Abstract: This disclosure describes one or more embodiments of systems, non-transitory computer-readable media, and methods that utilize channel pruning and knowledge distillation to generate a compact noise-to-image GAN. For example, the disclosed systems prune less informative channels via outgoing channel weights of the GAN. In some implementations, the disclosed systems further utilize content-aware pruning by utilizing a differentiable loss between an image generated by the GAN and a modified version of the image to identify sensitive channels within the GAN during channel pruning. In some embodiments, the disclosed systems utilize knowledge distillation to learn parameters for the pruned GAN to mimic a full-size GAN.

Abstract: Apparatuses, systems, and techniques are presented to synthesize consistent images or video. In at least one embodiment, one or more neural networks are used to generate one or more second images based, at least in part, on one or more point cloud representations of one or more first images.

Abstract: A system and method includes generating approximate distributions for distinct classes of data samples; computing a first partial Jensen-Shannon (JS) divergence and a second partial JS divergence based on the approximate distribution of the disparity affected class of data samples with reference to the approximate distribution of the control class of data samples; computing a disparity divergence based on the first partial JS divergence and the second partial JS divergence; generating a distribution-matching term based on the disparity divergence, wherein the distribution-matching term mitigates an inferential disparity between the control class of data samples and the disparity affected class of data samples during a training of an unconstrained artificial neural network; constructing a disparity-constrained loss function based on augmenting a target loss function with the distribution-matching term; and transforming the unconstrained ANN to a disparity-constrained ANN based on a training of the unconstraine

Abstract: A mobile device with a route prediction engine is provided that can predict current/future destinations or routes to destinations for the user, and can relay prediction information to the user. The engine includes a machine-learning engine that facilitates the formulation of predicted future destinations and/or future routes to destinations based on user-specific data. The user-specific data includes data about (1) previous destinations traveled, (2) previous routes taken, (3) locations of calendared events, (4) locations of events for which the user has electronic tickets, and/or (5) addresses parsed from e-mails and/or messages. The prediction engine relies on one or more of user-specific data stored on the device and data stored outside of the device by external devices/servers.

Abstract: Systems, methods, tangible non-transitory computer-readable media, and devices for associating objects are provided. For example, the disclosed technology can receive sensor data associated with the detection of objects over time. An association dataset can be generated and can include information associated with object detections of the objects at a most recent time interval and object tracks of the objects at time intervals in the past. A subset of the association dataset including the object detections that satisfy some association subset criteria can be determined. Association scores for the object detections in the subset of the association dataset can be determined. Further, the object detections can be associated with the object tracks based on the association scores for each of the object detections in the subset of the association dataset that satisfy some association criteria.

Abstract: According to one embodiment, an information processing method classifies an instance including a combination of data items of subclasses of either physical world classes describing physical entities or cyber world classes describing concepts. The information processing method comprises the steps of: obtaining first data including the instance; and inferring and determining a subclass the instance belongs to by referring to at least either definition data or log data. The definition data defines the subclasses. The log data includes a set of the first data obtained in the past, each of the first data including the instance with the corresponding subclass defined in the definition data.

Abstract: System and methods for performing analytical operations are described. A hardware-based regular expression (RegEx) engine performs a regular expression operation on a stream of data units based on a finite automata (FA) graph. Performing includes configuring a regular expression engine of a hardware-based regular expression accelerator to, beginning at a root node in the plurality of nodes of the FA graph, step the regular expression engine through one or more nodes of the FA graph until the regular expression engine arrives at a skip node and to consume, at the skip node, two or more data units from the stream of data units before traversing one of the directional arcs to another node.

Abstract: A processing unit to support inference acceleration for machine learning (ML) comprises an inline post processing unit configured to accept and maintain one or more lookup tables for performing a tanh and/or sigmoid operation/function. The inline post processing unit is further configured to accept data from a set of registers configured to maintain output from a processing block instead of streaming the data from an on-chip memory (OCM), perform the tanh and/or sigmoid operation on each element of the data from the processing block on a per-element basis via the one or more lookup tables, and stream post processing result of the per-element tanh and/or sigmoid operation back to the OCM after the tanh and/or sigmoid operation is complete.

