JP2011134268A - Apparatus and method for processing information, and computer program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To perform accurate cost accounting without acquiring information on resources input to a business activity, for example, additional information such as operation time or the like. <P>SOLUTION: A business efficiency promotion strategy by business unit is designated, and a DEA (Data Envelopment Analysis) model corresponding to the efficiency promotion strategy is used to extract, from DMU (Decision Making Unit) data including input cost data and output data for each business unit stored in a storage device, DMU data of a business unit which performs efficient business of the business units. The DMU data extracted by the extraction means is used to derive a cost model, and the cost model is used to perform fixed cost-variable cost breakdown processing to break down the input cost into fixed costs and other costs. <P>COPYRIGHT: (C)2011,JPO&INPIT

Description

  The present invention relates to a technique for performing cost calculation.

  Appropriately calculating and managing the cost of product production and service provision is very important in terms of formulating management plans and reducing business activity costs. For example, by predicting the cost according to the expected sales in the future, or by extracting high-cost establishments and comparing them with low-cost establishments, it can be used to identify and improve problems in current operations. It becomes possible.

  In such cost calculation, a method of calculating the cost by dividing the input cost for business activities into each product or service based on a certain allocation standard has been generally used (for example, non-patent literature). 1). However, if for some reason it is not possible to set an appropriate allocation standard, or if it is difficult to set an allocation standard that apportions costs appropriately because the proportion of indirect costs is large, the apportioned cost is actually There is a problem that it is not suitable.

  As a method for increasing the accuracy of apportionment, there is activity based costing (hereinafter referred to as “ABC”). In ABC, costs can be calculated with high accuracy by measuring costs for each activity in a business activity and analyzing cost factors (cost drivers) that affect the generation of costs.

In addition to the method of apportioning input costs based on the allocation standard, cost calculation is performed using a linear regression model typified by the least square method. The cost calculation method by linear regression model, assuming a cost structure business activities (1) linear model such as, for calculating the product or the cost bid b _i for each service, the sections a. For example, in the least square method (multiple regression analysis), which is the most common method, cost decomposition is realized by solving an optimization problem with equation (2) as an objective function and equation (3) as a constraint. This is further disclosed in Non-Patent Document 1.

  Patent Document 1 proposes a system for calculating costs in consideration of the use of ABC. Patent Document 2 proposes a system that calculates the production cost of a product based on the production cost of parts in a mixed production site.

JP 2004-252710 A JP 2006-85734 A

Okamoto Kiyoshi "Cost Accounting"

  In the conventional cost calculation technology, in order to produce each product or service, calculation accuracy is improved by more accurately grasping how much resources have been invested. For this purpose, for example, it is necessary to acquire information such as how long the worker has been engaged in production of each product or provision of services. However, in order to acquire such information, a lot of labor is required, and particularly in a business providing services, it may be difficult to grasp the labor such as time required for each service.

  In addition, even when trying to improve accuracy by using ABC, the definition of activities based on operation surveys, measurement of costs by activity, and analysis of cost factors (cost drivers) that affect the generation of costs It takes a lot of effort.

  When the costs invested in business activities are rationally utilized, the maximum product or service output can be obtained with respect to the input costs, and the efficiency of business activities is improved. However, in reality, it is difficult to invest management resources according to demand without excess or deficiency.

  In addition, due to various circumstances for each business office, there is a cost that is not directly linked to added value, other than the cost required for production of products or services. For example, the cost corresponding to the waiting time when too much management resources are invested for the demand, or the cost corresponding to the travel time when the work flow line is longer than other offices due to some individual circumstances Etc. are included. Taking this into account, the cost structure can be expressed as in equation (4).

When cost decomposition is performed using a linear regression model typified by the least squares method (multiple regression analysis), the cost error increases due to the C _NVA term in equation (4), and the effect of product or service output. There is a problem that it becomes difficult to extract. For this reason, in practice, sales are used as explanatory variables, not output, and the usage is limited to performing cost forecasting etc. by analyzing the relationship between sales and input costs. When sales are calculated as explanatory variables, it is assumed that the sales composition is constant, and it is naturally impossible to predict costs corresponding to future changes in the sales composition.

