides them to the user. The system allows users to specify high level natural language queries to obtain relevant search results, thereby improving the overall user experience.

Abstract: A computer-implemented method, in accordance with one embodiment, includes collecting touch data from one or more touch sensors coupled to a first product, the one or more touch sensors being configured to indicate when a human touches the one or more touch sensors and/or first product. Product vector information about the first product is received. Classification on the touch data and product vector information is performed using a hierarchical multilabel classification system for assigning the touch data to predefined patterns for each level of a classifier used by the hierarchical multilabel classification system. Features of a second product, e.g., a touch vector and a touch pattern, are transformed into a second feature vector. A featurewise difference detection is performed on the feature vectors to calculate a difference in distribution for features of the products to generate and output a caption indicative of the differences between the products.

Abstract: A system is configured to train a customer understanding model to generate a preference score for substitution items. The customer understanding model generates a preference score for each of a plurality of related substitution items based on order data including data indicative of at least one item ordered and location data indicating a location of a first store. The customer understanding model ranks each of the substitution items based on the preference score. Order data is transmitted including substitution data identifying each of the substitution items and corresponding rank. Performance data associated with a set of operations implemented based on the order data and the substitution data is obtained. An updated customer understanding model is trained based on the performance data and iteratively modified based on the updated training dataset and updated performance metrics generated from second performance data.

Abstract: Techniques described herein relate to a method for generating supply recommendations. The method includes identifying, by a supply recommendation engine, a recommendation generation event associated with a part; in response to identifying the recommendation generation event: obtaining part information associated with the recommendation generation event; obtaining a first constraint configuration; and generating a first recommendation based on the first constraint configuration and the part information; obtaining a second constraint configuration; in response to obtaining the second constraint configuration; generating a second recommendation based on the second constraint configuration and the part information; and performing supply actions based on the first optimization recommendations and the second optimization recommendations.

Abstract: An information processing apparatus includes a controller configured to execute operations, the operations including extracting text information regarding a shop from content of the shop, generating a content value vector in a plurality of dimensions based on the text information, calculating a person parameter for a user based on information input by the user, generating a user preference value vector in the plurality of dimensions based on the person parameter, and determining a similarity between the content value vector and the user preference value vector.

Abstract: Embodiments of the present disclosure disclose an information display method and apparatus, an electronic device, and a storage medium. The information display method includes: displaying a live page; obtaining popularity information corresponding to the resource; and displaying the popularity information in an area which is associated with the first multimedia information on the live page.

Abstract: Methods and systems for providing content and content recommendations are described. Content recommendations for users in a service area may be based on content requests from users within the same service area. Content recommendations over a period of time may dynamically change based on many factors, including: the number of requests for particular content within one or more time frames, the storage location of requested content relative to requesting users, and whether a request occurs within a time period of rapid shift in use and types of content requested. A content recommendation including one or more content recommendations may be provided to users.

Abstract: A method for purchasing goods, access authorizations or authorizations for using a service from a plurality of offered goods, access authorizations or authorizations for using a service. A defined spatial region is subdivided into defined subregions assigned, in each case, to a purchasable good, access authorization or authorization for using a service. A good, an access authorization or an authorization for using a service from a plurality of offered goods, access authorizations or authorizations for using a service is purchased, and a user registered in advance for carrying out the method on the basis of biometric features and/or on the basis of features, which may be assigned to the user uniquely, or an item registered in advance for carrying out the method is identified and localized in the defined subregion (1, 2, 3) assigned to the good, access authorization or authorization for using a service.

Abstract: A method for using an electronic shopping list to resolve ambiguity associated with a selected product may include accessing an electronic shopping list associated with a customer of a retail store; receiving image data captured using one or more image sensors in the retail store; analyzing the image data to detect a product selection event involving a shopper; identifying a product associated with the detected product selection event based on analysis of the image data and further based on the electronic shopping list; and based on the identification of the product, updating a virtual shopping cart associated with the shopper.

Abstract: An electronic system for the customization, visualization, integration, purchase, and acquisition of a vehicle from a vehicle dealer or manufacturer/seller of custom aftermarket parts. The system is implemented on a computer server or equivalent device, where the server, operated by the manufacturer, is accessible over the internet via a suitable end-user operated computing device, the server generating a menu driven visual interface viewable on the computing device. The system allows for all aspects of a customized vehicle purchase to be performed by the user, substantially streamlining the selection and acquisition process. The system can be interfaced with third party parts databases, allowing for incorporation of parts from a variety of manufacturers. The system may also be used to purchase aftermarket parts for used cars.

