JP6057781B2 - Simulation apparatus, simulation method, and simulation program - Google Patents

Description

  The present invention relates to a simulation apparatus, a simulation method, and a simulation program for simulating fluctuations in the number of products held.

  A technique for appropriately managing the amount (number of possessions) of products is known (for example, Patent Document 1).

JP 2002-169861 A

  In the conventional technique for managing the number of products held, the fluctuation of the number of products may not be accurately predicted. An object of the present invention is to provide a simulation apparatus, a simulation method, and a simulation program that can accurately predict fluctuations in the number of products held.

  As one aspect, the simulation apparatus determines the number of occurrences of sudden demand for a product for each period when the sudden demand for the product occurs and when the sudden demand for the product occurs until the product is paid out. An unexpected demand prediction unit that predicts for each time, and a simulation unit that simulates a change in the number of products held based on the number of occurrences of the sudden demand of the product predicted by the sudden demand prediction unit.

  As one aspect, the simulation method is a simulation method executed by a simulation apparatus, and the number of occurrences of sudden demand for a product is determined for each period when the sudden demand for the product occurs and the sudden demand for the product occurs. And a step of predicting for each required lead time until the product is paid out, and a step of simulating a change in the number of products held based on the number of sudden demands of the product.

  The simulation program, as one aspect, pays the product to the simulation device the number of occurrences of sudden demand for the product, every period when the sudden demand for the product occurs, and after the sudden demand for the product occurs. And a step of simulating fluctuations in the number of products held based on the number of occurrences of sudden demand for the products.

  The simulation apparatus, the simulation method, and the simulation program according to the present invention have an effect that it is possible to accurately predict a change in the number of products held.

FIG. 1 is a block diagram illustrating a configuration of a simulation apparatus according to the present embodiment. FIG. 2 is a diagram illustrating an example of generation of sudden demand forecast data. FIG. 3 is a diagram illustrating an example of generation of cancel prediction data. FIG. 4 is a diagram illustrating an example of generation of demand distribution data. FIG. 5 is a diagram illustrating an example of predicting the number of occurrences of sudden demand and the number of cancellations. FIG. 6 is a diagram showing logic for changing the change in the number of products held in association with the occurrence of sudden demand. FIG. 7 is a diagram showing logic for changing the change in the number of products held in response to the occurrence of cancellation. FIG. 8 is a diagram showing another logic for changing the change in the number of products held in response to the occurrence of cancellation. FIG. 9 is a diagram illustrating an example of a simulation result. FIG. 10 is a diagram illustrating an example of evaluation data. FIG. 11 is a flowchart illustrating an example of a processing procedure executed by the simulation apparatus.

  Embodiments of a simulation apparatus, a simulation method, and a simulation program according to the present invention will be described below in detail with reference to the drawings. Note that the present invention is not limited to the embodiments. In addition, the constituent elements in this embodiment include those that can be easily assumed by those skilled in the art, those that are substantially the same, and those in a so-called equivalent range.

  The configuration of the simulation apparatus according to the present embodiment will be described with reference to FIG. FIG. 1 is a block diagram illustrating a configuration of a simulation apparatus according to the present embodiment. A simulation apparatus 10 shown in FIG. 1 simulates fluctuations in the number of products held by a manufacturer. In the following, an example in which a manufacturer that produces a product with a long production lead time in a variety and small quantity production uses the simulation apparatus 10 will be described. When producing products with a long production lead time in high-mix low-volume production, if the number of products is not appropriate, there is a possibility that the product will be overstocked, or the product may not be delivered as requested due to shortage. Therefore, it is important to accurately predict fluctuations in the number of holdings.

  In this embodiment, the “product” refers to an article paid out to a customer, a distributor, a downstream process, or the like, and includes not only a final product but also a part used for production of another product or a repair part. “Holding” means that a manufacturer keeps a product without paying out in case of sudden demand. “Sudden demand” refers to demand in which regular production cannot deliver a product by a requested delivery date. “Production lead time” refers to a standard period required for production of a product.

  As illustrated in FIG. 1, the simulation apparatus 10 includes a display unit 11, an input unit 12, a communication unit 13, a medium reading unit 14, a control unit 15, and a storage unit 16.