  Therefore, in view of the above-described problems, an object of the present invention is to perform highly accurate cost calculation without acquiring information on resources input to a business activity, for example, additional information such as work time.

  In order to achieve the above object, an information processing apparatus of the present invention has the following configuration. That is, an information processing apparatus that performs cost calculation on output items using DMU data including input cost data and output data for each business unit stored in a storage device, and is a business efficiency policy for the business unit Using a DEA model corresponding to the efficiency policy, an extraction means for extracting DMU data of a business unit performing an efficient business out of the business units from the DMU data using a DEA model corresponding to the efficiency policy; Deriving means for deriving a cost model using the DMU data extracted by the extracting means, and using the cost model derived by the deriving means, the fixed change decomposition for decomposing the input cost into a fixed cost and other costs Disassembling means for performing processing.

  In order to achieve the above object, an information processing method of the present invention has the following configuration. That is, an information processing method in an information processing apparatus that performs cost calculation for output items using DMU data including input cost data and output data for each business unit stored in a storage device, The DMU data of a business unit that conducts an efficient business out of the business units is extracted from the DMU data by using a designating process for designating an efficiency policy of the system and a DEA model corresponding to the efficiency policy. Extracting the input cost into fixed costs and other costs using an extraction step, a derivation step for deriving a cost model using the DMU data extracted by the extraction means, and a cost model derived by the derivation means A solidification decomposition process.

  According to the present invention, it is possible to perform highly accurate cost calculation without acquiring information on resources input to a business activity, for example, additional information such as work hours.

It is a figure which shows an example of the block diagram of the cost calculation system of this invention. 2 is a block diagram illustrating an example of a hardware configuration of a management server 101. FIG. 4 is a flowchart illustrating an example of cost calculation processing performed by a CPU 201 of a server apparatus 101. It is a flowchart which shows the detail of the exclusion process of the inappropriate DMU data of step S303 of FIG. It is a flowchart which shows the detail of the calculation process of the efficient frontier of step S304 of FIG. It is a flowchart which shows the detail of the solidification decomposition | disassembly process with respect to the efficient frontier of step S305 of FIG. It is a flowchart which shows the detail of the solidification decomposition process with respect to the stratification result of the efficient frontier of step S308 of FIG. It is an example of the input screen which receives the input of the object period, object office, and efficiency improvement policy which are the object of cost calculation processing. It is a figure which shows an example of a structure of an input cost table. It is a figure which shows an example of a structure of a production amount information table. It is a figure which shows an example of a structure of a DMU exclusion data output screen. It is DMU data which performed the cost calculation process by the conventional method and this invention in an Example. It is a figure which shows the result of having applied the least squares method to the DMU data of FIG. It is a figure which shows the result of having calculated the efficiency frontier with respect to the DMU data of FIG. 10, and calculating the efficient frontier based on the formulas (12) to (18). It is a figure which shows the result of having performed solidification decomposition | disassembly by the least squares method with respect to the efficient frontier of FIG. It is a figure which shows the result of having performed the stratification process with respect to the efficient frontier of FIG. It is a figure which shows the result of having performed the solidification decomposition | disassembly by the least squares method with respect to the efficient frontier of the 1st layer of FIG. It is a figure which shows the result of having performed the solidification decomposition | disassembly by the least squares method with respect to the efficient frontier of the 2nd layer of FIG. It is a figure which shows the result decomposed | disassembled into the cost according to output based on (21) and (22) type | formula, and other cost. It is a figure which shows the cost according to output (total of all DMU) which calculated the DMU data of FIG. 12 by the conventional method and the method of this invention.

  Hereinafter, an example of an embodiment of the present invention will be described with reference to the drawings.

  FIG. 1 is a system configuration diagram showing an example of a configuration of a cost calculation system according to the present invention. In the figure, reference numeral 101 denotes a server device which includes a storage device for storing various data used for cost management calculation and performs cost calculation processing described later in response to a cost management calculation request from a client device described later. It is a processing device.

