Abstract: Embodiments described herein provide a system for facilitating efficient dataset management. During operation, the system obtains a first dataset comprising a plurality of elements. The system then determines a set of categories for a respective element of the plurality of elements by applying a plurality of AI models to the first dataset. A respective category can correspond to an AI model. Subsequently, the system selects a set of sample elements associated with a respective category of a respective AI model and determines a second dataset based on the selected sample elements.

Abstract: The present disclosure relates to methods and systems for determining an estimated time of arrival (ETA). The methods may include obtaining feature data related to an on-demand service order; obtain a parallel computing framework; determining a global ETA model based on the feature data and the parallel computing framework; and determining an ETA for a target route based on the global ETA model.

Abstract: According to a first aspect, it is presented a method for dynamically selecting a learning model for a sensor device. The learning model is configured for determining output data based on sensor. The method comprises the steps of: detecting a need for a new learning model for the sensor device based on performance of a currently loaded learning model in the sensor device; determining at least one feature candidate based on sensor data from the at least one sensor, wherein each one of the at least one feature candidate is associated with a different source of sensor data; selecting a new learning model, from a set of candidate learning models, based on the at least one feature candidate and input features of each one of the candidate learning models; and triggering the new learning model to be loaded on the sensor device, replacing the currently loaded learning model.

Abstract: A method for use with a computing device is provided. The method may include inputting an input data set into a first private artificial intelligence model generated using a first private data set and a second private artificial intelligence model generated using a second private data set. The method may further include receiving a first result data set from the first private artificial intelligence model and receiving a second result data set from the second private artificial intelligence model. The method may further include training an adaptive co-distillation model with the input data set and the first result data set. The method may further include training the adaptive co-distillation model with the input data set and the second result data set. The adaptive co-distillation model may not be trained on the first private data set or the second private data set.

Abstract: A dynamic learning method for a robot includes a training and learning mode. The training and learning mode includes the following steps: dynamically annotating a belonging and use relationship between an object and a person in a three-dimensional environment to generate an annotation library; acquiring a rule library, and establishing a new rule and a new annotation by means of an interactive demonstration behavior based on the rule library and the annotation library; and updating the new rule to the rule library and updating the new annotation to the annotation library when it is determined that the established new rule is not in conflict with rules in the rule library and the new annotation is not in conflict with annotations in the annotation library.

Abstract: Techniques and solutions are described for facilitating the use of machine learning techniques. In some cases, filters can be defined for multiple segments of a training data set. Model segments corresponding to respective segments can be trained using an appropriate subset of the training data set. When a request for a machine learning result is made, filter criteria for the request can be determined and an appropriate model segment can be selected and used for processing the request. One or more hyperparameter values can be defined for a machine learning scenario. When a machine learning scenario is selected for execution, the one or more hyperparameter values for the machine learning scenario can be used to configure a machine learning algorithm used by the machine learning scenario.

Abstract: A model correction tool automatically detects and corrects model drift in a model for a machine learning application. To detect drift, the tool continuously monitors input data, outputs, and/or technical resources (e.g., processor, memory, network, and input/output resources) used to generate outputs. The tool analyzes changes to input data, outputs, and/or resource usage to determine when drift has occurred. When drift is determined to be occurring, the tool retrains a model for a machine learning application.

Abstract: Example prediction methods and apparatus are described. One example includes sending a first model parameter and a second model parameter by a server to a plurality of terminals. The first model parameter and the second model parameter are adapted to a prediction model of the terminal. The server receives a first prediction loss sent by at least one of the plurality of terminals. A first prediction loss sent by each of the at least one terminal is calculated by the terminal based on the prediction model that uses the first model parameter and the second model parameter. The server updates the first model parameter based on the first prediction loss sent by the at least one terminal to obtain an updated first model parameter. The server updates the second model parameter based on the first prediction loss sent by the at least one terminal to obtain an updated second model parameter.

Abstract: A method for performance tuning in Automated Machine Learning (Auto ML) includes obtaining preset application program interface and system resources of the automatic machine learning system. Performance index measurement values are obtained according to the preset application program interface when the system pre-trains deep learning training model candidates. A distribution strategy and a resource allocation strategy are determined according to the performance index measurement values and the system resources and computing resources of the system are allocated according to the distribution strategy and the resource allocation strategy. The disclosure also provides an electronic device and a non-transitory storage medium.

