JP2003187051A - Business management plan support system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To improve calculating accuracy of a buying probability, and to improve accuracy of a sale predicting quantity, and thus the whole management plan. <P>SOLUTION: A present buying probability is calculated on the basis of a past buying probability (the price income ratio distribution) according to a rate of a selling price of a vehicle to an income of a past buyer and a rate (the price income ratio) of a selling price to an income of a present buying candidate, and a sale predicting quantity of the vehicle is calculated on the basis of the calculated buying probability. Since the buying probability changes according to the price income ratio, the calculating accuracy of the buying probability of a new vehicle can be improved by using the price income ratio of the present buying candidate for calculating the buying probability, and the accuracy of the sale predicting quantity, and thus the whole management plan can be improved. <P>COPYRIGHT: (C)2003,JPO

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a business plan support device for predicting expected sales volume, production variables, profits, etc. of new products to be sold.

[0002]

2. Description of the Related Art As means for predicting an expected sales volume of a new product, Japanese Patent Application Laid-Open No. 9-12039 filed by the present applicant.
Japanese Patent Publication No. 5 discloses an apparatus and method for predicting the sales of the next product from the sales results of the current product.

In this technique, a sales model formula is used in which the sales volume of a product is expressed by a linear sum of an element (xij) that influences the sales of the product and a coefficient (aij) that indicates the degree of influence of the element. The coefficient (aij) is determined based on the actual sales information of the product, and the determined coefficient (aij) is substituted into the above-mentioned sales model formula, and the characteristics of the product to be sold in the next period are calculated by the coefficient (aij). ) Is given as each element (xij) of the substituted sales model formula to calculate the sales forecast quantity of the product to be sold in the next period. Further, by identifying the purchaser element (x1j) among the elements (xij) that affect the sale of the product, the predicted sales tendency for each specification in the purchaser layer is calculated, and the product element (xij) is identified. As a result, the sales forecast quantity for each purchaser of the product of that specification is calculated.

[0004]

In the above publication, age, sex, clothes, hairstyle, occupation, etc. are used as the purchaser element (x1j), but the economic strength and concrete intention of the purchaser are taken into consideration. However, there is a certain limit to improving the prediction accuracy.
Further, if the sales forecast amount is not accurately obtained, it is also difficult to accurately obtain production variables such as product development costs and production personnel, as well as profits.

Therefore, an object of the present invention is to provide means for more accurately designing a business plan for a new product.

[0006]

[Means for Solving the Problems] The first aspect of the present invention is based on the past purchase probability according to the ratio of the product price to the income of the past purchaser and the ratio of the product price to the income of the current purchase candidate. In addition, the management plan support device includes a purchase probability calculation unit that calculates the current purchase probability and a sales prediction unit that calculates the sales forecast quantity of the product based on the calculated purchase probability.

According to the first aspect of the present invention, the purchase probability calculating means is based on the past purchase probability according to the ratio of the product price to the income of the past purchaser and the ratio of the product price to the income of the current purchase candidate. Calculates the current purchase probability.
The sales forecasting means calculates the sales forecast quantity of the product based on the calculated purchase probability.

In order to actually make a purchase, the income of the purchase candidate corresponding to the selling price must be obtained, but the larger the income is, the higher the purchase probability is. The relationship between income and purchase probability is not linear, for example, the purchase probability decreases when income exceeds a certain range. Here, the inventor of the present invention has
It was discovered that the product price fluctuates according to the ratio of the product price to the income, and the ratio of the product price to the income of the current purchase candidate is used to calculate the purchase probability. The accuracy of the probability calculation can be improved, and the accuracy of the sales forecast amount and thus the management plan can be improved.

A second aspect of the present invention is the business plan support apparatus of the first aspect of the present invention, further comprising an application-specific purchase probability storage means for storing the past purchase probability by application, and the purchase probability calculation means. Is a management plan support apparatus, wherein the current purchase probability is calculated based on the past purchase probability stored in the use-by-use purchase probability storage means corresponding to the current use of the purchase candidate. Is.

In the second aspect of the present invention, the purchase probability calculating means is
Among the past purchase probabilities by use stored in the use-by-use purchase probability storage means, the current purchase probability is calculated based on the one corresponding to the use of the current purchase candidate.

The inventor of the present invention has found that the purchase probability varies depending on the intended use of the purchaser (for example, whether it is for home use or for business use), and the past purchase by use is made. Since the current purchase probability according to the use of the current purchase candidate is calculated based on the probability, the present invention can further improve the calculation accuracy of the purchase probability of the new product.

