JP2014038406A - Component demand prediction system, component demand prediction method and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a component demand prediction system and the like capable of performing a demand prediction in a medium and a long term (for the unit of a year) with good accuracy.SOLUTION: A terminal receives an input of a component securing period (S1). Next, the terminal performs prediction processing of a predicted device residual rate of a calculation object device on the basis of an actual device residual rate of a device of a similar model (S2). Next, the terminal calculates the number of predicted installation on the basis of the existing number and the predicted device residual rate of the calculation object device (S3). Next, the terminal performs prediction processing of a component replacement rate of the calculation object device for each component or for each model (S4). Next, the terminal calculates required component quantity by using all of the component securing period, the predicted number of installation and the predicted component replacement rate as the required component quantity (S5). Next, the terminal calculates an erroneous prediction degree of the predicted component replacement rate or the required component quantity (S6).

Description

  The present invention relates to a parts demand forecasting system and the like for forecasting demand for parts used for equipment repair.

  In order to respond quickly when a failure occurs in a device, it is necessary to store the necessary parts in advance instead of placing an order for the parts each time a failure occurs. For example, Patent Literature 1 discloses a component demand prediction method for predicting the demand for components to be replaced in gas equipment repair.

  In the method described in Patent Document 1, the component usage rate calculation unit calculates the number of devices corresponding to the length of the unit period actually used for all owned devices registered in the customer-owned device data storage unit. Count by device, calculate the number of units by device type and by use period, derive the number of parts used by device and by use period based on the part usage record data, and calculate this by use period by device type By dividing by the number of components, the component usage rate, which is a value defined by the device type and the specific usage period, is calculated for each component, with respect to the proportion of the number of used components necessary for all owned devices. Then, the parts demand forecasting unit adds the calculation results obtained by multiplying the component usage rate and the number of existing machines by usage period by equipment type for each equipment type and usage period. Derive the number of forecast demand by parts.

JP 2010-231375 A

  By the way, in many cases, the vendors of devices used in ordinary households make long-term maintenance contracts with customers. Therefore, equipment vendors may have to keep parts necessary for repair for several years in order to deal with repair of sold equipment even when the manufacture and sale of the equipment is finished. . Furthermore, even in the sale of equipment, in order to further improve customer satisfaction (CS) so that customers do not have to wait as much as possible, information on parts that will be needed in the long term in the future is provided to manufacturers in advance to produce plans By reflecting the above, it will be possible to construct a smoother parts distribution system. However, since an excessive amount of parts ordering leads to disposal loss, it is necessary to predict the demand for an appropriate quantity of parts. That is, it is necessary for a device vendor to accurately predict medium- to long-term (yearly) demand.

  However, in the component demand prediction method described in Patent Document 1, since there is no mechanism for predicting the future, it is limited to short-term (daily or monthly) demand prediction, and medium-to-long-term (yearly) demand prediction is not possible. For example, in the component demand prediction method described in Patent Document 1, it is impossible to predict the demand for components to be used five years later (15 years after installation) with respect to equipment that has only been installed for 10 years.

  The present invention has been made in view of the above-described problems, and an object of the present invention is to provide a parts demand forecasting system and the like capable of accurately forecasting medium- to long-term (yearly) demand. It is.

  A first invention for achieving the above-mentioned object is a parts demand forecasting system configured to predict demand for parts used for repair of equipment, which is configured by a computer, and receives parts securing period input. Based on the receiving means, the predicted equipment remaining rate calculating means for calculating the predicted equipment remaining ratio based on the actual equipment remaining ratio of equipment of similar models, the existing number of devices to be calculated and the predicted equipment remaining rate A predicted installed number calculating means for calculating a predicted installed number, a predicted parts replacement rate calculating means for calculating a predicted parts replacement rate for each part or model, the parts securing period, the predicted installed number, and the predicted parts replacement. And a required component quantity calculating means for calculating the required component quantity by using all of the rates. According to the first aspect of the invention, it is possible to accurately perform medium- to long-term (yearly) demand prediction.