Abstract: Various embodiments are directed to overlaying relevant product information in augmented reality via the use of near-field communication (NFC) and a product selection system. A user may authenticate into an application or user profile. Information about the user in the user profile may be used to determine which products are relevant to the user. Information related to the relevant products may then be displayed to the user in augmented reality, which improves at least the overall shopping and in-store experience.

Abstract: An information processing device includes a control unit. The control unit registers, for each user, identification information that links the user's personal information with purchase information including sales conditions and payment conditions for the product purchased by the user. The control unit generates a link including identification information and information that causes the display screen of the mobile terminal owned by the user to transition to a dedicated page within a predetermined application installed on the mobile terminal. When the dedicated page is displayed on the display screen based on the link, the control unit prompts the user to apply for a contract based on the purchase information. Upon receiving a contract application from a user, the control unit settles the contract application.

Abstract: Disclosed herein is system and method for sealed bid auctions through the implementation of computer device, wherein an auction includes sealed bids, assigning random IDs for undisclosed real IDs, and obtaining double confirmation from both bidders and vendors. Vendors may choose to have a reserve price such as an open reserve price and a conditional hidden reserve price. The system generates random bidder IDs and allows the bidders to self-determine into two different bidding categories, where one bidding category pays the full winning bid amount and the other bidding category purchases a “price-protection policy” that allows the recalculation of the final winning bid amount based on the “price-protection formula”, wherein the “price-protection formula” is calculated as a sum of the “price-protection fee”, the second-highest bid amount, and the amount from a pre-determined percentage of a difference between the highest bid amount and a second-highest bid amount.

Abstract: Disclosed is system and method for sealed bid reverse online auctions through remote computer devices according to a set of predetermined rules, where the reverse auction includes sealed bids, and assigned random identification numbers for auction bidders. The system allows bidders to opt into one of two different bidding categories. Category one requires payment of the winning bid amount. Category two requires a commitment to purchase a price-protection policy, allowing recalculation of the final winning bid amount based on a price-protection formula calculated by subtracting the price-protection fee from a sum of the lowest or winning bid amount and an amount equal to a predetermined percentage of a difference between a next lowest bid amount and the lowest winning bid amount. The system also allows for the allocation of at least a portion of the price-protection fee.

Abstract: The present technology relates to a financial service provision system and a simple payment company server therefor.

Abstract: An apparatus, method and computer program product for identifying a validation check for a set of numbers is provided. The apparatus comprises circuitry configured to: obtain first data comprising a set of unique numbers for which a validation check is unknown; determine a plurality of candidate validation functions to apply to the first data; determine a plurality of candidate weightings to apply to the first data; for each of the plurality of candidate validation functions and each of the plurality of candidate weightings: apply the candidate validation function to the first data; and determine, for each number of the set of unique numbers, whether the candidate validation function confirms that the number is valid; and when the number of confirmations for a candidate weighting and a candidate validation function is above a predetermined threshold, identify the candidate validation function and candidate weighting as the validation check for the first data.

Abstract: A system and method of automatic cashflow categorization of bank transactions are provided herein. The method may the following steps: collecting banking data and Enterprise Resource Planning (ERP) data associated with a plurality of users; training, by a computer processor, and based on the banking data and the ERP data associated with the plurality of users, a global model for mapping the banking data associated with the plurality of users into cashflow categories; and training, by the computer processor, and based on the global model and tagged dataset from a specific user of the plurality of user, a user-specific model for mapping the banking data associated with the specific users into cashflow categories associated with the specific user.

Abstract: An automatic system including a server is provided. The server is configured to: upon receiving a bucket creation request from a user device, create one or more virtual budgeting buckets associated with a user account of a user of the user device; receive a certain amount of fund in at least one of the one or more virtual budgeting buckets; detect engagement data of the user with the one or more virtual budgeting buckets; determine, based on the engagement data, whether the user meets goals of the one or more virtual budgeting buckets; provide a predictive model; input the engagement data and completeness of the goals into the predictive model; determine a creditworthiness of the user based on the predictive model; and provide a credit line to the user based on the creditworthiness.

