JP2015207229A - Business support system and business support method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a business support system for enabling a user to intuitively grasp a relation between an economy index and a reliability index (so called, business data) and an inflow speed and an outflow speed (so called, on-site data).SOLUTION: A business support system includes: a data reception part 1; and a restoration matrix estimation part 2. The data reception part 1 receives observation data indicating a relation between an inflow speed m and an outflow speed d and an economy index ER and a reliability index LT. The restoration matrix estimation part 2 estimates a restoration matrix for matching a coordinate axis corresponding to the inflow speed m and the outflow speed d with a coordinate axis corresponding to the economy index ER and the reliability index LT. The business support system is helpful for a user to grasp a relation between business data and on-site data in a real time.

Description

  The present invention relates to a system and method for supporting management.

  In conventional management systems, improvement approaches such as JIT, TQC, and TPM are often taken. The improvement approach is aimed at increasing profits as costs decrease by finding improvement goals and problems and improving the corresponding systems and methods. However, even if the technique obtained by this improvement approach is partially best (for example, cost), it is not necessarily the best for the whole corporate management (for example, profit).

  As a method proposed in view of this problem, there is supply chain management (SCM). This is combined with constraint theory (TOC) and aims at total optimization, but it is a kind of improvement approach and has a problem that it is weak strategically and theoretically.

  Therefore, the present inventor has proposed a technique described in Patent Document 1 below. With this technique, it is possible to maximize the economics such as profit (throughput) and improve the reliability such as lead time in terms of games (that is, in competition).

  The outline of Patent Document 1 below is as follows. An average arrival interval (outflow speed) d as a demand strategy and an average processing time (outflow speed) m as a production strategy are taken on the vertical axis and the horizontal axis, respectively. Average profit gain (economic index) ER per unit time, average operating cost EC per unit time, average net gain (marginal profit) EN (= ER-EC), economic lead time (reliability index) LT, etc. Management data is displayed corresponding to the values of d and m described above.

  According to the technique disclosed in Patent Document 1, the process (transition process) can be found in order to bring the current input / output position (position determined by d and m) closer to the ideal or target strategic position.

  Incidentally, in order to acquire the average arrival interval time d and the average processing time m, which are the basis for acquiring the data of the gain ER and the cost EC, the following method is commonly used. That is, the arrival distribution and the processing distribution in a specific example (for example, a factory) are acquired in advance, and d and m are estimated based on these statistical data.

  However, a method of statistically acquiring distribution data in advance and calculating based on the distribution data must ensure the number of data to be statistically significant in advance and is difficult to prepare. Also, this method has a problem that the processing time of the computer becomes long because the processing is complicated and the amount of calculation increases.

  Therefore, the present inventor has proposed a management data management method capable of easily acquiring data for management in Patent Document 2 below.

  In the method described in Patent Document 2 below, the relationship between the gain ER and cost EC data, the average arrival interval time d and the average processing time m can be calculated graphically, and the calculation is easy. There is.

  However, even the method of Patent Document 2 below has a problem that it is difficult to display the relationship between the gain ER and cost EC data, the average arrival interval time d, and the average processing time m in real time in an easy-to-understand manner for the user. It was.

JP 2002-49449 A JP 2002-197261 A

  The present invention has been made in view of the above situation. The main object of the present invention is to allow the user to intuitively and easily grasp the relationship between the economic index and the reliability index (so-called management data) and the inflow speed and outflow speed (so-called on-site data). It is to provide technology that can.

  The present invention can be expressed as an invention described in the following items.

(Item 1)
A data reception unit and a restoration matrix estimation unit;
The data receiving unit is configured to receive observation data indicating a relationship between an inflow speed and an outflow speed, an economic index and a reliability index,
The restoration matrix estimation unit is configured to estimate a restoration matrix for matching the coordinate axes corresponding to the inflow speed and the outflow speed with the coordinate axes corresponding to the economic index and the reliability index. .

  Here, “management” in the present invention is not limited to the management of so-called business entities, but is used as a concept including the management and management of various management entities such as factories, offices, and sales floors.

