Abstract: A computer system holds supply chain plan information including at least one of a production plan, a sales plan, a delivery plan and a procurement plan, receives an order change request including a request for change in delivery date, conducts a simulation on the supply chain with a constraint of a changed delivery date to generate new supply chain plan information, and generates negotiation proposal information for partner companies in order to ask whether the partner companies grant the new supply chain plan information, sends the negotiation proposal information to the partner companies, conducts another simulation with new constraints in accordance with answers to the negotiation proposal information received from the partner companies to generate new supply chain plan information, generates an answer to the order change request that includes a changed delivery date based on the generated supply chain plan information and outputs the generated answer.

Abstract: Conventional simulation-based optimization, even when automated, requires substantial user-involved development time. Accordingly, embodiments are disclosed to automate various aspects of simulation-based optimization. In particular, an optimization configurator and associated data structures are disclosed for generating and running optimization templates that can be easily constructed (e.g., via lists of available components), revised, evaluated, and re-run as needed. The optimization templates may comprise a plurality of optimization configurations that each define and pair an optimization algorithm with a simulator of a real-world system. Embodiments can reduce development time, are applicable to various domains, can be used by novice users without specialized knowledge, and can improve the overall quality of optimization for the operations of real-world systems, such as supply chains.

Abstract: Systems and methods described herein can involve, for an input of supplier features associated with one or more suppliers, supply chain network features and predicted demand features, processing the input through a trained deep learning model configured to intake the input and output primary supplier from the one or more suppliers, backup supplier from the one or more suppliers, order quantity for the primary supplier, and reservation capacity from the backup supplier; and executing a contract with the primary supplier and the backup supplier based on the order quantity and reservation capacity.

Abstract: A plan parameter obtaining an optimal result between a plurality of software pieces that are linkingly operated is calculated. A value chain plan linking method that uses a value chain plan linking apparatus that combines and executes a plurality of software pieces according to a task. At least any one of the plurality of software pieces uses, as an input parameter, an output parameter obtained from any one of other software pieces included in the plurality of software pieces. The value chain plan linking apparatus executes a different solution requiring step of calculating a plurality of the output parameters in each of the plurality of software pieces, and a displaying step of displaying, as an overall plan, the output parameter obtaining a best key performance indicator value in the entire value chain according to a combination of the input and output parameters of the plurality of software pieces.

Abstract: A procurement work assistance device includes a storage unit configured to store order history information, delivery history information, and a procurement plan in which an item to be procured is registered, a delivery expectation index calculation unit configured to calculate, by using the order history information, a delivery expectation index indicating easiness of delivery for each item of each supplier, and an order plan formulation unit configured to generate delivery expectation index histogram information indicating a relationship between the delivery expectation index and a delivery rate calculated based on the delivery history information, calculate a delivery expectation index of the item in the procurement plan, determine, by using the delivery expectation index histogram information, the supplier having the highest delivery rate associated with the delivery expectation index, and generate order plan information including the item in the procurement plan and the determined supplier.

Abstract: Example implementations described herein involve systems and methods for bound enhanced reinforcement learning systems for distribution supply chain management which can include initializing a replay buffer, a first state-action value function network having first random weights, and a second state-action value function network having second random weights; determining an action corresponding to an inventory ordering quantity at one or more facility in a multi-echelon supply chain network based on an (epsilon) ?-greedy exploration policy; executing the action in a simulated environment, and storing transition results in the replay buffer; calculating an upper bound and a lower bound of the optimal inventory costs; incorporating the upper bound and the lower bound with at least hyper-parameters T1, ?2 in updating at least one of the first or the second state-action value function networks; and performing a gradient descent on the first state-action value function network based on the upper or the lower bound.

Abstract: Conventional simulation-based optimization, even when automated, requires substantial user-involved development time. Accordingly, embodiments are disclosed to automate various aspects of simulation-based optimization. In particular, an optimization configurator and associated data structures are disclosed for generating and running optimization templates that can be easily constructed (e.g., via lists of available components), revised, evaluated, and re-run as needed. The optimization templates may comprise a plurality of optimization configurations that each define and pair an optimization algorithm with a simulator of a real-world system. Embodiments can reduce development time, are applicable to various domains, can be used by novice users without specialized knowledge, and can improve the overall quality of optimization for the operations of real-world systems, such as supply chains.

