JP2000163380A - Computer and storage medium - Google Patents

Abstract

PROBLEM TO BE SOLVED: To visually confirm how critical an error is by displaying a graph of a function obtained by a function calculating means and displaying a symbol showing how critical an error calculated by an error calculating means on the graph. SOLUTION: A function calculating means on a CPU 2 obtains a function showing the correlation between two sets of numerals as elements and substitute the numeral representing the elements constituting one set and the elements constituting the other set in the obtained function and an error calculating means on the CPU 2 calculates an error. At a display part 4, the graph of the function obtained by the function calculating means is displayed and on the graph, a symbol showing how critical the error calculated by the error calculating means is displayed. Consequently, it is made possible to visually and easily confirm how critical the error is.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

The present invention relates to a computing device and a storage medium, and more particularly, to a computing device and a storage medium capable of calculating and analyzing an error between an actually measured value and a regression value in a regression calculation.

[0002]

2. Description of the Related Art Conventionally, software executed by a computer analyzes data obtained through experiments and the like, draws points indicated by the data on coordinates, and further displays straight lines and curves that best fit the data. One having a regression calculation function of calculating a function and drawing a graph thereof has been developed. In addition, a small computer having a function calculation function and a graph drawing function, which has a regression calculation function similar to the above-mentioned software, has been developed.

[0003] The regression calculation is a calculation in which, for two sets each having a plurality of elements, each element constituting each set is analyzed to obtain a function indicating the correlation between the sets.

In the conventional regression calculation function, when performing a regression calculation on a plurality of input statistical data, a user inputs a regression model formula (y = ax + b or the like) or a regression name (li).
ne regression), and using a least-squares method or the like based on the selected regression model formula or regression name, a function formula of a straight line or curve that best approximates it to multiple sets of statistical data (Hereinafter referred to as a regression formula).

[0005]

However, when performing a regression calculation in the conventional regression calculation function, if the user selects a non-optimal one from among a plurality of regression model equations or regression names, a regression equation is obtained. There was a problem that it was meaningless. Also, when performing regression calculations on data obtained by experiments on nature, etc.,
In the error between the measured value and the regression value obtained by regression calculation,
In many cases, important phenomena and providences in the natural world are included, and there has been a demand for the development of software having a function of calculating and analyzing an error between the actually measured value and the regression value.

An object of the present invention is to provide a calculation device and a storage medium capable of calculating and analyzing an error between an actually measured value and a regression value in a regression calculation and displaying the error in various display formats in detail. That is.

[0007]

The present invention has the following features in order to achieve the above object. Reference numerals and the like assigned to each element are reference numerals and the like in the drawings described later. According to the first aspect of the present invention, there is provided a function calculating means for obtaining a function indicating a correlation between two sets each having a plurality of numerical values as elements (2 in FIG. 1; step S11 in FIG. 2), and one of the two sets. Error calculating means for calculating an error between a numerical value indicating an element forming a set of the set and a numerical value calculated by substituting the elements forming the other set into a function obtained by the function calculating means (2 in FIG. 1) Step S20 in FIG.
2) display control means for displaying a graph of the function obtained by the function calculation means and displaying a symbol display indicating the magnitude of the error calculated by the error calculation means on the graph (FIG. 1) 4; (a) of FIG.
Step S206 in FIG. 3).

According to the first aspect of the invention, the function calculating means obtains a function indicating a correlation between two sets each having a plurality of numerical values as elements, and the error calculating means determines one of the two sets. Calculating an error between a numerical value indicating an element constituting the set and a numerical value calculated by substituting the element constituting the other set into the function obtained by the function calculating means, and the display control means comprises: In addition to displaying the graph of the function obtained by the above, a symbol display indicating the magnitude of the error calculated by the error calculating means is displayed on the graph.

A storage medium according to a seventh aspect of the present invention is a storage medium storing a program for calculating a function, wherein a computer for obtaining a function indicating a correlation between two sets each having a plurality of numerical values as elements is provided. Calculate an error between an executable program code, a numerical value indicating an element forming one of the two sets, and a numerical value calculated by substituting the element forming the other set into the obtained function. Computer-executable program code, and a computer-executable program code for displaying a graph of the obtained function and displaying a symbol indicating the magnitude of the calculated error on the graph. Are stored.

According to the present invention, the computer obtains a function indicating a correlation between two sets each having a plurality of numerical values by using the program code, and configures one of the two sets. The error between the numerical value indicating the element to be calculated and the numerical value calculated by substituting the elements constituting the other set into the obtained function is calculated, and a graph of the obtained function is displayed, and the calculated value is calculated on the graph. A symbol display indicating the magnitude of the error is displayed.

Accordingly, the display control means can display a symbol indicating the magnitude of the error calculated by the error calculating means on the graph of the function obtained by the function calculating means, so that the magnitude of the error can be reduced. It is possible to easily confirm it visually. For example, when an arrow is used as a symbol display, the magnitude and sign of the error can be easily recognized from the size and direction of the arrow.

Further, as in the invention according to claim 2, in the computing device according to claim 1, the display control means displays a list of errors calculated by the error calculation means (4 in FIG. 1; A configuration characterized in that step S208 in FIG. 3) is also possible.

According to the second aspect of the present invention, since the list of errors calculated by the error calculating means can be displayed by the display control means, the errors can be easily examined and analyzed, and As a result, it is possible to grasp the physical meaning of the actually measured value data.