(Item 2)
In addition, it has an inverse estimator,
The configuration according to item 1, wherein the inverse estimation unit is configured to calculate both or one of the inflow speed and the outflow speed based on the restoration matrix and designation of the economic index and reliability index. Management support system.

(Item 3)
The restoration matrix is decomposed into at least a whitening matrix, a strategy matrix, and a unitary matrix,
Item 3. The management support system according to item 1 or 2, wherein the strategy matrix can be set to contents according to a user's desire.

(Item 4)
In addition, it has an output unit,
The output unit is configured to display the inflow speed and the outflow speed, and the economic index and the reliability index in a state where coordinate axes corresponding to the output speed and the outflow speed coincide with each other. The management support system described in 1.

(Item 5)
The management support system according to any one of items 1 to 4, wherein the economic index is data relating to profit.

(Item 6)
The management support system according to any one of items 1 to 5, wherein the reliability index is data relating to a lead time.

(Item 7)
The management support system according to any one of items 1 to 6, wherein the outflow speed is calculated using POS data.

(Item 8)
The management support system according to any one of items 1 to 7, wherein the inflow speed is calculated using POP data.

(Item 9)
A management support method executed using a device,
Receiving observation data indicating the relationship between the inflow speed and outflow speed and the economic index and reliability index;
A management support method comprising: estimating a restoration matrix for matching the coordinate axes corresponding to the inflow speed and the outflow speed with the coordinate axes corresponding to the economic index and the reliability index.

(Item 10)
A computer program for causing a computer to execute each step according to item 9.

  This computer program is stored in an appropriate recording medium (for example, an optical recording medium such as a CD-ROM or a DVD disk, a magnetic recording medium such as a hard disk or a flexible disk, or a magneto-optical recording medium such as an MO disk). Can be stored. This computer program can be transmitted via a communication line such as the Internet.

  According to the present invention, it is possible for a user to intuitively understand the relationship between an economic index and a reliability index (so-called management data) and an inflow speed and an outflow speed (so-called on-site data). Become. Therefore, according to the present invention, the on-site data that satisfies the management data or the management data when the on-site data is defined can be displayed so that the user can easily understand the gap between the two. It becomes possible.

It is a block diagram for demonstrating the outline of the management support system in one Embodiment of this invention. It is a flowchart for demonstrating the procedure of the management support method using the apparatus of FIG. It is explanatory drawing which shows an example of the observation data (what is called a pair map) regarding an economical efficiency parameter | index, a reliability parameter | index, an inflow speed, and an outflow speed. It is explanatory drawing which shows another example (example of another production type) of the pair map shown in FIG. In a pair map, it is explanatory drawing which shows the Z-axis which shows an economical index and a reliability parameter | index, and the L-axis which shows an inflow speed and an outflow speed. It is a flowchart for demonstrating the procedure which estimates a decompression | restoration matrix. It is explanatory drawing which shows an example of a whitening signal notionally. It is explanatory drawing which shows an example of a strategy matrix. It is explanatory drawing which shows an example of a separated signal notionally. It is explanatory drawing which shows an example of a source signal notionally.

  A configuration of a management support system (hereinafter sometimes simply referred to as “system”) according to an embodiment of the present invention will be described with reference to FIG.

(Configuration of this embodiment)
The system of the present embodiment includes a data receiving unit 1 and a restoration matrix estimation unit 2. Further, this system includes an inverse estimation unit 3 and an output unit 4 as additional elements.

(Data reception part)
The data receiving unit 1 is configured to receive observation data indicating the relationship between the inflow speed and the outflow speed, the economic index, and the reliability index.

The economic index in the present embodiment is data relating to revenue (ER). Further, the reliability index in the present embodiment is data related to the lead time (LT). Note that the economic index may be any value having some cycle characteristics and indicating economic efficiency. The reliability index may be a value related to reliability indicating some span (number of cycles). Revenue is sometimes referred to as sales or gain. In general,
EN = ER-EC
Represented as:

here,
EN: Profit EC: Cost.

  The meaning of the terms revenue and lead time is well known in the field, so a detailed description thereof is omitted (Reference 1: M. Matsui, “An enterprise-aided theory and logic for real-time management”). ", International Journal of Production Research, Volume 51, Issue 23-24, 2013).