Abstract: Computer implemented systems and methods are disclosed for extracting specific data using machine learning algorithms. In accordance with some embodiments, a memory device that stores at least a set of computer executable instructions for a machine learning algorithm and a pre-fill engine; and at least one processor that executes the instructions that cause the pre-fill engine to perform functions that include: receiving electronic documents, seed dataset documents, and pre-fill questions; determining output data that enable navigation through the electronic documents using the machine learning algorithm; determining output questions that enable navigation through the electronic documents using the machine learning algorithm; determining output documents to enable navigation through the electronic documents using the machine learning algorithm; and presenting one or more answers for one or more of the output questions using a graphical user interface.

Abstract: A system and a method are disclosed for replacing a listing of a canceled booking for a guest user. In an embodiment, an accommodation management system receives an indication that a booking by the guest user has been canceled. The system retrieves, from an attribute database, attributes of the canceled listing and maps each attribute to a set of similar attributes in an equivalence table. The system retrieves, from a listing database, a set of comparable listings, each of which includes one or more of the mapped similar attributes and available during the same time period as the canceled booking. The system books one of the comparable listings for the guest user during the time period by populating a booking data structure with a connection between the comparable listing and the guest user.

Abstract: Aspects described herein may provide determination of a pedestrian route for a user to reach a seating area inside of a venue. Financial transaction data of the user may be reviewed to determine the user purchased one or more tickets to an event at the venue. Information regarding the event or the venue may be determined including seating charts for the venue and whether the tickets are for assigned or unassigned seats. Crowd densities inside and outside of the venue may be determined. The pedestrian route may be determined based on the crowd densities, number of tickets, and type of seating. The route may be updated as conditions change including any change to the crowd densities or change to seating availability. The route may increase a likelihood that the user reaches the seating area prior to a start of the event, and in a less stressful manner.

Abstract: A device, system and method for mode-based synchronization of data records is provided. Booking data is received, at one or more computing devices, from one of a first and second client device. When received from the first client device, in a first order mode for the booking data, the device(s): cause an order management system (OMS) to generate: order data at a first database; and cause a legacy system to generate a corresponding passenger name record (PNR) at a second database, the corresponding PNR being slaved to the order data. When received from the second client device, in a legacy mode for the booking data, the device(s): cause the legacy system to generate, a PNR and/or ticket data at the second database; and cause the OMS to generate corresponding order data at the first database, the corresponding order data being slaved to the PNR and/or the ticket data.

Abstract: A method for generating a report is provided. The method may include acquiring a key word related to an industry field, and acquiring one or more condition values related to the report to be generated. The method may also include determining a report template having one or more data query sections and one or more conclusion sections based on the industry field and the one or more condition values, and acquiring report data based on the one or more data query sections of the report template. The method may further include determining one or more conclusions based on the report data, and generating the report based the data acquired based on the report data, the one or more conclusions, and the template.

Abstract: A method for managing customers for a store includes generating first account identification information from stored account information of a customer. The method also includes transmitting a list of candidate payees within a predefined distance of a current geolocation of a personal communication device of the customer and identifying the store as a party to a transaction with the customer based on feedback. The method still further includes receiving, from the store, a transaction message indicating the customer is a counterparty to the transaction, the transaction message comprising second account identification information received at the communication device of the store from the customer. The method also includes determining the first account identification information matches the second account identification information.

Abstract: According to the embodiments illustrated herein, a method is disclosed. The method comprises receiving, by a computing device comprising a processor, an input from an operator device, wherein the input facilitates determining a task to be performed. Further, the method comprises activating, by the computing device, a first light device associated with a first location in a workplace in response to receiving the input, wherein the first location is associated with the task to be performed. Furthermore, the method comprises receiving, by the computing device, a first voice input from the operator device, indicative of an exception encountered during execution of the task. Additionally, the method includes modifying the task, in response to determining that the first voice input is indicative of the exception encountered during execution of the task.

