JP2012198689A - Demand prediction device, demand prediction method and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To achieve more accurate demand prediction in consideration of the number of operating components in a market, durability output number of components, and seasonal variation.SOLUTION: A demand prediction device 100 includes: a plan and result information collection part 103 which collects replacement record information of components, sales plan information and sales result information of the components; a replacement criterion calculation part 105 which calculates a distribution of the number of component replacements indicating the distribution of the number of component replacements from the replacement record information; a replacement prediction number calculation part 107 which calculates the replacement prediction number of components based on the sales plan information and the sales result information of components, and the distribution of the number of component replacements; a seasonal variation calculation part 108 which calculates a seasonal variation based on order reception information and the replacement record information; a replacement prediction number correction part 109 which corrects the replacement prediction number by the seasonal variation; and a life cycle classified demand prediction number calculation part 111 which calculates a divergence rate based on the replacement prediction number after correction and the order reception information, and calculates the demand prediction number of the components for each life cycle based on the replacement prediction after correction and the divergence rate.

Description

  The present invention relates to a demand prediction apparatus, a demand prediction method, and a program.

  Conventionally, demand prediction of functional parts such as an image forming apparatus has been performed. In such a conventional technology, statistical calculation such as Weibull, cumulative secondary, moving average, etc. is performed using the past order actual value of parts, etc., and the calculated value closest to the past actual result is adopted. The inventory of goods was managed by forecasting demand.

  However, with such a conventional technology, it is difficult to predict demand according to the number of operating parts of the image forming apparatus or the like in the market and the durable output number of parts. For this reason, demand prediction and parts procurement were followed, and there was a problem that the total amount of parts was insufficient. It was also difficult to manage inventory in line with seasonal fluctuations in market economic activity.

  The present invention has been made in view of the above, and a demand prediction device capable of realizing a more accurate demand prediction in consideration of the number of operating parts in the market, the number of durable outputs of the parts, and seasonal variation, The main purpose is to provide a demand forecasting method and program.

  In order to solve the above-described problems and achieve the object, a demand prediction apparatus according to the present invention includes a product replacement result information, a plan result information collection unit that collects the product sales plan and sales result information, The exchange of the product based on the exchange standard calculation unit for calculating the exchange number distribution indicating the distribution of the exchange number of the product from the exchange result information, the sales plan and sales result information of the product, and the exchange number distribution. And an exchange prediction number calculation unit for calculating the prediction number.

  The demand forecasting method according to the present invention is a demand forecasting method executed by a demand forecasting device, comprising collecting product replacement record information, the product sales plan and sales record information, and the replacement record From the information, a replacement number distribution indicating the distribution of the replacement number of the product is calculated, a sales plan and sales result information of the product, and a replacement predicted number of the product is calculated based on the replacement number distribution. And a step.

  In addition, the program according to the present invention includes a step of collecting product replacement result information, a sales plan and sales result information of the product, and a replacement number distribution indicating a distribution of the replacement number of the product from the replacement result information. And causing the computer to execute a step of calculating, a step of calculating a predicted replacement number of the product based on the sales plan and sales performance information of the product and the distribution of the number of replacements.

  According to the present invention, there is an effect that more accurate demand prediction can be realized in consideration of the number of operating parts in the market, the number of durable outputs of the parts, and seasonal variations.

FIG. 1 is a network configuration diagram of the demand prediction system of the present embodiment. FIG. 2 is a block diagram illustrating a functional configuration of the demand prediction apparatus 100 according to the present embodiment. FIG. 3 is a flowchart illustrating a procedure of demand prediction processing according to the present embodiment. FIG. 4 is a schematic diagram illustrating an example of a master download screen. FIG. 5 is a schematic diagram illustrating an example of a master upload screen. FIG. 6 is an explanatory diagram showing an example of a replacement record acquisition priority table. FIG. 7 is an explanatory diagram showing an example of the replacement number distribution. FIG. 8 is a graph of the number of replacement predictions corrected by the sales plan, the order record, the number of operating units, the replacement record, and the amount of seasonal variation. FIG. 9 is an explanatory diagram illustrating an example of a technique for calculating the demand forecast number. FIG. 10 is an explanatory diagram illustrating an example of a method for calculating the demand forecast number. FIG. 11 is an explanatory diagram illustrating an example of a screen displayed on the display unit in calculating the demand forecast number. FIG. 12 is an explanatory diagram illustrating an example of a batch result display screen.