  Reference numerals 102-1 and 102-2 are client apparatuses (hereinafter collectively referred to as the client apparatus 102), and whether the BOM is registered, changed, or deleted with respect to the management server 101, or whether the BOM is normally registered This is a computer used by the user in order to make a request for determination processing to be described later. Reference numeral 103 denotes a network such as a LAN (Local Area Network) for connecting the server apparatus 101 and the client apparatus 102 so that they can communicate with each other.

  FIG. 2 is a schematic diagram illustrating an example of a hardware configuration of an information processing apparatus applicable as the server apparatus 101 in FIG.

  The CPU 201 comprehensively controls devices and controllers described later connected to the system bus 204. Further, the ROM 203 or the external memory 211 is necessary to realize a BIOS (Basic Input / Output System) or an operating system program (hereinafter referred to as OS) that is a control program of the CPU 201 and functions executed by each server or each PC. Various programs to be described later are stored. The RAM 202 functions as a main memory, work area, and the like for the CPU 201.

  The CPU 201 implements various operations by loading a program necessary for execution of processing into the RAM 202 and executing the program. An input controller (input C) 205 controls input from a pointing device such as a keyboard 209 or a mouse (not shown). A video controller (VC) 206 controls display on a display device such as the display device 210. The display device is, for example, a CRT display or a liquid crystal display. These are used by the administrator as needed. The present invention is not directly related.

  A memory controller (MC) 207 is a hard disk (HD), floppy disk (registered trademark FD) or PCMCIA card slot for storing boot programs, browser software, various applications, font data, user files, editing files, various data, and the like. Controls access to an external memory 211 such as a compact flash memory connected via an adapter.

  A communication I / F controller (communication I / FC) 208 is connected to and communicates with an external device via a network, and executes communication control processing in the network. For example, Internet communication using TCP / IP is possible.

  Note that the CPU 201 enables display on the display device 210 by executing outline font rasterization processing on a display information area in the ROM 203, for example. Further, the CPU 201 enables a user instruction with a mouse cursor (not shown) on the display device 210.

  A program used to execute various processes of the management server 101 of the present invention is recorded in the external memory 211, and is executed by the CPU 201 by being loaded into the RAM 202 as necessary. Furthermore, definition files and various information tables used by the program according to the present invention are stored in the external memory 211.

  Next, an example of the cost calculation process performed by the CPU 201 of the server apparatus 101 will be described with reference to FIG. A program for causing the CPU 201 to execute this processing is recorded in the external memory 211. The CPU 201 loads the program into the RAM 202 as necessary, and executes this processing according to the control of the program. Further, various data used by the program according to the present invention is stored in the external memory 211.

In this embodiment, the efficiency is evaluated based on the input cost and the actual output, and the combination of the input cost and the output when it is assumed that the establishment is determined to be efficient for the establishment determined to be inefficient. (Hereinafter referred to as efficient frontier). An efficiency policy is a policy that defines whether to increase efficiency by reducing input costs (input-oriented) or by increasing output (output-oriented) in calculating the efficient frontier. Point to.

  First, in step S301, the CPU 201 determines a target period, a target office, and an efficiency policy to be processed for cost calculation. In this determination, the CPU 201 obtains the target period, the target establishment, and the efficiency policy data input from the user via the input screen displayed on the display device of the client device 102 from the client device 102, and the data The target period, target office, and efficiency policy will be determined accordingly.

  FIG. 8 is an input screen for accepting input of a target period, a target office, and an efficiency policy that are to be processed for cost calculation. In this input screen, a processing target period setting unit 801, a target establishment selection check box 802, and an efficiency policy selection unit 803 are set. A target period, a target office, and an efficiency policy are input according to an instruction from a user who operates the client apparatus 102 from a keyboard 207 or an operation unit including a pointing device (not shown).

  When the determination button 804 is pressed, the CPU 201 of the client apparatus 102 transmits the target period, the target establishment, and the efficiency policy data input via the input screen 800 to the server apparatus 101, thereby reducing the cost. A request for calculation processing is made to the server apparatus 101. The above is the description of the input screen in FIG.

By selecting the period, establishment, etc. to be processed using such a screen, for example, when calculating the cost of production activities of companies with factories in multiple countries, narrow down establishments to country units Therefore, it is possible to calculate more realistic costs considering characteristics such as differences in labor costs between countries.

