Abstract: In one embodiment, a system includes an automatic speech recognition (ASR) module, a natural-language understanding (NLU) module, a dialog manager, one or more agents, an arbitrator, a delivery system, one or more processors, and a non-transitory memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to receive a user input, process the user input using the ASR module, the NLU module, the dialog manager, one or more of the agents, the arbitrator, and the delivery system, and provide a response to the user input.

Abstract: According to one aspect, a system for resource management may perform receiving a total resource request, a vector of two or more maximum available resources associated with two or more corresponding resource providers, and a number of resource providers and calculating an individual resource request for each of the two or more resource providers by iteratively comparing the vector of two or more maximum available resources with a vector of a current average resource residual, taking a minimum between those vectors as a running tally for the individual resource requests, and recalculating the current average resource residual.

Abstract: A cell management module for a power supply module including a plurality of power cells includes at least one cell-sensing circuit and a current measurement circuit connected to the at least one cell-sensing circuit. The at least one cell-sensing circuit includes a transformer having a first winding and a second winding inductively coupled to the first winding. A first sub-circuit of the cell-sensing circuit includes the first winding of the transformer and is operable to selectively pulse a first signal through the first winding. A second sub-circuit of the cell-sensing circuit includes the second winding of the transformer and one of the power cells of the power supply module. The current measurement circuit is connected to the first sub-circuit of the at least one cell-sensing circuit and infers a voltage of the power cell based on a measured current of the first signal.

Abstract: In one embodiment, a method includes receiving a request to train a natural-language understanding (NLU) model for a new domain, accessing a context-free grammar associated with the new domain, wherein the context-free grammar defines production rules with respect to ontology tokens associated with the new domain and utterance tokens for generating natural-language strings in the new domain, generating utterance-frame pairs based on traversing a hierarchical grammar tree associated with the context-free grammar based on the production rules, wherein each utterance-frame pair comprises an utterance and a corresponding frame, wherein each frame comprises ontology tokens associated with the new domain and utterance tokens corresponding to one or more of the ontology tokens of the frame, and training the NLU model based on the utterance-frame pairs.

Abstract: A cell management module for a power supply module including a plurality of power cells includes at least one cell-sensing circuit and a current measurement circuit connected to the at least one cell-sensing circuit. The at least one cell-sensing circuit includes a transformer having a first winding and a second winding inductively coupled to the first winding. A first sub-circuit of the cell-sensing circuit includes the first winding of the transformer and is operable to selectively pulse a first signal through the first winding. A second sub-circuit of the cell-sensing circuit includes the second winding of the transformer and one of the power cells of the power supply module. The current measurement circuit is connected to the first sub-circuit of the at least one cell-sensing circuit and infers a voltage of the power cell based on a measured current of the first signal.

Abstract: A fuel cell power plant system may include two or more power units and a fuel cell power plant controller. The two or more power units may be electrically connected. Each one of the two or more power units may include two or more fuel cell systems. The fuel cell power plant controller may be electrically connected to the two or more power units and may include a user control circuitry and a monitoring circuitry. The user control circuitry may control a mode of operation of the fuel cell power plant system to be run in an operation mode, a standby mode, a maintenance mode, or an emergency stopped mode. The monitoring circuitry may monitor the two or more power units of the fuel cell power plant system for one or more fault conditions, one or more alarms, or an amount of energy produced.

Abstract: A fuel cell power plant cooling system may include a power unit coolant supply line configured to receive a coolant, two or more fuel cell system coolant supply lines connected to the power unit coolant supply line and configured to receive coolant from the power unit coolant supply line, two or more fuel cell systems configured to be cooled by the two or more fuel cell system coolant supply lines, respectively, two or more fuel cell system return supply lines connected to the two or more fuel cell system coolant supply lines, respectively, and configured to receive coolant from the two or more fuel cell system coolant supply lines, and a power unit return supply line connected to the two or more fuel cell system return supply lines and configured to receive coolant from the two or more fuel cell system return supply lines, respectively.

Abstract: A fuel cell power plant system may include a fuel supply line, two or more fuel cell system fuel supply lines, and two or more power units. The fuel supply line may be configured to receive fuel. The two or more fuel cell system fuel supply lines may be connected to the fuel supply line and may be configured to receive fuel from the fuel supply line. The two or more power units may be configured to be fueled by the two or more fuel cell system fuel supply lines, respectively.

Abstract: A fuel cell power plant system may include two or more electrically connected power units, two or more voltage channels, and a fuel cell power plant controller. Each one of the two or more power units may include two or more fuel cell systems. The two or more voltage channels may be respectively connected to the two or more power units. The fuel cell power plant controller may be electrically connected to the two or more power units.

Abstract: A heat exchanger for a fuel cell power plant system may include a first loop and a second loop. For the first loop, a first coolant may be passed through a fuel cell stack, a thermostat, a first portion of a first plate of the heat exchanger, and a fuel cell pump. For the second loop, a second coolant may be passed through a second portion of the first plate of the heat exchanger.