  Exemplary embodiments of a demand prediction apparatus, a demand prediction method, and a program according to the present invention will be described below in detail with reference to the accompanying drawings.

  FIG. 1 is a network configuration diagram of the demand prediction system of the present embodiment. As shown in FIG. 1, the demand prediction system of the present embodiment includes a demand prediction device 100, a plurality of master management systems 200-1 to 200-n, and a plurality of maintenance management systems 300-1 to 300-n. The plurality of planned performance management systems 400-1 to 400-n are connected via a network such as the Internet.

  In the following, the master management systems 200-1 to 200-n are referred to as the master management system 200, the maintenance management systems 300-1 to 300-n are referred to as the maintenance management system 300, and the planned performance management system 400-- 1 to 400-n is expressed as a planned performance management system 400.

  The demand prediction device 100 predicts the demand for goods and calculates the number of demand predictions. Here, in the present embodiment, the demand prediction apparatus 100 is a demand for parts of the image forming apparatus, particularly preventive maintenance parts (hereinafter simply referred to as “parts”), which are functional parts for which quality degradation is predicted, as products. The number of predictions is calculated. However, the present invention is not limited to this, and can be applied to any product of the image forming apparatus as a product. Further, the present invention can be applied to products of apparatuses other than the image forming apparatus.

  Here, the image forming apparatus is a printer apparatus, a copying apparatus, a facsimile apparatus, a scanner apparatus, or a multifunction machine including at least two of a printer function, a copying function, a facsimile function, and a scanner function, but is not limited thereto. It is not a thing.

  The master management system 200 is a computer that manages master data related to parts. The master data related to parts corresponds to information on the configuration, model, parts, etc. of the image forming apparatus.

  The maintenance management system 300 is a computer that manages data related to maintenance management of the image forming apparatus. The data relating to maintenance management corresponds to replacement result data of parts of the image forming apparatus.

  The planned performance system 400 is a computer that manages data related to sales plans and sales results of the image forming apparatus and its parts.

  FIG. 2 is a block diagram illustrating a functional configuration of the demand prediction apparatus 100 according to the present embodiment. As shown in FIG. 2, the demand prediction apparatus 100 according to this embodiment includes a master database 120 (hereinafter referred to as “master DB”), a component-related master creation unit 101, a planned performance information collection unit 103, and an exchange. A reference calculation unit 105, an exchange prediction number calculation unit 107, a seasonal fluctuation amount calculation unit 108, an exchange prediction number correction unit 109, a life cycle demand prediction number calculation unit 111, and a display unit 130 are mainly provided. Yes.

  The component-related master creation unit 101 receives various master data from the master management system 200 and generates a master DB 120. Here, the master DB 120 is stored in a storage medium such as a hard disk drive (HDD). Specifically, the component-related master creation unit 101 registers a component configuration master, a model master, a component master, and the like in the master DB 120 from various master data related to components.

  The planned result information collecting unit 103 collects replacement result data of parts of the image forming apparatus from the maintenance management system 300. Here, the replacement result data includes the number of parts exchanged, the number of output parts, and the number of exchanges indicating the durable output number of parts.

  Further, the planned result information collecting unit 103 collects a sales plan and actual data related to the sales plan and sales result of the parts of the image forming apparatus from the planned result management system 400.

  Here, the sales plan and the actual data of the image forming apparatus and its parts include the number of operating units in the market of the image forming apparatus and its parts and the actual order data.

  Here, the number of output sheets, the number of replacements, and the number of operating units are acquired for each base, each month, and each model.

  The replacement standard calculation unit 105 calculates a replacement number distribution indicating the distribution of the number of replacement parts from the replacement result data as a replacement reference. More specifically, the replacement standard calculation unit 105 calculates the replacement number distribution by dividing all the replacement number of parts for each output number and replacement number by the replacement number for each output number and replacement number. .