Abstract: A building system including one or more storage devices storing instructions thereon that, when executed by one or more processors, cause the one or more processors to receive an indication to execute an artificial intelligence (AI) agent of a digital twin, the digital twin including the AI agent and a graph data structure, the graph data structure including nodes representing entities of a building and edges between the nodes representing relationships between the entities of the building. The instructions cause the one or more processors to execute the AI agent based on data of the building to generate an inference that is a prediction of a future data value of a data point of the building for a future time and store at least one of the inference, or a link to the inference, in the graph data structure.

Abstract: A management system operates in conjunction with entities to provide component recommendations for objects. The management system trains a machine learning model used to generate the component recommendations. The machine learning model is trained based on historical component entries describing components previously provided and identifiers of the components. The management system generates training data by classifying the historical component entries into predetermined component classifications. After the machine learning model is trained, the management system generates a customized recommendation of components for an object based on likelihoods of selection of the predetermined component classifications.

Abstract: A method and system for determining predictably feasible model designs. The method includes defining a plurality of model designs, wherein the plurality of model designs include a plurality of infeasible model designs, wherein one or more of the infeasible model designs are infeasible due to limits in technology; storing information representing a plurality of technological trends; and classifying one or more of the infeasible model designs as predictably feasible model designs, wherein the predictable feasible model designs are those infeasible model designs expected to become feasible model designs if one or more of the plurality of technological trends continues as anticipated.

Abstract: Mechanisms are provided to implement a bias identification engine that identifies bias in the operation of a trained cognitive computing system. A bias risk annotator is configured to identify a plurality of bias triggers in inputs and outputs of the trained cognitive computing system based on a bias risk trigger data structure that specifies terms or phrases that are associated with a bias. An annotated input and an annotated output of the trained cognitive computing system is received and processed by the bias risk annotator to determine if they comprise a portion of content that contains a bias trigger. In response to at least one of the annotated input or annotated output comprising a portion of content containing a bias trigger a notification is transmitted, to an administrator computing device, that specifies the presence of bias in the operation of the trained cognitive computing system.

Abstract: An abduction apparatus 1 includes: a probability calculation unit 2 configured to, with respect to each of candidate hypotheses generated using observation information and knowledge information, calculate a probability that the candidate hypothesis holds true as an explanation of the observation information; and a reward selection unit 3 configured to, when the candidate hypothesis holds true, select a reward value regarding the candidate hypothesis that has held true by referring to reward definition information in which a condition that the candidate hypothesis holds true is associated with the reward value.

Abstract: Systems and methods for automatically building a machine learning model are disclosed. A plurality of variables is displayed via a graphical user interface (GUI). A target variable and a first independent variable are identified from the plurality of variables. A parameter associated with the machine learning model is identified. Collected data is received via the GUI. A first machine learning model is built using as inputs, the parameter and the collected data associated with the first independent variable and the target variable. A change is made to at least a portion of the inputs used to build the first machine learning model. A second machine learning model is built based on the change. A prediction accuracy of the first machine learning model is compared to the prediction accuracy of the second machine learning model. Either the first or second machine learning model is selected based on the prediction accuracy.

Abstract: Systems and methods are described for facilitating operation of a plurality of computing devices. Data indicative of enumerated resources of a computing device is collected. The data is collected without dependency on write permissions to a file system of the one computing device. A condition of the computing device is determined based on historical data associated with enumerated resources of other computing devices. The identified condition can be updated as updated historical data becomes available. A communication to the computing device may be sent based on the identified condition.

Abstract: A computer-implemented method for determining alternative plans for a user may include: determining an event status of an event based on one or more parameters, wherein the event status comprises a target event indicator, wherein the one or more parameters comprise event population; obtaining event data of a target event; obtaining transactional data of the user, wherein the transactional data includes transaction time and transaction location; determining, via one or more processors, a likelihood of a potential transaction of the user associated with the target event by processing the transactional data and the event data using a trained machine learning model; and transmitting, to the user, a notification based on the determined likelihood of the potential transaction, wherein the notification includes a suggestion for alternative travel plans of the user.

