Abstract: Techniques are disclosed for identifying related events. In some cases, a first event triggers an analysis in which subsequent events within a time window are analyzed. A duration of a time window may be based on one or more attributes of a triggering event. Events subsequent to the triggering event are analyzed to determine if any of the subsequent events are related to or otherwise associated with the triggering event. The system determines a duration of the time window based on attributes associated with the triggering event. Basing the duration of the time window on attributes associated with the triggering event enables the system to search for related subsequent events within a time period within which any related events are likely to occur.

Abstract: The present application relates to a decorative tree and a tree stand thereof. The tree stand includes: a pole assembly configured to support a decoration; a support mechanism fixed on the pole assembly; a support arm hinged to the support mechanism and having a unfolded state and a folded state; a movable base movably disposed on the pole assembly and operably connected to the support arm to drive the support arm to switch between the unfolded state and the folded state; and a first locking mechanism disposed on the movable base and having a locked state and an unlocked state. When in the locked state, the first locking mechanism is capable of locking the support arm in the unfolded state; and when in the unlocked state, the first locking mechanism is capable of unlocking the movable base from the unfolded state. The support arms have the unfolded state and the folded state by hinging the support arm to the support mechanism, so that the overall volume of the tree stand can be changed.

Abstract: The present application relates to a decorative tree and a tree stand thereof. The tree stand includes: a pole assembly, support arms connected to a bottom end of the pole assembly and configured to be connected to a bottom of a decorative mesh; a first mounting member mounted on a top end of the pole assembly and including a locking portion; and a second mounting member movably disposed on the pole assembly and configured to be connected to a top of the decorative mesh. The second mounting member includes an engaging portion configured to be engaged with the locking portion to limit a movement of the second mounting member relative to the pole assembly.

Abstract: Systems and methods for candidate recommendation are provided. Candidate vectors are generated from candidate documents, and an initial ranking is performed according to a distance metric between the candidate vector and an objective vector generated based on an objective document to select a subset of the candidate documents. A feature vector is generated for each of the selected candidate documents. The feature vector includes features derived from a first vectorized representation of content from one of the candidate document and the objective document and a second vectorized representation of content from the one of the candidate document and the objective document. The feature vector is provided to a machine learning model to generate a score for each of the selected candidate documents. The selected candidate documents are ranked according the scores generated at the machine learning model to provide a ranked candidate list.

Abstract: Techniques are disclosed for organizing and distributing artifacts generated by processing pipelines for the training or application of machine learning models. An application may subscribe to a playlist of a stream of events and locally store a copy of the playlist. The subscriber may merge locally stored and/or selected events to generate a merged stream of events. The subscriber may then execute the merged event stream including the newly added instance of the event.

Abstract: Techniques for determining a Next Best Action (NBA) are disclosed, with the determination being based on a position within an application, past actions by a user when experiencing a similar application context, and/or tasks in queue for the user to execute from current state of the application. Techniques are also disclosed for displaying an interface that includes the NBA in conjunction with a specific rationale for presenting the NBA, such as recommendations by a trusted person, based on the user's and/or other users' past behavior, and descriptions developed based on the specific NBA. Also, methods for determining a best NBA are disclosed, with the NBA being selected by applying static rules to a data set, heuristically analyzing the data set, and/or applying a machine learning model to the data set.

Abstract: In some examples a first parameter for respective applicants or candidates can be computed based on respective text data from a text dataset that can include a plurality of different types of text data. The first parameter can be populated with a given portion of text of the respective text data. A second parameter for a job requisition can be computed based on the respective text data used to compute the first parameter for a given applicant or candidate. The second parameter can be populated with a different portion of text of the respective text data used to compute the first parameter. Synthetic test data can be generated based on the computed parameters to test a machine learning (ML) ranking model that has been trained on training data that is from a different data source than the text dataset to validate a performance of the ML ranking model.

Abstract: Techniques are disclosed for organizing and distributing artifacts generated by processing pipelines for the training or application of machine learning models. An application may subscribe to a playlist of a stream of events and locally store a copy of the playlist. The subscriber may merge locally stored and/or selected events to generate a merged stream of events. The subscriber may then execute the merged event stream including the newly added instance of the event.

Abstract: Techniques for generating navigational target recommendations for a user are disclosed. A system propagates sets of user attributes through one neural network and sets of navigational target attributes through another neural network. The neural networks are configured to generate, as outputs, vectors mapped to a same vector space. The system trains the neural networks to identify relationships between the sets of user attributes and the sets of navigational targets. Once the neural networks have been trained, the system generates an embedding for a user by propagating the user's attributes through the trained user attribute neural network. The system also generates embeddings for different navigational targets by propagating the attributes for the different navigational targets through the navigational target neural network. The system identifies relationships between the user and the navigational targets based on the embeddings.