  Assuming that it is a pull type (estimated production type), the outflow speed (d) in this embodiment is calculated using POS (Point of Sale) data. The inflow speed (m) in the present embodiment is calculated using POP (Point of Production) data. The outflow speed d is sometimes called demand speed. The inflow speed m is sometimes called production speed. However, in the push type (made-to-order type), the correspondence is reversed. The meaning of these terms is also well known in this field, so a detailed description thereof will be omitted (see Reference 1 described above).

  Details of the operation of the data receiving unit 1 will be described later.

(Restore matrix estimation unit)
The restoration matrix estimation unit 2 is configured to estimate a restoration matrix for matching the coordinate axes corresponding to the inflow speed and the outflow speed with the coordinate axes corresponding to the economic index and the reliability index.

  The restoration matrix of this embodiment is decomposed into at least a whitening matrix, a strategy matrix, and a unitary matrix. The strategy matrix can be set to contents according to the user's wishes.

  In addition, when the relationship between the inflow speed and the outflow speed, the economic index and the reliability index is known, the estimation of the restoration matrix is called identification, but in this specification, the identification is treated as a kind of estimation.

  Details of the operation of the restoration matrix estimation unit 2 in this embodiment will also be described later.

(Inverse estimation part)
The inverse estimation unit 3 is configured to calculate both or one of the inflow speed and the outflow speed based on the restoration matrix and the designation of the economic index and the reliability index.

  Details of the operation of the inverse estimation unit 3 in this embodiment will also be described later.

(Output part)
The output unit 4 is configured to display the inflow speed and the outflow speed, the economic index, and the reliability index in a state where the corresponding coordinate axes are matched.

  The output unit 4 is, for example, a display that can present an image to the user, but is not limited thereto, and may be an output device such as a printer. In short, the output unit 4 only needs to have a function of transmitting necessary information to the user.

(Operation of this embodiment)
Next, a management support method executed using the above-described apparatus of the present embodiment will be described with further reference to FIG.

(Step SA-1 in FIG. 2)
First, the data receiving unit 1 receives observation data indicating the relationship between the inflow speed and the outflow speed, the economic index, and the reliability index. An example of such data is shown in FIG. 3 as a reference example. In this figure, the horizontal axis represents the inflow (supply) speed m, and the vertical axis represents the outflow (demand) speed d. FIG. 4 is an example of observation data in a production type different from that in FIG. FIG. 5 shows an abstraction of the concrete data in FIG. 3 and FIG.

In FIG. 3, values of ER (revenue), EC (cost), EN (profit), and LT (lead time) corresponding to specific d and m are shown. Further, FIG. 3 also shows MI (information amount) and PS (set price) values. The parameter c ₂ in FIG. 4 is related to the demand speed, and the parameter i ₂ is related to the production speed.

  As shown by the inventors in Patent Document 1 and Reference Document 1, when ER is used as a reference, there are an ER maximum value 11 and an ER minimum value 12 at which ER is maximum (see FIG. 5). The management strategy is usually selected from the ellipse 10 including these two extreme values 11 and 12. That is, it can be assumed that the business strategy moves along the axis Z (see FIG. 5) connecting the extreme values 11 and 12 in general. The extreme value 12 in FIG. 5 is the point with the lowest cost, but it is known that the minimum cost point is usually the minimum profit point.

  Similarly, as shown by the inventors in Patent Document 1 and Reference Document 1, when LT is used as a reference, there are an LT maximum value 21 and an LT minimum value 22 at which LT is maximized (see FIG. 5). . The production strategy is usually selected from the ellipse 20 including these two extreme values 21 and 22. That is, it can be assumed that the production strategy generally moves along the axis L (see FIG. 5) connecting the extreme values 21 and 22.

  According to the knowledge of the present inventor, the point 13 at which the profit is maximum is in the vicinity of the intersection of the axis Z and the axis L as a general tendency (see Reference 1).

(Step SA-2 in FIG. 2)
Next, the restoration matrix estimation unit 2 estimates a restoration matrix for matching the coordinate axes corresponding to the inflow speed m and the outflow speed d with the coordinate axes corresponding to the economic index ER and the reliability index LT. A specific example of restoration matrix estimation will be described with further reference to FIG.