Abstract: Systems, methods, and apparatus are provided for intelligent, integrated, and interactive remote reporting. A remote natural language request for a report may be received from a user at an edge device. A first machine learning model may generate a list of existing reports based on past usage by the user. If no existing report satisfies the request, a second, enterprise-level machine learning model may map the request to relevant data sets and rank the mapped data sets along with additional related data sets based on enterprise-wide usage. An integrated reporting platform may receive selected data sets and report parameters as a JSON request, convert the request to compatible executable instructions, and generate the report. The integrated reporting platform may be a wrapper layer encompassing multiple proprietary reporting engines. Feedback from the integrated reporting platform may be applied to update the machine learning models.

Abstract: A resource processing method and apparatus. The method is achieved by a computer configured to execute the following steps: generating a resource allocation chart based on a resource allocation request; processing the resource allocation chart and generating an access entrance of the resource allocation chart; opening the access entrance to enable at least one third party resource supplier to respond to the resource allocation request via the access entrance. The method further comprises: when the resources are not available or not suitable for allocation, receiving a resource allocation chart, wherein the resource allocation chart is based on the resource allocation request; generating an access entrance of the resource allocation chart; opening the access entrance to at least one third party resource supplier; and receiving the allocated resources from the at least one third party resource supplier by responding to the resource allocation request through the access entrance.

Abstract: A method by which a server performs specialist platform control is provided. In order to resolve the aforementioned problem, the control method comprises the steps of: registering the specialist; acquiring specialist information of the registered specialist; computing career information of the specialist on the basis of the acquired specialist information; matching a project corresponding to the specialist on the basis of the career information of the specialist; acquiring project data computed according to the project performance result when the matching project is performed by the specialist; and updating the career information of the specialist on the basis of the project data.

Abstract: A system to generate and maintain a database of service provider skills and rankings with various categories is disclosed. Skills and rankings are generated from a number of corpus texts as well as service provider content. The database is dynamically updated to reflect changes to the corpus texts and/or service provider content.

Abstract: A system comprising: a skills data store; an employee action data store; at least one hardware processor; and one or more software modules that are configured to, when executed by the at least one hardware processor, retrieve skills data and employee action data from the skills data store and employee action data store, train a classification model, wherein training a classification model comprises performing feature preprocessing, generating an LDA topic vector and TF/IDF Word2Vec similarity scoring, and use AutoML to train ML models, and infer employee skills and levels based on the classification model and employee action data.

Abstract: Techniques are generally described for onboarding optimization for new hires. In various examples, labor order data specifying a target number of new hires may be received. In some examples, a first machine learning model may predict a number of new hire appointments to offer based at least in part on the labor order data. In further examples, an optimization component may allocate the number of new hire appointments to respective time slots based at least in part on candidate preferences. In some additional examples, data may be sent to a first application effective to display a list of available new hire appointment time slots of the respective time slots.

Abstract: According to some embodiments, a communication device database may store information about a plurality of communication devices, including at least one communication address associated with each communication device, wherein each communication device is associated with a resource unit. Moreover, a network based segmentation server may access information in a resource status database, automatically assign each resource unit to a resource segment based on at least one pre-determined algorithm and information in the resource status database, and transmit information about the resource segments.

Abstract: A technique is described for implementing drones as a service. As an example, a drone may receive instructions from one or more network elements, coordinate operations with the one or more network elements, and perform at least one task associated with the instructions. The drone may deliver a container to a first location and perform object recognition to validate an object of a subscriber being delivered to a second location. The drone may measure the weight and dimensions of the object to confirm the object is within operating guidelines. After verifying the object is within operating guidelines, the drone may transport the container containing the object to the second location.

Abstract: A computer implemented method includes obtaining, by the computer, assay data for a feedstock containing measurements for one or more aspects of the first feedstock, a first equipment model containing properties of processing units, and processing conditions containing one or more variables by which the first feedstock will be processed by the processing units. The computer determines a corrosion amount of the processing units using the processing conditions, the properties of the processing units contained in the equipment model, and the assay data for the feedstock, and stores/displays the corrosion amount of the processing units. A safety warning may be displayed, and the feedstock rejected if the corrosion amount exceeds a predetermined safety level for one or more of the processing units.

