International Business Machines Corporation

Ryan R Anderson

Joseph N Kozhaya

Anita Govindjee

Javier Torres

Justin Melby

William J O Green

Shikhar Kwatra

Lakshminarayanan Krishnamurthy

Rama Kalyani T Akkiraju

Niyati Parameswaran

Christopher Michael Madison

Joseph M Kaufmann

Tate Thomas Harnack

Benjamin Luedeman

John D Wolpert

Al Chakra

Phillip V Mann

Jessica R Eidem

Gary Francis Diamanti

Stephen Peter Mroz

Michael D O'Connell

Marvin Miles Misgen

Jenna Reinen

Sourav Mazumder

Rodrigo Goulart Silva

Rachel Ostrand

Hugh G Kohl

Susannah Shattuck

Annabella Cavello

Barak Krakauer

In an approach to monitoring and querying autobiographical events, one or more computer processors receive data from one or more sensors associated with a user. Based on the received data from the one or more sensors, one or more computer processors detect an autobiographical event associated with the user. One or more computer processors convert the received data from the one or more sensors into one or more observations associated with the autobiographical event. One or more computer processors convert the one or more observations into one or more questions associated with the one or more observations. One or more computer processors query the user with the one or more questions. One or more computer processors receive at least one response to the one or more questions from the user.

Monitoring and querying autobiographical events

A computer-implemented process for training a natural language processing (NLP) agent having a reinforced learning model includes the following operations. A type of document from a document corpus is identified using metadata particularly associated with the document. The NLP agent tokenizes the document to generate a plurality of tokens. Using a schema identified from the type of the document, one of the plurality of tokens is compared to a system of record (SOR) field from the schema. A similarity score between the one of the plurality of tokens with a correct value and a reward based upon the similarity score are generated. A determination is made that an optimum minimum average similarity rate has not been obtained. Based upon the determination, the reinforced learning model is trained using a loss function that includes the reward.

Machine learning for training NLP agent

Microservices are predictively deployed on edge devices in a network. An application is run on a client device, the application comprising a set of microservices runnable on any edge device in a set of two or more edge devices. A state of the client device at a first time is determined, the state including one or more microservices currently being run for the client device, and for each microservice currently being run, an edge device running the microservice. One or more microservices that are likely to be run at a second time subsequent to the first time and a location of the client device at the second time are predicted. Based on the predicted location, a next edge device in the set of edge devices is determined for running the one or more microservices predicted to be run at the second time.

Intelligent dynamic communication handoff for mobile applications

Vibration shock mitigation for components in a server rack includes a server rack comprising: a first server component chassis and a second server component chassis installed in adjacent locations within the server rack; and a chassis gap filler comprising: an elastic dampening sheet configured for placement between the first server component chassis and the second server component chassis, wherein the elastic dampening sheet is further configured to cover a portion of one side of the first server component chassis; and at least two attachment points configured to secure the elastic dampening sheet to the server rack.

Vibration shock mitigation for components in a server rack

A method administers a therapeutic treatment for a neurological impairment of a patient. One or more processor(s) display query content on a display, and then receive responses to the query content from a patient. The processor(s) identify a physiological locus of a neurological impairment of the patient based on the responses to the query content from the patient, and administer a therapeutic treatment to the patient based on the identified physiological locus of the neurological impairment of the patient.

Diagnosing and treating neurological impairments

Utilizing a computing device executing a master chatbot and one or more modular chatbots to respond to one or more chat messages. A computing device executing the master chatbot receives one or more chat messages. The computing device parses the received one or more chat messages to discover an intent and entities contained within the chat messages. A ranking algorithm is employed to rank the master chatbot and a plurality of modular chatbots, the ranking algorithm scoring the master chatbot and the plurality of modular chatbots based upon the intent and entities contained within the one or more chat messages. The master chatbot responds to the chat message if the ranking algorithm rates the master chatbot highest or forwards automatically the one or more chat messages to a ranked modular chatbot for response if the ranking algorithm rates the ranked modular chatbot highest.