  The predicted replacement number calculation unit 107 is based on the number of operating parts included in the part sales plan and sales performance data and the replacement number distribution calculated by the replacement standard calculation unit 105, for each base, for each month, for each model, for each part. The expected number of replacements is calculated.

  The seasonal fluctuation amount calculation unit 108 calculates the seasonal fluctuation amount based on the order reception result data of the data related to the sales plans and sales results of the image forming apparatus and its parts, and the replacement result data.

  More specifically, the seasonal fluctuation amount calculation unit 108 calculates the output number fluctuation index, which is the change in the output number per month with respect to the average value of the output number for 12 months, and the rate of change in the order rate of parts relative to the number of operating units per month. And the monthly order divergence rate, which is the monthly divergence rate of the order record data with respect to the predicted exchange number considering the change in the number of output sheets, is calculated as a seasonal variation amount. However, these seasonal variations are merely examples, and are not limited to these.

  The replacement prediction number correction unit 109 corrects the replacement prediction number calculated by the replacement prediction number calculation unit 107 with the seasonal variation amount calculated by the seasonal variation amount calculation unit 108.

  Further, if the part is a unit part to be sold as a single unit (a unit including a photosensitive drum, a developing device, etc.), the replacement prediction number correction unit 109 receives the order rate of the single part based on the order record data. Is calculated, and the number of replacements is corrected with the order rate of a single item.

  More specifically, the predicted replacement number correction unit 109 corrects the predicted replacement number of parts with the output number fluctuation index, the order rate fluctuation index, and the monthly order deviation rate. Here, when the part is a unit part to be sold as a single unit, the replacement prediction number correction unit 109 calculates the replacement prediction number, the output number fluctuation index, the order rate fluctuation index, the monthly order divergence ratio, and the single order. Correct by rate.

  The life cycle demand forecast number calculation unit 111 calculates a divergence rate based on the corrected exchange prediction number and the order record information, and based on the exchange prediction and divergence rate corrected by the exchange prediction number correction unit 109. Then, the number of parts demand forecast for each period of the life cycle is calculated. Here, the life cycle demand prediction number calculation unit 111 calculates a value obtained by dividing the order record data by the corrected replacement prediction number as the deviation rate.

  The display unit 130 is a display device such as a display device that displays various screens.

  Next, the detail of the demand prediction process by the demand prediction apparatus comprised as mentioned above is demonstrated. FIG. 3 is a flowchart illustrating a procedure of demand prediction processing according to the present embodiment.

  First, the component-related master creation unit 101 receives various master data related to each component of the image forming apparatus from the master management system 200 via the network, creates a component-related master, and registers it in the master DB 120 (step S11). . As the component-related master registered in the master DB 120, as shown in FIG. 1, a component configuration master that indicates the configuration of the components of the image forming apparatus, a model master that indicates the model of the image forming apparatus, and components that are various information of the components themselves There are masters.

  The user acquires various masters by downloading necessary masters by pressing a start button corresponding to the necessary masters from the master download screen shown in FIG. Further, when the user corrects or adds various masters in the master DB 120, the master is managed by the master management system 200 by pressing the start button corresponding to the master after correction and addition from the master upload screen shown in FIG. Upload to.

  Returning to FIG. 3, next, the planned performance information collection unit 103 receives replacement performance data (that is, the number of replacements, the number of output sheets, and the number of replacements) from the maintenance management system 300 via the network, and from the planned performance management system 400. The sales plan and the actual data (that is, the number of operating units, the actual order received) are received and acquired via the network (step S22).

  Here, in the present embodiment, the priority order for obtaining the replacement record data is determined. FIG. 6 is an explanatory diagram showing an example of a replacement record acquisition priority table. As shown in FIG. 6, in the replacement priority data acquisition priority table, the output number and replacement number of replacement result data from each of the domestic maintenance management systems 1 and 2 and the overseas maintenance management systems 3 and 4 are displayed. Whether or not to obtain the priority order is determined, and the plan record information collecting unit 103 selects the maintenance management system 300 according to the priority order defined in this table, and obtains replacement result data.