Abstract: A system and method are presented for cold start candidate recommendation. In some examples, a search query request that includes a candidate search parameter can be received for a candidate list. During a first search query, a subset of candidates from a plurality of candidates can be identified based on a comparison of each candidate vector for each candidate and a candidate search parameter vector for the candidate search parameter, and ranked to provide an initial ranked candidate list based on assigned scores for the subset of candidates. During a second search query, the search parameter a candidate index can be evaluated to identify a set of candidates from the plurality of candidates, re-ranked to provide an updated ranked candidate list corresponding to the candidate list based on updated assigned scores for the set candidates and a re-ranking parameter.

Abstract: Techniques for providing recommended attribute value pairs for clustering a set of users are disclosed. The system may provide an administrator with attributes and attribute values prior to executing the clustering. The administrator may select some combinations of attribute value pairs, which the system may then use for execution of the clustering. Other techniques are disclosed for enabling an administrator to apply administrator-defined constraints to a list of recommended actions generated by a machine learning model. In some cases, the recommended actions may be specific to a particular group of users identified by execution of the administrator-informed clustering process.

Abstract: Techniques are disclosed for identifying related events. In some cases, a first event triggers an analysis in which subsequent events within a time window are analyzed. A duration of a time window may be based on one or more attributes of a triggering event. Events subsequent to the triggering event are analyzed to determine if any of the subsequent events are related to or otherwise associated with the triggering event. The system determines a duration of the time window based on attributes associated with the triggering event. Basing the duration of the time window on attributes associated with the triggering event enables the system to search for related subsequent events within a time period within which any related events are likely to occur.

Abstract: Techniques are disclosed for organizing and distributing artifacts generated by processing pipelines for the training or application of machine learning models. An application may subscribe to a playlist of a stream of events and locally store a copy of the playlist. The subscriber may merge locally stored and/or selected events to generate a merged stream of events. The subscriber may then execute the merged event stream including the newly added instance of the event.

Abstract: In some examples a first parameter for respective applicants or candidates can be computed based on respective text data from a text dataset that can include a plurality of different types of text data. The first parameter can be populated with a given portion of text of the respective text data. A second parameter for a job requisition can be computed based on the respective text data used to compute the first parameter for a given applicant or candidate. The second parameter can be populated with a different portion of text of the respective text data used to compute the first parameter. Synthetic test data can be generated based on the computed parameters to test a machine learning (ML) ranking model that has been trained on training data that is from a different data source than the text dataset to validate a performance of the ML ranking model.

Abstract: A system and method are presented for cold start candidate recommendation. In some examples, a search query request that includes a candidate search parameter can be received for a candidate list. During a first search query, a subset of candidates from a plurality of candidates can be identified based on a comparison of each candidate vector for each candidate and a candidate search parameter vector for the candidate search parameter, and ranked to provide an initial ranked candidate list based on assigned scores for the subset of candidates. During a second search query, the search parameter a candidate index can be evaluated to identify a set of candidates from the plurality of candidates, re-ranked to provide an updated ranked candidate list corresponding to the candidate list based on updated assigned scores for the set candidates and a re-ranking parameter.

Abstract: Systems and methods for candidate recommendation are provided. Candidate vectors are generated from candidate documents, and an initial ranking is performed according to a distance metric between the candidate vector and an objective vector generated based on an objective document to select a subset of the candidate documents. A feature vector is generated for each of the selected candidate documents. The feature vector includes features derived from a first vectorized representation of content from one of the candidate document and the objective document and a second vectorized representation of content from the one of the candidate document and the objective document. The feature vector is provided to a machine learning model to generate a score for each of the selected candidate documents. The selected candidate documents are ranked according the scores generated at the machine learning model to provide a ranked candidate list.

Abstract: Techniques for determining a Next Best Action (NBA) are disclosed, with the determination being based on a position within an application, past actions by a user when experiencing a similar application context, and/or tasks in queue for the user to execute from current state of the application. Techniques are also disclosed for displaying an interface that includes the NBA in conjunction with a specific rationale for presenting the NBA, such as recommendations by a trusted person, based on the user's and/or other users' past behavior, and descriptions developed based on the specific NBA. Also, methods for determining a best NBA are disclosed, with the NBA being selected by applying static rules to a data set, heuristically analyzing the data set, and/or applying a machine learning model to the data set.

Abstract: An interactive, animated, and robotic doll having movable appendages, such as a head, arms, and legs. The doll includes motors, gears and other linkages to actuate the movement of these appendages. A lockout mechanism is operatively incorporated into the doll for preventing conflicting forces from occurring. The lockout mechanism may include a shuttlecock interposed two independent linkages that drive motion in a single appendage. The shuttlecock slides between two positions, each of which limits the movement of a corresponding one of the two linkages when the other of the two linkages is actuating motion in the appendage.

Abstract: An interactive, animated, and robotic doll having movable appendages, such as a head, arms, and legs. The doll includes motors, gears and other linkages to actuate the movement of these appendages. A lockout mechanism is operatively incorporated into the doll for preventing conflicting forces from occurring. The lockout mechanism may include a shuttlecock interposed two independent linkages that drive motion in a single appendage. The shuttlecock slides between two positions, each of which limits the movement of a corresponding one of the two linkages when the other of the two linkages is actuating motion in the appendage.