A third aspect of the present invention is the business plan support apparatus according to the first or second aspect of the present invention, in which the purchase interval between the past purchaser and the current purchase candidate when the same type of product is purchased multiple times. Based on the number of years elapsed since the previous purchase of, further comprising substitution coefficient calculation means for calculating a substitution coefficient indicating the current purchase probability, the sales forecasting means, the sales probability by multiplying the purchase probability by the substitution coefficient It is a management plan support device characterized by calculation.

In the third aspect of the present invention, the substitution coefficient calculating means is based on the purchase interval when the past purchaser purchases the same type of product a plurality of times, and the number of years after the previous purchase of the current purchase candidate. Calculate an alternative coefficient that indicates the current purchase probability. In addition, the sales forecasting unit calculates the forecasted sales amount by multiplying the purchase probability by the substitution coefficient.

As described above, according to the third aspect of the present invention, based on the purchase interval when the past purchaser purchases the same type of product a plurality of times and the number of years elapsed since the previous purchase of the current purchase candidate,
Since the sales forecast quantity is calculated, the accuracy of calculating the purchase probability of a new product can be further improved.

In a fourth aspect of the present invention, a similarity storage means for storing a similarity between a new product and a plurality of existing products, a production variable storage means for storing production variables of the plurality of existing products, and A business plan support device comprising: a production variable calculation means for calculating the production variable of a new product by multiplying the similarity and the production variable of the existing product.

In the fourth aspect of the present invention, the production variable calculation means is
The production variable of the new product is calculated based on the production variables of the plurality of existing products and the similarities between the plurality of existing products and the new product. Since the production variable of the new product is expected to have a value similar to the production variable of the similar existing product, the production variable can be accurately calculated in the fourth aspect of the invention, and thus the accuracy of the entire management plan can be improved. Can be improved.

A fifth aspect of the present invention is the business plan support apparatus of the fourth aspect of the present invention, wherein the production variable calculation means uses the similarity calculated for each element of the new product. It is a support device.

In the fifth aspect of the present invention, the production variable calculating means is
Since the similarity calculated for each element of the new product is used, it is possible to improve the calculation accuracy of the production variables of the entire new product.

The production variables in the present invention are preferably either development costs or production personnel as in the sixth aspect of the present invention. The production variables may be both development costs and production personnel.

A seventh aspect of the present invention is the business plan support apparatus according to any one of the first to sixth aspects of the present invention, wherein the production variable is calculated from the product of the sales forecast quantity of the product and the sale price of the product. It is a business plan support device further comprising a profit calculation means for subtracting.

In the seventh aspect of the present invention, the profit calculation means subtracts the production variable from the product of the sales forecast quantity and the sales price of the product. The accuracy of the whole plan can be improved.

[0022]

BEST MODE FOR CARRYING OUT THE INVENTION Preferred embodiments of the present invention will be described below with reference to the drawings. FIG. 20 is a schematic configuration diagram of the business plan support apparatus according to the embodiment of the present invention. In the figure, the management plan support device is configured as a computer system, and has a console 201 including a display unit such as a CRT and an input unit such as a keyboard and a mouse, and a CPU.
And a memory 203 for temporarily storing various processing programs and data, which includes various processing programs and outputs based on user inputs.
And a storage unit 204 including a hard disk device, a user interface controller 205 that controls each interface and operation, and a disk controller 2
06 and are included. The storage unit 204 stores various databases described below and various computer programs for causing a computer to perform various processes described below.

FIG. 1 is a system block diagram of the business plan support apparatus shown in FIG. This management plan support device basically includes a consumer information database 1, a consumer information classification unit 2, a newly purchased consumer information database 3, and
Alternative purchase consumer information database 4, product information database 5, new purchase probability calculation unit 6, alternative purchase probability calculation unit 7, specification-specific demand forecast amount database 8, sales calculation unit 9, and sales database 10. , Released / unreleased determination unit 11 and unreleased demand forecast amount database 12
Development cost calculation unit 13, development personnel calculation unit 14, released demand forecast amount database 15, production cost calculation unit 1
6, production personnel calculation unit 17, cost calculation unit 18, personnel calculation unit 19, cost database 20, newly hired personnel database 21, outsourcing personnel database 22, profit calculation unit 23, and profit database 24.
, Purchase probability distribution database 25, development variable / production variable database 26, and sales price database 27
And a similarity database 28.