According to a third aspect of the present invention, there is provided the computer apparatus according to the second aspect, wherein an error range defined by the magnitude of the absolute value of the error and a plurality of correspondences between an arbitrary color and an error range are set. The display control unit further includes a range color setting unit (2 in FIG. 1; steps S401 and S402 in FIG. 7). The display control unit sets the error range color setting when displaying a list of errors calculated by the error calculation unit. Each error is colored and displayed based on the correspondence between the error range and the color set by the means (4 in FIG. 1; step S4 in FIG. 7).
07).

According to the third aspect of the present invention, the error range color setting means sets a plurality of correspondences between the error range defined by the magnitude of the absolute value of the error and an arbitrary color. When displaying the list of errors calculated by the error calculation means, the display control means colors each error based on the correspondence between the error range and the color set by the error range color setting means. To display.

Therefore, when displaying the list of errors, the display control means displays each error with a color based on the correspondence between the error range and the color set by the error range color setting means. Therefore, the distribution of the magnitude of the error can be easily visually confirmed.

According to a fourth aspect of the present invention, there is provided a function calculating means for obtaining a function indicating a correlation between two sets each having a plurality of numerical values as elements (2 in FIG. 1; step S11 in FIG. 2); Error calculating means for calculating an error between a numerical value indicating an element constituting one of the sets and a numerical value calculated by substituting the elements constituting the other set into the function obtained by the function calculating means (FIG. 3; step S202); discrimination means for discriminating the minimum and maximum errors among the errors calculated by the error calculation means (2 in FIG. 1; steps S504 to S507 in FIG. 9); Display control means for displaying the expression of the determined function and displaying the minimum and maximum errors determined by the determination means (4 in FIG. 1; step S510 in FIG. 9);
It is characterized by having.

According to the fourth aspect of the invention, the function calculating means obtains a function indicating a correlation between two sets each having a plurality of numerical values as elements, and the error calculating means determines one of the two sets. And calculating a difference between a numerical value indicating an element constituting the set and a numerical value calculated by substituting the element forming the other set into the function obtained by the function calculating means. Of the error calculated by
The minimum and maximum errors are determined, and the display control means displays the function formula obtained by the function calculation means and displays the minimum and maximum errors determined by the determination means.

The storage medium according to claim 8 is a storage medium storing a program for calculating a function, wherein the computer for obtaining a function indicating a correlation between two sets each having a plurality of numerical values as elements is provided. Calculate an error between an executable program code, a numerical value indicating an element forming one of the two sets, and a numerical value calculated by substituting the element forming the other set into the obtained function. Computer-executable program code, a computer-executable program code for determining a minimum and a maximum error among calculated errors, and an expression of a determined function. And a computer-executable program code for displaying the calculated minimum and maximum errors.

According to the eighth aspect of the present invention, the computer obtains a function indicating a correlation between two sets each including a plurality of numerical values by using the program code, and forms one of the two sets. The error between the numerical value indicating the element to be performed and the numerical value calculated by substituting the elements constituting the other set into the obtained function is calculated, and the minimum and maximum errors among the calculated errors are determined and calculated. In addition to displaying the expression of the determined function, the determined minimum and maximum errors are displayed.

Therefore, the display control means can display the expression of the function obtained by the function calculating means and display the minimum and maximum errors determined by the determining means. For example, when performing a regression calculation, it is possible to determine whether or not an optimal regression model equation that minimizes the minimum and maximum errors has been selected, and as a result, it is possible to determine an optimal regression equation. Become.

According to a fifth aspect of the present invention, in the computing device of the fourth aspect, maximum and minimum color setting means (2 in FIG. 1) for setting a color to the minimum and maximum errors determined by the determination means, respectively. 11. The display control means further includes a step S601) of FIG. 11, wherein the display control means adds the color set by the maximum and minimum color setting means to the minimum and maximum errors among the errors calculated by the error calculation means. (4 in FIG. 1; Step S60 in FIG. 11)
3 and FIG. 12).

According to the fifth aspect of the present invention, the maximum and minimum color setting means sets colors for the minimum and maximum errors determined by the determination means, respectively, and the display control means sets the error calculation means. Of the error calculated by
A list of errors is displayed by adding the colors set by the maximum and minimum color setting means to the minimum and maximum errors.

Therefore, the display control means can display a list of errors by adding the color set by the maximum and minimum color setting means to the minimum and maximum errors among the errors calculated by the error calculation means. In addition, the minimum and maximum errors can be easily visually confirmed, and the examination and analysis of the errors can be efficiently performed. As a result, it is possible to grasp the physical meaning of the actually measured value data.

[0025] The invention described in claim 6 is the second invention.
5. The calculating device according to any one of 5), further comprising a percentage conversion means (2 in FIG. 1; steps S301 and S302 in FIG. 5) for converting the error calculated by the error calculation means into a percentage. The means is characterized by displaying the error as a percentage converted by the percentage conversion means (4 in FIG. 1).

According to the sixth aspect of the invention, the percentage conversion means converts the error calculated by the error calculation means into a percentage, and the display control means converts the error by the percentage conversion means. Display as a percentage.

Accordingly, the error can be displayed by the display control means in the percentage converted by the percentage conversion means, so that the error can be more clearly examined and analyzed.

DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, an embodiment of a computer 1 according to the present invention will be described in detail with reference to FIGS.

