Abstract: A system uses conversation engines to process natural language requests and conduct automatic conversations with users. The system generates responses to users in an online conversation. The system ranks generated user responses for the online conversation. The system generates a context vector based on a sequence of utterances of the conversation and generates response vectors for generated user responses. The system ranks the user responses based on a comparison of the context vectors and user response vectors. The system uses a machine learning based model that uses a pretrained neural network that supports multiple languages. The system determines a context of an utterance based on utterances in the conversation. The system generates responses and ranks them based on the context. The ranked responses are used to respond to the user.

Abstract: A system is provided for a machine learning engine using clustered case objects in a case management system. The system includes a multi-layer neural network. The system is configured to receive case object data comprising a case object and contextual objects in the case management system associated with the case object, the contextual objects comprising word vectors, generate a context embedding for the case object using the word vectors for the contextual objects, and cluster the case object with other case objects in the case management system based on the context embedding for the case object and other context embeddings for the other case objects.

Abstract: A system is configured to analyze a corpus of historical chat data to identify the list of “best” responses. As such, the user is not required to identify a list of canned responses for input into the system. The described system uses a context word embedding function and response word embedding function to generate context vectors and response vectors corresponding to the corpus of conversation data, and the vectors are represented by a respective context matrix and a response matrix. The system processes these matrices to generate scores for responses, clusters the responses, and identifies the responses corresponding to the best scores for each cluster.

Abstract: A system and apparatus that reduces tire scrub on a truck and or trailer during turns. The system minimizes the redistribution of the load among the tires thereby spreading the load of the trailer or truck among the tires avoiding unnecessary overloading. The system operates without operator intervention and is capable of operating automatically on trailers, without control signals from the truck.

Abstract: A multi-tenant system stores a hierarchy of machine-learned models, wherein each machine-learned model is configured to receive as input a set of search results and generate as output scores for ranking the set of search results. Each machine-learned model is associated with a set of dimensions. The system evaluates search query performance. Performance below a threshold causes a new model to be generated and added to the hierarchy of models. Upon execution of a new search query associated with the same set of dimensions as the newly created model, the new model is used to rank that search query's search results.

Abstract: An apparatus for a vehicle is provided that has an axle and a spindle sleeve with a spindle sleeve inner surface axis coaxial with the axis of the axle, and a spindle sleeve outer surface axis not coaxial with the axis of the axle. A hub has an axis coaxial with the spindle sleeve outer surface axis, and the hub at least partially defines a chamber. First and second ports extend through a wall of the hub to the chamber. The hub rotates about the spindle sleeve through the aid of two bearings. Lubricant is present within the chamber, and the first port provides a pathway for a pressurized fluid to be introduced into the chamber to force the lubricant out of the chamber via the second port.

Abstract: An apparatus for a vehicle is provided that includes an axle with a keyway. A spindle sleeve is present that has a spindle sleeve inner surface axis coaxial with the axis of the axle. A spindle sleeve outer surface axis is not coaxial with the axis of the axle, and the spindle sleeve has a sleeve washer that has a keyway tab. A retaining nut is in selective rotating communication with the sleeve washer such that rotation of the retaining nut is communicated to the sleeve washer to cause the spindle sleeve to rotate relative to the axle when the retaining nut is in rotating communication with the sleeve washer. Rotation of the retaining nut is not communicated to the sleeve washer to cause the spindle sleeve to rotate relative to the axle when the retaining nut is not in rotating communication with the sleeve washer.

Abstract: An apparatus for a vehicle is provided that has an axle with an axis. A spindle sleeve with a spindle sleeve inner surface axis coaxial with the axis of the axle is present, along with a spindle sleeve outer surface axis that is not coaxial with the axis of the axle. The spindle sleeve has an inner surface and an outer surface. A sleeve washer is present along with a bearing that has an inner race, an outer race, and a roller. The inner race has an inner surface and a front surface in which the front surface is located forward of the inner surface in a lateral direction. The inner race has a curved surface that extends from the front surface to the inner surface, and the sleeve washer engages the front surface. The apparatus also includes a retainer that engages the spindle sleeve and the curved surface.

Abstract: A user provides a description of a neural network to a visualization tool. The visualization tool displays a user interface that includes a visual of the neural network based on the description. If the user interacts with a node or connection, for example by placing a cursor on the node/connection in the user interface, the user interface displays information associated with the node/connection. If the user selects a node of a layer, the neural network is applied to an input that corresponds to the selection and the user interface displays the propagation of the input through the neural network. Additionally, the user interface displays results from applying the neural network to the input.

Abstract: An apparatus for a vehicle is provided that has a spindle sleeve (12) with a spindle sleeve inner surface axis (14) that is coaxial with the axis of an axle (16). The spindle sleeve (12) has a spindle sleeve outer surface axis (20) that is oriented at an angle to the axis of the axle. A hub (28) is present that has a hub axis (30) that is coaxial with the spindle sleeve outer surface axis (20). A rotor (32) is coaxial with the hub axis (30) and brake calipers (34) are carried by the axle. A brake caliper positional correction device (36) is present and is carried by the axle (16) and has a correction surface (38) that carries the brake calipers (34). The correction surface (38) orients the brake calipers (34) such that the brake calipers (34) are properly positioned with respect to the rotor (32).