Consumer information classification unit 2, new purchase probability calculation unit 6, alternative purchase probability calculation unit 7, sales calculation unit 9, sold /
Unreleased determination unit 11, development cost calculation unit 13, development personnel calculation unit 14, production cost calculation unit 16, production personnel calculation unit 17, cost calculation unit 18, personnel calculation unit 19, and profit calculation unit 23.
Is a computer program for causing a computer to perform various calculations to be described later.
Installed on 4.

Further, the consumer information database 1, the newly purchased consumer information database 3, the alternative purchased consumer information database 4, the product information database 5, the specification-specific demand forecast amount database 8, the sales database 10, the unreleased demand forecast amount database. 12, released demand forecast amount database 15, cost database 20, newly hired personnel database 21, outsourcing personnel database 22,
Revenue database 24, Purchase probability distribution database 2
5, the development variable / production variable database 26, the selling price database 27, and the similarity database 28 are all configured by the storage unit 204 in FIG. 20, the database software stored in the storage unit 204, and a data file in a table format.

The consumer information database 1 has the data members shown in FIG. In the example shown, the consumer ID
The consumer identified by "1" said, "I have a driver's license, I currently own vehicle A, and I use it for commuting and leisure. If I buy next, I want a sports utility vehicle. , The number of years of ownership of the vehicles currently owned is 5.5 years, and the income is 25 million yen / year ”. Such consumer information is acquired based on sales records at dealers and market research such as interviews and questionnaires of sales staff, and is stored in an integrated manner.

The consumer information classifying unit 2 classifies the data instances of the consumer information stored in the consumer information database 1 into those of new purchase consumers and those of alternative purchase consumers and stores them. The process is performed as shown in FIG. First, consumer information is read from the consumer information database 1 (S31), the presence or absence of a driving license is determined (S32), and consumers without a driving license are excluded.
Next, based on the income information, the consumers are ranked according to their income range (S33), and based on the data of "desired vehicle type for purchase", an evaluation score indicating the vehicle preference is calculated (S34). Next, it is determined whether or not there are owned vehicles (S3
5) If there are owned vehicles, the number of years elapsed is ranked based on the data of "years of owned vehicles" (S3
6), the data instance concerned is written in the alternative purchase consumer information database 4 (S37). If there is no owned vehicle, the data instance is written in the newly purchased consumer information database 3 (S38).

The new purchase consumer information database 3 and the alternative purchase consumer information database 4 are respectively shown in FIG.
The data member of FIG. 5 is provided.

The product information database 5 has the data members shown in FIG. In the illustrated example, the vehicle identified by the vehicle name “A” has “the product specification is a 3-box type and the selling price is 3 million yen”. In the illustrated example, vehicles with vehicle names A, C, D, and E are in-house products, while vehicles with vehicle names B, F, and G are products of other companies. Further, the product information database 5 includes data of vehicles that are currently being sold by the company and other companies, as well as vehicles that have not been released and are candidates for new development.

In the purchase probability distribution database 25, as a past purchase record, a price / income ratio distribution, which is a probability distribution in which the number of purchase cases is arranged with (commodity price) / (income) as a random variable, is “commuting”. It is created and stored in advance as a data file for each purpose of "leisure" and "corporation". For example, the contents of the price / income ratio distribution data file 25a for the use "commuting" of a certain vehicle are as shown in FIG. The contents of the price / income ratio distribution data files 25b and 25c for the uses "leisure" and "corporation" are not shown.

Further, in the purchase probability distribution database 25,
As a past purchase record when multiple purchases (that is, alternative purchases) have been made in the past, the probability that each purchaser has elapsed years (that is, the number of years since the previous purchase at the time of replacement purchase) A holding age distribution, which is a probability distribution formed by arranging the number of purchase cases as variables, is created and stored in advance as a data file. For example, the possession age distribution data file 25d for a certain vehicle
19 is as shown in FIG.

The new purchase probability calculation unit 6 executes a series of processes for obtaining the probability of how much new purchase can be expected, as shown in FIG. First, the consumer data is read from the newly purchased consumer information database 3 (S7).
1) Further, the product data is read from the product information database 5 (S72).

Then, the product preference included in the former is compared with the product specification included in the latter (S73), and a vehicle matching the product preference is extracted. For example, consumer ID
In the case of the consumer specified by "3", since this consumer desires a minivan, car names C, E, F, G are extracted as vehicles having a product specification of a minivan here.

