Abstract: Methods and systems for performing multi-task learning of query intent and named entities are provided. One method includes receiving a query comprising query text. The method further includes providing the query text to a neural network model implemented on a computing system, the neural network model having a plurality of layers, wherein at least one layer comprises a plurality of loss functions including a named entity tag learning loss function and an intent classification loss function. The method also includes obtaining, from the neural network model, an identification of a named entity and a query intent derived from the query text. A query response may be formulated based, at least in part, on the named entity and query intent.

Abstract: Methods and systems for generating link predictions are provided. In one aspect, a method includes initializing a graph including a plurality of nodes representing selections of items in a training dataset to a multivariate normal distribution having a predetermined mean and a predetermined initial variance, the items in the training dataset comprising items in an item collection. The method includes, for each node in the graph, modeling embeddings for the node as embeddings of each neighboring node having a shared edge, with each being updated based at least in part on a transition probability and a variance. A predetermined number of iterations of updating are executed each iteration including an updated variance based on a learning rate. Based on receipt of an identification of an item from among the item collection, a plurality of predicted selections of items are identified using the embeddings for a node corresponding to the item.

Abstract: A method of generating a fixed-price variable-offer multi-tier thread generator may include receiving, a by a computer processor(s), at least a fixed price, a thread expiration criteria and specification for at least two offerings for the fixed price. Each of the at least two offerings correspond to one of at least two tiers of offerings, where the fixed price entitles a first member and any subsequent members on a thread to redeem a qualified offer associated with a qualified tier, in exchange for paying the fixed price, upon the occurrence of at least one thread expiration criteria. The at least one product or service offerings the thread qualifies for, upon the occurrence of the at least one thread expiration criteria, may be dependent upon a total number of members, including the first member who starts a thread from the thread generator and any subsequent members who join the thread and who have agreed to pay the fixed price.

Abstract: Methods and systems for performing multi-task learning of query intent and named entities are provided. One method includes receiving a query comprising query text. The method further includes providing the query text to a neural network model implemented on a computing system, the neural network model having a plurality of layers, wherein at least one layer comprises a plurality of loss functions including a named entity tag learning loss function and an intent classification loss function. The method also includes obtaining, from the neural network model, an identification of a named entity and a query intent derived from the query text. A query response may be formulated based, at least in part, on the named entity and query intent.

Abstract: A method of generating a fixed-price variable-offer multi-tier thread generator may include receiving, a by a computer processor(s), at least a fixed price, a thread expiration criteria and specification for at least two offerings for the fixed price. Each of the at least two offerings correspond to one of at least two tiers of offerings, where the fixed price entitles a first member and any subsequent members on a thread to redeem a qualified offer associated with a qualified tier, in exchange for paying the fixed price, upon the occurrence of at least one thread expiration criteria. The at least one product or service offerings the thread qualifies for, upon the occurrence of the at least one thread expiration criteria, may be dependent upon a total number of members, including the first member who starts a thread from the thread generator and any subsequent members who join the thread and who have agreed to pay the fixed price.

Abstract: A method of generating a fixed-price variable-offer multi-tier thread generator may include receiving, a by a computer processor(s), at least a fixed price, a thread expiration criteria and specification for at least two offerings for the fixed price. Each of the at least two offerings correspond to one of at least two tiers of offerings, where the fixed price entitles a first member and any subsequent members on a thread to redeem a qualified offer associated with a qualified tier, in exchange for paying the fixed price, upon the occurrence of at least one thread expiration criteria. The at least one product or service offerings the thread qualifies for, upon the occurrence of the at least one thread expiration criteria, may be dependent upon a total number of members, including the first member who starts a thread from the thread generator and any subsequent members who join the thread and who have agreed to pay the fixed price.

Abstract: Methods and systems for generating link predictions are provided. In one aspect, a method includes initializing a graph including a plurality of nodes representing selections of items in a training dataset to a multivariate normal distribution having a predetermined mean and a predetermined initial variance, the items in the training dataset comprising items in an item collection. The method includes, for each node in the graph, modeling embeddings for the node as embeddings of each neighboring node having a shared edge, with each being updated based at least in part on a transition probability and a variance. A predetermined number of iterations of updating are executed each iteration including an updated variance based on a learning rate. Based on receipt of an identification of an item from among the item collection, a plurality of predicted selections of items are identified using the embeddings for a node corresponding to the item.

Abstract: A method of generating a fixed-price variable-offer multi-tier thread generator may include receiving, a by a computer processor(s), at least a fixed price, a thread expiration criteria and specification for at least two offerings for the fixed price. Each of the at least two offerings correspond to one of at least two tiers of offerings, where the fixed price entitles a first member and any subsequent members on a thread to redeem a qualified offer associated with a qualified tier, in exchange for paying the fixed price, upon the occurrence of at least one thread expiration criteria. The at least one product or service offerings the thread qualifies for, upon the occurrence of the at least one thread expiration criteria, may be dependent upon a total number of members, including the first member who starts a thread from the thread generator and any subsequent members who join the thread and who have agreed to pay the fixed price.

Abstract: Offset weight devices and methods of use. Some devices including a handle having a beveled end, an arm attached to the handle and at least one weight attached to the arm. Other devices include a central handle, a frame circumscribing at least part of the outer edge of the central handle, a rope or cable affixed to the frame, and at least one weight affixed to the rope or cable. The methods include holding an exercise device having a handle and at least one offset weight in a hand, and performing a fundamental upper extremity exercise. Other methods include determining an exercise protocol by evaluating a physical skill to determine fundamental motions associated with the skill and specifying an exercise using an offset weight device. Also included is a system for exercising with an offset weight device having a measuring device to measuring the results of using the offset device.

Abstract: This invention relates to the field of medical devices and particulary to a system for use for cryotherapy to injuries. The apparatus can be comprised of a container comprising a bottom surface and a body comprising at least one horizontal circumferential score line, wherein the bottom surface is attached to the body so as to form a container open at one end, where the horizontal circumferential score line facilitates the removal of a portion of the body of the container to enable a user to easily expose a layer of ice for purposes of cryotherapy. Such a system can also include a tray for holding several of such ice massage devices and a hooded enclosure for and protected and efficient storage of such a tray with such massage devices within a freezer space.