First, the configuration will be described. FIG. 1 is a block diagram showing the internal configuration of a computing device 1 to which the present invention has been applied.
In FIG. 1, a computing device 1 includes a CPU (Central P
processing unit) 2, input unit 3, display unit 4, display drive circuit 5, RAM (Random Access Memory) 6, ROM
(Read Only Memory) 7, storage device 8, and storage medium 9
It is constituted by.

The CPU 2 reads out a predetermined program from the ROM 7 or the storage medium 9 and temporarily stores it in the RAM 6 based on an instruction input through the input unit 3, executes various processes based on the program, and executes a computing device. Centralized control of each unit. That is, the CPU 2 executes various processing based on the read predetermined program, stores the processing results in the RAM 6, and causes the display unit 4 to display the processing results via the display driving circuit 5. The processing result is stored in the storage device 8 based on an instruction input via the input unit 3.
Via the storage medium 9.

In a regression error calculation process (see FIG. 2) described later, when an input for executing the error calculation is performed by the user, the CPU 2 first performs a regression process and performs an actual measurement previously input by the user. The X coordinate value (Xn) and the Y coordinate value (Yn ″) of the value data are stored in LIST1 and LIST2 of the LIST stored in the RAM 6, respectively. The Y coordinate value corresponding to the X coordinate value (Xn) of the data, that is, the regression data (Yn) is calculated, and it is determined whether or not the percentage calculation key of the input unit 3 is input. An error calculation process (see FIG. 3) is executed.

In the error calculation processing, the CPU 2 calculates an error (hereinafter referred to as Zn) between the Y coordinate value (Yn ″) of the actually measured value data and the regression data (Yn) for each actually measured value data.
It is stored and displayed in LIST3 of LIST stored in AM6.

When the percentage operation key is input,
The CPU 2 executes a percent calculation process (see FIG. 5). In the percent calculation process, the CPU 2 calculates an error (Zn) between the Y coordinate value (Yn ″) of the actually measured value data and the regression data (Yn) in each of the actually measured values. The ratio is calculated for each data, and the ratio of the error (Zn) to the Y coordinate value (Yn ") of the actually measured value data is calculated as a percentage.
Is stored in the LIST 3 of the LIST stored in the RAM 6 and displayed.

Next, the CPU 2 waits for input of various mode keys. Here, when the user inputs a color setting mode key, a maximum / minimum display key, or a maximum / minimum color setting mode key of the input section 3, the CPU 2 enters the CPU 2. Executes color display processing (see FIG. 7), maximum and minimum display processing (see FIG. 9), or maximum and minimum color display processing (see FIG. 11).

In the color display process, the CPU 2 first
A plurality of OVER values and colors are set, and then Zn or Zn ″ is sequentially read from LIST 3 and compared with each OVER value to determine which OVER value is exceeded.
The CPU 2 displays Zn or Zn ″ in a color set in accordance with the OVER value.

In the maximum / minimum display processing, the CPU 2
First, Zn or Zn "is sequentially read from LIST3, and the minimum and maximum Zn or Zn" are obtained. Next, the CPU 2
The minimum and maximum Zn or Zn ″ are stored in the RAM 6 and displayed together with the regression equation and a graph of the regression equation on the display unit 4.

In the maximum and minimum color display processing, the CPU 2
First, Zn or Zn ″ is sequentially read from LIST3, and the minimum and maximum Zn or Zn ″ are obtained and stored in the RAM 6. Next, the CPU 2 determines the minimum and maximum Zn or Zn ″.
Are set to different colors, and when displaying Zn or Zn ″, only the minimum and maximum Zn or Zn ″ are displayed in the set color.

The input unit 3 includes a character input key, a number input key, up / down / left / right keys, a LIST key, a percentage calculation key, a maximum / minimum display key, a maximum / minimum color setting mode key, a color setting mode key, and various function keys. And a pressing signal of the pressed key
Output to U2.

The display unit 4 is an LCD (Liquid Crystal D)
isplay) and performs various displays based on the drive signal input from the display drive circuit 5. Display drive circuit 5
Generates a drive signal based on display data and drawing data input from the CPU 2 and performs display control of the display unit 4.

The RAM 6 temporarily stores designated application programs, input instructions, input data, processing results, and the like, and also stores X-coordinate values (Xn) and Y-coordinate values (Yn ") of actual measurement data previously input by the user. ), Error (Z
n), and a LIST for storing the error (Zn) percentage (Zn ″) and the like.

The ROM 7 stores a basic program corresponding to the computer 1. That is, it stores an initial display menu program to be executed when the power of the computing device 1 is turned on, a basic program that does not need to be rewritten, such as various function operation programs, and an error operation processing program.
It stores a percentage calculation processing program, a color display processing program, a maximum / minimum display processing program, a maximum / minimum color display processing program, and the like.

The error calculation processing program, the percentage calculation processing program, the color display processing program, the maximum / minimum display processing program, the maximum / minimum color display processing program, and the like may be stored in the storage medium 9 in advance. .

The storage device 8 has a storage medium 9 for storing programs, data, and the like, and the storage medium 9 is constituted by a magnetic or optical storage medium or a semiconductor memory. The storage medium 9 is fixedly provided in the storage device 8 or is detachably mounted. The storage medium 9 is processed by various processing programs corresponding to the computing device 1 and each processing program. Data and the like are stored.