  Returning to the description of FIG. After the target establishment, the target period, and the efficiency improvement policy are determined in step S301, the target establishment target is determined from the input cost information table (FIG. 9) and the output information table (FIG. 10) stored in the external memory 211. The input cost and output in the period are acquired (step S302). Then, the obtained data is linked to the input cost / output amount for each establishment for a certain period. Data obtained by associating input cost information and output information for each business site is referred to as DMU (Decision Making Unit) data.

  Here, the input cost information table and the output information table will be described with reference to FIGS.

  FIG. 9 is a diagram showing an example of the configuration of the input cost information table. As shown in the figure, the input cost information table 900 includes a year 901, a month 902, a business office 903, and an input cost 904.

  The year 901 is a data item for specifying the year in which the cost indicated by the record is input. The month 902 is a data item for specifying the month in which the cost indicated by the record is input. The business office 903 is a data item for specifying the business office where the cost indicated by the record is input. The year 901, month 902, and office 903 are key items of the input cost data table 900.

  The input cost 904 is a data item indicating the amount actually input. For example, the input cost at the A office in April 2008 is 200,000 yen, the input cost at the B office is 182,000 yen, and the input cost at the C office is 203,000 yen. is there. This configuration is merely an example, and even if other data items are added, it does not have any of the above-described data items, and a plurality of the above-described data items are combined to form one data item. Of course, it does not matter. Data registration may be performed on a daily basis, a weekly basis, or the like. Furthermore, the input cost may be created by calculating the total value based on more detailed cost data such as labor costs and expenses.

  FIG. 10 is a diagram illustrating an example of the configuration of the output information table. As shown in the figure, the output information table 1000 includes a year 1001, a month 1002, a business office 1003, a service A output 1004, and a service B output 1005.

  The year 1001 is a data item for specifying the year in which the cost indicated by the record is input. The month 1002 is a data item for specifying the month in which the cost indicated by the record is input. The business establishment 1003 is a data item for specifying the business establishment where the cost indicated by the record is input. The year 1001, the month 1002, and the office 1003 are key items of the output information data table 1000.

  Service A output 1004 is a data item indicating a unit of output of service A, and service B output 1005 is a data item indicating a unit of output of service B. For example, in April 2008, the output of service A at office A is 100 units, the output of service B is 90 units, the output of service A at office B is 90 units, and the output of service B The output is 90 units, the output of service A at establishment C is 85 units, and the output of service B is 110 units. This configuration is merely an example, and even if other data items are added, it does not have any of the above-described data items, and a plurality of the above-described data items are combined to form one data item. Of course, it does not matter. Data registration may be performed on a daily basis, a weekly basis, or the like.

  Returning to the description of FIG. Next, the CPU 201 performs processing for excluding DMU data that is inappropriate for cost calculation. Details of this processing will be described with reference to FIG.

  FIG. 4 is a flowchart showing details of the inappropriate DMU data exclusion process in step S303 of FIG. A program for causing the CPU 201 to execute this processing is recorded in the external memory 211. The CPU 201 loads the program into the RAM 202 as necessary, and executes this processing according to the control of the program. Further, various data used by the program according to the present invention is stored in the external memory 211.

  First, the CPU 201 calculates DMU data whose input cost or output value is 0 (or missing) or DMU data which is a negative value in order to more accurately calculate the efficiency described later. Are excluded from processing. Subsequently, in step S402, DMU data whose input cost or output value is significantly different from other DMU data and DMU data corresponding to an outlier are excluded. As a method of excluding outliers, in the DMU data, a method for determining and excluding outliers based on deviations from the average for each item of input cost and output, determining outliers by using a box whiskers, Any method, such as a method of excluding this, or a method of determining and excluding outliers by using cluster analysis, or a combination of these may be used.

  Thereafter, excluded DMU data output screen information used to display the excluded data on the display device of the client apparatus 102 is generated (step S403). When this output screen information is sent to the client device, the output screen shown in FIG. 11 is displayed on the display device.