  Returning to FIG. 3, next, the replacement standard calculation unit 105 calculates the replacement number distribution as the replacement standard from the replacement record data (step S23). More specifically, the replacement standard calculation unit 105 calculates the replacement number distribution by the following equation (1). FIG. 7 shows an example of the replacement number distribution.

(All number of parts replaced per number of output sheets and replacement sheets) / (Number of parts replaced)
... (1)
Returning to FIG. 3, next, the predicted replacement number calculation unit 107 predicts the number of replacement parts for each base, model, and month from the number of operating units in the sales plan and actual data and the replacement number distribution obtained in step S23. A certain exchange prediction number is calculated (step S24).

  Next, the seasonal fluctuation amount calculation unit 108 corrects the predicted number of exchanges, based on the sales plan and the actual order received results, the output number and the exchanged number of the actual exchange data, and the seasonal fluctuation amount (output number fluctuation index, received order). Rate fluctuation index, monthly order divergence rate).

  Of the seasonal variations, the output sheet variation index is calculated by the following equation (2).

Output number fluctuation index =
[(Average number of output by month / model)-(Average number of output by model for 12 months)]
/ Average number of output sheets by model for 12 months (2)
Next, the predicted replacement number correction unit 109 corrects the predicted replacement number of parts calculated in step S24 with the seasonal fluctuation amount (output number fluctuation index, order rate fluctuation index, monthly order deviation rate) calculated in step S25. (Step S26).

  Then, the predicted replacement number correction unit 109 determines whether or not the target part is a single unit part to be sold with reference to the part master of the master DB 120 (step S27). Then, if the target part is a unit part (step S27: Yes), the replacement prediction number correction unit 109 corrects the part replacement prediction number with a single item order rate by referring to the order record. (Step S28). In step S27, when the target part is not a unit part (step S27: No), the correction based on the single item order rate is not performed.

  FIG. 8 is a graph of the number of replacement predictions corrected by the sales plan, the order record, the number of operating units, the replacement record, and the amount of seasonal variation. As shown in FIG. 8, the number of exchange predictions is corrected with the amount of seasonal variation.

  Returning to FIG. 3, the life cycle demand prediction number calculation unit 111 calculates a deviation rate from the corrected replacement prediction number and the order record (step S <b> 29). Here, the demand forecast number calculation unit 111 by life cycle calculates the division value as a deviation rate by dividing the order received result by the corrected exchange prediction number. As shown in FIG. 8, the difference between the order record and the predicted exchange number is the divergence rate.

  Returning to FIG. 3, next, the life cycle demand forecast number calculation unit 111 calculates the part demand forecast number from the corrected replacement forecast number and the deviation rate calculated in step S <b> 29 (step S <b> 30). . As shown in FIG. 8, the life cycle includes a rising period, an initial flow period, a growth period, and a maturation period. 9 and 10 are explanatory diagrams showing examples of methods for calculating the demand forecast number.

  For example, as shown in FIG. 9, in the case of a part of an image forming apparatus of a predecessor machine that is a model prior to the current model, the demand forecast number calculation unit 111 by life cycle determines the predecessor during the life cycle startup period. The demand forecast number is obtained only from the machine deviation rate. Specifically, as illustrated in FIG. 10, the life cycle demand prediction number calculation unit 111 calculates the demand prediction number by correcting the replacement prediction number with the deviation rate of the predecessor.

  Further, for example, as shown in FIG. 9, in the case of a part of an image forming apparatus of the own model that is the current model, the magnitude relationship between the deviation rate of the own model and a predetermined reference deviation rate in the period C of the initial flow period and The number of demand forecasts is obtained by the magnitude relationship between the actual order and the number of forecasted exchanges. Specifically, as shown in FIG. 10, in the case of the parts of the image forming apparatus of the own model, the demand forecast number calculation unit 111 by life cycle has a divergence rate higher than the reference divergence rate in the period C of the initial flow period. When it is large and the order record is smaller than the predicted number of replacements, an 18-month uniform increase straight line of the replacement predicted number is obtained, and the value indicated by this straight line is calculated as the demand predicted number.

