Abstract: Machine learning models are used to invoke a sequence of tools in response to a user request. A list of available tools is culled before a machine learning model selects from the remaining tools to generate a plan. The plan, which describes tool invocations in natural language, is then converted to code that can programmatically invoke the tools. In some configurations, the list of available tools is first culled by removing tools that do not appear in similarly described plans. The list may further be culled by removing tools that do not appear in plans generated by machine learning models. Then, a machine learning model is prompted to generate a final plan from the culled list and the user request. In some configurations, the final plan is converted to code by prompting a machine learning model to extrapolate from the code of similar plans.

Abstract: Described herein are techniques for optimizing real-time traffic flow of a multi-class vehicle network. In some embodiments, a trained machine learning model may be used to determine one or more segments of a street network where traffic congestion is predicted to occur at a predetermined future time. The vehicles may include a first type of vehicle and a second type of vehicle, each occupying different portions of a given segment. A subset of vehicles occupying the segments at the predetermined future time may be identified and, for each, a set of alternative routes may be determined. Quantum optimization data, including the pre-selected routes, the alternative routes, and an indication of whether the vehicle is of a first or second type, may be provided to a quantum computing system, which may return an updated route for at least some of the vehicles to minimize traffic congestion at the predetermined future time.

Abstract: A technique produces a reduced-size language model using explanation tuning. Explanation tuning composes a prompt that includes two parts: a system instruction and a client instruction. The client instruction expresses a query. The system instruction requests a language model to formulate responses to queries that describe final results and processes of producing the final results. The language model responds to the prompt by providing a language-model response that describes a final result and a process of producing the final result, e.g., by providing a step-by-step explanation of how the final result is derivable. In some implementations, the technique uses a teacher-student approach to producing the reduced-size language model. In some examples, the technique performs training in two stages using two respective teacher language models, the first-stage model being less versatile and accurate compared to the second-stage model.

Abstract: The present disclosure relates to methods and systems for searching and finding one or more tables that contain an answer to a query within documents. The methods and systems receive the query with query terms and search a table index for one or more related tables to the query terms. The methods and systems locate an answer to the query in the cells of the related tables and provide an output with the answer highlighted in the cells of the related tables in response to the query.

Abstract: The present disclosure relates to methods and systems for searching and finding one or more tables that contain an answer to a query within documents. The methods and systems receive the query with query terms and search a table index for one or more related tables to the query terms. The methods and systems locate an answer to the query in the cells of the related tables and provide an output with the answer highlighted in the cells of the related tables in response to the query.

Abstract: Technologies pertaining to electronic document understanding are described herein. A document is received, wherein the document includes a section of a type. An image of the document is generated, and a candidate region is identified in the image of the document, wherein the candidate region encompasses the section. A label is assigned to the candidate region based upon text of the section, wherein the label identifies the type of the section. An electronic document understanding task is performed based upon the label assigned to the candidate region.

Abstract: A system described herein may identify proximity events using geofencing capabilities of user equipment (“UE”) such as mobile phones. The UE may interact with a mobile client manager (“MCM”) to identify landmarks (or “locations of interest”) near the UE. The UE may identify a set of local landmarks that are nearest to the UE. The UE may utilize geofence-based location services to reduce power consumption when outside geofences associated with local landmarks. If the UE enters a geofence associated with a local landmark, the UE may utilize granular location services for increased accuracy. The UE may notify the MCM when the UE “dwells” near a given landmark by entering the geofence associated with the landmark but does not approach a threshold distance of the landmark. The UE may cease utilizing granular location services when dwelling, and may instead use location services based on push messages received from the MCM.

Abstract: Technologies pertaining to electronic document understanding are described herein. A document is received, wherein the document includes a section of a type. An image of the document is generated, and a candidate region is identified in the image of the document, wherein the candidate region encompasses the section. A label is assigned to the candidate region based upon text of the section, wherein the label identifies the type of the section. An electronic document understanding task is performed based upon the label assigned to the candidate region.

Abstract: A system described herein may identify proximity events using geofencing capabilities of user equipment (“UE”) such as mobile phones. The UE may interact with a mobile client manager (“MCM”) to identify landmarks (or “locations of interest”) near the UE. The UE may identify a set of local landmarks that are nearest to the UE. The UE may utilize geofence-based location services to reduce power consumption when outside geofences associated with local landmarks. If the UE enters a geofence associated with a local landmark, the UE may utilize granular location services for increased accuracy. The UE may notify the MCM when the UE “dwells” near a given landmark by entering the geofence associated with the landmark but does not approach a threshold distance of the landmark. The UE may cease utilizing granular location services when dwelling, and may instead use location services based on push messages received from the MCM.

Abstract: A system described herein may identify proximity events using geofencing capabilities of user equipment (“UE”) such as mobile phones. The UE may interact with a mobile client manager (“MCM”) to identify landmarks (or “locations of interest”) near the UE. The UE may identify a set of local landmarks that are nearest to the UE. The UE may utilize geofence-based location services to reduce power consumption when outside geofences associated with local landmarks. If the UE enters a geofence associated with a local landmark, the UE may utilize granular location services for increased accuracy. The UE may notify the MCM when the UE “dwells” near a given landmark by entering the geofence associated with the landmark but does not approach a threshold distance of the landmark. The UE may cease utilizing granular location services when dwelling, and may instead use location services based on push messages received from the MCM.