  The display unit 11 includes a display device such as a liquid crystal panel or an organic EL (Organic Electro-Luminescence) panel, and displays various information such as characters and figures based on a control signal transmitted from the control unit 15. The input unit 12 includes an input device such as a keyboard, and outputs a signal corresponding to an operation performed by the user on the input device to the control unit 15. The communication unit 13 controls transmission / reception of information with other devices based on a predetermined communication protocol. The medium reading unit 14 reads a program and data from a portable non-transitory storage medium such as an optical disk, a magneto-optical disk, or a memory card.

  The control unit 15 includes a CPU (Central Processing Unit) 15a that is an arithmetic device and a memory 15b that is a storage device, and implements various functions by executing programs using these hardware resources. Specifically, the control unit 15 reads out a program stored in the storage unit 16 and expands it in the memory 15b, and causes the CPU 15a to execute instructions included in the program expanded in the memory 15b. And the control part 15 reads / writes data with respect to the memory 15b and the memory | storage part 16, or controls operation | movement of the communication part 13 grade | etc., According to the execution result of the command by CPU15a.

  The storage unit 16 includes a nonvolatile storage device such as a magnetic storage device or a semiconductor storage device, and stores various programs and data. The program stored in the storage unit 16 includes a simulation program 161. The data stored in the storage unit 16 includes performance data 162, sudden demand prediction data 163, cancellation prediction data 164, demand distribution data 165, and evaluation data 166.

  Note that all or part of the programs and data that are stored in the storage unit 16 in FIG. 1 are stored in a non-transitory storage medium that can be read by the medium reading unit 14. May be. Further, all or part of the program and data that the storage unit 16 stores in FIG. 1 may be acquired from another device through communication by the communication unit 13.

  The simulation program 161 provides a function for simulating fluctuations in the number of products held. The simulation program 161 includes a performance data analysis unit 161a, an unexpected demand prediction unit 161b, a cancellation prediction unit 161c, a simulation unit 161d, and an evaluation unit 161e.

  The performance data analysis unit 161a analyzes the performance data 162, and generates sudden demand prediction data 163, cancellation prediction data 164, and demand distribution data 165.

  The sudden demand prediction unit 161b predicts the number of sudden demands for a product for each period in which sudden demand occurs and for each required lead time of the product based on the sudden demand prediction data 163 and the demand distribution data 165. The “required lead time” refers to a period from when demand occurs until a product is paid out. In other words, the “required lead time” is a period from order receipt to delivery date.

  Based on the cancellation prediction data 164, the cancellation prediction unit 161c predicts the number of product cancellations for each period in which sudden demand occurs.

  The simulator 161d simulates fluctuations in the number of products held based on the number of sudden demands predicted by the sudden demand prediction unit 161b and the number of cancellations predicted by the cancellation prediction unit 161c.

  The evaluation unit 161e performs an evaluation on the number of products held based on the result of the simulation by the simulation unit 161d. The evaluation result by the evaluation unit 161e is stored in the evaluation data 166.

  The performance data 162 is data relating to sales performance. The performance data 162 holds, for each product, when the demand for the product occurs and when the product is paid out. The sudden demand forecast data 163 holds information for predicting the number of sudden demands of products. The cancellation prediction data 164 holds information for predicting the number of product cancellations. The demand distribution data 165 holds information indicating the distribution (occurrence ratio) of the number of occurrences of sudden demand for each requested lead time. The evaluation data 166 holds information related to evaluation for the number of products held.

  The generation of the sudden demand forecast data 163 will be described with reference to FIG. FIG. 2 is a diagram illustrating an example of generation of the sudden demand forecast data 163. The actual data analysis unit 161 a derives an approximate expression indicating the relationship between the annual number of products paid out and the annual number of sudden demands based on the actual data 162. The annual number of products paid represents the amount of demand for the product. The approximate expression is derived for each production lead time of the product. The actual result data analysis unit 161a may derive an approximate expression based on data of a specified period among data stored in the actual result data 162.

  For example, the result data analysis unit 161a extracts data (actual value) of sudden demand of a product whose production lead time is six months from the result data 162. The sudden demand data is data in which the required lead time is shorter than the production lead time. Sudden demand data may include data in which the required lead time is shorter than the production lead time due to changes such as the delivery time being advanced in addition to the data in which the required lead time is shorter than the production lead time from the beginning. .

