Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating trajectory predictions for one or more agents in an environment. In one aspect, a method comprises: obtaining scene context data characterizing a scene in an environment at a current time point and generating a respective predicted future trajectory for each of a plurality of agents in the scene at the current time point by sampling a sequence of discrete motion tokens that defines a joint future trajectory for the plurality of agents using a trajectory prediction neural network that is conditioned on the scene context data.

Abstract: One or more computing devices, systems, and/or methods for automatically determining document profiles for documents and/or using the document profiles to generate content in response to queries are provided. In an example, a first document may be identified. A first language model may be used to determine a set of features based upon the first document. A second language model may be used to determine a plurality of sets of attributes based upon the set of features and the first document. The plurality of sets of attributes may include a first set of attributes associated with a first feature of the set of features and/or a second set of attributes associated with a second feature of the set of features. A first document profile associated with the first document may be generated based upon the set of features and the plurality of sets of attributes.

Abstract: A system described herein may establish communications with a plurality of artificial intelligence/machine learning ("AI/ML") systems; provide an interface to a plurality of client devices; receive, via the interface and from a particular client device, of the plurality of client devices, a particular input; select, based on one or more input handling models, a particular subset of AI/ML systems to which the particular input should be forwarded; output the input to the selected subset of AI/ML systems; receive a set of outputs that are each associated with a particular AI/ML system of the selected subset of AI/ML systems; and output, via the interface and to the particular client device, at least one of one or more outputs, of the set of outputs received from the selected subset of AI/ML systems, or an aggregated output that is generated based on the set of outputs received from the subset of AI/ML systems.

Abstract: One or more computing devices, systems, and/or methods for dynamic resource slice allocation are provided. A bidding engine dynamically tracks available network slices and available edge computing resources to generate a current list of resource slices corresponding to combinations of available network slices and available edge computing resources. A bidding auction is conducted for the current list of resource slices. A user equipment device is determined to be a winner of the bidding auction for a resource slice based upon a bidding request from the user equipment device. In this way, the user equipment device is provide with access to the resource slice based upon a determination that the user equipment device won the bidding auction.

Abstract: A device may receive and store credentials identifying security levels of users for access to functionalities of an on-premises device, and may receive a credential of a user and a request to access a functionality of the on-premises device. The device may determine whether a security level of the credential matches a first security level of the credentials, and may reject the request when the security level fails to match the first security level. The device may determine, when the security level matches the first security level, whether a computing resource of the on-premises device matches a computing resource of the first security level, and may provide the user with access to the computing resource when the computing resource matches the computing resource of the first security level. The device may reject the request when the computing resource fails to match the computing resource of the first security level.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating trajectory predictions for one or more agents in an environment. In one aspect, a method comprises: obtaining scene context data characterizing a scene in an environment at a current time point and generating a respective predicted future trajectory for each of a plurality of agents in the scene at the current time point by sampling a sequence of discrete motion tokens that defines a joint future trajectory for the plurality of agents using a trajectory prediction neural network that is conditioned on the scene context data.

Abstract: A system described herein may determine that a first measure of likelihood of demand for a particular service from a first set of edge computing devices exceeds a first threshold, and may instruct the first set of edge computing devices to provision resources to provide the particular service. The system may subsequently determine that a second measure of likelihood of demand for the particular service from a second set of edge computing devices exceeds a second threshold, the second set of edge computing devices being a subset of the first set of edge computing devices, and may initiate a service state synchronization operation with respect to the second set of edge computing devices. The system may select a particular edge computing device, of the second set of edge computing devices, to provide the particular service to a User Equipment (“UE”).

Abstract: One or more computing devices, systems, and/or methods for dynamic resource slice allocation are provided. A bidding engine dynamically tracks available network slices and available edge computing resources to generate a current list of resource slices corresponding to combinations of available network slices and available edge computing resources. A bidding auction is conducted for the current list of resource slices. A user equipment device is determined to be a winner of the bidding auction for a resource slice based upon a bidding request from the user equipment device. In this way, the user equipment device is provide with access to the resource slice based upon a determination that the user equipment device won the bidding auction.

Abstract: A service provider may receive item price information and/or point of sale (POS) transaction information from a plurality of merchant devices associated with a plurality of merchants. The service provider may categorize the plurality of merchants according to the types of items offered by the respective merchants, and may further categorize the merchants according to the locations at which they conduct business. The service provider may subsequently determine a price recommendation or other pricing information for a particular item offered by a particular merchant. A merchant device of the particular merchant may present the pricing information in a user interface that enables the merchant to view projected sales at various different price points. Further, the merchant may be able to specify one or more factors used for determining the recommend price, such as a desired business model, a desired clientele, a desired profit margin, or the like.