Abstract: Described herein is a computer implemented method for maintaining a plurality of issues, each issue having an associated rank value, the rank values of the plurality of issues defining an order of the plurality of issues. The method comprises receiving a rank operation request to change the rank of a subject issue; determining relevant issues to the rank operation request; and attempting to acquire locks on each of the relevant issues. In response to successfully acquiring locks on each of the relevant issues a new rank value for the subject issue is calculated and saved.

Abstract: A method comprising generating, during multiple user sessions of a first user with a software application, first clickstream data from the multiple user sessions, and extracting, from the first clickstream data, a first plurality of task instances of the first user performing a first plurality of tasks. The method also includes decomposing, from the first clickstream data, each task instance of the first plurality of task instances into a first plurality of steps to obtain a first plurality of decomposed task instances. The first plurality of steps in the first plurality of decomposed task instances are each associated with a timestamp. The method further includes training a first user model with the first plurality of decomposed task instances to learn a user optimal order to perform the first plurality of tasks and presenting, to the first user, the user optimal order to perform the first plurality of tasks.

Abstract: According to one embodiment, there is provided a computing device and method for evaluating driving risk. The computing device includes an input circuit and a processor. The input circuit is configured to receive data from a vehicle. The data includes at least one of GPS data, acceleration data or image data of views external of the vehicle or inside the cabin. Thereafter, the processor is configured to identify a plurality of risks based on the data received from the vehicle, determine a plurality of weightages which are assigned to the plurality of risks, and generate a score based on the plurality of weightages for the plurality of risks.

Abstract: Provided are an index value calculator to calculate an index value obtained by quantifying a degree of status for evaluation items, a teamwork evaluator to evaluate a teamwork based on the index value, a support content determiner to select target persons to be supported including the members of the team based on the evaluation result of the teamwork and determine support contents in accordance with the target persons to be supported, and a presentation information generator to generate presentation information for presenting the determined support contents for each of the output devices corresponding to the selected target persons to be supported, and the teamwork evaluator evaluates the teamwork using an evaluation logic configured by combining logical formulas for comparing a threshold value set for evaluation items with the calculated index value.

Abstract: A system and method is disclosed for incrementally adjusting a supply chain plan. The system includes a database operable to store data associated with one or more supply chain entities and a server system coupled with the database. The server system receives one or more perturbations in supply chain plan inputs from one or more of the supply chain entities, wherein the perturbations are received during a period of time separating a supply chain planning session from a subsequent supply chain planning session and accesses the data stored in the database associated with the one or more supply chain entities. The server system also incrementally and optimally adjusts the supply chain plan based on the one or more received perturbations and the data stored in the database and communicates the incrementally adjusted supply chain plan to the one or more supply chain entities.

Abstract: The technology relates to a seamless interface between an autonomous vehicle service provider and one or more ridesharing, ride-hailing or delivery partner companies, in order to provide timely, efficient rider or delivery services and support. A partner trip application programming interface (API) provides robust features to the ridesharing or ride-hailing partner companies and also supports delivery of meals, groceries, packages or other cargo. For instance, the API may be employed with delivery partners (e.g., food, package or bulk cargo delivery), and/or for concierge services (e.g., a hotel or medical provider or an e-commerce specialist that coordinates deliveries). The technology supports both ad hoc and scheduled trips. Agents for different partners may schedule trips to or from specific stores or other (geofenced) locations, and observe and manage trips for an entire enterprise. Permissions can be tailored for each agent.

Abstract: The present invention discloses a disruptive low capital and operational cost logistics system and method that provides for fast and massive delivery of e-commerce merchandise, including same day delivery, of thousands of items and packages, in extensive geographical areas, such as whole states, countries and continents, reducing the need for building, operating, or using multiple fulfillment warehouses located near the consumers as in traditional e-commerce logistics, creating a revolution in the e-commerce industry worldwide. In a disruptive manner, the systems and methods of the present invention facilitate the logistics for e-commerce delivery processes, and also may allow at the same time reducing the use of massive quantities of cardboard packages that are used for protection and containment for e-commerce orders, being sustainably beneficial for the e-commerce market, the environment, and the consumer.