  The predicted part replacement rate calculating means in the first invention determines whether or not the actual value data of the component replacement rate of the device to be calculated exists for a predetermined number of years or more, and the actual value data is a predetermined number of years. If there is more than one, it is determined whether or not there is a peak in the actual value data, and three patterns of a medium-term prediction with a peak, a medium-term prediction without a peak, and a long-term prediction are automatically determined, and each pattern differs. Prediction processing may be performed. As a result, it is possible to accurately predict a future portion that has no record in consideration of external factors such as maintenance measures.

  Further, the predicted component replacement rate calculating means in the first invention may calculate a model-specific standard component replacement rate and perform a prediction process using the model-specific standard component replacement rate. As a result, it is possible to prevent the prediction from deviating greatly.

  In addition, the first invention may further include a prediction degree calculating means for calculating the prediction part replacement rate or the degree of unforeseen prediction of the required part quantity. As a result, the quantity of parts corresponding to fluctuations in demand can be held as inventory.

  A second invention is a parts demand forecasting method for forecasting demand for parts used for repair of equipment executed by a computer, wherein the control unit of the computer accepts an input of a parts securing period. Step, based on the actual device remaining rate of the device whose model is similar, based on the predicted device remaining rate calculating step of calculating the predicted device remaining rate, the existing number of devices to be calculated and the predicted device remaining rate, A predicted installed number calculating step for calculating a predicted installed number, a predicted component replacement rate calculating step for calculating a predicted part replacement rate for each part or model, the component securing period, the predicted installed number, and the predicted part replacement rate. And a necessary part quantity calculating step for calculating the required part quantity using all of the above. According to the second invention, medium-to-long-term (yearly) demand prediction can be accurately performed.

  A third invention is a program for causing a computer to execute a parts demand forecasting method for forecasting demand for parts used for repair of equipment, and accepting an input of a parts securing period from the control unit of the computer A securing period input acceptance step, a predicted device remaining rate calculating step for calculating a predicted device remaining rate based on the actual device remaining rate of devices of similar models, the existing number of devices to be calculated and the predicted device remaining rate A predicted installed number calculating step for calculating a predicted installed number, a predicted component replacement rate calculating step for calculating a predicted component replacement rate for each part or model, the component securing period, the predicted installed number, and the A required part quantity calculating step for calculating a required part quantity by using all of the predicted part replacement rates. By installing the third invention on a general-purpose computer, the parts demand prediction system of the first invention can be obtained, and the parts demand prediction method of the second invention can be executed.

  According to the present invention, it is possible to provide a parts demand forecasting system and the like capable of accurately performing medium- to long-term (yearly) demand forecasting.

The figure which shows the outline | summary of the components demand prediction system 1 Hardware configuration diagram of computer realizing terminal 2 (server 3) The figure which shows an example of the apparatus installation information 20 The figure which shows an example of the repair parts information 30 The figure which shows an example of the repair performance information 40 The flowchart which shows the flow of a process of the components demand prediction system 1 A figure showing an example of data on the actual equipment remaining rate A figure showing an example of parts replacement rate data for a specific device Prediction process of part replacement rate for each part regarding the first pattern Prediction process of part replacement rate for each part regarding the second pattern Prediction process of part replacement rate for each part regarding the third pattern Diagram showing an example of standard part replacement rate by model code Diagram explaining the prediction process of part replacement rate for each model The figure explaining the calculation process of the degree of unforeseen prediction which evaluated only the parts exchange rate Diagram explaining the process of calculating the degree of unforeseen prediction for the required parts quantity

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. If the present invention is applied to a device having the above-described problems, the same effect can be obtained.