  The performance data analysis unit 161a calculates the number of sudden demands generated for each product by totalizing the extracted performance values for each product and converting it to the number of cases per year. Furthermore, the performance data analysis unit 161 a acquires the annual payout number of the product corresponding to the extracted data from the performance data 162.

  The combination of the annual payout number of each product and the annual occurrence number of sudden demand obtained in this way shows a distribution as shown in the graph 20 of FIG. From such a distribution, an approximate expression 20a indicating the correlation between the number of annual payouts and the number of sudden demands can be obtained.

  By performing the same process for products with other production lead times, it is possible to obtain an approximate expression indicating the correlation between the number of annual payments and the number of sudden demands. For example, for a product with a production lead time of 10 months, a distribution like a graph 21 can be obtained, and an approximate expression 21a can be obtained from such a distribution. Furthermore, for a product with a production lead time of 12 months, a distribution as shown in the graph 22 can be obtained, and an approximate expression 22a can be obtained from such a distribution.

  The actual result data analysis unit 161a generates the sudden demand prediction data 163 using the approximate expression thus obtained. The sudden demand forecast data 163 shown in FIG. 2 holds the predicted value of the annual number of sudden demands for each number of products paid out and for each production lead time of the products. The number of product demands generated is considered to vary depending on the magnitude of product demand. Furthermore, it is considered that the probability that the demand becomes an unexpected demand varies depending on the length of the production lead time of the product. For this reason, as shown in the example of FIG. 2, by maintaining the predicted value of the annual number of sudden demands for each number of paid-out products and for each production lead time of the products, The accuracy of prediction can be improved.

  The generation of the cancellation prediction data 164 will be described with reference to FIG. FIG. 3 is a diagram illustrating an example of generation of the cancellation prediction data 164. Based on the actual data 162, the actual data analysis unit 161a derives an approximate expression indicating the relationship between the annual number of products paid out and the annual number of cancellations. The actual result data analysis unit 161a may derive an approximate expression based on data of a specified period among data stored in the actual result data 162.

  In order to derive the approximate expression, the record data analysis unit 161 a extracts cancel data from the record data 162. The cancellation data is data of a product for which the payout has been canceled. The performance data analysis unit 161a may extract only data of products that have already begun production at the time of cancellation, as data for cancellation, from among data that has been withdrawn or that has been postponed more than the manufacturing LT. When deriving an approximate expression based on data for a specified period, the performance data analysis unit 161a may extract data other than the sudden demand whose delivery date was postponed outside the period as cancellation data.

  The performance data analysis unit 161a calculates the number of cancellations generated for each product by totalizing the extracted performance values for each product and converting the total value into the number of cases per year. Furthermore, the performance data analysis unit 161 a acquires the annual payout number of the product corresponding to the extracted data from the performance data 162.

  The combination of the number of annual payouts and the number of annual cancellations obtained for each product thus obtained shows a distribution as shown by a graph 23 in FIG. From such a distribution, an approximate expression 23a indicating the correlation between the number of annual payouts and the annual number of cancellations can be obtained.

  The performance data analysis unit 161a generates the cancel prediction data 164 using the approximate expression obtained in this way. The cancellation prediction data 164 shown in FIG. 3 holds a predicted value of the annual number of cancellations for each number of paid-out products. The number of product cancellations is considered to vary depending on the magnitude of product demand. For this reason, as in the example shown in FIG. 3, the prediction value of the annual number of cancellations is held for each annual number of paid-out products, so that the accuracy of prediction of the number of cancellations can be improved.

  In the example shown in FIGS. 2 and 3, the year is used as the unit of aggregation, but the unit of aggregation is not limited to the year. The unit of aggregation may be, for example, day, week, month, quarter, or half year. The method for obtaining the approximate expression may be, for example, a least square method or another known method. The obtained approximate expression may be an expression other than the linear expression.

  The generation of the demand distribution data 165 will be described with reference to FIG. FIG. 4 is a diagram illustrating an example of generation of demand distribution data 165. The actual data analysis unit 161 a generates data indicating the distribution (occurrence ratio) of the number of occurrences of sudden demand for each requested lead time based on the actual data 162. Data indicating the distribution of the occurrence number of sudden demand is generated for each production lead time of the product. The actual result data analysis unit 161a may generate data indicating the distribution of the occurrence number of sudden demands based on data for a specified period among the data stored in the actual result data 162.