  FIG. 11 is a diagram illustrating an example of a DMU exclusion data output screen displayed on the display device of the client device 102. The DMU exclusion data output screen 1100 displays the DMU number 1101, year 1102, month 1103, business division 1104, input cost 1105, service A output 1106, and service B output 1107 of the excluded DMU data. When the OK button 1108 in the figure is pressed, the client apparatus 102 ends the display of the DMU exclusion data output screen.

Returning to the description of FIG. After completion of the inappropriate DMU data exclusion process in step S303, the CPU 201 performs an efficient frontier calculation process (step S304). Details of this processing will be described with reference to FIG. This efficient frontier calculation is performed for the purpose of reducing the influence of c _{nva in} the above-described equation (4) and bringing it closer to the condition assumed in the equation (1).

  FIG. 5 is a flowchart showing details of the efficient frontier calculation process in step S304 of FIG. A program for causing the CPU 201 to execute this processing is recorded in the external memory 211. The CPU 201 loads the program into the RAM 202 as necessary, and executes this processing according to the control of the program. Further, various data used by the program according to the present invention is stored in the external memory 211.

First, the CPU 201 assigns 1 to K, which is a counter variable of DMU data (step S501). Thereafter, a DEA model for the Kth DMU data (DMU (K)) is generated, and an efficient frontier is calculated (step S502). Note that the DEA model generated by this processing is determined based on the efficiency improvement policy set for each office in step S301 in FIG.

  For example, when the efficiency policy is “input-oriented”, for example, a solution of an input-oriented BCC (Banker-Charnes-Cooper) model expressed by the following equations (5) to (9) in the DEA model is obtained. Based on the result, the efficient frontier is calculated by the equations (10) and (11). In practice, if the increase in output is not taken into account or cannot be taken into account, the output in the efficient frontier is not calculated, and the actual output may be used. Here, the optimization problem by the input-oriented BCC model is illustrated, but the DEA model to be used is described in, for example, “Measurement and improvement of management efficiency” written by Tone Kaoru (Nichikagiren Publisher). A CCR model, IRS model, DRS model, GRS model, or the like may also be used.

  On the other hand, when the efficiency policy is “output-oriented”, for example, a solution of the output-oriented BCC model expressed by the equations (12) to (16) in the DEA model is obtained, and based on the result (16) The efficient frontier is calculated by the equation (17). In practice, when the reduction of the input cost is not considered or cannot be considered, the efficiency input cost in the efficient frontier is not calculated, and the actual input cost may be used. Here, the optimization problem by the output-oriented BCC model is illustrated, but the DEA model to be used is described in, for example, “Measurement and improvement of management efficiency” written by Tone Kaoru (Nikkagi Renren Publishing Co., Ltd.). A CCR model, IRS model, DRS model, GRS model, or the like may also be used.

  In order to simplify the explanation, only two types of input-oriented and output-oriented are listed for efficiency. However, there are innumerable combinations of input costs and output on the efficient frontier. In essence, a combination of input-oriented and output-oriented policies may be taken. A calculation method that simultaneously considers reduction in input costs and increase in output as needed, for example, additive type described in Tone Tone's “Measurement and Improvement of Management Efficiency” (Nikka Giren Publisher) Of course, it is possible to use efficient frontier calculation by a model.

  After the process of step S502 is completed, the CPU 201 determines whether the efficient frontier calculation process of step S502 has been performed for all the DMU data, and the calculation process for all the DMU data has been completed. If it is determined that there is no (NO in step S503: “K = number of target DMUs?”), The process proceeds to step S504, K is incremented, and the efficient frontier calculation process of step S502 is performed for the next DMU data. Do. On the other hand, if it is determined in step S503 that the efficient frontier calculation process for all the DMU data has been completed, this process ends. The above is the detailed description of the efficient frontier calculation process.

  Returning to the description of FIG. After completing the efficient frontier calculation process in step S304, the CPU 201 performs a solidification decomposition process for the efficient frontier (step S305). Details of this processing will be described with reference to FIG.

  FIG. 6 is a flowchart showing details of the solidification decomposition process for the efficient frontier in step S305 of FIG. A program for causing the CPU 201 to execute this processing is recorded in the external memory 211. The CPU 201 loads the program into the RAM 202 as necessary, and executes this processing according to the control of the program. Further, various data used by the program according to the present invention is stored in the external memory 211.