FIG. 1 is a diagram showing an outline of a parts demand prediction system 1. As shown in FIG. 1, in the component demand prediction system 1, for example, a terminal 2 and a server 3 are connected via a network 6. The network 6 is, for example, the Internet or a LAN (Local Area Network). The terminal 2 is, for example, a PC (Personal
Any device that can connect to the network 6 and perform data communication (HTTP communication, TCP / IP communication, etc.), such as a computer (hereinafter referred to as “computer”) or a mobile terminal (mobile phone, smartphone, tablet terminal, etc.) But it ’s okay. Similarly to the terminal 2, the server 3 may be connected to the network 6 and can perform data communication, but is preferably a high-performance server computer.

  The terminal 2 is installed with a parts demand prediction program 4 which is an embodiment of the present invention. The server 3 is constructed with a database (hereinafter “DB”) 5 for storing various data used in the embodiment of the present invention. In the embodiment of the present invention, the terminal 2 functions as various means according to the component demand prediction program 4 and presents the necessary component quantity to the user. The terminal 2 transmits a data request command to the server 3 as necessary. The server 3 searches the DB 5 for the data request and transmits the requested data to the terminal 2.

  In addition, the structure of the components demand prediction system 1 is not restricted to the example shown in FIG. For example, the parts demand prediction system 1 may be configured with only the terminal 2. That is, the terminal 2 may include the DB 5.

  Further, the parts demand prediction program 4 may be installed in the server 3. In other words, the server 3 may function as various means according to the part demand prediction program 4 and present the necessary part quantity to the user. In this case, the terminal 2 serves as an interface with the user. That is, the terminal 2 transmits data input from the user to the server 3 and outputs (displays, prints, etc.) data received from the server 3.

  Further, instead of DB5, data may be stored as a simple file. The data stored in the DB 5 may be acquired from an external server.

  FIG. 2 is a hardware configuration diagram of a computer that realizes the terminal 2 (server 3). Note that the hardware configuration in FIG. 2 is an example, and various configurations can be adopted depending on the application and purpose.

  A computer that realizes the terminal 2 (server 3) includes a control unit 11, a storage unit 12, a media input / output unit 13, a communication control unit 14, an input unit 15, a display unit 16, a peripheral device I / F unit 17, and the like. 18 is connected.

  The control unit 11 includes a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), and the like. The CPU calls a program stored in the storage unit 12, ROM, recording medium, etc. to a work memory area on the RAM and executes it, drives and controls each device connected via the bus 18, and will be described later. Realize processing. The ROM is a non-volatile memory and permanently holds a computer boot program, a program such as BIOS, data, and the like. The RAM is a volatile memory, and temporarily stores programs, data, and the like loaded from the storage unit 12, ROM, recording medium, and the like, and includes a work area used by the control unit 11 for performing various processes.

  The storage unit 12 is, for example, an HDD (Hard Disk Drive), and stores a program executed by the control unit 11, data necessary for program execution, an OS (Operating System), and the like. As for the program, a control program corresponding to the OS and an application program for causing a computer to execute processing to be described later are stored. Each of these program codes is read by the control unit 11 as necessary, transferred to the RAM, read by the CPU, and executed as various means.

  The media input / output unit 13 (drive device) inputs / outputs data, for example, media such as a CD drive (-ROM, -R, -RW, etc.), DVD drive (-ROM, -R, -RW, etc.) Has input / output devices. The communication control unit 14 has a communication control device, a communication port, and the like, is a communication interface that mediates communication between the computer and the network 6, and controls communication with other computers via the network 6. The network 6 may be wired or wireless.

  The input unit 15 inputs data and includes, for example, a keyboard, a pointing device such as a mouse, and an input device such as a numeric keypad. An operation instruction, an operation instruction, data input, and the like can be performed on the computer via the input unit 15. The display unit 16 includes a liquid crystal panel, a display device such as an organic EL, and a logic circuit or the like (video adapter or the like) for realizing a video function of a computer in cooperation with the display device. The input unit 15 and the display unit 16 may be integrated like a touch panel display.

  The peripheral device I / F (interface) unit 17 is a port for connecting a peripheral device to the computer, and the computer transmits and receives data to and from the peripheral device via the peripheral device I / F unit 17. The peripheral device I / F unit 17 is configured by a USB or the like, and usually includes a plurality of peripheral devices I / F. The connection form with the peripheral device may be wired or wireless. The bus 18 is a path that mediates transmission / reception of control signals, data signals, and the like between the devices.