Abstract: A data processing system analyzes a corpus of conversation data collected at an interactive conversation service to train an intent classification model. The intent classification model generates vectors based on the corpus of conversation data. A set of intents is selected and an intent seed input for each intent of the set of intents is input into the model to generate an intent vector corresponding to each intent. Vectors based on user inputs are generated and compared to the intent vectors to determine the intent.

Abstract: A data processing system analyzes a corpus of conversation data collected at an interactive conversation service to train an intent classification model. The intent classification model generates vectors based on the corpus of conversation data. A set of intents is selected and an intent seed input for each intent of the set of intents is input into the model to generate an intent vector corresponding to each intent. Vectors based on user inputs are generated and compared to the intent vectors to determine the intent.

Abstract: Disclosed are various embodiments for a knife configured to be positioned, at least partially, within a grip of a firearm. The knife may include a blade body having a first blade side and a second blade side. The blade body may include a base and a knife edge portion. The knife may further include a handle portion. The handle portion may include the base of the blade body, a first handle attachment coupled to the base on the first blade side, and a second handle attachment coupled to the base on the second blade side. The knife may include an attachment mechanism for positioning at least the knife edge portion within an interior of the grip of the firearm.

Abstract: Disclosed are some implementations of systems, apparatus, methods and computer program products for extracting topics from a corpus of exchanges. The system generates vector representations of utterances of an entity common to the exchanges and uses the vector representations to cluster the utterances. The system labels the clusters and uses the labeled clusters to generate an exchange label sequence for each of the exchanges, where each exchange label sequence corresponds to a sequence of utterances generated by the entity. The system processes the exchange label sequences to generate one or more subsets of the utterances, where each of the subsets corresponds to a particular topic.

Abstract: Disclosed are some implementations of systems, apparatus, methods and computer program products for extracting state flow structures from a corpus of exchanges. The system generates vector representations of utterances of an entity common to the exchanges and uses the vector representations to cluster the utterances. The system labels the clusters and uses the labeled clusters to generate an exchange label sequence for each of the exchanges, where the exchange label sequence corresponds to a sequence of utterances generated by the entity. The system processes the exchange label sequences to generate a state flow structure, where each of the states is represented by a corresponding set of utterances.

Abstract: DESCRIBED HEREIN ARE SYSTEMS, APPARATUS, METHODS AND COMPUTER PROGRAM PRODUCTS FOR MACHINE LEARNING INTENT CLASSIFICATION. IN VARIOUS EMBODIMENTS, HISTORICAL UTTERANCES PROVIDED BY USERS MAY BE UTILIZED FOR BOT TRAINING. CONTEXT AND PERSONALLY IDENTIFIABLE INFORMATION MAY BE REMOVED FROM THE UTTERANCES. THE UTTERANCES MAY BE ASSOCIATED WITH VECTORS. THE UTTERANCES AND VECTORS MAY BE USED TO DETERMINE RECOMMENDATIONS.

Abstract: A system is configured to analyze a corpus of historical chat data to identify the list of “best” responses. As such, the user is not required to identify a list of canned responses for input into the system. The described system uses a context word embedding function and response word embedding function to generate context vectors and response vectors corresponding to the corpus of conversation data, and the vectors are represented by a respective context matrix and a response matrix. The system processes these matrices to generate scores for responses, clusters the responses, and identifies the responses corresponding to the best scores for each cluster.

Abstract: Disclosed are some implementations of systems, apparatus, methods and computer program products for integrating question generation and answer retrieval in a question answer system. The system generates a question using a set of documents and determines whether it is semantically distinct from questions in a question-answer repository. After determining that the question is semantically distinct from questions in the question-answer repository, the system adds the question to the question-answer repository. Upon receipt of a user-submitted question, the system uses the question-answer repository to identify a semantically similar question. The system retrieves an answer corresponding to the identified question from the question-answer repository and provides the answer in response to the user-submitted question.

Abstract: A data processing system analyzes a corpus of conversation data received at an interactive conversation service to train a response recommendation model. The response recommendation model generates response vectors based on custom responses and using the trained model and generates a context vector based on received input at the interactive conversation service. The context vector is compared to the set of response vectors to identify a set of recommended responses, which are recommended to an agent conversing with a user using the interactive conversation service.

Abstract: A record management system retrieves relevance information through an information retrieval model that models relevance between users, queries, and records based on user interaction data with records. Relevance information between different elements of the record management system are determined through a set of learned transformations in the information retrieval model. The record management system can quickly retrieve relevance information between different elements of the record management system given the set of learned transformations in the information retrieval model, without the need to construct separate systems for different types of relevance information. Moreover, even without access to contents of records, the record management system can determine relevant records for a given query based on user interaction data and the determined relationships between users, queries, and records learned through the information retrieval model.