  First, the CPU 201 performs a multiple regression analysis on the efficient frontier calculated in step S304 of FIG. 3 (the above-described equations (2) and (3)) (step S601). Here, cost decomposition by multiple regression analysis (least square method) when the cost model is linear will be described as an example, but it is meaningful to specify a cost model and apply an efficient frontier to this. The cost model may be a polynomial model other than the linear model, and the calculation method may not be a multiple regression analysis.

  Then, the partial regression count obtained as a result of the multiple regression analysis in step S601 is stored as a production cost unit (step S602), and then 1 is substituted into K which is a counter variable of the DMU data (step S603).

In step S604, the CPU 201 decomposes the input cost of each DMU data into the output cost and the other costs according to the equations (19) and (20) based on the cost unit of each output.

Thereafter, if it is determined in step S605 that the processing in step S604 has not been completed for all DMU data (NO in step S605: “K = number of target DMUs?”), The process proceeds to step S606. K is incremented, and the input cost of the next DMU data is decomposed into the output cost and other costs. On the other hand, if it is determined in step S605 that all DMU data has been processed, the process proceeds to step S607, and the processing results in step S604 are aggregated and stored. The above is the detailed description of the solidification decomposition process for the efficient frontier.

  Returning to the description of FIG. After the solidification decomposition process for the efficient frontier in step S305 is completed, it is determined whether to stratify the efficient frontier (step S306). When considering actual business activities, it may be difficult to represent an efficient frontier with a single cost model (assuming linearity) for reasons such as economies of scale working. If there is a large error in the result of the return to the cost model, it can be expected to increase the accuracy by performing stratification by an appropriate method. The determination of the stratified implementation is made by the CPU 201 according to a predetermined rule based on, for example, the result of multiple regression analysis (determination coefficient, t value, residual tendency, etc.).

  If it is determined in step S306 that stratification is to be performed (YES in step S306), the process proceeds to step S307 to perform efficient frontier stratification. Stratification methods include stratification according to input costs, stratification according to efficiency index values, stratification by cluster analysis, and Tone Toshi, “Measurement and Improvement of Management Efficiency” ”(Nikka Giren Publisher) can be considered a method based on the calculation of the scale (applicable only when the DEA model is a BCC model), but what method is used for stratification? It doesn't matter.

  After the stratification process in step S307 ends, the process proceeds to step S308, and a solidification decomposition process is performed on the stratification result. In this process, the solid variable decomposition in step S305 is performed for each layer on the DMU data classified in each layer as a result of the layered process in step S307. Details of this processing will be described with reference to FIG.

  FIG. 7 is a flowchart showing details of the solidification decomposition process for the stratified result of the efficient frontier in step S308 of FIG. A program for causing the CPU 201 to execute this processing is recorded in the external memory 211. The CPU 201 loads the program into the RAM 202 as necessary, and executes this processing according to the control of the program. Further, various data used by the program according to the present invention is stored in the external memory 211.

  First, the CPU 201 assigns 1 to L which is a counter variable of a layer (step S701). Thereafter, multiple regression analysis is performed on the efficient frontier included in the layer L (step S702). This process is the same as the process of step S601 in FIG.

Then, the partial regression count obtained as a result of the multiple regression analysis in step S702 is stored as the cost unit of production of layer L (step S703), and then 1 is substituted into K which is a counter variable of DMU data (step S703). S704). Thereafter, the CPU 201 decomposes the input cost of each DMU data included in the layer L into the output cost and the other costs according to the equations (21) and (22) based on the cost unit of each output ( Step S705).

Thereafter, if it is determined in step S706 that the processing in step S705 has not been completed for all DMU data included in layer L (NO in step S706: “K = number of target DMUs?”) In step S708, K is incremented, and the input cost of the next DMU data is decomposed into the output cost and the other costs. On the other hand, if it is determined in step S706 that the processing for all DMU data has been completed, the process proceeds to step S708, and the processing results in step S604 for the layer L DMU data are totaled and stored. Thereafter, the process proceeds to step S709, and it is determined whether the processes for all layers are completed.