Abstract: Examples are disclosed that facilitate connecting in a secure and efficient manner a mobile device to networked-enabled devices located in a premises. The security of the networked-enabled, connected devices in the premises may be maintained by use of a gateway device situated behind a home router. Through the home router, the gateway device maintains a persistent connection with a network component of a service provider. When an authorized application executing on a mobile device attempts to connect with the gateway device to communicate with the respective customer connected devices, the device control application is connected to a pre-established communication port to allow direct communication between the device control application and the respective customer connected device. A service provider's network component in some examples maintains the pre-established connection for the duration of the session in which the customer connected device is to be controlled via a mobile device, or longer.

Abstract: A geo-fencing system includes a plurality of beacons defining zones within a venue. The system receives a first beacon identifier from a mobile device and registers the mobile device in a first zone corresponding to the first beacon. The system causes a first menu to be displayed on the mobile device, indicating options for the first zone. In response to selection of one of the options, the system registers the mobile device as being active in the first zone. The system then receives a second beacon identifier and registers the mobile device as being in the second zone. The system also suspends the activity of the mobile device in the first zone and causes options to be displayed to continue or terminate the activity in the first zone.

Abstract: We constructed S. Gallinarum strains deleted for the global regulatory gene fur (FIG. 1) and evaluated their virulence and protective efficacy in Rhode Island Red chicks and Brown Leghorn layers. The fur deletion mutant was a virulent and, when delivered orally to chicks, elicited excellent protection against lethal S. Gallinarum challenge. We also examined the effect of a pmi mutant and a combination of fur deletions with mutations in the pmi and rfaH genes, which affect O-antigen synthesis, and ansB, whose product inhibits host T cell responses. The ?Afur ?pmi and ?fur ?ansB double mutants were attenuated, but not protective when delivered orally to chicks. However, a ?pmi ?fur strain was substantially immunogenic when administrated intramuscularly. Altogether our results show that the fur gene is essential for virulence of S. Gallinarum and the fur mutant is effective as a live recombinant vaccine against fowl typhoid.

Abstract: Examples are disclosed that facilitate connecting in a secure and efficient manner a mobile device to networked-enabled devices located in a premises. The security of the networked-enabled, connected devices in the premises may be maintained by use of a gateway device situated behind a home router. Through the home router, the gateway device maintains a persistent connection with a network component of a service provider. When an authorized application executing on a mobile device attempts to connect with the gateway device to communicate with the respective customer connected devices, the device control application is connected to a pre-established communication port to allow direct communication between the device control application and the respective customer connected device. A service provider's network component in some examples maintains the pre-established connection for the duration of the session in which the customer connected device is to be controlled via a mobile device, or longer.

Abstract: A geo-fencing system includes a plurality of beacons defining zones within a venue. The system receives a first beacon identifier from a mobile device and registers the mobile device in a first zone corresponding to the first beacon. The system causes a first menu to be displayed on the mobile device, indicating options for the first zone. In response to selection of one of the options, the system registers the mobile device as being active in the first zone. The system then receives a second beacon identifier and registers the mobile device as being in the second zone. The system also suspends the activity of the mobile device in the first zone and causes options to be displayed to continue or terminate the activity in the first zone.

Abstract: Account information associated with a mobile device is obtained through a mobile wireless communication network from a database of subscriber account records for mobile wireless communication service subscribers. The account information may identify the previous mobile device, the mobile device, and/or length of usage of the mobile device. Advice information is selected from a database of advice regarding operation of the mobile devices such that the selected advice information is adapted for the account, and the selected advice information is then provided via a user interface element of the mobile device. Additionally, multiple levels of search related phrases, in which the phrases at each level correspond to a user-selected phrase at the previous level, are presented via a user element of a mobile device.

Abstract: Account information associated with a mobile device is obtained through a mobile wireless communication network from a database of subscriber account records for mobile wireless communication service subscribers. The account information may identify the previous mobile device, the mobile device, and/or length of usage of the mobile device. Advice information is selected from a database of advice regarding operation of the mobile devices such that the selected advice information is adapted for the account, and the selected advice information is then provided via a user interface element of the mobile device. Additionally, multiple levels of search related phrases, in which the phrases at each level correspond to a user-selected phrase at the previous level, are presented via a user element of a mobile device.

Abstract: Content networking provides a content-based routing architecture, in which a virtual overlay network called the “virtual content network” is superimposed over the physical network. The content network contains content routers as the nodes and “pathways” as links. The content-based routers at the edge of the content network may be either a gateway to the client domain or a gateway to the server domain whereas the interior ones correspond to the content switches dedicated for steering content requests and replies. The pathways are virtual paths along the physical network that connect the corresponding content routers. The tags for tagging content requests at the ingress points are designed to incorporate several different attributes of the content in the routing process. The path chosen for routing the request is the optimal path and is chosen from multiple paths leading to the replicas of the content.

Abstract: The long-standing problem of secure communication is to distribute/generate unbreakable key over a communication channel. Classically the problem is believed to be unsolvable. For secure communication and authentication we are dependent on computationally secure cipher systems. Over the last two decades quantum key distribution systems have been developed to solve the problem, but the problem is yet to be solved in practical settings. The invented classical key distribution/generation system solves the problem.

Abstract: Content networking is an emerging technology, where the requests for content accesses are steered by “content routers” that examine not only the destinations but also content descriptors such as URLs and cookies. In the current deployments of content networking, “content routing” is mostly confined to selecting the most appropriate back-end server in virtualized web server clusters. This invention presents a novel content-based routing architecture that is suitable for global content networking. In this content-based routing architecture, a virtual overlay network called the “virtual content network” is superimposed over the physical network. The content network contains content routers as the nodes and “pathways” as links.