Abstract: Techniques described herein include identifying an appropriate and/or optimal way to communicate with a credit customer, customer, or debtor. In one example, this disclosure describes a method that includes receiving, by a computing system, state information for a debtor, wherein the state information includes information about delinquency history for the debtor and prior efforts to contact the debtor to collect a delinquent debt; identifying, based on the state information for the debtor, a communication channel to use to contact the debtor about the delinquent debt, initiating contact with the debtor through the identified communication channel; storing data identifying how the debtor reacted to the initiated contact through the identified communication channel; and determining whether to initiate further communications with the debtor about the delinquent debt.

Abstract: There are provided systems and methods for multi-layer artificial intelligence models for progressive predictions during data pipeline management. A service provider may provide AI functionalities, such as through a multi-layer ML model framework that employs multiple layers for different ML models that process different features. The features in one layer and ML model may process data for static features, where an output from this layer may be used as an input with data for dynamic feature that provide a predictive score or output for the input data. The static features may only be required to be processed once or a few times in the first layer and may not be required to be further processed again at later times. With the second layer, the data for the dynamic features may change, and thus the second layer may process new data without being required to reprocess the static features.

Abstract: A method and system are provided for electronically issuing, tracking and processing casino credit, including rim credit and marker credit, and for tracking bets and generating player ratings. The system allows for real-time display of markers, rim credit and their status. The system may link to other systems such as a casino credit system for cross-sharing of information. The system comprises a processing server in communication with one or more mobile processing devices.

Abstract: A system and computer-implemented method of continuously updating information about one or more of a customer approved for a mortgage and a real estate property identified as mortgage ready. The method includes monitoring information accessed from a memory storage location corresponding to a customer identification number, the information used to determine the customer is approved for a mortgage, and receiving new information about the customer, the new information used to determine the customer is approved for a mortgage. The method also includes updating, at a memory coupled to the one or more processors, the memory storage location to include the new information. The method still further includes recalculating the amount in which the customer is approved for a mortgage based upon the new information received.

Abstract: Systems and methods for non-fungible token data indexing can include processing blockchain data and/or web page data to identify token data associated with a non-fungible token. The identified token data can then be utilized to generate index data associated with the non-fungible token. The index data can be utilized to generate an index database. The index database can then be utilized for non-fungible token search and/or for generating derivative data associated with the non-fungible tokens. The surfaced non-fungible token search results can be provided in a specific search result panel and/or adjacent to general search results.

Abstract: Systems and methods for non-fungible token indexing can include obtaining and identifying token data associated with a plurality of non-fungible tokens. In generating an index database, the systems and methods may index a token multiple times and/or may index tokens with same or similar payloads. The systems and methods can identify the duplicate token indexing and can adjust the index database based on the identification of duplicate token index data. The adjustment can affect the determination of which search results to surface in response to a search query.

Abstract: In a general aspect, a conversion network is applied to units of exchange and stores of value. In some aspects, a method for operating the conversion network includes: by operation of a conversion node, receiving a conversion request from a client node for transforming from a first value in a unit of exchange to a second value in a store of value; generating a transaction entry in a transaction entry database and an interest in pooled unit entry in an interest in pooled unit database according to the conversion request; and generating a pairing record in a pairing record database configured for determining a third value of the interest in pooled unit entry based on a fourth value of the transaction entry. The transaction entry includes a first set of data elements including a first identification of the transaction entry, and information of the conversion request and the client node.

Abstract: A system for providing an operator interface for displaying market data, trader options, and trader input includes a memory and a processor. The memory stores market data for a trading product, where the market data includes an inside market price for the trading product. The processor initiates display of a market data section of a tile, where the market data section comprises the market data. The processor initiates display of a trader input section of the tile, where the trader input section comprises options. The processor receives a selection of a bid-offer pair for the trading product from the options and updates the trader input section to indicate the selected bid-offer pair.

Abstract: Systems and methods are disclosed for a distributed trading system. The preferred invention offer solutions to problems that arise with High-Frequency Trading and the future of stock market regulation. The use of a distributed object brokered interface to facilitate transactions not only makes the trading faster but also more secure.

Abstract: The method includes aggregating historic investment data corresponding to multiple financial assets and calculating performance return percentages with reference to the latest investment quote, at each period. The method includes facilitating generation of a visual representation including contour areas indicating a variation of performance-range zones for the multiple financial assets and financial asset lines indicating change in the rank of the multiple financial assets with time. The method includes triggering a buying, selling, or exchanging action of a financial asset among the plurality of financial assets when a mouse corresponding to the pointer is clicked by a user, the pointer hovering over the financial asset line of the financial asset on the visual representation to perform the triggered action.