(Step SB-1 in FIG. 6)
First, as a premise, the observation data shown in FIG. 5 can be regarded as an observation signal. Therefore, whitening is performed by multiplying this observation signal by a correlation matrix (whitening matrix) V. If the whitened signal is T and the observed signal is X,
T = VX
It can be expressed. Here, X can also be regarded as a vector having d and m as elements. The whitened state is schematically shown in FIG. Note that the mathematical operation of whitening itself is the same concept as in the case of the existing independent component analysis, and thus detailed description of the operation itself is omitted. Note that the vector arithmetic expressions shown in this specification are merely examples, and are not intended to restrict the order of multiplication, for example. These vector arithmetic expressions are merely examples for understanding the concept.

(Step SB-2 in FIG. 6)
Next, the separation signal Y is obtained by multiplying the whitening signal T by the separation matrix U. Thereby, the Z-axis shown in FIG. 5 can be made parallel to the d-axis, and the L-axis can be made parallel to the m-axis.

That is, the separation signal Y is
Y = VUX = PX
It can be expressed. The matrix P (= VU) described above is an example of a restoration matrix in the present invention. However, as will be described later, in the present embodiment, a further addition of a strategy matrix is handled as a restoration matrix.

  The above-described separation matrix U is known as a unitary matrix. In addition, since the rotation of the shaft is similar in concept to the existing independent component analysis, a detailed description of the rotation operation is omitted.

(Step SB-3 in FIG. 6)
Next, in the present embodiment, a strategy matrix S is set. In FIG. 6, a strategy matrix is set after step SB-2, but the timing of this setting is arbitrary. The user may set a strategy matrix in advance and register it in the system, or may change and use the strategy matrix as necessary. Alternatively, the strategy matrix can be dynamically generated and applied on the system side according to system settings. It is also possible to set a strategy matrix at the time of inverse estimation described later.

  An example of the strategy matrix is shown in FIG. This is merely an example, and can take various forms depending on the strategic purpose.

(Step SB-4 in FIG. 6)
Next, in the present embodiment, a matrix Q obtained by multiplying the matrix P by the strategy matrix S is handled as a restoration matrix. As mentioned above, the order of multiplication is not constrained, for example
Q = VSU
It can be set as follows.

(Step SA-3 in FIG. 2)
Next, the output unit 4 outputs the space expressed as the separated signal (see FIG. 9) as a solution space (hereinafter referred to as “Matsui compass”). This output is usually performed in a form that can be perceived by the user, but may be handled as an input to some system.

(Step SA-4 in FIG. 2)
Next, the user inputs index data that seems to be appropriate to the inverse estimation unit 3 on the system side while watching the situation as shown in FIG. The index data is a value of ER or LT that becomes a management target. Then, the inverse estimation unit can estimate the values of d and m that achieve the target value using the restoration matrix Q estimated as described above (that is, using the inverse matrix). This enables near real-time control of the production site according to the management strategy. As described above, the management target is usually the maximization of profit, which is in the vicinity of the intersection of the Z axis and the L axis in FIG. Therefore, in this embodiment, it is possible to use, as the index data, values of ER and LT that are likely to satisfy such conditions graphically.

  On the other hand, in the present embodiment, virtual (or predicted) observation data d and m are input, and the values of ER and LT are dynamically estimated using the above-described restoration matrix Q, as shown in FIG. It can also be displayed. As a result, the values of ER and LT (or the relationship between them and the maximum profit point) when priority is given to the situation at the production site can be graphically displayed in a form that is easy for a manager to judge. Therefore, in this embodiment, there is an advantage that it is possible to determine in real time whether the d and m match the management target of the entire company.

Furthermore, as the present inventor has clarified (reference document 1), the asset W of the company is expressed by the following equation (Matsui's equation).
W = ZL
Where Z (ER) = EC + EN
L: Lead time.

  It is also possible to set the target value of ER, LT or d, m in consideration of W obtained by this equation. Here, it should be noted that the cycle value ER is a value per cycle of d.