Abstract: The supply chain management apparatus includes: an input unit that receives input information indicating a change in market conditions; a storage unit that stores supply chain information in which constituent companies of a supply chain, T&Cs information in which T&Cs of each of the constituent companies of the supply chain is registered, and a condition for a key performance indicator which should be satisfied, the condition for a key performance indicator being set for each of the constituent companies; a T&Cs calculation unit that, when the input information is received, calculates a supply chain plan corresponding to the change in the market conditions indicated by the input information based on a predetermined calculation method, and when a key performance indicator calculated based on the supply chain plan does not meet the condition for the key performance indicator, changes the T&Cs so that the key performance indicator is optimal.

Abstract: A plan parameter obtaining an optimal result between a plurality of software pieces that are linkingly operated is calculated. A value chain plan linking method that uses a value chain plan linking apparatus that combines and executes a plurality of software pieces according to a task. At least any one of the plurality of software pieces uses, as an input parameter, an output parameter obtained from any one of other software pieces included in the plurality of software pieces. The value chain plan linking apparatus executes a different solution requiring step of calculating a plurality of the output parameters in each of the plurality of software pieces, and a displaying step of displaying, as an overall plan, the output parameter obtaining a best key performance indicator value in the entire value chain according to a combination of the input and output parameters of the plurality of software pieces.

Abstract: A procurement work assistance device includes a storage unit configured to store order history information, delivery history information, and a procurement plan in which an item to be procured is registered, a delivery expectation index calculation unit configured to calculate, by using the order history information, a delivery expectation index indicating easiness of delivery for each item of each supplier, and an order plan formulation unit configured to generate delivery expectation index histogram information indicating a relationship between the delivery expectation index and a delivery rate calculated based on the delivery history information, calculate a delivery expectation index of the item in the procurement plan, determine, by using the delivery expectation index histogram information, the supplier having the highest delivery rate associated with the delivery expectation index, and generate order plan information including the item in the procurement plan and the determined supplier.

Abstract: The supply chain management apparatus includes: an input unit that receives input information indicating a change in market conditions; a storage unit that stores supply chain information in which constituent companies of a supply chain, T&Cs information in which T&Cs of each of the constituent companies of the supply chain is registered, and a condition for a key performance indicator which should be satisfied, the condition for a key performance indicator being set for each of the constituent companies; a T&Cs calculation unit that, when the input information is received, calculates a supply chain plan corresponding to the change in the market conditions indicated by the input information based on a predetermined calculation method, and when a key performance indicator calculated based on the supply chain plan does not meet the condition for the key performance indicator, changes the T&Cs so that the key performance indicator is optimal.

Abstract: A parallel distributed processing control system used in production distribution planning includes: a storage unit storing step information of steps constituting a production distribution process of a product, CPU information of CPUs that calculate a value of a simulation result for the step, and a constraint value in the production distribution process; a divided model generation unit generating a divided model by grouping the steps; a CPU allocation unit allocating the divided model to the plurality of CPUs; an engine execution unit enabling the CPU to calculate the value for the step constituting the divided model; and a constraint monitoring unit determining whether the value satisfies a condition specified by the constraint value. An output information generation unit generates result information using the value satisfying the condition; and the CPU allocation unit allocates the divided model so that processing loads of the plurality of CPUs are equalized.

Abstract: A parallel distributed processing control system used in production distribution planning includes: a storage unit storing step information of steps constituting a production distribution process of a product, CPU information of CPUs that calculate a value of a simulation result for the step, and a constraint value in the production distribution process; a divided model generation unit generating a divided model by grouping the steps; a CPU allocation unit allocating the divided model to the plurality of CPUs; an engine execution unit enabling the CPU to calculate the value for the step constituting the divided model; and a constraint monitoring unit determining whether the value satisfies a condition specified by the constraint value. An output information generation unit generates result information using the value satisfying the condition; and the CPU allocation unit allocates the divided model so that processing loads of the plurality of CPUs are equalized.

Abstract: In a supply chain, an optimal task logic is automatically presented in accordance with a status change occurring in each enterprise in a short time. A task support system generates scenario information of a simulation and generates task logic combining information by combining the scenario information and the task logic of each enterprise. Then, KPI information for each task logic in a scenario is calculated by performing a simulation based on the task logic combining information. Next, status change information relating to a task is read, and a search for a scenario closest thereto is performed. Then, a scenario closest to the status change information is referred to, a KPI relating to the scenario from the KPI information is acquired, a scenario achieving the input importance KPI most is acquired, and a task logic that is combined with the scenario in the task logic combining information is calculated as an optimal task logic.