Abstract: A device may receive data that identifies applications utilized by users, databases utilized by the applications, and the users, and may process the received data, with first models, to determine context data that matches the users and events associated with the applications, and task data that identifies tasks to be performed by the users in response to the events. The device may process the received data and the context data, with a second model, to generate role data that identifies user interfaces utilized by the users to access the applications, and credentials of the users, and may process the context data, the task data, and the role data, with a third model, to generate persona data that identifies personas, and assignment data that assigns each of the users to one of the personas. The device may perform actions based on the persona data and the assignment data.

Abstract: A method for providing candidate recommendations for an open position based on problem solving proficiency and culture matching includes: receiving job posting data from a first computing system, the job posting data including employer culture markers and job criteria values; receiving candidate information for a candidate, the candidate information including candidate culture markers, text submissions, and candidate values; determining a culture match score by comparing the employer culture markers against the candidate culture markers; determining a problem solving proficiency level for the candidate by applying a problem solving algorithm to the text submissions; and transmitting a hiring recommendation for the candidate to the first computing system based on the determined culture match score and problem solving proficiency level for the candidate and the criteria values.

Abstract: An information processing apparatus includes an accumulation unit that accumulates history information regarding a flight history of an aircraft. A specification unit, based on the history information accumulated by the accumulation unit, specifies a candidate to be an operation assistant who assists an operation planned by an assisted operator. An output unit outputs information regarding the candidate to be the operation assistant specified by the specification unit.

Abstract: A method for improving communications in a digital collaboration environment by receiving a communication directed to a first user, determining that the first user is unavailable, in response to determining that the first user is unavailable, determining a second user based on an attribute, and notifying the second user about the communication directed to the first user.

Abstract: A computer-implemented method for improving efficiency in an electronic procurement system for sourcing resources, comprising, during digital electronic interactions of a buyer computer with one or more software platforms and without receiving explicit request for recommendations from the buyer computer: automatically generating, at a coding computer, implicit observation data of the buyer computer; automatically determining, at the coding computer, one or more active sourcing events from a plurality of sourcing events, based on at least the implicit observation data of the buyer computer; using the coding computer, causing to display at least one of the one or more active sourcing events in a graphical user interface.

Abstract: Initial sales cluster is divided by the control circuit into a plurality of velocity buckets. Subsequently, each velocity bucket is divided into a plurality of micro-clusters. The micro-clusters are defined according to demographic information or store characteristic information. A importance score and a performance score for each of the micro-clusters is determined. An optimal sales cluster and a corresponding optimal planogram for each retail store in each micro-cluster are determined based upon the importance score and the performance score.

Abstract: A case management system is configured to provide one or more case generation and management functions. As configured, the case management system enables a user to define a workflow, the workflow including one or more states, one or more operations which may be performed at the one or more states, and one or more transitions corresponding to the operations and defining a sequence of the states; to generate and configure a state machine; to receive a workflow identifier to assign to the state machine; and through a command received from a client device, to open and manage a case based on the configuration of the state machine.

Abstract: An engineering support system that supports engineering of a process control system, the engineering support system includes: a server device that creates a work list including work order information that specifies a work order of work included in the process control system; and at least one client device that gives work authority to each worker based on the work list issued by the server device and that enables work on devices included in the process control system within a scope of given work authority to be implemented in the work order.

Abstract: Proposed is an automated telematics-based system (1) for score-driven operations associated with motor vehicles (41, . . . , 45) or transportation means of passengers or goods and based on a dynamic, telematics-based data aggregation, and method thereof, for automated risk-transfer related to complex peer-to-peer lending schemes, especially related to vehicles and car sharing schemes and sharing economy transportation schemes related to risks associated with damages to third parties. The telematics-based system (1) comprises telematics devices (411, . . . , 415) associated with the plurality of motor vehicles (41, . . . , 45), wherein the telematics devices (411, . . . , 415) comprise a wireless connection (42101-42108) to a central, expert-system-based circuit (11). The telematics devices (411, . . . , 415) are connected via interfaces (421, . . . , 425) to the sensors and/or measuring devices (401, . . . , 405) and/or an on-board diagnostic system (431, . . .