  FIG. 3 is a diagram illustrating an example of the device installation information 20. The device installation information 20 is information indicating a device installation status. The device installation information 20 includes data items such as a customer number 21, a device code 22, a manufacturer code 23, a model code 24, an installation date 25, and a removal date 26. The device installation information 20 is stored in the DB 5.

  The customer number 21 is a number for identifying the customer who is the owner of the device. The device code 22 is an identifier for identifying a device. The manufacturer code 23 is an identifier for identifying the manufacturer of the device. The model code 24 is an identifier for identifying the type of device.

  The installation date 25 is the date on which the device was installed. The removal date 26 is the date when the device was removed. The reason for removal is not limited to the failure of the device, but may be due to the convenience of the device owner. The removal date 26 is NULL (no value) until the device is removed.

  FIG. 4 is a diagram illustrating an example of the repair part information 30. The repair part information 30 is information indicating a replacement part used for repairing the device. The repair part information 30 includes data items such as a work title 31, a customer number 32, a replacement part code 33, a work completion date 34, and the number of replacement parts 35. The repair part information 30 is stored in the DB 5.

  The work subject 31 is an identifier for identifying the subject of repair work. The customer number 32 is the same as the customer number 22 of the device installation information 20. The replacement part code 33 is a code for identifying a replacement part used for repairing the device. The work completion date 34 is the date of completion of the repair work. The number of replacement parts 35 is the number of replacement parts used for repairing the device.

  FIG. 5 is a diagram illustrating an example of the repair record information 40. The repair record information 40 is information indicating details of the repair work record. The repair record information 40 includes data items such as a work name 41, a customer number 42, a part code 43, a part name 44, a device code 45, a manufacturer code 46, and a part price 47. The repair record information 40 is stored in the DB 5.

  The work subject 41 is the same as the work subject 31 of the repair part information 30. The customer number 42 is the same as the customer number 32 in the repair part information 30. The part code 43 is an identifier for identifying a part of the device, and the code system is the same as the replacement part code 33 of the repair part information 30. The part name 44 is the name of the part specified by the part code 43. The device code 45 is the same as the device code 22 of the device installation information 20. The manufacturer code 46 is the same as the manufacturer code 23 of the device installation information 20. The part price 47 is the price of the part specified by the part code 43.

  Prior to the description of the processing of the component demand prediction system 1, the formulation of a calculation formula for component demand prediction will be described collectively.

The following are definitions of variables used in the calculation formula.

The following is a formula for calculating the actual parts replacement rate. The actual part replacement rate is an actual value of the number of parts used per number of installed parts for each part in the years elapsed since the installation of the equipment used for parts.

The following is a formula for calculating the estimated number of installed units. The predicted installed number is the number of installed devices at a certain point in the future, and is a predicted value.

The following is a formula for calculating the predicted parts replacement rate. The part replacement rate is a part replacement rate at a certain point in the future, and is a predicted value.

The following is a calculation formula for the required part quantity up to m years after the part i. The required part quantity is a required part quantity for a predetermined part securing period and is a predicted value.

  FIG. 6 is a flowchart showing a processing flow of the component demand prediction system 1. Below, it demonstrates centering on FIG. 6, and FIGS. 7-15 is referred as needed.

  As illustrated in FIG. 6, the control unit 11 of the terminal 2 receives an input of a component securing period (S1). The parts securing period is a period (year) in which parts need to be secured in accordance with a maintenance contract with a customer. The component securing period is determined by the user and is input to the terminal 2 via the input unit 15. The control unit 11 of the terminal 2 stores the input component securing period in the RAM or the storage unit 12.