Next, the extracted selling price of each vehicle is compared with the income rank of the consumer (S74), and the ratio of the selling price to the income (that is, the price-income ratio).
Is calculated for each vehicle as in Equation 1.

[Equation 1] Vehicle C: 200 (10,000 yen) / 1500 (10,000 yen) = 0.133 Vehicle E: 300 (10,000 yen) / 1500 (10,000 yen) = 0.2 Vehicle F: 250 (10,000 yen) / 1500 (10,000 yen) = 0.167 Vehicle G: 150 (10,000 yen) / 1500 (10,000 yen) = 0.1

Next, the usage coefficient is calculated based on the usage information corresponding to each consumer ID (S75). The calculation of the usage coefficient is performed using, for example, a predetermined data table in which the usage name and the numerical value are in one-to-one correspondence.

Next, a new purchase probability is calculated according to the calculated usage coefficient (S76). In calculating the new purchase probability, the data of the price / income ratio distribution stored in the purchase probability distribution database 25 is used. That is, first, the usage coefficient is compared with a predetermined threshold value, and the price-income ratio distribution corresponding to the usage coefficient is selected and selected from a plurality of sets of past price-income ratio distributions stored according to the usage according to the comparison result. The new purchase probability according to the use is calculated using the calculated price-income ratio distribution.

For example, when a consumer as a purchase candidate lists "commuting" as a use, a use coefficient corresponding to the use "commuting" is selected, and this use coefficient is compared with a predetermined threshold value. In accordance with the comparison result, the three types of price income ratio distribution data files 25a, 25b, 25 shown in FIG. 18 are acquired from the purchase probability distribution database 25.
From c, the price / income ratio distribution data file 25a for the purpose "commuting" according to the purpose coefficient is selected. The selected price / income ratio distribution data file 25a is the number of past cases purchased for the purpose of commuting to be (product price) /
(Income) is arranged and stored as a random variable.
Then, from the price-income ratio distribution, the probability (frequency) corresponding to the value of the price-income ratio for the vehicle is read as the current purchase probability of the vehicle. For the example of the expression 1, the purchase probability is as shown in the following expression 2.

[Formula 2] Vehicle C: 0.00090 Vehicle E: 0.00080 Vehicle F: 0.00085 Vehicle G: 0.00080

Then, the calculated current purchase probability of the vehicle is calculated as the number of samples (here, for example, among the total population in a unit market such as “in Japan”, a consumer who has a driver's license and has no vehicle). The demand forecast amount is calculated by multiplying the
Is written for each specification (by vehicle name) (S77). For example, when the number of samples is 10,000, the demand forecast amount of each vehicle is as shown in the following Expression 3.

[Formula 3] Vehicle C: 9 people Vehicle E: 8 people Vehicle F: 8.5 people Vehicle G: 8 people

The above processing is repeatedly executed for all the consumer ID samples stored in the newly purchased consumer information database 3 (S78), and this routine is terminated on condition that the processing for all consumers is completed.

The alternative purchase probability calculation unit 7 executes a series of processes for obtaining the probability of how much an alternative purchase is expected, as shown in FIG. The contents of the processing here are substantially the same as the steps shown in FIG. 7, except that the data of the alternative purchase consumer information database 4 is used in place of the new purchase consumer information database 3 and the possession history. The difference is that the coefficient is calculated and used (S86).

In the process of step S86, the possession age distribution data stored in the purchase probability distribution database 25 is used. That is, the probability corresponding to the elapsed years of possession of each alternative purchase consumer (the number of years elapsed from the time of the previous purchase to the present) is read out from the distribution of the elapsed years of possession as the possession history coefficient.

For example, when the vehicle currently owned by the alternative purchase consumer who is a purchase candidate has been five years after the purchase, it corresponds to "5 years" in the probability distribution of FIG. The probability (frequency) is read as the holding history coefficient of the purchase candidate.

The possession history coefficient calculated in this manner is multiplied by the purchase probability obtained based on the probability distribution corresponding to the value of (commodity price) / (income) of each vehicle, and thereby the alternative purchase probability. Is calculated (S87). The subsequent processing is the same as that in the routine shown in FIG.

By the processing of FIGS. 7 and 8 described above, the instance having the data members shown in FIG. 9 is stored in the specification-specific demand forecast amount database 8.