Abstract: A computing device, a computer program product, and a computer-implemented method for delivering enhanced financial services and, more particularly, for facilitating enhanced network communication between a user and a financial institution via a client device. A digital financial management platform for the client device includes a chat support platform that facilitates an enhanced user chat experience by protecting the privacy of a user. The chat support platform facilitates a more enhanced chat experience during a virtual chat communication between the user and a virtual support agent of the financial institution by enabling the user to have all or selective portions of the data and information shared by the user deleted upon command from all memory of one or more financial institution servers associated with a financial institution.

Abstract: A computing device, a computer program product, and a computer-implemented method for delivering enhanced financial services and, more particularly, for facilitating enhanced network communication between a user and a financial institution via a client device. A digital financial management platform for the client device includes a chat support platform that facilitates an enhanced user chat experience by transmitting, in response to receiving/acquiring a user request or command during a virtual chat communication session between the user and a virtual support agent of the financial institution on the client device when executing a mobile application or desktop application associated with the financial institution over a communication network, to receive an alert to the client device. The alert may contain data and information related to a financial account of the user and/or a financial service offered by the financial institution.

Abstract: Testing prototype indices is provided. The method comprises receiving input of a number of historical index values and performing a number of Monte Carlo simulations based on the historical index values to predict future index values. A number of attributes of the historical index values are calculated, and the Monte Carlo simulations are correlated with the attributes to identify a filtered subset of predicted future index values having an accuracy above a defined threshold. The filtered subset of predicted future index values are fed into a deep neural network (DNN) that outputs a confidence score for each of the filtered subset of predictive future index values.

Abstract: A method for analyzing an investment portfolio includes using a trained base model to obtain an estimated rate of return of a corresponding investment asset. Factor data are substituted into the corresponding base model and SHAP algorithm is performed on the base model to obtain respective SHAP values corresponding to the factor data. A portfolio ratio of investment assets is obtained by calculating environmental parameters and the estimated rate of return. The estimated rate of return is calculated in terms of the portfolio ratio to obtain an estimated rate of return of the investment portfolio. The SHAP values corresponding to the investment portfolio are calculated in terms of the portfolio ratio. A plurality of key factors are selected by determining a degree of influence of each of factors affecting the investment assets according to the SHAP values of the investment portfolio corresponding to the factor data.

Abstract: One embodiment of a computer-implemented method may include receiving one or more target parameters associated with a client, where the one or more target parameters may be based on one or more factors. The method may further include determining a risk tolerance measurement for the client associated with achieving the target parameter(s). The method may further include determining an optimal source quantity associated with achieving the target parameter(s) based on the risk tolerance measurement. The method may further include determining optimal allocation parameters for allocating the optimal source quantity. The method may further include generating a user interface including one or more duration-dependent hybrids, where the one or more duration-dependent hybrids may include one or more product offerings based at least in part on the optimal source quantity and the optimal allocation parameters.

Abstract: A system includes a processing circuit that is configured to establish a wireless connection with an analyst device; detect a trigger event based on detecting a mentioning of a security from the analyst device; in response to detecting the trigger event, receive analyst tracking information from the analyst device relating to the security; generate a data synopsis for the security based on the received analyst tracking information; and provide a graphical user interface to a manager computing device depicting the data synopsis.

Abstract: A computer system may include one or more processors configured to: (1) obtain insurance claim information; (2) generate, via an ML chatbot (or voice bot), the customized presentation based upon the insurance claim information; and/or (3) provide, via the ML chatbot, the customized presentation to a user device, such as a visual depiction and/or a verbal description of the customized presentation.

Abstract: Proposed is a digital, state discrete system and platform and corresponding method thereof, for automated underwriting and pricing of individually predicted loss covers using a combination of a Markov Chain modelling structure and configurable elements at least comprising states and/or state transitions and/or cashflows specific to the product it instantiates. The digital system comprises a simulation engine using deterministic transition and interest rates of a discrete process to conduct calculations per policy, wherein parts of the process are used with stochastic transition and interest rates of a discrete process for conducting simulations on portfolio level.

Abstract: A computer system may include at least one memory and at least one processor in communication with the at least one memory. The processor may be programmed to: (1) receive photographic data including one or more images of a structure; (2) in response to receiving the photographic data, apply the photographic data to a structure assessment model configured to determine a structural status of the structure, wherein the structure assessment model is trained using historical photographic data including a plurality of historical images of structures; (3) receive an output from the structure assessment model, wherein the output at least one determined characteristic of the structure; and/or (4) based upon the output, transmit a message to a user computing device associated with the structure that causes display of the determined characteristic.