  Also, for example, as shown in FIG. 9, in the period D of the initial flow period, the demand forecast number is obtained from the magnitude relationship between the deviation rate and the standard deviation rate and the magnitude relationship between the order record and the exchange forecast number. Specifically, as illustrated in FIG. 10, the life cycle demand forecast number calculation unit 111 has a deviation rate larger than the reference deviation rate during the period D of the initial flow period, and the order record is equal to or greater than the exchange forecast number. In this case, the regression line of the actual order is obtained, and the value indicated by the regression line is calculated as the demand forecast number.

  Further, for example, as shown in FIG. 9, in the period of F, G, H, I, and J in the growth / maturity period, the demand forecast number is obtained by the main part or the dependent part. That is, the life cycle demand forecast number calculation unit 111 calculates the demand forecast number using the calculation formula shown in the demand forecast result when the conditions of F, G, H, I, and J in the growth / maturity period are met. Here, the main part is a part that leads the change in the number of exchanges, and corresponds to, for example, a black (K) image forming unit. The subordinate parts are parts whose number of replacement varies following the main part. For example, cyan (C), magenta (M), and the like following the black (K) image forming unit as the main part. This corresponds to an image forming unit of each color of yellow (Y).

  FIG. 11 is an explanatory diagram illustrating an example of a screen displayed on the display unit 130 in calculating the demand forecast number. As shown in FIG. 11, it can be understood which of the methods shown in FIGS. 9 and 10 has been adopted in calculating the demand forecast number.

  FIG. 12 is an explanatory diagram showing an example of a batch result display screen when steps S11 to S30 described above are executed as a series of batch processes. As shown in FIG. 12, the status of each process (whether it is a normal end), a process group, a batch issue date / time, an end date / time, and the like are displayed on the display unit 130. A detailed history of batch results is displayed on the display unit 130 by pressing a log button for each process on the screen shown in FIG.

  As described above, in the present embodiment, the part replacement number distribution is calculated from the part replacement result data, the part sales plan and the sales result data, the part replacement predicted number is calculated, and the seasonal variation amount is calculated. Since the number of demand predictions is calculated by correcting the number of replacement predictions, more accurate demand forecasting can be realized in consideration of the number of operating parts in the market, the number of durable outputs of parts, and seasonal variations.

  The demand prediction apparatus 100 according to the present embodiment includes a control device such as a CPU, a storage device such as a ROM (Read Only Memory) and a RAM, an external storage device such as an HDD and a CD drive device, and a display device such as a display device. And an input device such as a keyboard and a mouse, and has a hardware configuration using a normal computer.

  The demand prediction program executed by the demand prediction apparatus 100 of the present embodiment is a file in an installable or executable format, such as a CD-ROM, a flexible disk (FD), a CD-R, a DVD (Digital Versatile Disk), or the like. And recorded on a computer-readable recording medium.

  Further, the demand prediction program executed by the demand prediction apparatus 100 of the present embodiment may be provided by being stored on a computer connected to a network such as the Internet and downloaded via the network. Moreover, you may comprise so that the demand prediction program performed with the demand prediction apparatus 100 of this embodiment may be provided or distributed via networks, such as the internet.

  Moreover, you may comprise so that the demand prediction program performed with the demand prediction apparatus 100 of this embodiment may be provided by incorporating in ROM etc. previously.

  The demand prediction program executed by the demand prediction apparatus 100 according to the present embodiment includes the above-described units (part-related master creation unit 101, planned performance information collection unit 103, replacement reference calculation unit 105, replacement prediction number calculation unit 107, seasonal variation. The module configuration includes an amount calculation unit 108, a replacement prediction number correction unit 109, and a life cycle demand prediction number calculation unit 111). As actual hardware, a CPU (processor) loads a demand prediction program from the storage medium. By reading and executing the above-described units, the above-described units are loaded on the main storage device, and the component-related master creation unit 101, the plan record information collection unit 103, the replacement reference calculation unit 105, the replacement prediction number calculation unit 107, and the seasonal variation calculation unit 108. The replacement prediction number correction unit 109 and the life cycle demand prediction number calculation unit 111 are generated on the main storage device. You have me.