In the sales calculation unit 9, a series of processes for obtaining sales is executed as shown in FIG. 10 based on the data stored in the specification-specific demand forecast amount database 8. First, the data from the demand forecast quantity by specification database 8 is read (S101), and then the selling price of the new product calculated by a predetermined optimization calculation and stored in the selling price database 27 is read. Sales are calculated by multiplying the selling price, the total forecasted demand for new purchases and the forecasted demand for alternative purchases, and the market share read from a predetermined data table (S102). This market share is based on the past performance of the company that sells the vehicle and the sales power of the new product in the planned sales period based on the management plan, and the abundance of competitor products in the planned sales period of the new product. , Which is separately calculated in advance and stored in the predetermined data table.

The calculated sales are written in the sales database 10 (S103). The sales database 10 is a data file in a table format having vehicle names and sales as data members stored in the storage unit 204. These processes are repeatedly executed until the processes for all the vehicles are completed (S104), and this routine is terminated on condition that the processes for all the vehicles are completed.

In the released / unreleased decision section 11, a series of processes for discriminating between a released vehicle and an unreleased vehicle among the data stored in the specification-specific demand forecast amount database 8 is executed.
It is executed as shown in FIG. First, the data from the demand forecast quantity database 8 for each specification is read (S11
1) Next, it is judged from the car name in the data (for example, "A") whether or not the car is manufactured in-house, and in the case of the company, the sale completion flag is added to the record of the car name. And is written in the released demand forecast amount database 15 (S114).

If the vehicle is manufactured by another company and the demand forecast amount is larger than the same product specifications of the company, it is determined that new development is necessary (S).
113), an unreleased flag is added to the record of the vehicle name, and it is written in the unreleased demand forecast amount database 12 (S115). For an unreleased vehicle, the development cost and the development personnel are further calculated in order to newly develop the vehicle.

The data in the development variable / production variable database 26 is used to calculate the development cost and the development personnel. The development variable / production variable database 26 includes data of past performance values regarding vehicles that have already been released, and has data members shown in FIG. Of the data stored here, those related to other companies include financial data such as the annual reports of the other companies and the types and number of vehicles released in each year.
It is pre-calculated based on the selling price, purchased parts ratio, etc., and stored in the development variable / production variable database 26.

The data in the similarity database 28 is also used to calculate the development cost and the development personnel. In the similarity database 28, for all combinations of unreleased vehicles and existing vehicles, the similarity indicating the degree of similarity when the exact same case is “1” and the completely different case is “0”,
It is calculated and stored in advance.

Here, the degree of similarity is calculated in units of vehicle type, but the degree of similarity for each vehicle type is the specifications of each vehicle (3 boxes, 2 boxes, sports utility,
Station wagon, cab wagon, minivan, etc.),
Partial similarity of evaluation items such as function (steering system, suspension system, etc.), performance (displacement, maximum speed, fuel efficiency, acceleration performance, minimum turning radius, etc.), equipment (fog lights, navigation system, audio system, etc.) The degree of similarity calculated as a total of the partial degrees of similarity is, for example, 3 if there are 35 evaluation items.
The distance between the score of the unreleased vehicle and the score of the existing vehicle in the five-dimensional space is calculated, and is calculated according to Equation 4.

## EQU00004 ## Score for vehicle A: Pa = (xa1, xa2,
..., xa35) Score for vehicle B: Pb = (xb1, xb2, ...,
xb35) Similarity between vehicles A and B: Sab = √ {(xa1−xb1) ^ 2 +
(Xa2-xb2) ^ 2 + ... + (xa35-xb35) ^ 2}

The development cost calculation unit 13 and the development personnel calculation unit 14 multiply the known development cost and the development personnel based on the case of the existing vehicle by the similarity between the existing vehicle and the unreleased vehicle to obtain the unreleased vehicle. A series of processes for calculating the vehicle development cost and the development personnel are executed as shown in FIG.

In FIG. 13, first, the data of the demand forecast amount of the unreleased vehicle is read from the unreleased demand forecast amount database 12 (S131), and the existing vehicle development is performed from the development variable / production variable database 26. Data of costs and development personnel are read (S132).

Next, for an unreleased vehicle, its development cost, in-house development personnel, and outside-vehicle development personnel are calculated as estimated values (S133).

The development cost of the unreleased vehicle (i) is the product of the development cost of the existing vehicle (j) and the similarity between the unreleased vehicle (i) and the existing vehicle (j) read from the similarity database 28. , Is calculated by adding up all existing vehicles (j) whose development costs are known.