  Next, the control unit 11 of the terminal 2 performs a device remaining rate prediction process (S2). Here, it is assumed that “devices with similar models have the same device survival rate”. “Devices with similar models” are, for example, “devices with the same model code”, “equipment of the same type of device (for example, a water heater) and the same manufacturer”, “equipment series (for example, part of the device code is In addition, it is possible to define the closest device as similar in a range where there is an actual device remaining rate described later, and the present invention is not limited to these examples. DB 5 stores data on the actual device remaining rate (the actual value of the device remaining rate).

  FIG. 7 is a diagram illustrating an example of data on the actual device remaining rate. In the graph of FIG. 7, the horizontal axis represents “the number of years since the installation of the device”, and the vertical axis represents the “device remaining rate”. In the example shown in FIG. 7, the data of the device remaining rate during the part securing period is included for a specific device.

  When a device having no actual device remaining rate data is a calculation target, the control unit 11 of the terminal 2 applies the actual device remaining rate data of a device of a similar model to the calculation target device according to the above-described assumption. , Processing described later is executed. For example, the control unit 11 of the terminal 2 uses the model code as a search key to acquire data on the actual device remaining rate as shown in FIG. 7 from the DB 5 of the server 3. And the control part 11 of the terminal 2 memorize | stores the acquired data in RAM or the memory | storage part 12 as an estimated apparatus residual rate regarding the apparatus of calculation object.

Returning to the description of FIG. Next, the control unit 11 of the terminal 2 calculates the predicted installation number (S3). The control unit 11 of the terminal 2 calculates the predicted installed number according to the calculation formula of the above formula (2). The existing number of devices to be calculated is substituted into E _{i, s, t} in Equation (2). For F (t) in Expression (2), the predicted device remaining rate stored in the RAM or the storage unit 12 in S2 is substituted. The predicted device remaining rate stored in the RAM or the storage unit 12 is, for example, a previous-age device remaining rate (actual value) related to devices having the same model code.

  In this way, the number of devices to be calculated at a certain time in the future is predicted by multiplying the existing number of devices to be calculated by the device remaining rate (actual value) compared to the previous years for devices with the same model code. can do.

  Returning to the description of FIG. Next, the control unit 11 of the terminal 2 performs a part replacement rate prediction process (S4). The control unit 11 of the terminal 2 calculates a predicted parts replacement rate (a predicted value of parts replacement rate) according to the calculation formula of the above formula (3).

The part replacement rate prediction process includes the following two types.
・ Parts replacement rate prediction process for each part ・ Model replacement ratio prediction process for each model

  First, the process for predicting the part replacement rate for each part will be described with reference to FIGS. In the prediction process of the part replacement rate for each part, an assumption is made that “the part replacement rate differs for each part”.

  FIG. 8 is a diagram illustrating an example of component replacement rate data of a specific device. In the graph of FIG. 8, the horizontal axis represents “the number of years since installation of the device”, and the vertical axis represents “component replacement rate”. In the example shown in FIG. 8, data on the part replacement rate up to the middle stage is included for a specific device. The final stage is the target of prediction.

  The parts replacement rate increases with increasing right according to aging. However, depending on external factors such as maintenance measures, it may not always increase. In the embodiment of the present invention, such characteristics are automatically discriminated for each part, and a future part having no record is accurately predicted.

  First, the control unit 11 of the terminal 2 determines whether or not the data of the actual value of the component replacement rate of the calculation target device exists for a predetermined number of years or more. When the number of years is not less than a predetermined number of years, the medium-term forecast is used.

  Next, the control part 11 of the terminal 2 determines whether there is a “peak” in the graph data of the actual value when the actual value of the component replacement rate is equal to or greater than a predetermined number of years. The determination conditions for “peak” include, for example, “one maximum value”, “if there are a plurality of maximum values, the difference between the largest value and the second largest value is a predetermined value or more”, and the like. For example, if the number of installed units tends to decay due to replacement of new equipment before the failure, or if a new purchase is made without necessarily repairing after the failure, there will be a peak in the component replacement rate that will increase to the right. .