DESCRIPTION OF SYMBOLS 100 Demand prediction apparatus 101 Parts related master preparation part 103 Plan performance information collection part 105 Replacement reference calculation part 107 Replacement prediction number calculation part 108 Seasonal fluctuation amount calculation part 109 Replacement prediction number correction part 111 Life prediction demand prediction number calculation part 200-1 to 200-n Master management system 300, 300-1 to 300-n Maintenance management system 400, 400-1 to 400-n Plan results management system

JP 2007-199844 A JP 2003-233710 A

Claims (10)

A replacement result information of the product, a plan result information collecting unit for collecting the sales plan and the sales result information of the product,
From the replacement record information, an exchange standard calculation unit that calculates a replacement number distribution indicating a distribution of the replacement number of the product,
Based on the sales plan and sales performance information of the product, and the replacement number distribution, a replacement prediction number calculation unit that calculates the replacement prediction number of the product,
A demand forecasting device characterized by comprising: The sales plan and sales result information of the product include the number of operating units in the market of the product and the order result information of the product,
The replacement result information includes the number of replacements of the product, the output number of the product, and the replacement number indicating the durable output sheet of the product,
The replacement standard calculation unit divides the total number of replacements of the product for each of the output number and the replacement number by the replacement number of the products by dividing the replacement number distribution by the replacement number of the products. Calculate
The demand prediction device according to claim 1, wherein the predicted replacement number calculation unit calculates the predicted replacement number of the product based on the operating number and the replacement number distribution.   The demand prediction device according to claim 1, wherein the predicted replacement number calculation unit calculates a predicted replacement number for each base, each month, each model, and each part. A seasonal variation calculation unit for calculating a seasonal variation based on the order record information and the exchange record information;
An exchange prediction number correction unit for correcting the exchange prediction number by the amount of seasonal variation;
The demand prediction apparatus according to claim 2, further comprising: The seasonal variation calculation unit is an output number variation index that is a variation of the output number per month with respect to an average value of the output number for 12 months, and a variation rate of the order rate of the product with respect to the number of operating units per month. An order rate fluctuation index and a monthly order divergence rate, which is a monthly divergence rate of the order results with respect to the exchange forecast number taking into account the change in the output number, are calculated as the seasonal variation amount.
The demand prediction device according to claim 4, wherein the replacement prediction number correction unit corrects the replacement prediction number with the output number fluctuation index, the order rate fluctuation index, and the monthly order deviation rate. Further, when the product is a unit part to be sold as a single unit, the seasonal variation amount calculation unit calculates, as the seasonal variation amount, the monthly order rate of the single item of the product based on the order reception result. Calculate
The said exchange prediction number correction | amendment part correct | amends the said exchange prediction number by the said output sheet number fluctuation | variation index | exponent, the said order receipt rate fluctuation | variation index | exponent, the said monthly order difference deviation rate, and the said single item order receipt ratio. Demand forecasting equipment. Life that calculates a divergence rate based on the corrected number of replacement forecasts and the order record information, and calculates a demand forecast number of the product for each life cycle based on the corrected exchange prediction and the divergence rate The demand prediction apparatus according to claim 5, further comprising a cycle-specific demand prediction number calculation unit.   8. The demand prediction device according to claim 7, wherein the life cycle demand prediction number calculation unit calculates a value obtained by dividing the order record information by the corrected replacement prediction number as the deviation rate. . A demand prediction method executed by a demand prediction device,
Collecting product replacement performance information, and the sales plan and sales performance information of the product;
From the replacement result information, calculating a replacement number distribution indicating a distribution of the replacement number of the product,
Calculating a predicted number of replacements of the product based on the sales plan and sales result information of the product and the distribution of the number of replacements;
Demand forecasting method characterized by including. Collecting product replacement performance information, and the sales plan and sales performance information of the product;
From the replacement result information, calculating a replacement number distribution indicating a distribution of the replacement number of the product,
Calculating a predicted number of replacements of the product based on the sales plan and sales result information of the product and the distribution of the number of replacements;
A program that causes a computer to execute.

Images