The program, data, and the like stored in the storage medium 9 may be configured to be received and stored from another device connected via a communication line or the like. The storage medium 9 is stored in another connected device.
May be provided so that programs, data, and the like stored in the storage medium 9 are used via a communication line.

Next, the operation will be described. FIG. 2 is a flowchart showing the flow of the regression error calculation process executed by the CPU 2.

In FIG. 2, the CPU 2 first determines whether or not an input for executing an error calculation has been made by the user (step S10). If the input has not been made (step S10: NO), a normal operation is performed. The process proceeds to the regression calculation process, and when input is made (step S10: YES),
A regression process is performed (Step S11). The regression process is a process of analyzing, with respect to two sets each including a plurality of numerical values, each element constituting each set and performing a calculation for obtaining a function indicating a correlation between the sets. Here, the X coordinate value (Xn) of the actually measured value data input in advance by the user
And the Y coordinate value (Yn ″) are stored in the LIST stored in the RAM 6.
These are stored in LIST1 and LIST2, respectively. For example, if the measured data is (1, 0.7), (2.44, 7.45), (4.65, 7.5)
If given in 1), LIST1 contains "1", "2.4
4 "and" 4.65 "are stored, and" 0.7 "," 7.
45 "and" 7.51 "are stored.

Next, the CPU 2 calculates a Y coordinate value corresponding to the X coordinate value (Xn) of the actually measured value data in the regression formula calculated by the regression processing, that is, regression data (Yn) (step S12). Then, the CPU 2 controls the input unit 3
Is determined (step S13), and if not entered (step S13).
13: NO), and execute an error calculation process (see FIG. 3) (step S20). In the error calculation processing, the CPU 2
Indicates the Y coordinate value (Yn ″) of the measured value data and the regression data (Y
n) and the error (Zn) is calculated for each actual measurement value data.
It is stored and displayed in LIST3 of LIST stored in M6.

In step S13, when the percentage calculation key is input (step S13: YES),
The CPU 2 executes a percentage calculation process (see FIG. 5) (step S30). In the percent operation,
The CPU 2 calculates an error (Zn) between the Y coordinate value (Yn ") of the actually measured value data and the regression data (Yn) for each actually measured value data, and further calculates the error (Zn) for the Y coordinate value (Yn") of the actually measured value data. Calculate the percentage of error (Zn) as a percentage (Zn ″),
It is stored in LIST3 of LIST stored in RAM 6 and displayed.

Next, the CPU 2 waits for input of various mode keys (step S14). Here, the user sets the color setting mode key, maximum / minimum display key,
Or, when the maximum / minimum color setting mode key is input, the CP
U2 is a color display process (see FIG. 7) (step S40),
Maximum and minimum display processing (see FIG. 9) (step S50) or maximum and minimum color display processing (see FIG. 11) (step S6)
Perform 0).

In the color display processing of step S40, C
The PU 2 first sets a plurality of OVER values and colors. This OVER value is the value of Zn stored in LIST3 or
This is a value used as a reference for setting a color when displaying the Zn ″ with a color. When the absolute value of Zn or Zn ″ is larger than any one of a plurality of OVER values, Zn
Alternatively, Zn "is displayed in a color corresponding to the corresponding OVER value. Next, the CPU 2 reads Zn or Zn" from LIST3.
Are sequentially read and compared with each OVER value,
It is determined whether the value exceeds the R value. Then, the CPU 2
Alternatively, Zn "is displayed in a color set corresponding to the corresponding OVER value.

In the maximum / minimum display processing in step S50, the CPU 2 first reads Zn or Zn "sequentially from LIST3, and obtains the minimum and maximum Zn or Zn". Next, the CPU 2 stores the minimum and maximum Zn or Zn ″ in the RAM.
6 and are displayed together with the regression formula and a graph of the regression formula on the display unit 4.

In the maximum / minimum color display processing in step S60, the CPU 2 first reads Zn or Zn ″ sequentially from LIST3, finds the minimum and maximum Zn or Zn ″,
Store it in M6. Next, the CPU 2 determines the minimum and maximum
Different colors are set for Zn or Zn ″, and when displaying Zn or Zn ″, only the minimum and maximum Zn or Zn ″ are displayed in the set color.

FIG. 3 is a flowchart showing the flow of the error calculation process executed by the CPU 2. In FIG. 3, first, the CPU 2 compares the Y coordinate value (Yn ″) of the actually measured value data input by the user in advance with step S in FIG.
The regression data (Yn) calculated in step 11 is sequentially read from the RAM 6 (step S201), and "(Yn")-
(Yn) → Zn ”to calculate Zn (Step S2)
02).

Next, the CPU 2 determines whether all Zn have been calculated (step S203). If not all Zn has been calculated (step S203: NO), the CPU 2 returns to step S201 and returns to step S201. Is calculated (step S203: YES), all Zn are stored in LIST3 of the RAM 6 (step S204). Then, the CPU 2
Regression formula data, graph drawing data, and error display data are generated (step S205), and the display driving circuit 5 is generated.
To display the regression formula data, display the graph based on the graph drawing data, and further calculate the Y coordinate value (Yn ″) of the actually measured value data and the regression data (Yn) based on the error display data. The error is displayed on the display unit 4 using an arrow (step S206).

