Abstract: A continual learning method, comprising: obtaining, for each of a plurality of classes, a mean of each of a plurality of features generated by passing a plurality of training samples to a pre-trained convolutional neural network, and a covariance matrix of the plurality of features, wherein each of the training samples belongs to one of the classes; obtaining extracted features from the pre-trained convolutional neural network for an additional training sample belonging to a class of said classes; generating a centred feature vector using the mean for the class and the extracted features; updating, using the centred feature vector and the covariance matrix, the covariance matrix, wherein said updating is performed for diagonal elements of the covariance matrix but not for off-diagonal elements; updating the mean for the class using the extracted features; and outputting, based on the updated mean and updated covariance matrix, weights of a streaming linear discriminant analysis (SLDA) model.

Abstract: An apparatus for processing a workpiece with ultrasound comprises a base frame having a slide. A tool holder is connected to the slide via leaf springs, whereby a lifting device can move the tool holder relative to the slide.

Abstract: A method of collaboration includes creating an electronic document file representing a document, file having a plurality of sections denoted by table of contents metadata and using the table of contents metadata; identifying a plurality of document sections, receiving user input reflecting a preference for division of the plurality of document sections into separate section files and dividing the electronic document file into a plurality of separate section files; in response to user input indicating a first access control preference, providing access to a first of the plurality of separate section files to a first user; in response to user input indicating a second access control preference, providing access to a second of the plurality of separate section files to a second user; storing edits made by the first user to the first of the plurality of separate section files, in the first of the plurality of separate section files; storing edits made by the second user to the second of the plurality of separate

Abstract: Systems/techniques that facilitate automatic product support systems and methods via generative artificial intelligence (GAI) and customer interactions are provided. In various embodiments, a system can access an electronic interaction record pertaining to a software product. In various aspects, the system can synthesize, via execution of GAI on the electronic interaction record, first text that describes a problem afflicting the software product. In various instances, the system can determine, based on executing the GAI on the first text, whether there is an available software feature in an available software feature repository that addresses or solves the problem. In various cases, the system can, in response to a determination that there is no available software feature that addresses or solves the problem, synthesize, via execution of the GAI on the first text, a recommended design alteration to the software product that would address or solve the problem.

Abstract: Embodiments described herein relate to systems and methods for automated content assessment for collaboration platforms. An automation rule may be established that uses a condition component that utilizes a generative output engine. A trigger component may trigger the automation rule to run, for example when an object is created or modified. A content portion from the object may be used to generate a condition prompt for the generative output engine that also includes a classifier string for the content portion and a set of example input-output content to classifier pairs. Based on a returned generative response, the condition component of the automation rule may be satisfied, and one or more next components of the automation rule performed in response. In some examples, the next component may include actions or additional conditions that utilize the generative output engine.

Abstract: Systems and methods for receiving an indication authorized by a first entity to transfer ownership rights in a token to a second entity are provided. The indication comprises a set of verifiable qualifications associated with the second entity, the token comprising a record of a first value associated with the token, a record of at least a set of restrictions associated with the token, and a reference to an executable program. In response to execution of the executable program, committing to one or more records of an electronic ledger in the electronic ledger platform at least one of: the transfer of the token to the second entity in exchange for currency corresponding to the first value, in response to determining that the second entity is qualified for the ownership of the token based on an evaluation of the set of verifiable qualifications and the set of restrictions.

Abstract: Certain aspects of the disclosure provide a method for providing user support by generating recommended response for a customer verbatim with an ensemble of machine learning models. The method includes processing a customer verbatim with a topic model trained to identify a topic associated with the customer verbatim. The method further includes processing the customer verbatim with a sentiment model trained to determine a sentiment of the customer verbatim. The method further includes processing the customer verbatim with an actionability model trained to assign an actionability score to the customer verbatim. The method includes processing the topic, the sentiment, and the actionability score with a recommendation model to generate the recommended response to the customer verbatim.

Abstract: A system and method for verifying and managing claims involving three-dimensional (3D) print structures and components thereof is disclosed. The system employs a verification model that is trained to detect whether a given structure includes a 3D printed portion, as well as the type of 3D print mixture used and/or its manufacturer. This information can be used to reduce the likelihood of fraud by insured persons following damage to their insured structures. In some embodiments, the information can also be used to determine whether a subrogation clause should be triggered, and the 3D print replacement part be requested for printing from the manufacturer. In another example, the damaged 3D printed part can be printed by a local service partner in or near the region where the damaged structure is located, and installation performed by a trusted contractor.

Abstract: A session shared data system accesses a first communication between a user and a support agent on a first communication channel and stores communication data associated with the first communication in a session shared data object. The session shared data system accesses a subsequent communication between the user and a second agent on a second communication channel, receives a query associated with the subsequent communication and transmits the response to a device of the second agent.