Abstract: A service provider may receive item price information and/or point of sale (POS) transaction information from a plurality of merchant devices associated with a plurality of merchants. The service provider may categorize the plurality of merchants according to the types of items offered by the respective merchants, and may further categorize the merchants according to the locations at which they conduct business. The service provider may subsequently determine a price recommendation or other pricing information for a particular item offered by a particular merchant. A merchant device of the particular merchant may present the pricing information in a user interface that enables the merchant to view projected sales at various different price points. Further, the merchant may be able to specify one or more factors used for determining the recommend price, such as a desired business model, a desired clientele, a desired profit margin, or the like.

Abstract: Embodiments described herein provide for an election procedure, in a high availability (“HA”) environment, for a backup controller to assume operations performed by a master controller in the event that the master controller becomes unreachable. The master controller may be associated with (e.g., provisioned on) the same set of hardware as one or more worker nodes, and may control operation of the one or more worker nodes. The election procedure may be performed based on performance metrics, location, or efficiency metrics associated with candidate backup controllers (e.g., cloud-based backup controllers), including performance of communications between particular backup controllers and the one or more worker nodes.

Abstract: A device may receive and store credentials identifying security levels of users for access to functionalities of an on-premises device, and may receive a credential of a user and a request to access a functionality of the on-premises device. The device may determine whether a security level of the credential matches a first security level of the credentials, and may reject the request when the security level fails to match the first security level. The device may determine, when the security level matches the first security level, whether a computing resource of the on-premises device matches a computing resource of the first security level, and may provide the user with access to the computing resource when the computing resource matches the computing resource of the first security level. The device may reject the request when the computing resource fails to match the computing resource of the first security level.

Abstract: Embodiments described herein provide for an election procedure, in a high availability (“HA”) environment, for a backup controller to assume operations performed by a master controller in the event that the master controller becomes unreachable. The master controller may be associated with (e.g., provisioned on) the same set of hardware as one or more worker nodes, and may control operation of the one or more worker nodes. The election procedure may be performed based on performance metrics, location, or efficiency metrics associated with candidate backup controllers (e.g., cloud-based backup controllers), including performance of communications between particular backup controllers and the one or more worker nodes.

Abstract: A service provider may receive item price information and/or point of sale (POS) transaction information from a plurality of merchant devices associated with a plurality of merchants. The service provider may categorize the plurality of merchants according to the types of items offered by the respective merchants, and may further categorize the merchants according to the locations at which they conduct business. The service provider may subsequently determine a price recommendation or other pricing information for a particular item offered by a particular merchant. A merchant device of the particular merchant may present the pricing information in a user interface that enables the merchant to view projected sales at various different price points. Further, the merchant may be able to specify one or more factors used for determining the recommend price, such as a desired business model, a desired clientele, a desired profit margin, or the like.

Abstract: A service provider may receive item price information and/or point of sale (POS) transaction information from a plurality of merchant devices associated with a plurality of merchants. The service provider may categorize the plurality of merchants according to the types of items offered by the respective merchants, and may further categorize the merchants according to the locations at which they conduct business. The service provider may subsequently determine a price recommendation or other pricing information for a particular item offered by a particular merchant. A merchant device of the particular merchant may present the pricing information in a user interface that enables the merchant to view projected sales at various different price points. Further, the merchant may be able to specify one or more factors used for determining the recommend price, such as a desired business model, a desired clientele, a desired profit margin, or the like.

Abstract: The invention discloses a system and method for selective erasure, encryption and or copying of data on a remote device if the remote device has been compromised or the level of authorization of a roaming user in charge of the remote device has been modified.

Abstract: A service provider may receive item price information and/or point of sale (POS) transaction information from a plurality of merchant devices associated with a plurality of merchants. The service provider may categorize the plurality of merchants according to the types of items offered by the respective merchants, and may further categorize the merchants according to the locations at which they conduct business. The service provider may subsequently determine a price recommendation or other pricing information for a particular item offered by a particular merchant. A merchant device of the particular merchant may present the pricing information in a user interface that enables the merchant to view projected sales at various different price points. Further, the merchant may be able to specify one or more factors used for determining the recommend price, such as a desired business model, a desired clientele, a desired profit margin, or the like.

Abstract: A service provider may receive item price information and/or point of sale (POS) transaction information from a plurality of merchant devices associated with a plurality of merchants. The service provider may categorize the plurality of merchants according to the types of items offered by the respective merchants, and may further categorize the merchants according to the locations at which they conduct business. The service provider may subsequently determine a price recommendation or other pricing information for a particular item offered by a particular merchant. A merchant device of the particular merchant may present the pricing information in a user interface that enables the merchant to view projected sales at various different price points. Further, the merchant may be able to specify one or more factors used for determining the recommend price, such as a desired business model, a desired clientele, a desired profit margin, or the like.

Abstract: The invention discloses a system and method for selective erasure, encryption and or copying of data on a remote device if the remote device has been compromised or the level of authorization of a roaming user in charge of the remote device has been modified.

Abstract: This invention discloses a system and method for selective erasure, encryption and or copying of data on a remote device if the remote device has been compromised or the level of authorization of a roaming user in charge of the remote device has been modified.