Abstract: A device may receive historical risk data identifying historical risks associated with entities, and historical compliance data identifying historical compliance actions performed by the entities. The device may train a machine learning model with the historical risk data and the historical compliance data to generate a structured semantic model, and may receive entity risk data identifying new and existing risks associated with an entity. The device may receive entity compliance data identifying new and existing compliance actions performed by the entity, and may process the entity risk data and the entity compliance data, with the structured semantic model, to determine risk and compliance insights for the entity. The risk and compliance insights may include insights associated with a key performance indicator, a compliance issue, a regulatory issue, an operational risk, a compliance risk, or a qualification of controls. The device may perform actions based on the risk and compliance insights.

Abstract: An online system receives a content item including a link to a landing page and determines a likelihood the landing page violates an online system policy based on a structural similarity between the landing page and a web page violating the policy. To determine the likelihood, the online system determines a hierarchical structure associated with the web page violating the policy and an additional hierarchical structure associated with the landing page. The hierarchical structure represents a structure of at least a portion of the web page and the additional hierarchical structure represents a structure of a corresponding portion of the landing page. The online system compares the hierarchical structure and additional hierarchical structure. Based on the comparison, the online system computes a measure of dissimilarity between the hierarchical structure and additional hierarchical structure and determines a likelihood the landing page violates the policy based on the measure of dissimilarity.

Abstract: A method and system for capturing research decision flow in a Research and Development (R&D) activity are provided. The method includes defining an objective of the R&D activity and determining one or more requirements for fulfilling the objective of the R&D activity. Further, the method includes identifying a set of risks associated with failure to satisfy the one or more requirements. Furthermore, the method also includes defining a set of tests to verify that the requirements are satisfied or the risks have been mitigated. Furthermore, the method also includes developing a task plan to satisfy the one or more requirements and mitigate one or more risks of the set of risks. Furthermore, the method also includes linking the objective, the one or more requirements, the set of risks and the task plan, to generate a linked information record.

Abstract: A computer-implemented method, comprises providing, by a platform server configured to hold security assets on behalf of a plurality of user accounts, a plurality of user accounts hosted by the platform server, each of the plurality of user accounts holding shares of a common equity with associated shareholder voting rights. The platform server receives a request to send proxy voting rights, wherein the proxy voting rights indicate a desire of the first user to transfer a shareholder voting instruction to a second user. The platform server determines based on transaction history of one or more user accounts of the plurality of user accounts, one or more recommended proxy users for transferring the proxy voting rights. The platform server transmits to the application executing on the device associated with the first user, a request to select one of the recommended proxy users.

Abstract: Disclosed herein are techniques and tools for verifying data for semantic correctness and/or verifying data for network correctness. In one respect, a method includes receiving an input defining at least two master nodes and at least one master link, each master node having at least one or more respective data properties populated with master node data and the master link having at least one or more master link data, the master nodes and master link defining a master semantic network, importing source data into a second semantic network, comparing the source data to the master node data and making a first determination that the source data reflects a data relationship defined by the master node data, and based on the first determination, populating the source data into the second semantic network, wherein the source data populated within the second semantic network reflects the data relationship defined by the master node data and the master link data.

Abstract: A system, method and article of manufacture are provided for detecting message impressions from a document. The document includes one or more data collection areas adapted to receive input, and one or more message areas. Each message area includes a message. Memory representations of messages are stored in a memory. The document is received at a document processing engine which is adapted to access the memory to obtain the representations of messages. Message impressions are detected from the document by analyzing the document in the document processing engine. Message impressions are detected if it is determined that there is relevant input in the one or more data collection areas, and the document includes a representation of one or more of the messages.

Abstract: A system performs a loss factor determination which refers to, for each of two or more different Ms from among 4 Ms (Man, Machine, Material, and Method), a time series data group representing a time series of a state of an element belonging to the M, and which determines, for each period between time points, whether or not a state combination in the same period between time points corresponds to one or a plurality of loss state combinations. In each period between time points, the state combination is a combination of two or more states belonging to the period between time points and corresponding to the two or more Ms. The loss state combination is a state combination defined as an opportunity loss. With each loss state combination, a loss factor, which is a factor of an opportunity loss corresponding to the loss state combination, is associated.