Abstract: Disclosed is a an apparatus for performing smart logistics monitoring including a display unit, a memory, a sensor unit sensing at least one of a temperature, acceleration, humidity, illuminance, inclination, impact, and location of an inside of a logistics vehicle, and a control unit that generates respective status information of a logistics according to a sensed result at a predetermined period, generates a respective QR code indicating the respective status information, and displays the respective QR code on a screen of the display unit. The respective QR code is converted and displayed on the screen depending on an order in which the respective QR code is generated.

Abstract: In some examples, a computing device sends, to an application on a user device, item information to cause the application to present a user interface including information about items available from a merchant. In response to receiving a user input via the user interface to select an item from the merchant, the computing device determines that a likelihood that the item will be unavailable exceeds a threshold. The computing device sends a communication that causes the application to present a plurality of selectable options to indicate actions to perform when the item is unavailable. The computing device receives a request to place the order for the item, and an indication of the action to perform. In response to receiving a communication from the merchant device indicating that the item is unavailable, the computing device sends an instruction to the merchant device indicating the action to perform.

Abstract: Disclosed herein is a cross-dock management system comprises: a plurality of movable platforms configured to hold one or more pallets or parcels; at least one barcode or RFID tag positioned on each of said movable platforms, pallets, or parcels, wherein the barcode readers are configured to read the barcodes and RFID readers are configured to read the RFID tags. The data scanned by the barcode readers and RFID readers is stored in a local warehouse database and is used to determine an optimized placement and load for each movable platform in the warehouse.

Abstract: Systems, methods, and apparatus are disclosed that provide a pickup process for items purchased from a store. In some embodiments, a mobile computing device of a customer may determine whether the mobile computing device and therefore the customer are in a pickup zone for a store. In response to determining that the mobile computing device is in the pickup zone, the mobile computing device may notify the customer and request whether the customer wishes to initiate pickup of purchased items from the store. The mobile computing device may notify a merchandise pickup system of the customer's desire to pickup the purchased items.

Abstract: According to the present invention, a load receiving vehicle is provided. The load receiving vehicle comprises a storage unit usable as a receiving place of a delivery article; a lock control unit capable of controlling lock and unlock of a door of the storage unit; and a communication unit, wherein if the communication unit receives delivery schedule information representing a delivery schedule to the load receiving vehicle, information based on the delivery schedule information is provided to a driver.

Abstract: Techniques for predicting a manufacturer and/or contents of a received package are described herein. Images of a package may be received from cameras. A visual vector for the package in a vector space of package attributes may be generated using the images. Physical attributes of the package may be received. A subset of candidate packages may be determined by comparing the physical attributes of a plurality of historically received packages to the physical attributes of the package. A ranking of the subset of candidate packages may be determined by identifying a distance in the vector space of the package attributes between a vector for the subset of candidate packages and the visual vector for the package. An identifier associated with a particular package of the ranked subset of candidate packages may be obtained. Data for the particular package may be retrieved from a database using the identifier.

Abstract: The invention relates to the monitoring of products by means of active radio tags. According to the invention, packagings of products are provided with an active radio tag that detects at least one environmental condition and/or at least one packaging state, and which emits a signal at time intervals, which provides information about a unique identifier and at least one state in which the respective product is found. The signal is picked up by a receiver that extracts the unique identifier and the state information and transmits same together with location information to an external server.

Abstract: The invention relates to the monitoring of products by means of active radio tags. According to the invention, packagings of products are provided with an active radio tag that detects at least one environmental condition and/or at least one packaging state, and which emits a signal at time intervals, which provides information about a unique identifier and at least one state in which the respective product is found. The signal is picked up by a receiver that extracts the unique identifier and the state information and transmits same together with location information to an external server.

Abstract: The invention relates to the monitoring of products by means of active radio tags. According to the invention, packagings of products are provided with an active radio tag that detects at least one environmental condition and/or at least one packaging state, and which emits a signal at time intervals, which provides information about a unique identifier and at least one state in which the respective product is found. The signal is picked up by a receiver that extracts the unique identifier and the state information and transmits same together with location information to an external server.

Abstract: The invention relates to the monitoring of products by means of active radio tags. According to the invention, packagings of products are provided with an active radio tag that detects at least one environmental condition and/or at least one packaging state, and which emits a signal at time intervals, which provides information about a unique identifier and at least one state in which the respective product is found. The signal is picked up by a receiver that extracts the unique identifier and the state information and transmits same together with location information to an external server.