If it is determined that the above process has not been completed for all layers (NO in step S709: “L = number of target layers?”), The process proceeds to step S710 and L is incremented. The processing from S702 will be repeated. If it is determined that the processing has been completed for all layers, this processing is terminated. The above is the detailed description of the solidification decomposition process for the stratified result.

Hereinafter, the comparison between the cost calculation according to the present invention and the cost calculation according to the conventional method (the least square method with respect to the actual data) will be described with respect to the DMU data shown in FIG. In addition, the DMU data shown in FIG. 10 produced the output of service A and service B by the normal random numbers N (200, 50 ² ), respectively, and created the input cost by equation (23). FIG. 13 shows the result of applying the least square method to the DMU data of FIG. 12 and performing the solid change decomposition (conventional method).

FIG. 14 shows the result of calculating the efficient frontier based on the equations (12) to (18) with the efficiency policy as the output direction for the DMU data of FIG. In the case of an output-oriented BCC model, the efficiency index 1401 in FIG. 14 is the reciprocal of η _{k in} the equation (12) and indicates the degree of efficiency. The efficiency index takes a value from 0 to 1, and the closer to 1, the higher the efficiency is determined. In particular, an efficiency index value of 1 is called an efficient DMU. Further, the efficiency input cost 1402, the service A efficiency output 1403, and the service B efficiency output indicate the input cost, the service A output, and the service B output in the efficient frontier, respectively.

FIG. 15 shows the result of performing the solid change decomposition by the least square method on the efficient frontier of FIG. Compared with the conventional method (FIG. 13), it can be seen that the coefficient of determination or the t value of each explanatory variable is improved.

FIG. 16 is a diagram illustrating a result of performing a stratification process on the efficient frontier of FIG. Here, the efficiency input cost 1602, the service A efficiency output 1603, and the service B efficiency output 1604 are standardized so that the average is 0 and the standard deviation is 1, and the two layers are divided by clustering by the Ward method. In addition, the least square method was applied to the DMU data for each layer, and solidification decomposition was performed. The results are shown in FIG. 15 (first layer) and FIG. 16 (second layer). After the stratification process, by performing the solidification decomposition according to the shape of the corresponding frontier for each layer, it becomes possible to calculate the cost more in line with the actual situation. FIG. 17 and FIG. 18 show the results obtained by subjecting the first layer and the second layer to solid change decomposition by the least square method, respectively.

FIG. 19 shows the result of decomposition into output-specific costs and other costs based on equations (21) and (22). Further, FIG. 20 shows the cost by output (total of all DMUs) calculated by the conventional method and the method of the present invention. When compared with the cost for each output calculated from the cost model of equation (23), it can be seen that the result obtained by the method of the present invention has a smaller cost error than the conventional method.

As described above, according to the present invention, it is possible to perform cost calculation with high accuracy without acquiring information on resources input to a business activity, for example, additional information such as work time.

  The present invention can be implemented as a system, apparatus, method, program, storage medium, or the like, and can be applied to a system including a plurality of devices. You may apply to the apparatus which consists of one apparatus.

  In the present invention, a software program (in the embodiment, a program corresponding to the flowcharts shown in FIGS. 3 to 7) for realizing the functions of the above-described embodiments is supplied directly or remotely to a system or apparatus. Including. The present invention also includes a case where the system or the computer of the apparatus is achieved by reading and executing the supplied program code.

  Accordingly, since the functions of the present invention are implemented by computer, the program code installed in the computer also implements the present invention. In other words, the present invention includes a computer program itself for realizing the functional processing of the present invention.

  In that case, as long as it has the function of a program, it may be in the form of object code, a program executed by an interpreter, script data supplied to the OS, and the like.

  Examples of the recording medium for supplying the program include a flexible disk, hard disk, optical disk, magneto-optical disk, MO, CD-ROM, CD-R, and CD-RW. There are also magnetic tape, nonvolatile memory card, ROM, DVD (DVD-ROM, DVD-R) and the like.