  For example, the performance data analysis unit 161a extracts data on a product having a production lead time of 6 months from the performance data 162. The performance data analysis unit 161a aggregates the extracted performance values for each requested lead time, and calculates the number of demands generated (number of products paid out) for each requested lead time.

  The combination of the required lead time and the number of occurrences of demand obtained in this way shows a distribution such as a graph 24 in FIG. The performance data analysis unit 161a extracts data of the sudden demand period from such distribution. When the production lead time is 6 months, data with a required lead time of 0 to 5 months is extracted as data for the sudden demand period. And the performance data analysis part 161a calculates the ratio of the generation number of demand for every request | requirement lead time based on the extracted data. In this way, data indicating the distribution (occurrence ratio) of the number of occurrences of sudden demand for each requested lead time is generated for a product with a production lead time of 6 months.

  By performing the same process for products with other production lead times, a combination of the required lead time and the number of occurrences of demand is obtained, and data on the period of sudden demand is extracted from this to request the ratio of the number of occurrences of demand. It can be calculated for each lead time. For example, for a product with a production lead time of 10 months, a combination of the required lead time and the number of occurrences of demand as shown in graph 25 is obtained. Then, data with a required lead time of 0 to 9 months is extracted from this, and the ratio of the number of sudden demand occurrences is calculated for each required lead time. Further, for a product with a production lead time of 12 months, a combination of the required lead time and the number of demands as shown in graph 26 is obtained. Then, data with a required lead time of 0 months to 11 months is extracted from this, and the ratio of the number of sudden demand occurrences is calculated for each required lead time.

  The performance data analysis unit 161 a stores data indicating the distribution (occurrence ratio) of the occurrence number of sudden demands thus obtained for each requested lead time in the demand distribution data 165. The demand distribution data 165 shown in FIG. 4 holds the occurrence ratio of the unexpected demand for each required lead time for each production lead time. The timing at which the number of products held varies depending on the required lead time, that is, the length of the period until delivery. For this reason, as shown in the example of FIG. 4, the occurrence ratio of the unexpected demand for each required lead time is held for each production lead time of the product, and this is used for the simulation to change the number of products held. The accuracy of prediction can be improved.

  In the example illustrated in FIG. 4, the occurrence ratio of the unexpected demand for each requested lead time is calculated using the data of the demand other than the unexpected demand. As described above, by using demand data other than the sudden demand, even when the sudden demand data is relatively small, it is possible to obtain the occurrence ratio of the sudden demand for each required lead time with high accuracy. However, the performance data analysis unit 161a may calculate the occurrence ratio of the sudden demand for each required lead time using only the sudden demand data when the sudden demand data is sufficiently large. Thereby, the generation | occurrence | production ratio for every request | requirement lead time of sudden demand can be obtained with a still higher precision.

  With reference to FIGS. 5 to 10, simulation of fluctuations in the number of products held will be described. The sudden demand prediction unit 161b predicts the number of sudden demands generated during the simulation period for each predetermined period and for each requested lead time based on the sudden demand prediction data 163 and the demand distribution data 165. Furthermore, the cancel prediction unit 161c predicts the number of cancels occurring during the simulation period for each predetermined period based on the cancel prediction data 164.

  In this embodiment, the unit of the predetermined period is the season (10 days). However, the unit of the predetermined period is not limited to the season. The unit of the predetermined period may be a day, a week, a month, a quarter, or a half year.

  FIG. 5 is a diagram illustrating an example of predicting the number of occurrences of sudden demand and the number of cancellations. FIG. 5 shows an example of predicting the number of occurrences of sudden demand and the number of cancellations of a product whose production lead time is 6 months and the annual number of payouts is 10.

  The sudden demand forecasting unit 161b obtains, from the sudden demand forecast data 163, a predicted value of the annual number of sudden demands corresponding to the production lead time of the product to be simulated and the number of annual payouts. Furthermore, the sudden demand prediction unit 161b acquires distribution data corresponding to the production lead time of the product to be simulated (data indicating the distribution of the number of sudden demand occurrences for each requested lead time) from the demand distribution data 165.