  Therefore, in the present embodiment, a so-called compass (Matsui compass) that adjusts the balance between the management goals of the management side and the situation of the production site is displayed as shown in FIG. 9, and d, m, ER, and LT are displayed. Appropriate indicators from both sides (management side and production side) can be input to bring the state of the company closer to the management target.

  FIG. 10 shows an example of an unknown source signal. In this figure, signals S1 and S2 are both functions of d and m. Then, there is an LT axis above a certain value of S1, and the LT value fluctuates with time about the axis. Similarly, there is an ER axis above a specific value of S2, and the ER value varies with time about that axis. It is generally difficult to directly measure such a relationship. On the other hand, according to the present embodiment, as described above, the separation signal (solution space) as shown in FIG. 9 can be presented to the user using the observation signal. Even if the source signal is unknown, the user can make a management decision as described above while looking at this solution space (Matsui Compass). Here, in FIG. 10, two types of source signals S1 and S2 are assumed, but the number of signals may be three or more. Similarly, the number of types of observation data indicating the relationship between the inflow speed and the outflow speed, the economic index, and the reliability index is not particularly limited.

  The operation of the above-described embodiment can be implemented by incorporating appropriate computer software into the computer.

  The contents of the present invention are not limited to the above embodiment. In the present invention, various modifications can be made to the specific configuration within the scope of the claims.

  For example, the application target of the present invention may be not only a management body but also a management body that is a part thereof. In this case, the observation data indicating the relationship between the inflow speed and outflow speed described above, the economic index and the reliability index can be determined according to the property of the target management body. In short, the present invention has applicability to various management objects having an input / output relationship.

  Each component in the above-described embodiment only needs to exist as a function block, and does not have to exist as independent hardware. As a mounting method, hardware or computer software may be used. Furthermore, one functional element in the present invention may be realized by a set of a plurality of functional elements, and a plurality of functional elements in the present invention may be realized by one functional element.

  Moreover, the functional element may be arrange | positioned in the position physically separated. In this case, the functional elements may be connected by a network. It is also possible to realize functions or configure functional elements by grid computing or cloud computing.

DESCRIPTION OF SYMBOLS 1 Data reception part 2 Restoration matrix estimation part 3 Inverse estimation part 4 Output part 10 Ellipse about ER 11 ER local maximum 12 ER local minimum 13 Point where profit becomes the maximum 20 Ellipse about LT 21 LT local maximum 22 LT local minimum d Outflow (demand) m Inflow (production) speed EC cost ER gain (economic indicator)
LT Lead time (reliability index)
Q restoration matrix S strategy matrix

Claims (10)

A data reception unit and a restoration matrix estimation unit;
The data receiving unit is configured to receive observation data indicating a relationship between an inflow speed and an outflow speed, an economic index and a reliability index,
The restoration matrix estimation unit is configured to estimate a restoration matrix for matching the coordinate axes corresponding to the inflow speed and the outflow speed with the coordinate axes corresponding to the economic index and the reliability index. . In addition, it has an inverse estimator,
The said reverse estimation part becomes a structure which calculates the inflow speed and / or outflow speed based on the said restoration | reconstruction matrix and the designation | designated about the said economical efficiency parameter | index and a reliability parameter | index. Management support system. The restoration matrix is decomposed into at least a whitening matrix, a strategy matrix, and a unitary matrix,
The management support system according to claim 1, wherein the strategy matrix can be set to contents according to a user's desire. In addition, it has an output unit,
The output unit is configured to display the inflow speed and the outflow speed, and the economic index and the reliability index in a state where coordinate axes corresponding to the output index and the outflow speed coincide with each other. Management support system described in the section.   The management support system according to claim 1, wherein the economic index is data relating to profit.   The management support system according to claim 1, wherein the reliability index is data related to a lead time.   The management support system according to claim 1, wherein the outflow speed is calculated using POS data.   The management support system according to claim 1, wherein the inflow speed is calculated using POP data. A management support method executed using a device,
Receiving observation data indicating the relationship between the inflow speed and outflow speed and the economic index and reliability index;
A management support method comprising: estimating a restoration matrix for matching the coordinate axes corresponding to the inflow speed and the outflow speed with the coordinate axes corresponding to the economic index and the reliability index.   A computer program for causing a computer to execute each step according to claim 9.

Images