As described above, the control unit 11 of the terminal 2 automatically determines the following three patterns and performs prediction suitable for each pattern.
(First pattern) Medium-term forecast, with peak (second pattern) Medium-term forecast, no peak (second pattern) Long-term forecast

  FIG. 9 is a diagram illustrating a process for predicting a part replacement rate for each part related to the first pattern. In the example shown in FIG. 9, the actual value is shown by a solid line and the predicted value is shown by a dotted line. In the example shown in FIG. 9, since the actual value exists for a predetermined number of years or more, it is “medium term prediction”. Moreover, since there is one maximum value, it is “with peak”. Therefore, the example shown in FIG. 9 belongs to the first pattern. In FIG. 9, it is assumed that the parts replacement rate will be 0% in the end. However, this is because “it is assumed that no parts are actually used in view of the operating years of the equipment. “Ageless years”. The same applies to FIGS. 10 and 11.

In the case of the first pattern, it is considered that an external factor such as a maintenance measure has occurred after the peak. Therefore, there is a high possibility that the parts replacement rate will drop. Therefore, as shown in FIG. 9, the control unit 11 of the terminal 2 approximates the part replacement rate up to the middle board by a power approximation of “y = ax ^b + c” (a <0, b> 0, c> 0). To do. Further, the control unit 11 of the terminal 2 approximates the part replacement rate in the final stage by linear approximation of “y = ax + b” (a <0, b> 0).

  FIG. 10 is a diagram for explaining the process of predicting the part replacement rate for each part regarding the second pattern. In the example shown in FIG. 10, the actual value is shown by a solid line and the predicted value is shown by a dotted line. In the example shown in FIG. 10, since the actual value exists for a predetermined number of years or more, it is “medium term prediction”. Moreover, since there are two local maximum values and there is no difference between the two values, it is “no peak”. Therefore, the example shown in FIG. 10 belongs to the second pattern.

  In the case of the second pattern, it is considered that an external factor such as a maintenance measure has not occurred. Therefore, there is a high possibility that the parts replacement rate will be maintained for a while. Therefore, as shown in FIG. 10, the control unit 11 of the terminal 2 obtains a weighted average for the last three years and keeps the value constant for the part replacement rate up to the middle stage. Further, the control unit 11 of the terminal 2 approximates the part replacement rate in the final stage by linear approximation of “y = ax + b” (a <0, b> 0).

  FIG. 11 is a diagram illustrating a process for predicting a part replacement rate for each part regarding the third pattern. In the example shown in FIG. 11, the actual value is shown by a solid line and the predicted value is shown by a dotted line. In the example shown in FIG. 11, the actual value does not exist for a predetermined number of years, and therefore “long-term prediction”. Therefore, the example shown in FIG. 11 belongs to the third pattern.

  In the case of the third pattern, there is a high possibility that the component replacement rate will rise for a while. Therefore, as illustrated in FIG. 10, the control unit 11 of the terminal 2 approximates the component replacement rate up to the early stage by linear approximation of “y = ax” (a> 0). Further, the control unit 11 of the terminal 2 obtains the weighted average of the latest three years for the part replacement rate of the middle board, and makes the value constant. Further, the control unit 11 of the terminal 2 approximates the part replacement rate in the final stage by linear approximation of “y = ax + b” (a <0, b> 0).

  Next, the process of predicting the part replacement rate for each model will be described with reference to FIGS. In the process of predicting the part replacement rate for each model, an assumption is made that “the part replacement rate is constant for each model”.

  FIG. 12 is a diagram illustrating an example of the standard part replacement rate for each model code. In the graph of FIG. 12, the horizontal axis represents “the number of years since installation of the device”, and the vertical axis represents “part replacement rate”. In the example shown in FIG. 12, median values (medians) are plotted from the data of the actual part replacement rates related to devices of a specific model code. However, the standard part replacement rate for each model code is not limited to the median (median) but may be an average value or a weighted average.