  If the sudden demand forecast data 163 is the same as the example shown in FIG. 2, the sudden demand prediction unit 161b obtains “1.77” as a predicted value of the annual number of sudden demands. Furthermore, if the demand distribution data 165 is the same as the example shown in FIG. 4, the sudden demand forecasting unit 161 b generates 0 months, 1 month, 2 months, 3 months, 4 months, and 5 months as distribution data. Lead time and occurrence ratio of “3.5%”, “24.6%”, “21.1%”, “24.6%”, “15.8%”, and “10.5%” Are associated with each other.

  The sudden demand forecasting unit 161b requests the number of sudden demands generated during the simulation period on a monthly basis using the predicted value of the annual number of sudden demands thus obtained and the probability indicated by the distribution data and random numbers. Set for each lead time. Specifically, the sudden demand forecasting unit 161b approximates the annual number of sudden demands to a predicted value of the number of sudden demands, and the ratio of the total number of sudden demands for each requested lead time. However, the number of occurrences of sudden demand is set so as to approximate the ratio in the distribution data.

  In the example illustrated in FIG. 5, the number of sudden demands is “6” in three years. That is, the annual number of sudden demands is “2 (6 ÷ 3)”, which is close to “1.77”, which is the predicted value of the annual number of sudden demands. Furthermore, in the example shown in FIG. 5, the total value of the number of sudden demand occurrences for each requested lead time is “0” in the order of 0 month, 1 month, 2 months, 3 months, 4 months, and 5 months. “1”, “1”, “2”, “1”, and “1”. That is, the ratio of the total number of sudden demand occurrences for each required lead time is “0%”, “16.66” in the order of 0 month, 1 month, 2 months, 3 months, 4 months, and 5 months. % ”,“ 16.66% ”,“ 33.33% ”,“ 16.66% ”, and“ 16.66% ”, and“ 3.5% ”and“ 24.6% ”in the distribution data. , “21.1%”, “24.6%”, and “15.8%”.

  The cancellation prediction unit 161c acquires a predicted value of the annual number of cancellations corresponding to the annual number of paid-out products to be simulated from the cancellation prediction data 164. If the cancellation prediction data 164 is the same as the example illustrated in FIG. 3, the cancellation prediction unit 161 c obtains “1.4” as the predicted value of the annual number of cancellations.

  The cancellation prediction unit 161c sets the number of cancellations occurring in the simulation period for each month using the probability indicated by the predicted value of the annual number of cancellations obtained in this way and a random number. Specifically, the cancellation prediction unit 161c sets the number of cancellations so that the annual number of cancellations approximates the predicted value of the annual number of cancellations.

  In the example shown in FIG. 5, the number of cancellations is “4” in three years. That is, the annual number of cancellations is “1.33 (4 ÷ 3)”, which is close to “1.4”, which is a predicted value of the annual number of cancellations.

  As described above, the sudden demand prediction unit 161b and the cancel prediction unit 161c predict the number of occurrences of sudden demand and the number of cancellations based on the probabilities obtained by analyzing the performance data 162. For this reason, the number of sudden demands and the number of cancellations are predicted with high accuracy. Furthermore, the sudden demand prediction unit 161b predicts the number of sudden demands for each request lead time based on the probability obtained by analyzing the performance data 162. For this reason, it is possible to realize a more accurate simulation by reflecting the variation in the required lead time, that is, the variation in the period until the delivery date, in the fluctuation of the number of possessions.

  The simulator 161d simulates fluctuations in the number of products held when sudden demand occurs as predicted by the sudden demand predictor 161b and cancellation occurs as predicted by the cancel predictor 161c. In order to simulate the change in the number of products held, the simulation unit 161d uses the logic shown in FIG. 6 and the logic shown in FIG. 7 or FIG.

  FIG. 6 is a diagram showing logic for changing the change in the number of products held in association with the occurrence of sudden demand. When sudden demand arises, production of the product starts. Thereafter, when the required lead time elapses from the occurrence of the sudden demand, that is, when the delivery date arrives, the number of products held decreases by one because the products are paid out. Thereafter, when the production lead time elapses from the occurrence of the sudden demand, the production started when the sudden demand occurs is completed, so the number of products held increases by one.

