A computer-implemented method for generating and deploying a reinforced learning model to train a chatbot. The method includes selecting a plurality of conversations, wherein each conversation includes an agent and a user. The method includes identifying, in each of the conversations, a set of turns and on or more topics. The method further includes associating one or more topics to each turn of the set of turns. The method includes, generating a conversation flow for each conversation, wherein the conversation flow identifies a sequence of the topics. The method includes applying an outcome score to each conversation. The method includes creating a reinforced learning (RL) model, wherein the RL model includes a Markov is based on the conversation flow of each conversation and the outcome score of each conversation. The method includes deploying the RL model, wherein the deploying includes sending the RL model to a chatbot.

Provided is a parameter calculating device that takes human prior knowledge into account. The parameter calculating device according to the present invention is provided with: an identifying means that identifies intermediate states from a certain state to a target state and rewards concerning the intermediate states on the basis of a plurality of states concerning a target system, associated information by which two states among the plurality of states are associated with each other, rewords concerning at least some of the states, model information including parameters representing the states of the target system, and given ranges concerning the parameters; and a parameter calculating means that calculates the values of the parameters in the case where the identified rewards and the degrees of the differences between the values of the parameters and the given ranges satisfy predetermined conditions.

A method for the automated booking of manual activities carried out by a worker in an industrial manufacturing plant while processing a workpiece is disclosed. The booking is performed in a digital control system for the creation of a digital process chain of the manufacturing. The digital process chain includes activity profiles, each of which is assigned to a manual activity. The method includes: providing movement data of a manual activity to be booked; providing position data of the manual activity to be booked; evaluating the movement data and the position data, wherein the movement data and the position data are input data of a classification process in which the input data are classified with respect to the activity profiles and a specific activity profile is output for the movement data; and booking the output specific activity profile in the digital process chain of the workpiece.

A method and an apparatus for exclusive reinforcement learning are provided, comprising: collecting information of states of an environment through the communication interface and performing a statistical analysis on the states using the collected information; determining a first state value of a first state among the states in a training phase and a second state value of a second state among the states in an inference phase based on analysis results of the statistical analysis; performing reinforcement learning by using one reinforcement learning unit of a plurality of reinforcement learning unit which performs reinforcement learnings from different perspectives according to the first state value; and selecting one of actions determined by the plurality of reinforcement learning unit based on the second state value and applying selected action to the environment.

Provided is a dispatching method in a factory based on reinforcement learning. The dispatching method in a factory based on reinforcement learning may comprise: constructing a Markov decision process (MDP) for dispatching actions of a dispatcher in the factory and resulting rewards and states of the factory; performing learning by applying reinforcement learning (RL) to the constructed MDP; and as a result of said RL, selecting a job that maximizes a weighted sum of a plurality of scored dispatching rules.

A cleanup support system that supports a cleanup behavior includes: a first obtaining unit configured to obtain first information indicating a level of interest of a target person in cleanup; a second obtaining unit configured to obtain second information indicating a level of achievement of the cleanup performed by the target person; a determination unit configured to determine a content of control corresponding to the first information obtained and the second information obtained, with reference to a rule which associates the level of interest in the cleanup and the level of achievement of the cleanup with a content of control performed on a device; and a control unit configured to control the device according to the content of control determined.

A production system includes a cell control apparatus that is connected to a machine control apparatus and an inspection control apparatus. The cell control apparatus includes a storage part that stores data on a state of the manufacturing machine, data on an environment state, and data on an inspection result of a product. The cell control apparatus includes a correlation analysis part that selects a variable relating to an abnormality based on a correlation between the inspection result of the product, and the data on the state of the manufacturing machine and the data on the environment state when the abnormality occurs in the inspection result, and a determination value setting part that sets a determination value of the variable relating to the abnormality.

A computer-implemented method executed by a robotic system for performing a positional search process in an assembly task is presented. The method includes decomposing, by the robotic system, a perturbation motion into a plurality of actions, the perturbation motion being a motion for an assembly position searched by the robotic system, each action of the plurality of actions related to a specific direction. The method further includes performing reinforcement learning by selecting an action among decomposed actions and assembly movement actions at each step of the positional search process based on corresponding force-torque data received from at least one sensor associated with the robotic system. The method also includes outputting a best action at each step for completion of the assembly task as a result of the reinforcement learning.

A work center in a manufacturing setup includes a machine learning model that uses a decision tree to facilitate the work of a supervisor on the production line to choose a machine to perform a particular operation on a particular part. The decision tree outputs a ranking of machines indicating the suitability of the ranked machines for performing the particular operation on the particular part.

A robotic device management service obtains a set of parameters of a simulation environment and a set of components for execution of a simulation of a robotic device application. Based on these parameters, the robotic device management service selects a set of resources for executing the application in a simulation environment. The robotic device management service may launch the set of components among the set of resources and monitor execution of the application in the simulation environment to ensure completion of the simulation.