  In accordance with the above assumption, the control unit 11 of the terminal 2 applies the data of the standard part replacement rate for each model code having the same model code to the calculation target device, and executes processing to be described later. For example, the control unit 11 of the terminal 2 acquires standard part replacement rate data for each model code as shown in FIG. 12 from the DB 5 of the server 3 using the model code as a search key. And the control part 11 of the terminal 2 memorize | stores the acquired data in RAM or the memory | storage part 12 as a prediction components replacement | exchange rate regarding the apparatus of calculation object.

  FIG. 13 is a diagram for explaining prediction processing of a part replacement rate for each model. In the graph shown in FIG. 13A, actual values up to the middle stage are shown. On the other hand, the control unit 11 of the terminal 2 performs a process of predicting the part replacement rate for each model, and calculates the predicted part replacement rate for the final stage. In the graph shown in FIG. 13B, the actual value up to the middle stage and the predicted value of the final stage are shown.

  Next, the control unit 11 of the terminal 2 calculates the necessary part quantity (S5). The control unit 11 of the terminal 2 substitutes the component securing period input in S1, the predicted number of installed units calculated in S3, and the predicted component replacement rate calculated in S4 into the calculation formula of Formula (4). The quantity (predicted value) is calculated. That is, the control unit 11 of the terminal 2 uses the three parts of the part securing period (year), the predicted number of installed units (units), and the part replacement rate (pieces / unit / year), so that the necessary part quantity (pieces) for each part is used. ) Is calculated.

  Returning to the description of FIG. Next, the control unit 11 of the terminal 2 calculates the predicted part replacement rate and the degree of unforeseen required part quantity (S6).

  FIG. 14 is a diagram for explaining the process of calculating the degree of prediction failure with only the part replacement rate as the evaluation target. In the graph shown in FIG. 14, the horizontal axis represents “the number of years since installation of the device”, and the vertical axis represents “part replacement rate”. In the example shown in FIG. 14, it is assumed that the distribution of the parts replacement rate over time t follows a normal distribution, and the predicted off-degree is obtained.

The normal distribution followed by the distribution of component replacement rates over time t is as follows.

  FIG. 15 is a diagram for explaining the calculation process of the degree of prediction divergence with the required part quantity as an evaluation target. For example, the control unit 11 of the terminal 2 calculates an expected value of the necessary component quantity for each year using the past data for three years as a learning period, and calculates a prediction error from the actual value.

  The control unit 11 of the terminal 2 calculates the deviation of the center of the normal distribution based on the calculation result. Then, the control unit 11 of the terminal 2 calculates the necessary component quantity distribution in consideration of the deviation of the center of the normal distribution. Specifically, the control unit 11 of the terminal 2 calculates a normal distribution that averages a value obtained by adding a deviation amount of the center of the normal distribution to the average part quantity (expected value). FIG. 15 shows a necessary part quantity distribution in consideration of the deviation of the center of the normal distribution. In this example, the required number of parts when the safety factor α% is also shown.

  Returning to the description of FIG. Next, the control part 11 of the terminal 2 outputs a prediction result (S7). The control unit 11 of the terminal 2 displays the necessary part quantity calculated in S4 and the predicted off-degree calculated in S6 on the display unit 16.

  As described above, according to the component demand prediction system 1 in the embodiment of the present invention, it is possible to accurately perform medium- to long-term (yearly) demand prediction. As a result, even when the manufacture and sale of the equipment are finished, it is possible to hold an appropriate amount of parts necessary for dealing with the repair of the sold equipment. Also, in order to further improve CS so that customers will not wait as much as possible even during the sale of equipment, information on parts that will be required in the long term in the future will be provided to manufacturers in advance and reflected in the production plan. This makes it possible to build a smoother parts distribution system.

[Effects of the embodiment of the present invention]
The component demand prediction system 1 determines whether or not the actual value data of the component replacement rate of the device to be calculated exists for a predetermined number of years or more in the prediction process of the component replacement rate for each component. If there is a specified number of years or more, it is determined whether or not there is a peak in the actual value data, and the three patterns of medium-term forecast with peak, medium-term forecast without peak, and long-term forecast are automatically identified for each pattern. Different prediction processes are performed. As a result, it is possible to accurately predict a future portion that has no record in consideration of external factors such as maintenance measures.