Then, the CPU 2 determines whether or not the LIST key of the input section 3 has been input (step S207), and if it has been input (step S207: YES), the RAM 2
Xn, Y stored in LIST1-3 of LIST stored in 6
n ″ and Zn are listed on the display unit 4 (step S2).
08). If not input (step S207: N
O) or after the processing of step S208 is completed, the CPU
2 ends a series of error calculation processing.

FIG. 4 is a diagram showing an example of a display screen of the display unit 4 in the above-described error calculation processing. (A) shows a display example of a regression formula, a regression graph, and an error display obtained by regression processing and error calculation processing, and (b) shows a RAM.
6 shows a list of X-coordinate values (Xn), Y-coordinate values (Yn ″), and Zn of the actually measured value data stored in LIST1 to LIST3.

As shown in FIG. 9A, after the regression processing, when the error calculation processing is performed, the calculated regression equation K is expressed as “Y
= Ax + b; a = + 2.5033, b = -1.8204 "and the graph G1 of the regression equation K is drawn.
Here, the error between the actually measured value data “□” and the regression data “●” is displayed using “→” of the error display GH.

Thereafter, when the LIST key is input by the user, as shown in FIG.
X coordinate value (Xn), Y of the actual measurement value data stored in
The coordinate value (Yn ″) and Zn are respectively associated with each LI
A list is displayed for each ST. For example, Xn “2.44” stored in LIST1 corresponds to Yn “7.45” stored in LIST2 and Zn “+2.16” stored in LIST3.

FIG. 5 is a flowchart showing the flow of the percentage calculation process executed by the CPU 2. FIG.
First, the CPU 2 converts the Y coordinate value (Yn ″) of the actually measured value data input by the user in advance and the regression data (Yn) calculated in step S11 of FIG.
Read sequentially from M6 (step S301),
“[((Yn ″) − (Yn)) / (Yn ″)] × 100 → Z
By calculation of n "", the Y coordinate value (Yn ") of the actually measured value data
Zn ″ indicating the percentage of error (Zn) with respect to
Is calculated (step S302).

Next, the CPU 2 determines whether or not all Zn "have been calculated (step S303). If not all Zn" has been calculated (step S303: NO), the CPU 2 returns to step S301. Have been calculated (step S303: YES), all Zn ″ s are stored in the RAM 6.
(Step S304). And C
The PU 2 generates regression formula data, graph drawing data, and error display data (step S305), outputs the data to the display drive circuit 5, displays the input regression formula data, and is based on the graph drawing data. A graph is displayed, and an error between the Y coordinate value (Yn ″) of the actually measured value data and the regression data (Yn) is displayed on the display unit 4 using an arrow based on the error display data (step S306).

Then, the CPU 2 determines whether or not the LIST key of the input section 3 has been input (step S307). If the LIST key has been input (step S307: YES), the RAM 2
Xn, Y stored in LIST1-3 of LIST stored in 6
n "and Zn" are displayed in a list on the display unit 4 (step S
308). If not input (step S307:
NO), or after the process of step S308 ends, the CP
U2 ends a series of percent operation processing.

FIG. 6 is a diagram showing an example of the display screen of the display unit 4 in the above-described percentage calculation processing. (A) shows a display example of a regression formula, a regression graph, and an error display obtained by a regression process and a percentage calculation process,
(B) shows a list of X-coordinate values (Xn), Y-coordinate values (Yn "), and Zn" of the actually measured value data stored in LIST1 to LIST3 of the RAM 6.

As shown in FIG. 11A, after the regression processing, when the percentage calculation processing is performed, the calculated regression equation K
"Y = ax + b; a = + 2.5033, b = -1.8204" and the graph G1 of the regression equation K is drawn. Here, the measured value data “□” and the regression data “●”
Is displayed using “→” in the error display GH.

Thereafter, when the LIST key is input by the user, as shown in FIG.
X coordinate value (Xn), Y of the actual measurement value data stored in
The coordinate value (Yn ″) and Zn ″ are respectively associated with each other.
A list is displayed for each LIST. For example, Xn “2.44” stored in LIST1 becomes Yn “7.45” stored in LIST2.
And Zn ″ “+42.42” stored in LIST3.

FIG. 7 is a flowchart showing the flow of the color display process executed by the CPU 2. In FIG. 7, first, the CPU 2 waits for the user to input a plurality of OVER values and a plurality of colors corresponding to the OVER values (steps S401, S402).

Next, the CPU 2 sequentially reads out Zn or Zn ″ from LIST 3 of the RAM 6 (step S403),
In step S401, it is compared with each OVER value input by the user to determine which OVER value has been exceeded. Then, the CPU 2 specifies the color set corresponding to the corresponding OVER value in the read Zn or Zn ″ (step S404).
Determines whether all Zn or Zn ″ has been read (step S405), if not read (step S405: NO), returns to step S403, if read (step S405: YES), the user Waits for the input of the LIST key of the input unit 3 by the user (step S
406).

When the LIST key is input, the CPU 2
Xn stored in LIST1-3 of LIST stored in AM6,
A list of Yn "and Zn or Zn" is displayed on the display unit 4 (step S407). Here, of Zn or Zn ″ stored in LIST3, Zn or Zn ″ exceeding the OVER value preset by the user is displayed on the display unit 4 in a color set in accordance with the OVER value. You. After that, CPU2
Ends a series of color display processing.