Abstract: Systems and methods for determining an event and resulting damage using crowdsourced data are disclosed. A computer-implemented method in accordance with the present disclosure may comprise (i) receiving hazard event data; (ii) retrieving supplemental hazard event data (e.g., crowdsourced, donated, and/or public text data, image data, video data, and/or audio data) associated with the hazard event; (iii) applying the supplemental hazard event data to the trained event assessment model to generate model outputs; (iv) determining a recommendation based upon model outputs; and (v) transmitting a message.

Abstract: Methods and computer systems for providing access providing access to representations of computing events. Identifying, from a plurality of computing events, a set of computing events corresponding to a computing event category. The identification of the set of computing events including identifying a respective first category of each particular computing event in the set of computing events; and determining that each respective first category matches with a respective category defined in a list of categories maintained by a third-party server. Transmitting, to a computing device associated with a second category of a particular computing event of the set of computing events, an interface providing access to representations of computing events in the set of computing events.

Abstract: An individual or group reputation evaluation system and method, includes: an evaluatee terminal for requesting an evaluation about the social reputation of an evaluatee; a service server for receiving the evaluation request of the evaluatee terminal and analyzing the evaluation result; an evaluator terminal, which accepts the evaluation request of the evaluatee terminal in order to respond to the evaluation provided by the service server; and a viewer terminal, which requests the evaluation result for the user of the evaluatee terminal from the service server, in order to view same.

Abstract: The present disclosure provides a method for predicting carbon consumption and carbon emission of a hydrogen-rich blast furnace (BF) based on a C-rd theory.

Abstract: Certain aspects of the present disclosure relate to virtualizing battery resources for grid service applications. In particular, some of these aspects provide a method for configuring a plurality of virtual energy storage devices in an energy storage device of a fixed energy storage system; and performing two or more grid services concurrently with two or more virtual energy storage devices of the plurality of virtual energy storage devices.

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: Systems and methods are described that estimate a remaining useful life (RUL) of an electronic device. Time-series signals gathered from sensors in the electronic device are received. Statistical changes are detected in the set of time-series signals that are deemed as anomalous signal patterns. Anomaly alarms are generated, wherein an anomaly alarm is generated for each of the anomalous signal patterns. An irrelevance filter is applied to the set of anomaly alarms to produce filtered anomaly alarms, wherein the irrelevance filter removes anomaly alarms associated with anomalous signal patterns that are not correlated with previous failures of similar electronic devices. A notification may be generated indicating that the electronic device has a limited remaining useful life based on at least the anomalous signal patterns associated with the filtered anomaly alarms.

Abstract: The disclosure may address the problem of providing food and beverages at an appropriate price in accordance with the quality. A circulation count detection unit may detect the number of times a sushi dish has circulated on a conveyor from data obtained by a detection sensor. A price calculation unit may calculate the price of sushi placed on the sushi dish in accordance with the number of circulations of the sushi dish as detected by the circulation count detection unit. A container format conversion unit may execute a control for converting the format of the sushi dish in accordance with the price of the sushi changed by the price calculation unit. Thus, a consumer may be able to purchase sushi easily at an appropriate price in accordance with the quality.

Abstract: A system for managing hotel operations has a computing system, a user device, a GUI, and a datastore. The user device can be an attendant device or a manager device, and the user role can be an attendant or a manager. The datastore stores data related to a hotel, its rooms, its guests, its staff, its tasks, and its morning meeting. The GUI displays the morning meeting message from the manager device to the attendant device, and shows an attendant checklist panel with a list of rooms and a control to start and stop cleaning. The GUI changes the room status and receives the cleaning time, image, and note from the attendant device. Each room has information comprising id, number, status, type, cleaning indicator, and cleaning result, which comprises the user id, cleaning time, image, and note.

Abstract: A building analysis (“BA”) system for detecting events of a building includes a plurality of sensors positioned within a building, at least one memory device and a building analysis (“BA”) computing device communicatively coupled to the plurality of sensors, the BA computing device comprising one or more processors in communication with the at least one memory device, wherein the one or more processors are programmed to build an infrastructure profile for the infrastructure, the infrastructure profile including i) one or more reference parameters, ii) detected historic conditions of the one or more fixtures using historical sensor data received over a period of time, and iii) detected historic conditions of the at least one person using historical sensor data received over a period of time.