Abstract: The present disclosure discloses a method and an Internet of Things system for liquefied natural gas (LNG) management linked with warehousing, transportation, and a smart terminal.

Abstract: Disclosed herein are system, method, and computer program product embodiments for Computer-Aided Design (CAD) system add-ins configured to receive a CAD file of an assembly drawing, analyze the CAD file to extract part components located within the assembly drawing and add the extracted part components to a part component list of the assembly drawing. The system subsequently filters, based on a set of vendors sourcing the extracted part components, the part component list to identify specific vendors sourcing one or more of the part components or equivalent part components and determines availability of the part components for each of the identified specific vendors. The system subsequently generates, based on the availability of the part components, vendor-specific part component lists for each vendor with the availability, converts the vendor-specific part component lists to purchase orders and communicates the purchase orders to a corresponding one of the vendors.

Abstract: The system and methods described herein allow users to apply for a purchase of a good from multiple providers using provider specific methodologies for generating offers for the product. For example, the system described herein may include a multi-layer architecture that includes interactive micro-services that communicate together in a bi-directional manner to create a normalized process for the purchase of a good, such as commercial goods/products (e.g. a vehicle) or real property. The micro-services may assess prequalification for a loan or financing for a good, followed by determining eligibility of the good for financing, and further followed by calculating pricing details for loans (e.g. for financing purchase of the good) that would be offered for a consumer's particular financial credentials, for each of a plurality of lenders. Prequalification and pricing may be performed on a good by good basis, or for a plurality of goods near or substantially simultaneously.

Abstract: The system and methods described herein allow users to give their applicant information when seeking to submit an inquiry associated with a product provided by at least one entity, and have various lender microservices run in parallel, segregated by entity, in a jailed and self-contained, autonomous environment. The result of these microservices may be returned as a response to the inquity, being determined autonomously for each respective entity based on one or more respective rule sets or executable logic for each respective entity. Payloads for multiple entities may be combined in a single output from the jailed and self-contained environment due to outputs from the environment being encrypted in a universal format, wherein the outputs are decrypted in a user session in an application, allowing the user to see the results of the respective responses of each of the at least one entity, to their inquiry.

Abstract: A system for managing business to business communications may include an event generation unit configured to create a first event based on receiving a purchase order from a client. The system may also include an event detection unit in communication with the event generation unit, the event detection unit configured to detect the first event. The system may also include an action unit in communication with the event generation unit. The action unit may be configured to determine a first action to perform based on the detection of the first event, and perform the first action. The event generation unit may be further configured to create a second event based on the performance of the first action.

Abstract: A network-based communication fulfillment system includes a communication resource allocation server configured to receive a request for a communication service from a business user, wherein the communication service includes electronic communications and physical mailing pieces to be sent to recipients, an intelligent communication design server that can automatically create designs for the electronic communications and the physical mailing pieces, a communication server that can transmit the electronic communications to the recipients, and one or more product fulfillment centers that can print and finish the physical mailing pieces to be mailed to the recipients.

Abstract: A permissions management system and a method for managing permissions in a multiplatform environment. A centralized permissions management system is communicably coupled to a gateway service that receives API calls and requests for content from edge devices, such as user devices. The gateway forwards permissions requests to the centralized permissions management system that determines whether a given user identifier is permitted to access content referenced by a given content identifier. In response, the centralized permissions management system returns an authorization response that, in turn, is forwarded to an identified or determined platform which, in response, can serve content and/or service an API call.

Abstract: The present disclosure is directed toward systems, methods, and non-transitory computer readable media for generating, providing, and editing collaborative content items on client devices. For example, the disclosed systems provide a collaborative content item that includes a text display state and a render display state. A client device can provide for the collaborative content item to receive source text in the text display state. Then, based on the source text, the client device can provide for display of the collaborative content item in the render display state that generates a graphical representation for the collaborative content item based on rendering the source text. In some embodiments, the disclosed systems and methods allow two or more client devices to simultaneously modify the source text associated with the collaborative content item, and in turn, modify the graphical representation of the collaborative content item based on the modified source text.