FIG. 8 is a diagram showing an example of a display screen of the display unit 4 in the above-described color display processing. (A) shows each OVER in steps S401 and S402 of the color display processing.
(B) shows the X coordinate value (Xn), the Y coordinate value (Yn ″), and the Y coordinate value (Yn ″) of the actually measured value data stored in LIST 1 to 3 of the RAM 6. Zn ″
Is displayed in a list.

As shown in FIG. 9A, in the setting display screen for the OVER value and the color corresponding to the OVER value, 4
OVER values such as 0% and 60%, GREEN and BLUE
Are displayed in association with each other.

Thereafter, when the LIST key is input by the user, as shown in FIG.
X coordinate value (Xn), Y of the actual measurement value data stored in
The coordinate value (Yn ″) and Zn ″ are respectively associated with each other.
A list is displayed for each LIST. In the display list of LIST3, Z
Since n ″ “+42.42” exceeds the OVER value of 40%, it is displayed with a GREEN color border. Similarly, Zn ″ “− 32.49” is displayed with a border of BLUE color since the absolute value exceeds the OVER value of 20%.

FIG. 9 is a flowchart showing the flow of the maximum / minimum display processing executed by the CPU 2. In FIG. 9, first, the CPU 2 converts one Zn or Zn ″ into RA
Read from LIST stored in M6 (step S50)
1), a variable U indicating the maximum error and a variable V indicating the minimum error
(Step S502). Then, CPU2
Is to sequentially read Zn or Zn "from the LIST stored in the RAM 6 (step S503), and Zn or Zn"
It is determined whether or not the value is greater than (step S504). If it is larger (step S504: YES), the CPU 2
Updates the value of the variable U by substituting Zn or Zn ″ for the variable U (step S505). If the value is not larger (step S504: NO), it is determined whether or not Zn or Zn ″ is smaller than the variable V. Is determined (step S506). If it is smaller (step S506: YES), the CPU 2 substitutes Zn or Zn ″ for the variable V and updates the value of the variable V (step S507).

If Zn or Zn ″ is not smaller than the variable V in step S506 (step S506: N
O), after the processing of step S507 and the processing of step S505 are completed, the CPU 2
It is determined whether or not Zn "has been read from the LIST (step S508). If not all Zn or Zn" has been read (step S508: NO), the CPU 2 returns to step S503 and returns all Zn or Zn ". Is read (step S508: YES), the regression formula data
Graph drawing data, error display data, and maximum / minimum error data are generated (step S509). Here, the data substituted into the variables U and V are regarded as data indicating the maximum and minimum errors. Then, the CPU 2 outputs the respective data to the display drive circuit 5, and causes the display unit 4 to display the regression formula data and the maximum / minimum error data.
Display a graph based on the graph drawing data.
Based on the error display data, the Y coordinate value (Y
n ″) and the regression data (Yn) are displayed using arrows (see FIG. 10) (step S510).
The CPU 2 ends the series of maximum / minimum display processing.

FIG. 10 is a diagram showing a display example of the obtained regression formula, regression graph, error display, and the maximum and minimum errors obtained by the maximum and minimum display processing. (A) shows a display example when the maximum and minimum errors are obtained by a maximum and minimum display process from among the errors (Zn) obtained by the error arithmetic process, and (b) shows the error of the error obtained by the percent arithmetic process. From the percentage percentage (Zn ″),
9 shows a display example when a maximum and minimum error is obtained by a maximum and minimum display process.

In FIG. 9A, the calculated regression equation K is “Y = ax + b; a = + 2.5033, b = −1.8204”.
Is displayed, and among the errors (Zn) obtained by the error calculation processing, the largest Zn “+2.16” and the smallest Zn “−”
2.29 "is displayed. Also, a graph G1 of the regression equation K
Is drawn, and the error between the actually measured value data “□” and the regression data “●” is displayed using “→” of the error display GH.

In FIG. 13B, “Y = ax + b; a = + 2.5033, b = −1.8204” in the calculated regression equation K.
Is displayed, and among the percentages (Zn ") of the error ratios obtained by the percent operation processing, the largest Zn""+42.42%" and the smallest Zn "" -30.49% "are displayed. Also, a graph G1 of the regression equation K is drawn,
The error between the actually measured value data “□” and the regression data “●” is displayed using “→” of the error display GH.

FIG. 11 is a flowchart showing the flow of the maximum and minimum color display processing executed by the CPU 2. 11, first, the CPU 2 executes steps S501 to S508 of the above-described maximum / minimum display processing (FIG. 9).
Is performed. After that, the CPU 2 sets the color set by the user in advance to the variable U indicating the maximum error and the variable V indicating the minimum error (step S601). When the LIST key is input (step S602), C
The PU 2 displays a list of Xn, Yn ″, and Zn or Zn ″ stored in LISTs 1 to 3 of the LIST stored in the RAM 6 on the display unit 4 (step S603). Where the variables U and V
Zn or Zn ″ indicating the maximum and minimum errors assigned to
It is displayed on the display unit 4 in a color preset by the user. After that, the CPU 2 ends the series of maximum / minimum color display processing.

FIG. 12 is a diagram showing an example of the display screen of the display unit 4 in the above-described maximum and minimum color display processing. (A)
Shows a display example in which the maximum and minimum colors are obtained by the maximum and minimum color display processing from among the errors (Zn) obtained by the error calculation processing, and (b) shows the error of the error obtained by the percentage calculation processing. 5 shows a display example in the case where the maximum and minimum colors are obtained by the maximum / minimum color display processing.