The in-house development personnel of the unreleased vehicle (i) are similar to the in-house development personnel of the existing vehicle (j) in the similarity database 28.
It is calculated by adding the product of the similarity between the unreleased vehicle (i) read from the existing vehicle (j) and the existing vehicle (j) for all the existing vehicles (j) known to the in-house development personnel.

The external development personnel of the unreleased vehicle (i) are similar to the external development personnel of the existing vehicle (j) in the similarity database 28.
It is calculated by adding the product of the similarity between the unreleased vehicle (i) read from the existing vehicle (j) and the existing vehicle (j) for all the existing vehicles (j) known to the outside development personnel.

In the process of step S133, the similarity of all existing vehicles whose similarity is not 0 for a certain unreleased vehicle is normalized so that the sum of the similarities of such existing vehicles becomes 1. It is used after being converted.

On condition that the above processing is executed for all vehicles (S134), the calculated development costs of unreleased vehicles, the in-house development personnel and the outside development personnel are written in the development variable / production variable database 26. (S13
5) Then, this routine is finished.

In the production cost calculation unit 16 and the production personnel calculation unit 17, the unreleased demand is calculated based on the demand forecast amount stored in the unreleased demand forecast amount database 12 and the released demand forecast amount database 15 and the past results. Alternatively, a series of processes for calculating the current production cost and production personnel for the released vehicle is executed as shown in FIG. First, the demand forecast amount data for each vehicle is read from the unreleased demand forecast amount database 12 or the released demand forecast amount database 15 (S141), and the development variable /
The production cost of the existing vehicle and the data of the production personnel are read from the production variable database 26 (S142).

Next, the production cost and production personnel of the vehicle to be released this time are calculated as estimated values (S143).

The production cost of the vehicle (i) to be released this time is calculated by multiplying the production cost of the same vehicle (j) by the ratio of the current demand forecast amount and the previous demand amount of the same vehicle. It

Further, the production personnel of the vehicle (i) to be released this time can be multiplied by the production personnel of the same vehicle (j) by the ratio of the current demand forecast quantity to the previous demand quantity of the same vehicle. It is calculated.

When the vehicle to be released this time has a specification different from that of the existing vehicle of the company (when it is not yet released), the production cost is the similarity with the existing vehicle read from the similarity database 28, The demand forecast amount of the same vehicle to the previous demand amount of the same vehicle, and the production cost of the existing vehicle, and add this value for all existing vehicles (j) whose similarity to the unreleased vehicle is not 0. Calculated by combining. Further, the production personnel of the unreleased vehicle is multiplied by the similarity with the existing vehicle read from the similarity database 28, the ratio of the current demand forecast amount to the previous demand amount of the same vehicle, and the production personnel of the existing vehicle. , This value is calculated by adding up all existing vehicles (j) whose degree of similarity to the unreleased vehicle is not 0. In these cases,
The similarity for all existing vehicles whose similarity is not 0 for a certain unreleased vehicle is normalized and used so that the sum of the similarities for such existing vehicles is 1.

On condition that the above processing is executed for all vehicles (S144), the calculated production cost and production personnel of each vehicle are written in the development variable / production variable database 26 (S145), This routine ends.

The cost calculation section 18 executes a series of processes for calculating the cost from the development cost and the production cost obtained as described above, as shown in FIG. First, the data of development costs and production costs are read from the development variable / production variable database 26 (S151). Next, the cost is calculated by adding the production cost to the development cost (S152). Then, the calculated cost is written in the cost database 20 (S153).

In the profit calculation unit 23, a series of processes for calculating the profit from the cost calculated by the cost calculation unit 18 is executed as shown in FIG. First, sales data is read from the sales database 10 for each vehicle (S161). Next, cost data is read from the cost database 20 for each vehicle (S162). Then, by subtracting the cost from the sales, the profit for the vehicle is calculated (S163). The calculated profit is written in the profit database 24 for each vehicle (S164).

In the personnel calculation section 19, a series of processes for calculating newly hired personnel and outsourcing personnel from the production personnel obtained as described above are executed as shown in FIG. First, the development variable / production variable database 26
Data of production personnel is read from each vehicle (S17)
1). Next, the number of production personnel that can be allocated to the production of the vehicle to be produced this time is read from the predetermined personnel database (S172), and the number of production personnel and the hourly unit price in the case of outsourcing, and the production in the case of new hiring A predetermined optimization calculation is performed based on the number of employees and the hourly unit price, and the number of new hires and the number of outsourcing required for production are calculated (S173). The calculated number of newly hired personnel and the number of outsourced personnel are respectively written in the newly hired personnel database 21 and the outsourcing personnel database 22 (S174).