  FIG. 7 is a diagram showing logic for changing the change in the number of products held in response to the occurrence of cancellation. When demand arises, production of the product begins. After that, when cancellation occurs, the product is not paid out, so the number of products held by this demand does not decrease. Thereafter, when the production lead time elapses from the occurrence of demand, the production started when the demand occurs is completed, so the number of products held increases by one.

  FIG. 8 is a diagram showing another logic for changing the change in the number of products held in response to the occurrence of cancellation. When demand occurs, production of a product is started just before the production lead time from the delivery date, that is, at the timing when production is completed by the delivery date. If cancellation occurs after the start of production, the product will not be paid out, so the number of products held by this demand does not decrease. After that, when the required lead time elapses from the generation of demand, the production is completed, so the number of products held increases by one.

  FIG. 9 is a diagram illustrating an example of a simulation result. In the graph 27 shown in FIG. 9, the simulation result of the fluctuation of the number of products held is shown for each of the six patterns with the initial number of products held from 0 to 5. In each pattern, the simulation is performed using the same prediction by the sudden demand prediction unit 161b and the cancellation prediction unit 161c.

  In the graph 27 shown in FIG. 9, a portion where the number of possessions is less than 0 indicates a state where the number of retained products is insufficient, that is, a state where a shortage occurs. For example, in the graph 27, when the initial number of products held is 0, 1, 2, 3, and 4 at the time of the arrow 27a, 5, 4, 3, 2, This shows that one piece and one shortage occur.

  The sudden demand prediction unit 161b, the cancellation prediction unit 161c, and the simulation unit 161d execute prediction and simulation for a single product a designated number of times. Thereby, the same number of simulation results as shown in the graph 27 are created.

  The evaluation unit 161e evaluates the number of products held based on the status of the shortage in the plurality of simulation results thus obtained. The evaluation unit 161e can use, for example, the number of missing items, the probability of missing items, and the loss cost as values for evaluating the number of products held. The number of missing items is the number of times that a missing item occurs. The shortage occurrence probability is the probability that a shortage will occur. The loss cost is a value representing an operating loss or the like due to a shortage.

  FIG. 10 is a diagram illustrating an example of the evaluation data 166 generated by the evaluation unit 161e. In FIG. 10, the simulation unit 161d simulates fluctuations in the number of six types of products for each of the six patterns in which the initial number of products is 0 to 5, and the evaluation unit 161e The example of the evaluation data 166 in the case of evaluating the possession number of each product based on the occurrence probability is shown.

  By referring to such evaluation results, the person in charge of product production can determine the appropriate number of products, that is, the safety stock. For example, the evaluation data 166 shown in FIG. 10 indicates that the out-of-stock probability of the product with the product number “P001” is 0, 1, 2, 3, 4, and 5 in the initial possession number. Respectively, “90%”, “36%”, “2%”, “0%”, “0%”, and “0%”. In this case, if no out of stock is allowed, it is determined that three are safety stocks. On the other hand, if the out-of-stock occurrence probability of up to 5% is accepted, it is determined that two are safety stocks.

  A processing procedure executed by the simulation apparatus 10 will be described with reference to FIG. FIG. 11 is a flowchart illustrating an example of a processing procedure executed by the simulation apparatus 10. The processing procedure illustrated in FIG. 11 is realized by the control unit 15 executing the simulation program 161.

  The simulation apparatus 10 executes initial processing as steps S101 to S103. Specifically, the performance data analysis unit 161a generates sudden demand prediction data 163 based on the performance data 162 as step S101. The performance data analysis unit 161a generates cancel prediction data 164 based on the performance data 162 as step S102. The performance data analysis unit 161a generates demand distribution data 165 based on the performance data 162 as step S103.

  The simulation apparatus 10 may not execute the initial process every time. That is, the simulation apparatus 10 may execute the initial process in advance to generate the sudden demand prediction data 163, the cancellation prediction data 164, and the demand distribution data 165. Then, when the simulation apparatus 10 is instructed to execute the simulation, the simulation apparatus 10 may execute step S104 and subsequent steps using the sudden demand prediction data 163, the cancellation prediction data 164, and the demand distribution data 165 that are generated in advance. Good.

  The simulation apparatus 10 acquires simulation conditions as step S104. The simulation conditions include information on the product to be simulated, the number of patterns in the initial number of holdings, the designated number of simulations per product, and the like.