In FIG. 11A, the user sets LI
When the ST key is input, the X coordinate value (Xn) and the Y coordinate value (Y
n ″) and the error (Zn) are associated with each LIS
A list is displayed for each T. Here, assuming that the colors of GREEN and BLUE are respectively set in advance to the maximum and minimum Zn by the user, as shown in FIG.
Of the Zn stored in LIST3, Zn “+2.16” is the largest Zn
Therefore, it is displayed with a border of GREEN.
Also, since Zn “−2.29” is the minimum Zn, BLUE
It is displayed with a border of the color.

In FIG. 8B, when the LIST key is input by the user, the X coordinate value (Xn) and the Y coordinate value (Yn ″) of the actually measured value data stored in LIST 1 to 3 of the RAM 6 are displayed. ) And Zn ″ are associated with each LIST
A list is displayed for each. Here, assuming that the color of GREEN and the color of BLUE are respectively set to the maximum and minimum Zn ″ by the user in advance, as shown in FIG.
Of the Zn "stored in LIST3, Zn""+42.42" is the largest Zn ", so it is displayed with a border of GREEN, and Zn""-30.49" is the smallest Zn. ”, It is displayed with a border in the color of BLUE.

In FIG. 8B and FIG. 12,
Zn “+2.16” and Zn ″ “+42.42” are shaded in light black, and Zn “−2.29” and Zn ″ “-30.49” are shaded in dark black. Although it appears to be displayed, it is actually displayed in the color of GREEN or BLUE.

As described above, the CPU 2 first performs a regression process in a regression error calculation process described later.
The X-coordinate value (Xn) and the Y-coordinate value (Yn ″) of the actually measured data previously input by the user are stored in a LIST, and regression data (Yn) in a regression formula calculated by a regression process is calculated. If the percentage calculation key has not been input, the CPU 2 executes an error calculation process and
U2 calculates an error (Zn) between the Y coordinate value (Yn ″) of the actually measured value data and the regression data (Yn) for each actually measured value data, and calculates LI
Stored in ST and displayed. When the percentage calculation key is input, the CPU 2 executes a percentage calculation process and calculates an error (Zn) between the Y coordinate value (Yn ″) of the actually measured value data and the regression data (Yn) for each actually measured value data. Then, the ratio of the error (Zn) to the Y coordinate value (Yn ″) of the actually measured value data is calculated as a percentage (Zn ″).
And display it.

Next, the CPU 2 waits for input of various mode keys. Here, when the color setting mode key, the maximum / minimum display key, or the maximum / minimum color setting mode key is input, the CPU 2 executes the color display processing, Execute the maximum / minimum display processing or the maximum / minimum color display processing. In the color display processing, the CPU 2 causes a plurality of OVER values and color settings to be performed,
From the LIST, Zn or Zn ″ is sequentially read, and compared with each OVER value.
A list of Zn or Zn ″ stored in the ST is displayed. In the maximum / minimum display process, the CPU 2 reads Zn or Zn from the LIST.
n ″ are sequentially read out, the minimum and maximum Zn or Zn ″ are obtained and stored in LIST, and a regression equation and a graph of the regression equation are displayed and displayed. In the maximum / minimum color display processing, the CPU 2 reads out Zn or Zn ″ sequentially from the LIST, obtains the minimum and maximum Zn or Zn ″,
When the Zn or Zn ″ stored in the LIST is displayed in a list by setting different colors, only the minimum and maximum Zn or Zn ″ are displayed in the set color.

Therefore, according to the calculation device 1 in the present embodiment, the error (Zn) between the regression data (Yn) and the actually measured value data (Yn ″) obtained by the regression calculation, and the actually measured value data (Yn ″) ), The percentage (Zn ″) of the ratio of the error (Zn) is stored in the LIST, and the list can be displayed in a different color depending on the degree of exceeding the range set by the user in advance. The size can be visually checked and examined, the physical meaning of the measured value data can be grasped, and the regression formula obtained by regression calculation and a graph of the regression formula are displayed. Together with the maximum and minimum error (Zn) or the percentage (Zn ″) of the percentage of the error (Zn), the user can perform multiple regression model equations or regression when performing the regression calculation. It is possible to judge whether or not the optimal regression model equation has been selected from the names, and this helps to obtain the optimal regression equation.

In this embodiment, FIG.
As shown in FIGS. 6 and 10, the error between the actually measured value data “□” and the regression data “●” is displayed using “→” of the error display GH, but “⇒”, “⇔”, etc. May be displayed using other symbols.

[0084]

According to the first and seventh aspects of the present invention, the display control means displays a symbol indicating the magnitude of the error calculated by the error calculation means on the graph of the function obtained by the function calculation means. Can be displayed,
The magnitude of the error can be easily visually confirmed. For example, when an arrow is used as a symbol display, the magnitude and sign of the error can be easily recognized from the size and direction of the arrow.

According to the second aspect of the present invention, in addition to the effect of the first aspect, the list of errors calculated by the error calculating means can be displayed by the display control means, so that the display control means can easily display the list of errors. The error can be examined and analyzed, and as a result, the physical meaning of the actually measured value data can be grasped.

According to the third aspect of the present invention, in addition to the effect of the second aspect, the display control means, when displaying the error list, displays the error set by the error range color setting means. Since each error can be colored and displayed based on the correspondence between the range and the color, the distribution of the magnitude of the error can be easily visually confirmed.

