Abstract: The present invention is a masterbot architecture in a scalable multi-service virtual assistant platform that can construct a fluid and dynamic dialogue by assembling responses to end user utterances from two kinds of agents, information agents and action agents. A plurality of information agents obtain at least one information value from a parsed user input and/or contextual data. A plurality of action agents perform one or more actions in response to the parsed user input, the contextual data, and/or the information value. A masterbot arbitrates an activation of the plurality of information agents and the plurality of action agents. The masterbot comprises access to a machine-learning module to select an appropriate action agent, where one or more information agents are activated based on the selected appropriate action agent.

Abstract: The present invention is a masterbot architecture in a scalable multi-service virtual assistant platform that can construct a fluid and dynamic dialogue by assembling responses to end user utterances from two kinds of agents, information agents and action agents. A plurality of information agents obtain at least one information value from a parsed user input and/or contextual data. A plurality of action agents perform one or more actions in response to the parsed user input, the contextual data, and/or the information value. A masterbot arbitrates an activation of the plurality of information agents and the plurality of action agents. The masterbot comprises access to a machine-learning module to select an appropriate action agent, where one or more information agents are activated based on the selected appropriate action agent.

Abstract: The present invention is a masterbot architecture in a scalable multi-service virtual assistant platform that can construct a fluid and dynamic dialogue by assembling responses to end user utterances from two kinds of agents, information agents and action agents. A plurality of information agents obtain at least one information value from a parsed user input and/or contextual data. A plurality of action agents perform one or more actions in response to the parsed user input, the contextual data, and/or the information value. A masterbot arbitrates an activation of the plurality of information agents and the plurality of action agents. The masterbot comprises an action agent selector module to select an appropriate action agent; a prerequisite validator module to validate that one or more prerequisite conditions of the selected action agent have been met; and an action invocation module to perform one or more selected actions of the selected action agent.

Abstract: The present invention is a masterbot architecture in a scalable multi-service virtual assistant platform that can construct a fluid and dynamic dialogue by assembling responses to end user utterances from two kinds of agents, information agents and action agents. A plurality of information agents obtain at least one information value from a parsed user input and/or contextual data. A plurality of action agents perform one or more actions in response to the parsed user input, the contextual data, and/or the information value. A masterbot arbitrates an activation of the plurality of information agents and the plurality of action agents. The masterbot comprises an action agent selector module to select an appropriate action agent; a prerequisite validator module to validate that one or more prerequisite conditions of the selected action agent have been met; and an action invocation module to perform one or more selected actions of the selected action agent.

Abstract: The present invention is an action agent architecture in a scalable multi-service virtual assistant platform that can construct a fluid and dynamic dialogue by assembling responses to end user utterances from two kinds of agents, information agents and action agents. A plurality of information agents obtain at least one information value from a parsed user input and/or contextual data. A plurality of action agents perform two or more actions in response to the parsed user input, the contextual data, and/or an information value obtained from at least one of the information agents. The plurality of action agents are configured by specifying one or more triggering conditions, one or more action invocation parameters, one or more information agents as pre-requisites, and one or more responses. A natural language generation (NLG) module renders a response back to the user after the two or more actions are performed.

Abstract: The present invention is an action agent architecture in a scalable multi-service virtual assistant platform that can construct a fluid and dynamic dialogue by assembling responses to end user utterances from two kinds of agents, information agents and action agents. A plurality of information agents obtain at least one information value from a parsed user input and/or contextual data. A plurality of action agents perform one or more actions in response to the parsed user input, the contextual data, and/or an information value obtained from at least one of the information agents. The plurality of action agents are created through a declarative language by specifying one or more triggering conditions, one or more action invocation parameters, one or more information agents as pre-requisites, and one or more responses. A natural language generation (NLG) module renders a response back to the user after the one or more actions are performed.

Abstract: The present invention is an action agent architecture in a scalable multi-service virtual assistant platform that can construct a fluid and dynamic dialogue by assembling responses to end user utterances from two kinds of agents, information agents and action agents. The virtual assistant platform comprises a plurality of action agents to perform two or more actions in response to parsed user input, contextual data, and/or an information value obtained from an information agent. The plurality of action agents are interrelated via at least one follow-up connection which interrelates any two of the action agents such that a second action agent follows-up with a second action after a first action agent completes a first action based on a trigger condition. The second action agent utilizes at least one information value set by the first action agent or a system state change triggered by the first action agent.