As described above, in the present embodiment, the past purchase probability (price-income ratio distribution, FIG. 18) according to the ratio of the vehicle selling price to the past purchaser's income, and the current purchase candidate income. The new purchase probability calculating unit 6 and the alternative purchase probability calculating unit 7 (purchase probability calculating means) calculate the current purchase probability based on the ratio of the selling price to the price (price income ratio) (S76), and the calculated purchase probability. The vehicle sales forecast quantity is calculated based on (S77).

In order to actually make a purchase, the purchase candidate's income corresponding to the selling price must be present. However, the larger the income, the higher the purchase probability does not become. The relationship between income and purchase probability is not linear, for example, the purchase probability decreases when income exceeds a certain range. Here, the inventor of the present invention has
It was discovered that the price fluctuates according to the ratio of the product price to the income (price income ratio), and the price income ratio of the current purchase candidate is used to calculate the purchase probability. It is possible to improve the accuracy of calculating the purchase probability of the vehicle, and improve the accuracy of the forecasted sales amount and thus the overall management plan.

In the present embodiment, the new purchase probability calculation unit 6 and the alternative purchase probability calculation unit 7 (purchase probability calculation means).
Of the past purchase probabilities of the plurality of types of uses stored in the purchase probability distribution database 25 (purchase probability storage means for each use), the current purchase is based on the one corresponding to the use of the current purchase candidate. Probability is calculated (S75, S7
6).

The inventor of the present invention has found that the purchase probability differs depending on the intended use of the purchaser (for example, whether it is for home use or for business use), and the past purchase for each use is made. Since the current purchase probability according to the use of the current purchase candidate is calculated based on the probability, the present embodiment can further improve the calculation accuracy of the purchase probability of the new vehicle.

Further, in the present embodiment, the alternative purchase probability calculating unit 7 (substitution coefficient calculating means) causes the purchase interval when the past purchaser purchases the same type of product a plurality of times and the current purchase candidate's previous purchase. Based on the number of elapsed years, the substitution coefficient indicating the current purchase probability is calculated (S87), and the sales probability is calculated by multiplying the purchase probability by the substitution coefficient (S88). As described above, in the present embodiment, the sales forecast amount is calculated based on the purchase interval when the past purchaser purchases the vehicle multiple times and the number of years elapsed since the previous purchase of the current purchase candidate. Therefore, this can further improve the calculation accuracy of the purchase probability of a new vehicle.

Further, in this embodiment, the development cost calculation unit 13
The development personnel calculation unit 14, the production cost calculation unit 16, and the production personnel calculation unit 17 (production variable calculation means) are based on the production variables of a plurality of existing vehicles and the similarity between the plurality of existing vehicles and a new vehicle. To calculate the production variable of the new vehicle (S1
33, S143). Since the production variable of the new vehicle is expected to have a value similar to the production variable of the existing vehicle similar to this, the production variable can be accurately calculated in the present embodiment,
As a result, the accuracy of the entire business plan can be improved.

Further, in this embodiment, since the similarity is calculated for each element of the new vehicle (Equation 4), the calculation accuracy of the production variables of the entire new vehicle can be improved. Any parameter may be used as the parameter of the partial similarity used in the calculation of the similarity as long as it is a characteristic of the vehicle (or the product) that can affect the production variable. What was done is only an example. For example, parameters for each component such as an underbody, an upper body, an engine unit, a transmission unit, a drive unit, a chassis, or a module serving as a production unit may be used,
Also in this case, the production variables can be calculated accurately.

Further, in the present embodiment, since the production variables are the development cost and the production personnel, the effect of the present invention can be realized suitably. The production variable in the present invention may be either the development cost or the production personnel.

In the present embodiment, the profit calculation unit 23 (revenue calculation means) subtracts the cost, which is the sum of the development cost and the production cost as the production variables, from the product of the sales forecast quantity of the product and the sales price. Therefore, the accuracy of the overall sales plan can be improved by improving the accuracy of calculating the sales forecast quantity or the production variable. In addition to the configuration of the above embodiment, the personnel calculation unit 1
It is also possible to further subtract the product of the production required personnel and the labor cost hourly unit price calculated in step 9 (that is, the required personnel converted into expenses), the transportation cost, the factory rent, and the like.