Abstract: A social networking system builds a quality controlled and desired population-representative pool of human raters to provide ratings on content items to improve a feed ranking model used for providing its users with more relevant content. The system identifies a pool of candidate human raters for providing ratings on a feed of content items. For each candidate human rater of the pool of candidate human raters, the system presents a feed of content items based on a feed ranking model, obtains ratings on the feed of content items, and determines a score representing the consistency of the obtained ratings, the representativeness of the pool of human raters, or the relevance of the content provided by the ranking model. The system uses the computed scores to modify the ranking model used to present content to its users for improving the relevance of the presented content.

Abstract: Systems, apparatuses, and methods include an intraocular lens (IOL) cart that may assist with inventory management and may help users identify an IOL for use in a particular surgical application. The IOL cart may include sensors and indicators that provide information to a user and may update IOL inventory automatically whenever the IOL cart is accessed by a user.

Abstract: The technology relates to cargo vehicles. National, regional and/or local regulations set requirements for operating cargo vehicles, including how to distribute and secure cargo, and how often the cargo should be inspected during a trip. However, such regulations have been focused on traditional human-driven vehicles. Aspects of the technology address various issues involved with securement and inspection of cargo before a trip, as well as monitoring during the trip so that corrective action may be taken as warranted. For instance, imagery and other sensor information may be used to enable proper securement of cargo before starting a trip. Onboard sensors along the vehicle monitor the cargo and securement devices/systems during the trip to identify issues as they arise. Such information is used by the onboard autonomous driving system (or a human driver) to take corrective action depending on the nature of the issue.

Abstract: A system and method for en-route business selection and ordering with optimized packaging for food delivery and takeout. The system is a cloud-based network containing an optimization server, portals for restaurants, customers, and drivers to enter their information, a rules library, a label manager, and a food packaging optimization module which determines optimal packaging groupings and configurations based on a multitude of variables associated with the restaurant, customer preferences, and the available menu. The system may be accessed through web browsers or purpose-built computer and mobile phone applications.

Abstract: An electronic notification apparatus is disclosed. The electronic notification apparatus may include an image capture device which can scan a machine readable code on a physical object. A communication may thereafter be initiated to complete the transfer of the physical object to a user.

Abstract: A controller includes at least one processor that implements the instructions to execute a plurality of tasks. The plurality of tasks includes a management table obtaining task that obtains, from the management table including first information indicating a region and second information indicating a country or a region, a destination information obtaining task that obtains third information indicating a region of a shipping destination to which the terminal device is to be shipped, a first specifying task that specifies a first function, a determining task that determines whether a second function, with reference to the second information, needs to be specified, an estimation information obtaining task that in a case where the second function is determined to be necessary, obtains estimation information corresponding to the second information from an external device, and a second specifying task that specifies the second function.

Abstract: A receptacle for detecting delivery and retrieval events has a door sensor, an item sensor, a scanner, and a control unit for operating the sensors, and transmitting the sensor information for processing and analysis. A system can determine whether an event was a delivery or retrieval event based on sensor information and item tracking information. A system can further include an item configured to interact with a computing device.

Abstract: The present invention provides systems and methods for processing return transactions over a network. An embodiment of the invention discloses an online return application that generates an electronic return shipping label that can be delivered to a browser of a customer that wishes to make a return. Also, disclosed is the creation and transmission of label delivery links, which provide for dynamic generation and delivery of shipping labels.

Abstract: Event-based replenishment simulation for an enterprise supply chain is described. On a per item, per node, per epoch basis, the simulation may generate a stream of action events based on forecasted demand, supply chain logic, and policy inputs that are applied to a current-run state of the supply chain in order to yield a stream of observation events. Requested metrics may be received, and the observation events may then be transformed to predict values for the metrics as output of the simulation. The simulation may be repeated for a given epoch using discrete demand values from a demand distribution, for a plurality of epochs, and/or across a plurality of items at a plurality of nodes. Resultantly, the simulation output can be used for predicting a future run-state of the supply chain across items and nodes.

Abstract: The preset invention is an inventory-parts control system and supervisory arrangement suitable for tracking the actual use of and accounting for the ultimate disposition of at least some of the individual pieces constituting an implant (or a complete implant construct), which is then being surgically engrafted in-vivo. This inventory-parts control system and supervisory arrangement is accurate, reliable, and fully functional for inventory part control purposes during the surgery; and will account for the ultimate disposition of each required component item of that implant (or complete implant construct) individually and in a timely manner, as each part is individually surgically introduced and engrafted in-vivo at a preselected anatomic site upon or within the body of a living subject.