Abstract: The present invention is an action agent architecture in a scalable multi-service virtual assistant platform that can construct a fluid and dynamic dialogue by assembling responses to end user utterances from two kinds of agents, information agents and action agents. The virtual assistant platform comprises a plurality of action agents to perform two or more actions in response to parsed user input, contextual data, and/or an information value obtained from an information agent. The plurality of action agents are interrelated via at least one follow-up connection which interrelates any two of the action agents such that a second action agent follows-up with a second action after a first action agent completes a first action based on a trigger condition. The second action agent utilizes at least one information value set by the first action agent or a system state change triggered by the first action agent.

Abstract: The present invention is a scalable multi-service virtual assistant platform that can construct a fluid and dynamic dialogue by assembling responses to end user utterances from two kinds of agents, information agents and action agents. The information agents and action agents are managed by a masterbot or arbiter. The virtual assistant can gain new skills by getting instructions about a new service expressed in a form of pre-requisites and action combinations; the virtual assistant platform automatically handles dialogue generation, arbitration and optimization to survey prerequisites from the end user, and eventually to take action. The present invention allows a large number of services to implemented using a small number of building blocks. These building blocks can be used to assemble a much larger number of services. In turn, each service can be delivered through a large variety of conversations with end users, enabling a fluid and dynamic dialogue to be seamlessly implemented.

Abstract: A servo motor system and an operating method of the servo motor system are disclosed. The servo motor system includes a servo motor and a servo driver. The servo motor is electrically connected to the servo driver. The servo motor includes a motor unit and an encoder. The encoder is mechanically connected to the motor unit. The encoder includes a CPU and a memory unit. The memory unit is electrically connected to the CPU. Data parameters are saved in the memory unit. The servo driver uses data parameters of the motor unit saved in the memory unit for controlling the motor unit. The servo motor system and the operating method provide a mechanism to drive and offer compensation to an upgraded motor.

Abstract: A three-in-one AC servo drive includes a main console, a control module, a power module and a plurality of servo motors. A single drive can be connected to a plurality of motors. The power module and control module for the motors can be integrated to a single modular unit. Therefore, the redundant portion such as communication interface, display unit and I/O unit can be eliminated. The capacitor of the bus of the IGBT module can also be reduced, whereby the occupied space and cost can be reduced with less assembling time.

Abstract: A wire-saving optical encoder having servomotor identification information is applied to a wire-saving transmission design to provide a circuit and a method for processing servomotor identification information and encoded feedback control signals. With a microprocessor, a multiplexer and the servomotor identification information stored in the microprocessor, an output device and a driver for the feedback signals of the encoder constitute a wire-saving signal transmitting circuit. The microprocessor and multiplexer switch a signal transmission mode to transmit the servomotor identification information and phase change signal produced by the servomotor control parameters stored in a firmware by a serial output mode, and the same transmitting wire is used to transmit a rotor operating signal after the transmitting mode is switched, so as to save wires and lower costs for transmitting feedback signals and correctly identifying and effectively controlling a servomotor.

Abstract: An optical encoder includes a controller electrically connected to an optical sensor to discriminate displacement information of a glass disc. The controller comprises a pair of analog amplifiers for amplifying quadrature periodical output signals of the optical sensor, a pair of A/D converters electrically connected to the analog amplifiers for digitalizing the output of the analog amplifiers, a pair of hysteresis comparators electrically connected to the optical sensor for performing hysteresis comparison for the output of the optical sensor, an up/down counter electrically connected to the pair of hysteresis comparators for up/down counting the output of the hysteresis comparators and a firmware unit electrically connected to the pair of A/D converters and the up/down counter for performing interpolation for the quadrature periodical output signals and counting for the hysteresis compared signals. Therefore, optical encoded result of higher resolution can be achieved.

Abstract: An AC servo system with distributed movement control is used for multiple axes control in distributed manner includes at least one drive containing a programmable movement controller to perform a customized procedure to control I/O signal of local axis or other axis. The drive can download/perform movement program through communication network, edit axis parameter and monitor the axis status. The drive can set to be master/slave axis according to practical need. The master axis drive performs multiple axes simultaneous control and sends path command to each slave axis drive. The master axis drive calculates complementary command coordinate according to the path command and the path command received by the slave axis drive, whereby the movement trace of the master/slave axis drive can satisfy the path command requirement.