  Subsequently, in step S105, the sudden demand prediction unit 161b predicts the number of sudden demands of the product for each period in which sudden demand occurs and for each requested lead time of the product. Further, the sudden demand prediction unit 161b predicts the number of cancellations for each period in which sudden demand occurs, as step S106. Then, in step S107, the simulation unit 161d determines the number of products held based on the number of sudden demands predicted by the sudden demand prediction unit 161b and the number of cancellations predicted by the cancellation prediction unit 161c. Simulate fluctuations. The simulation unit 161d generates simulation results of a plurality of patterns with different initial numbers of products.

  In step S108, the simulation apparatus 10 determines whether the number of simulations of the product currently being simulated has reached the specified number. If the number of product simulations has not reached the specified number (step S108, No), the simulation apparatus 10 returns to step S105 and performs the simulation of the same product.

  If the number of product simulations has reached the specified number (step S108, Yes), the simulation apparatus 10 proceeds to step S109. In step S109, the evaluation unit 166e evaluates the simulation result. The evaluation unit 166e stores the evaluation result in the result data 166 as step S110.

  In step S111, the simulation apparatus 10 determines whether there is another product to be simulated. When there is another product to be simulated (step S111, Yes), the simulation apparatus 10 returns to step S105 and performs simulation of the other product. When there is no other product to be simulated (step S111, No), the simulation apparatus 10 ends the processing procedure illustrated in FIG.

  In addition, the aspect of this invention shown by said Example can be arbitrarily changed in the range which does not deviate from the summary of this invention. For example, the program shown in the above embodiment may be divided into a plurality of modules or may be integrated with other programs. Further, the functions of the simulation apparatus 10 may be distributed as appropriate.

  In the above-described embodiment, an example in which a manufacturer who produces a product with a long production lead time by multi-product small-quantity production uses the simulation apparatus 10 has been described. However, the user of the simulation apparatus 10 is not limited to this. For example, a manufacturer that produces a product with a short production lead time, a manufacturer that produces a small variety of products, and a manufacturer that mass-produces a product can also effectively use the simulation apparatus 10. The distributor who distributes the product can also effectively use the simulation apparatus 10.

DESCRIPTION OF SYMBOLS 10 Simulation apparatus 11 Display part 12 Input part 13 Communication part 14 Medium reading part 15 Control part 16 Memory | storage part 15a CPU
15b Memory 161 Simulation program 161a Actual data analysis unit 161b Unexpected demand prediction unit 161c Cancellation prediction unit 161d Simulate unit 161e Evaluation unit 162 Actual data 163 Unexpected demand prediction data 164 Cancellation prediction data 165 Demand distribution data 166 Evaluation data

Claims (6)

A sudden demand forecasting unit that predicts the number of sudden demands for a product for each period when the sudden demand for the product occurs and for each required lead time from when the sudden demand for the product occurs until the product is paid out When,
A simulation device comprising: a simulation unit that simulates a change in the number of possessed products based on the number of occurrences of sudden demand of the product predicted by the sudden demand prediction unit. A cancellation prediction unit that predicts the number of cancellations of the product for each period;
The simulation apparatus according to claim 1, wherein the simulation unit simulates a change in the number of the products held based on the number of the cancellations predicted by the cancellation prediction unit.   The said sudden demand prediction part estimates the number of occurrence of the sudden demand of the said product for every said request | requirement lead time based on distribution for every said request | requirement lead time of the actual value of the number of occurrence of the demand of the said product. Or the simulation apparatus of 2.   The abrupt demand forecasting unit, based on the distribution of the demand value of the product, the production lead time required for production out of the actual value of the number of demands of the product, The simulation apparatus according to claim 3, wherein the sudden demand number is predicted for each requested lead time. A simulation method executed by a simulation apparatus,
Predicting the number of occurrences of sudden demand for a product for each period in which sudden demand for the product occurs, and for each required lead time from the occurrence of sudden demand for the product until the product is paid out;
Simulating a change in the number of possessed products based on the number of sudden demands of the product. In the simulation device,
Predicting the number of occurrences of sudden demand for a product for each period in which sudden demand for the product occurs, and for each required lead time from the occurrence of sudden demand for the product until the product is paid out;
A simulation program for executing a step of simulating a change in the number of possessed products based on the number of sudden demands of the product.

Images