  As another program supply method, a browser on a client computer is used to connect to an Internet home page. The computer program itself of the present invention or a compressed file including an automatic installation function can be downloaded from the homepage by downloading it to a recording medium such as a hard disk.

  It can also be realized by dividing the program code constituting the program of the present invention into a plurality of files and downloading each file from a different homepage. That is, a WWW server that allows a plurality of users to download a program file for realizing the functional processing of the present invention on a computer is also included in the present invention.

  In addition, the program of the present invention is encrypted, stored in a storage medium such as a CD-ROM, distributed to users, and key information for decryption is downloaded from a homepage via the Internet to users who have cleared predetermined conditions. Let It is also possible to execute the encrypted program by using the downloaded key information and install the program on a computer.

  Further, the functions of the above-described embodiments are realized by the computer executing the read program. In addition, based on the instructions of the program, an OS or the like running on the computer performs part or all of the actual processing, and the functions of the above-described embodiments can also be realized by the processing.

  Further, the program read from the recording medium is written in a memory provided in a function expansion board inserted into the computer or a function expansion unit connected to the computer. Thereafter, the CPU of the function expansion board or function expansion unit performs part or all of the actual processing based on the instructions of the program, and the functions of the above-described embodiments are realized by the processing.

  The above-described embodiments are merely examples of implementation in carrying out the present invention, and the technical scope of the present invention should not be construed as being limited thereto. That is, the present invention can be implemented in various forms without departing from the technical idea or the main features thereof.

101 Server apparatus 102-1, 102-2 Client apparatus 103 LAN
201 CPU
202 RAM
203 ROM
204 System Bus 205 Input Controller 206 Video Controller 207 Memory Controller 208 Communication I / F (Interface) Controller 209 Keyboard 210 Display Device 211 External Memory

Claims (5)

An information processing device that performs cost calculation on output items using DMU data including input cost data and output data for each business unit stored in a storage device,
A designation means for designating a business efficiency policy for the business unit;
Extracting means for extracting DMU data of a business unit performing an efficient business out of the business units from the DMU data using a DEA model corresponding to the efficiency policy;
Derivation means for deriving a cost model using the DMU data extracted by the extraction means;
Using the cost model derived by the derivation means, decomposition means for performing a solid decomposition process to decompose the input cost into a fixed cost and other costs;
An information processing apparatus comprising: Projecting means for projecting DMU data of business units not extracted by the extracting means onto the efficient frontier according to the efficiency policy, and generating projected DMU data.
The derivation unit derives the cost model using projection DMU data input to an efficient frontier by the projection unit in addition to the DMU data extracted by the extraction unit. The information processing apparatus described. Determination means for determining whether to perform stratification processing on the DMU data;
And further comprising a stratification means for performing a stratification process on the DMU data when it is determined that the determination means performs stratification,
The derivation means calculates a cost model for each layer as a result of stratification by the stratification means, using the DMU data extracted by the extraction means among the DMU data included in the layer,
The information processing apparatus according to claim 1, wherein the decomposition unit performs a solidification decomposition process using a cost model derived for each layer. An information processing method in an information processing apparatus that performs cost calculation for output items using DMU data including input cost data and output data for each business unit stored in a storage device,
A designated process for designating a business efficiency policy for the business unit;
Using the DEA model corresponding to the efficiency improvement policy, extracting from the DMU data the DMU data of the business unit performing an efficient business out of the business units;
A derivation step of deriving a cost model using the DMU data extracted by the extraction means;
Using the cost model derived by the derivation means, a decomposition step for performing a solidification decomposition process that decomposes the input cost into a fixed cost and other costs;
An information processing method comprising: Computer
A computer program for functioning as an information processing device that performs cost calculation for a plurality of output items using DMU data including input cost data and output data for each business unit stored in a storage device,
The computer,
A designation means for designating a business efficiency policy for the business unit;
Extracting means for extracting DMU data of a business unit performing an efficient business out of the business units from the DMU data using a DEA model corresponding to the efficiency policy;
Deriving means for deriving a cost model using the DMU data extracted by the extracting means;
A computer program that functions as a decomposing unit that performs a solidification decomposition process that decomposes the input cost into a fixed cost and other costs using the cost model derived by the deriving unit.

Images