In the present embodiment, the present invention is applied to the business plan based on the demand forecast of vehicles. However, the present invention is not limited to vehicles, and demand forecasts such as movables such as daily necessities and real estate such as buildings are required. It can be applied to a business plan for all products that are applicable, and all such applications are within the scope of the present invention.

[Brief description of drawings]

FIG. 1 is a system block diagram of a business plan support apparatus as an embodiment of the present invention.

FIG. 2 is an explanatory diagram showing an example of a consumer information database.

FIG. 3 is a flowchart showing a process related to classification of consumer information.

FIG. 4 is an explanatory diagram showing an example of a new purchase consumer information database.

FIG. 5 is an explanatory diagram showing an example of an alternative purchase consumer information database.

FIG. 6 is an explanatory diagram showing an example of a product information database.

FIG. 7 is a flowchart showing a process related to calculation of a new purchase probability.

FIG. 8 is a flowchart showing a process related to calculation of an alternative purchase probability.

FIG. 9 is an explanatory diagram illustrating an example of a demand forecast amount database for each specification.

FIG. 10 is a flowchart showing a process related to calculation of sales.

FIG. 11 is a flowchart showing a process related to determination of whether or not the product has been sold.

FIG. 12 is an explanatory diagram showing an example of a production variable database.

FIG. 13 is a flowchart showing a process for calculating development costs and development personnel.

FIG. 14 is a flowchart showing a process relating to calculation of production cost and production personnel.

FIG. 15 is a flowchart showing a process related to cost calculation.

FIG. 16 is a flowchart showing a process for calculating a profit.

FIG. 17 is a flowchart showing a process related to calculation of personnel.

FIG. 18 is an explanatory diagram showing the contents of a price / income ratio distribution data file for each purpose in the purchase probability distribution database.

FIG. 19 is an explanatory diagram showing the contents of a possession elapsed years distribution data file in the purchase probability distribution database.

FIG. 20 is a schematic configuration diagram of a business plan support device.

[Explanation of symbols]

1 consumer information database, 2 consumer information classification section,
3 New purchase consumer information database, 4 Alternative purchase consumer information database, 5 Product information database, 6
New purchase probability calculation unit, 7 Alternative purchase probability calculation unit, 8
Demand forecast amount database by specification, 12 Unreleased demand forecast amount database, 13 Development cost calculation unit, 14 Development personnel calculation unit, 15 Released demand forecast amount database, 16
Production cost calculation unit, 17 production personnel calculation unit, 18 cost calculation unit, 23 profit calculation unit, 25 purchase probability distribution database, 28 similarity database.

Claims (7)

[Claims] 1. A purchase probability that calculates a current purchase probability based on a past purchase probability according to a ratio of a product price to a past purchaser's income and a ratio of a product price to a current purchase candidate's income. A business plan support device comprising: a calculating means; and a sales forecasting means for calculating a sales forecast quantity of a product based on the calculated purchase probability. 2. The business plan support apparatus according to claim 1, further comprising a purchase probability storage unit for each purpose in which the past purchase probability is stored for each use, wherein the purchase probability calculation unit purchases for each use item. A management plan support apparatus for calculating a current purchase probability based on a past purchase probability stored in a probability storage means corresponding to a current use of a purchase candidate. 3. The business plan support apparatus according to claim 1, wherein the purchase interval when a past purchaser purchases the same type of product multiple times, and the progress of the current purchase candidate after the previous purchase. Further characterized by further comprising a substitution coefficient calculation means for calculating a substitution coefficient indicating the current purchase probability based on the number of years, the sales forecasting means calculates the sales forecast quantity by multiplying the purchase probability by the substitution coefficient. Management plan support device. 4. A similarity storage means for storing the similarity between a new product and a plurality of existing products, a production variable storage means for storing the production variables of the plurality of existing products, the similarity and the existing A production plan calculation device for calculating a production variable of a new product by multiplying it with a production variable of the product, and a management plan support device comprising: 5. The business plan support apparatus according to claim 4, wherein the production variable calculation means uses the similarity calculated for each element of the new product. 6. The business plan support apparatus according to claim 4 or 5, wherein the production variable is development cost or production personnel. 7. The business plan support apparatus according to claim 1, further comprising a profit calculation means for subtracting a production variable from a product of a sales forecast quantity of the product and a sales price of the product. A management plan support device that is further equipped.