  The component demand prediction system 1 calculates a model-specific standard component replacement rate in a model-unit-based component replacement rate prediction process, and performs a prediction process using the model-specific standard component replacement rate. As a result, it is possible to prevent the prediction from deviating greatly.

  The parts demand prediction system 1 calculates the predicted part replacement rate and the degree of unforeseen prediction of the required part quantity. As a result, the quantity of parts corresponding to fluctuations in demand can be held as inventory.

  The preferred embodiments of the parts demand prediction system and the like according to the present invention have been described above with reference to the accompanying drawings, but the present invention is not limited to such examples. It will be apparent to those skilled in the art that various changes or modifications can be conceived within the scope of the technical idea disclosed in the present application, and these naturally belong to the technical scope of the present invention. Understood.

1 ……… Parts demand forecasting system 2 ……… Terminal 3 ……… Server 4 ……… Parts demand forecasting program 5 ……… Database (DB)
6 ... Network

Claims (6)

A parts demand forecasting system configured to predict demand for parts configured by a computer and used for equipment repair,
A component securing period input receiving means for receiving an input of a component securing period;
A predicted device remaining rate calculating means for calculating a predicted device remaining rate based on the actual device remaining rate of devices of similar models;
A predicted installed number calculating means for calculating a predicted installed number based on the existing number of devices to be calculated and the predicted device remaining rate;
Predicted part replacement rate calculating means for calculating a predicted part replacement rate for each part or model;
Required part quantity calculating means for calculating as a required part quantity using all of the parts securing period, the predicted installed number and the predicted parts replacement rate;
A parts demand forecasting system characterized by comprising: The predicted part replacement rate calculation means determines whether or not the actual value data of the component replacement rate of the device to be calculated exists for a predetermined number of years or more, and when the actual value data exists for a predetermined number of years or more Determines whether there is a peak in the actual value data, automatically determines three patterns of medium-term prediction with peak, medium-term prediction without peak, and long-term prediction, and performs different prediction processing for each pattern The parts demand forecasting system according to claim 1 characterized by things. 2. The component demand prediction system according to claim 1, wherein the predicted component replacement rate calculating unit calculates a model-specific standard component replacement rate and performs a prediction process using the model-specific standard component replacement rate. A prediction degree calculating means for calculating the predicted part replacement rate or the degree of unforeseen prediction of the required part quantity;
The component demand forecasting system according to claim 1, further comprising: A parts demand prediction method for predicting demand for parts executed by a computer and used for repair of equipment,
A control unit of the computer,
A component securing period input receiving step for receiving an input of a component securing period;
A predicted device remaining rate calculating step for calculating a predicted device remaining rate based on the actual device remaining rate of devices of similar models;
A predicted installed number calculating step for calculating a predicted installed number based on the existing number of devices to be calculated and the predicted device remaining rate; and
A predicted part replacement rate calculating step for calculating a predicted part replacement rate for each part or model;
A necessary part quantity calculating step for calculating as a required part quantity using all of the parts securing period, the predicted installed number and the predicted parts replacement rate;
The part demand prediction method characterized by performing this. A program for causing a computer to execute a parts demand forecasting method for forecasting demand for parts used for equipment repair,
In the control part of the computer,
A component securing period input receiving step for receiving an input of a component securing period;
A predicted device remaining rate calculating step for calculating a predicted device remaining rate based on the actual device remaining rate of devices of similar models;
A predicted installed number calculating step for calculating a predicted installed number based on the existing number of devices to be calculated and the predicted device remaining rate; and
A predicted part replacement rate calculating step for calculating a predicted part replacement rate for each part or model;
A necessary part quantity calculating step for calculating as a required part quantity using all of the parts securing period, the predicted installed number and the predicted parts replacement rate;
A program for running