Abstract: A computer system for sump pump monitoring and repair service provider notification may include one or more processors configured to: detect that a sump pump is faulty, transmit a prompt for service quotes to a machine learning (ML) chatbot to cause the ML chatbot to: request sump pump replacement or repair services from one or more service providers, receive cost estimates from the one or more repair service providers, receive schedule availability from the one or more repair service providers, receive, from the ML chatbot, the cost estimates and the schedule availability, and communicate the cost estimates and/or the schedule availability to a user associated with the sump pump.

Abstract: A computing system may include a memory and a processor configured to cooperate with the memory to interface with a plurality of virtual share exchanges (VSEs), receive requests from the VSEs to share payment of extraordinary healthcare bills from their members having a value exceeding a threshold bill amount across the other VSEs, and determine a shared reserve for each VSE that submits an extraordinary healthcare bill for payment sharing. The shared reserve may correspond to a value of member healthcare bills the VSE is permitted to share across the other VSEs. The processor may further verify that the VSE has not exceeded the shared reserve, and publish each extraordinary healthcare bill for payment sharing to the other VSEs as a respective member of each VSE upon verification that the VSE submitting the extraordinary healthcare bill has not exceeded the shared reserve.

Abstract: A computer-implemented approach is described that includes receiving a mass price computation request for a plurality of deals involving a plurality of vehicles. The request includes a data structure configured to store input values, and a tri-value field configured to store a tri-value, the tri-value being one of a first value, a second value, or a third value, the first value indicating a single computation is requested using the input values, the second value indicating a limited set of combinatorial calculations to be calculated using the input values, and the third value indicating a full set of combinatorial calculations using the input values. The approach further causes computing of each of the plurality of deals based on the data structure, and outputting results to a user device based on the mass price computation request.

Abstract: Insurance and warranty cataloging, detection and evaluation techniques are described for a micro insurance or warranty system. An example method for an insurance or warranty system includes receiving, at a server, an error code from a device of a user, processing the error code to extract sensor data related to one or more failed components of the device, determining the one or more failed components is covered within an insurance policy or warranty based on the sensor data, and issuing an insurance claim or warranty claim based on the one or more failed components being covered. In some embodiments, the micro insurance or warranty system includes analyzing the sensor data to determine the cause of the one or more failed components.

Abstract: Information handling systems are transported to a selected of plural micro manufacturing centers for harvesting of component modules to reuse in remanufactured information handling systems through an automated process that uses a robotic arm to harvest the component modules and rebuild the information handling systems. Component module health lifecycle information is applied to select components for harvesting. Carbon footprint, energy consumption, costs, any manual labor involved and time criticality are factored to select a geographical location to harvest the component modules and to send the system to subsequent end user locations.

Abstract: A method recycles residual material from processing a workpiece. The method includes the following steps: A) transmitting information about a desired material family of the residual material, tolerated accompanying materials in the residual material, and/or desired residual material part size, from a recycler computer to a workpiece processor computer; and B) workpiece processing with a processing machine while generating residual material. The method steps A) and B) can be carried out in any order or simultaneously and the following method step is carried out after the method step B): (D) collecting the residual material in a container with a logistics facility in accordance with the information transmitted.

Abstract: The information processing device manages a vehicle for package delivery and a logistics robot permanently installed in the apartment house. The information processing device includes a control unit that acquires information on whether maintenance of the logistics robot is necessary from the logistics robot, transmits information on the logistics robot that needs maintenance to the vehicle, and instructs the vehicle to collect the logistics robot that needs maintenance.

Abstract: An information processing apparatus includes a controller configured to acquire an identifier of a vehicle upon receiving a request for customization of the vehicle, identify one or more parts with which the vehicle is already equipped by searching a vehicle database that stores data on parts with which a plurality of vehicles is equipped using the acquired identifier as a key, and determine a work item for the customization according to the one or more identified parts.

Abstract: Embodiments of the invention relate generally to the field of content distribution platforms, and more particularly, to systems, methods, and apparatuses for implementing a consumer data aggregation platform for seamless product recall and consumer alert management.

Abstract: A self-guided troubleshooting guide generation method includes: receiving a first assistance request from the user; in response to receiving the first assistance request, scanning a first user interface (UI) through which the first assistance request is transmitted and extracting text from the first UI; parsing the extracted text and identifying an error message in the extracted text; comparing, after the identifying, the error message to data stored in an assistance request database; and generating, based on the comparing, solution information for resolving the error message and displaying the solution information on a display displaying the first UI.

Abstract: Disclosed herein are systems and method for streamlining renewable energy resource allocation. A method may include: receiving, from a user via a user interface, a request to view project and community information for a renewable energy project that reduces greenhouse gas emissions; identifying, from a plurality of renewable energy projects in a project database, a first renewable energy project located in a first community; determining a relevance score by comparing a first set of project attributes including budgetary and energy-based information of the first renewable energy project and a first set of community attributes including economical and demographical information of the first community with a set of user attributes including community preferences and project goals of the user; in response to determining that the relevance score is greater than a threshold relevance score, generating, for display on the user interface, project and community information for the first renewable energy project.