Abstract: The present invention discloses an inventory monitoring system with an intelligent shelf that includes a power and data communications hub having sensory logic of an inventory application, which generates sensory logic data related to inventory items tracked. Further included is a server computing device that includes a working logic of the inventory application, which updates server records using the sensory logic data received from the intelligent shelf. An Internet enabled mobile computing device having an interactive display logic of the inventory application displays updated server records received from the server computing device.

Abstract: Embodiments of the present disclosure include apparatuses, computer-implemented methods, and computer program products for automatic product verification and shelf product gap analysis. Some embodiments utilize a multi-imager imaging engine to capture at least two image data objects associated with at least a near field and a far field via corresponding near and far-field imagers. The far field image data object in some embodiments is processed to identify, and/or detect and decode, product information on a product label at a shelving location for future processing. The near-field image data object may be processed to identify a product set located within the environment surrounding the product label. The information identified from each image data object may be processed to identify whether one or more product mismatches, pricing mismatches, and/or product gaps are present at the shelving location, with improved likelihood of success for each task.

Abstract: A system and method for real-time inventory and food portion management. The system is a cloud-based network containing a predictive inventory management engine, an inventory optimization engine, a food logger, mobile and compute devices, staff and vendors, gateways for vendors and staff to interface with financial institutions and other 3rd party businesses, enterprise database to store and retrieve including financial data, staffing data, and inventory data. The system can optimize organizational operations by predicting and optimizing in real-time key operational decisions using artificial intelligence or other computerized methods around inventory and food portion management based upon a multitude of variables associated with the patron and enterprise.

Abstract: Systems and methods that employ an autonomous robotic vehicle (ARV) alone or in combination with a remote computing device during the installation of electronic shelf labels (ESLs) in a facility are discussed. The ARV may detect pre-existing product information from paper labels located on modular units prior to their removal and then detect the location of electronic shelf labels (ESLs) after installation. Pre-existing product information gleaned from the paper labels is associated with the corresponding ESLs. The ARV may also determine compliance or non-compliance of modular units to which an ESL is affixed with a planogram of the facility.

Abstract: A method, a computer program product, and a computer system manage meeting divergence for a meeting involving a plurality of participants to discuss a plurality of core intents. The method includes receiving a first contribution from a first one of the participants during the meeting. The method includes determining a first one of the core intents that the first contribution is associated. The method includes determining a linkage of the first contribution to at least one second, previous contribution provided during the meeting. The method includes generating a graphical representation of a progress of the meeting, the graphical representation including a first visual indicator corresponding to the first contribution and at least one second visual indicator respectively corresponding to the at least one second contribution. The first visual indicator is positioned with respect to the at least one second visual indicator to represent the linkage.

Abstract: A system includes a memory, a survey engine, and a reporting engine. The memory stores identifying information of a plurality of users. The survey engine determines a question to present to each user of the plurality of users and determines an interval for each user of the plurality of users. The determined interval for a first user of the plurality of users is different from the determined interval for a second user of the plurality of users. For each user, the survey engine communicates to that user, based on the stored identifying information, the determined question for that user according to the determined interval for that user and receives a response from each user of the plurality of users. The reporting engine generates a report based on the received response from the plurality of users.

Abstract: System and methods for enhancing user productivity by integrating multiple services and providing a centralized output to a user is disclosed. A message notification server may receive store a set of notification rules and, as various notifications are received, the server may dynamically monitor them for processing to users. The system may automatically re-rank the notifications based on changed conditions or to present messages of greatest urgency or importance. The system may also store sender-specific sets of rules, governing how notifications are to be handled for different application servers or services.

Abstract: In a computer-implemented method for information retrieval and a processing system of a computer-implemented information retrieval system, an input text is received by a Natural Language Processing, NLP, suite, wherein the NLP suite comprises a plurality of models. At least one of the plurality of models is a model trained using selected features. The selected features are determined using a feature selection process. The input text is processed by each one of the plurality of models. An intermediate representation of the input text is generated by each one of the plurality of models. An enhanced representation of the input text is generated by combining a plurality of the generated intermediate representations. Information is retrieved based on the enhanced representation of the input text.