Chatbot orchestration

A computer-implemented method, a computer program product, and a computer system for personalized machine learning model management and deployment on edge devices. An edge server monitors activities performed on respective ones of edge devices. The edge server associates machine learning models in a model set with respective ones of the activities. The edge server predicts a next set of activities that are to be performed on the respective ones of the edge devices. The edge server deploys, on the respective ones of edge devices, machine learning models that are associated with the next set of the activities. Applications on the respective ones of the devices, which execute the next set of the activities, leverage the machine learning models that are associated with the next set of the activities.

Personalized machine learning model management and deployment on edge devices

A method authenticates a user in order to activate an access mechanism for a device. One or more processors detect a real-time initial emotional state of the user, where the real-time initial emotional state of the user dynamically changes over time. The processor(s) present content as a stimulus to the user, and predict a predicted post-stimulus emotional state of the user, where the predicted post-stimulus emotional state of the user is predicted to be caused by the content being presented to the user, and where the predicted post-stimulus emotional state is dependent upon the real-time initial emotional state of the user. The processor(s) detect a real-time post-stimulus emotional state of the user. The processor(s) match the predicted post-stimulus emotional state of the user to the real-time post-stimulus emotional state of the user, and then authenticate the user and activate an access mechanism for a device.

User authentication by emotional response

In one general embodiment, an apparatus includes a base having a face and back, a center section, and a foldable section extending from the center section. The apparatus further includes a perforated sheet extending along the face of the base, members extending from the foldable section for engaging perforations of the perforated sheet, and the foldable section being positioned to apply tension to the perforated sheet upon folding of the foldable section toward the back of the base.

Suspension apparatus for suspending an item

An embodiment of the invention may include a method, computer program product and computer system for neural activity interpretation. The method, computer program product and computer system may include a computing device that presents a first user with a stimulus and monitors and maps the neural activity of the first user. The computing device may receive the first user's verbal reaction to the stimulus and map the linguistic data of the first user's verbal reaction to form a high dimensional vector based on the relationships of the mapped neural activity and the mapped verbal reaction of the first user. The computing device may associate the high dimensional vector with the stimulus presented resulting in a thoughts model. The computing device may receive a second user's neural activity and compare that second user's neural activity to the thoughts model to identify the neural activity in the second user.

Predicting thought based on neural mapping

Neural mapping

The present invention provides a block protector assembly including a protector contoured to conform to a block of pallet where the pallet includes a plurality of blocks, and an attachment mechanism coupled to the protector, where the attachment mechanism is configured to secure the protector to the block of the pallet, where the protector includes a rigid material. The present invention also provides a method including determining a contour of a block of a pallet, fabricating a protector to follow the contour of the block, and securing the protector to the block. In addition, the present invention provides a protector configured to prevent damage to a block of a pallet, where the protector includes a first side contoured to a first side of the block, a second side contoured to a second side of the block, and a third side contoured to a third side of the block.

Protecting pallet blocks

A method, apparatus, system and a computer program product are provided for scoring performance of a chatbot by capturing specified node performance metrics based on user interactions with one or more nodes in a dialog flow for the chatbot; assigning a score to each of the one or more nodes based on the specified node performance metrics; and assessing a performance measure for at least a portion of the chatbot by combining scores assigned to selected nodes in the dialog flow.

System and method for scoring performance of chatbots

A natural language query (NLQ) is translated to a structured data query (e.g., a SQL statement) by extracting entities from the NLQ and replacing them with generic variables to form a generic query. The generic query is associated with a structured question type which includes structured data variables using natural language classifiers (NLCs). Specific data is inserted in the structured question type in relation to the structured data variables based on the extracted entities to form the structured data query. An ensemble of NLCs trained with different ground truths can be used to yield multiple candidate question types. One of the candidate question types is selected based on confidence levels. The multiple NLCs can include an NLC which is optimized according to a focus of the generic query. For example, an NLC can be optimized for a specific data structure (such as SQL), or for comparative queries.

Growing community of inventors

Kensington, CA, United States of America

Ryan R Anderson