Abstract: In one embodiment, a method includes receiving a user input comprising a natural-language utterance by an assistant xbot from a client system associated with a user, determining a semantic representation of the user input based on a structural ontology defining a labeling syntax for parsing the natural-language utterance to semantic units comprising actions, objects, and attributes, wherein the semantic representation embeds at least one object within at least one action and declares at least one attribute of the embedded object to be acted upon, sending a request based on the semantic representation to an agent for executing a task corresponding to the user input, receiving results of the executed task mapped to a structure determined by the structural ontology from the agent, and sending from the assistant xbot to the client system instructions for presenting a response based on the results of the executed task.

Abstract: In one embodiment, a method includes receiving a user input comprising a natural-language utterance by an assistant xbot from a client system associated with a user, determining a semantic representation of the user input based on a structural ontology defining a labeling syntax for parsing the natural-language utterance to semantic units comprising actions, objects, and attributes, wherein the semantic representation embeds at least one object within at least one action and declares at least one attribute of the embedded object to be acted upon, sending a request based on the semantic representation to an agent for executing a task corresponding to the user input, receiving results of the executed task mapped to a structure determined by the structural ontology from the agent, and sending from the assistant xbot to the client system instructions for presenting a response based on the results of the executed task.

Abstract: In one embodiment, a system includes an automatic speech recognition (ASR) module, a natural-language understanding (NLU) module, a dialog manager, one or more agents, an arbitrator, a delivery system, one or more processors, and a non-transitory memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to receive a user input, process the user input using the ASR module, the NLU module, the dialog manager, one or more of the agents, the arbitrator, and the delivery system, and provide a response to the user input.

Abstract: In one embodiment, a method includes receiving a user input comprising a natural-language utterance by an assistant xbot from a client system associated with a user, determining a semantic representation of the user input based on a structural ontology defining a labeling syntax for parsing the natural-language utterance to semantic units comprising actions, objects, and attributes, wherein the semantic representation embeds at least one object within at least one action and declares at least one attribute of the embedded object to be acted upon, sending a request based on the semantic representation to an agent for executing a task corresponding to the user input, receiving results of the executed task mapped to a structure determined by the structural ontology from the agent, and sending from the assistant xbot to the client system instructions for presenting a response based on the results of the executed task.

Abstract: In one embodiment, a method includes receiving a user input comprising a natural-language utterance by an assistant xbot from a client system associated with a user, determining a semantic representation of the user input based on a structural ontology defining a labeling syntax for parsing the natural-language utterance to semantic units comprising actions, objects, and attributes, wherein the semantic representation embeds at least one object within at least one action and declares at least one attribute of the embedded object to be acted upon, sending a request based on the semantic representation to an agent for executing a task corresponding to the user input, receiving results of the executed task mapped to a structure determined by the structural ontology from the agent, and sending from the assistant xbot to the client system instructions for presenting a response based on the results of the executed task.

Abstract: In one embodiment, a method includes receiving a user input comprising a natural-language utterance by an assistant xbot from a client system associated with a user, determining a semantic representation of the user input based on a structural ontology defining a labeling syntax for parsing the natural-language utterance to semantic units comprising actions, objects, and attributes, wherein the semantic representation embeds at least one object within at least one action and declares at least one attribute of the embedded object to be acted upon, sending a request based on the semantic representation to an agent for executing a task corresponding to the user input, receiving results of the executed task mapped to a structure determined by the structural ontology from the agent, and sending from the assistant xbot to the client system instructions for presenting a response based on the results of the executed task.

Abstract: A cell management module for a power supply module including a plurality of power cells includes at least one cell-sensing circuit and a current measurement circuit connected to the at least one cell-sensing circuit. The at least one cell-sensing circuit includes a transformer having a first winding and a second winding inductively coupled to the first winding. A first sub-circuit of the cell-sensing circuit includes the first winding of the transformer and is operable to selectively pulse a first signal through the first winding. A second sub-circuit of the cell-sensing circuit includes the second winding of the transformer and one of the power cells of the power supply module. The current measurement circuit is connected to the first sub-circuit of the at least one cell-sensing circuit and infers a voltage of the power cell based on a measured current of the first signal.

Abstract: A system includes data processing hardware and memory hardware. The memory hardware is in communication with the data processing hardware and stores instructions that when executed on the data processing hardware cause the data processing hardware to perform certain operations. The operations include receiving a temperature corresponding to a battery, and determining whether the temperature is greater than a predetermined threshold temperature. The operations also include, when the temperature is greater than the predetermined threshold temperature, actuating an ejector to eject the battery from a power supply assembly.

Abstract: An enhanced postal data modeling framework, in which postal data which describes characteristics of a mail sortation process is accessed, and the postal data is mapped to production management data which describes characteristics of a model production management process in an initial state and which is capable of being processed by a production management application. The production management data is input for processing by the production management application to produce forecasted production management data which predicts characteristics of the model production management process in a subsequent state, the forecasted production management data is modeled to forecasted postal data which predicts characteristics of the mail sortation process, and at least a portion of the forecasted postal data is provided to a user.