According to the fourth and eighth aspects of the present invention, the display control means displays the expression of the function obtained by the function calculating means and displays the minimum and maximum errors determined by the determining means. Can be
As an example of the function calculating means, for example, when performing a regression calculation, it can be determined whether or not an optimal regression model equation that minimizes the minimum and maximum errors has been selected. Can be obtained.

According to the fifth aspect of the present invention, in addition to the effect of the fourth aspect, the display control means sets the minimum and maximum errors among the minimum and maximum errors among the errors calculated by the error calculation means. Since a list of errors can be displayed with the color set by the setting means, the minimum and maximum errors can be easily confirmed visually, and the error can be examined and analyzed efficiently. . As a result, it is possible to grasp the physical meaning of the actually measured value data.

According to the sixth aspect of the present invention,
In addition to the effect of the invention described in any one of the fifth to fifth aspects, the display control means can display the error as a percentage converted by the percentage conversion means.
It is possible to examine and analyze errors more clearly.

[Brief description of the drawings]

FIG. 1 is a block diagram showing an internal configuration of a computing device 1 to which the present invention has been applied.

FIG. 2 is a flowchart illustrating a flow of a regression error calculation process for obtaining an error between measured data and regression data.

FIG. 3 is a flowchart illustrating a flow of an error calculation process.

4A and 4B are diagrams illustrating an example of a display screen of a display unit 4 in the error calculation process of FIG. 3; FIG. 4A is a table of a regression formula, a regression graph, and an error display obtained by the regression process and the error calculation process; (B) shows LIST1 to LIST1 of the RAM 6.
3 shows a list of X-coordinate values (Xn), Y-coordinate values (Yn ″), and Zn of the actually measured value data stored in No.3.

FIG. 5 is a flowchart illustrating a flow of a percentage calculation process.

6A and 6B are diagrams illustrating an example of a display screen of a display unit 4 in the percentage calculation processing of FIG. 5; FIG. 6A is a table of a regression formula, a regression graph, and an error display obtained by the regression processing and the percentage calculation processing; (B) is a RAM
6 shows a list of X-coordinate values (Xn), Y-coordinate values (Yn ″), and Zn ″ of the actually measured value data stored in LIST1 to LIST3.

FIG. 7 is a flowchart illustrating a flow of a color display process.

8A and 8B are diagrams illustrating an example of a display screen of the display unit 4 in the color display processing of FIG. 7; FIG. 8A illustrates each OVER value and the OV in steps S401 and S402 of the color display processing;
FIG. 4B shows how a color corresponding to the ER value is set. FIG. 5B shows the X coordinate value (Xn), Y coordinate value (Yn ″), and Zn ″ of the actually measured value data stored in LIST1 to LIST3 of the RAM 6. This shows a list display.

FIG. 9 is a flowchart showing the flow of a maximum / minimum display process.

10 is a diagram showing a display example of the obtained regression formula, regression graph, error display, and the maximum and minimum errors obtained by the maximum and minimum display processing of FIG. 9; FIG. A display example in which the maximum / minimum error is obtained by the maximum / minimum display processing (FIG. 9) from the errors obtained by 3) is shown, and FIG. 5B is a percentage calculation processing (FIG. 5).
10 shows a display example in the case where the maximum / minimum error is obtained by the maximum / minimum display processing (FIG. 9) from the errors obtained by the above.

FIG. 11 is a flowchart illustrating a flow of a maximum / minimum color display process.

12 is a diagram illustrating an example of a display screen of the display unit 4 in the maximum and minimum color display processing of FIG.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Computing apparatus 2 CPU 3 Input part 4 Display part 5 Display drive circuit 6 RAM 7 ROM 8 Storage device 9 Storage medium

Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI Theme coat II (Reference) G09G 5/36 510 G06F 15/336 F term (Reference) 5B019 EA02 EA04 HG01 HG15 HG19 HG21 5B056 AA00 BB23 BB64 BB66 BB95 FF03 FF05H 5C082 AA22 BA12 BA16 BA27 BA34 BB14 CA12 CA81 CB06 DA86 DA87 MM05 MM06 MM10

Claims (8)

[Claims] A function calculating means for obtaining a function indicating a correlation between two sets each having a plurality of numerical values as an element; a numerical value indicating an element constituting one of the two sets; Error calculating means for calculating an error from a numerical value calculated by substituting constituent elements into a function obtained by the function calculating means; and displaying a graph of the function obtained by the function calculating means, And a display control means for displaying a symbol display indicating the magnitude of the error calculated by the error calculation means. 2. The calculation device according to claim 1, wherein said display control means displays a list of errors calculated by said error calculation means. 3. An error range color setting means for setting a plurality of correspondences between an error range defined by the magnitude of the absolute value of the error and an arbitrary color, wherein the display control means includes the error calculating means. When displaying a list of errors calculated by the method, each error is colored and displayed based on the correspondence between the error range and the color set by the error range color setting means. Item 3. The computing device according to Item 2. 4. A function calculating means for obtaining a function indicating a correlation between two sets each having a plurality of numerical values as elements, a numerical value indicating an element constituting one of the two sets, and Error calculating means for calculating an error from a numerical value calculated by substituting the constituent elements into a function obtained by the function calculating means; and discriminating minimum and maximum errors among the errors calculated by the error calculating means. And a display control means for displaying the equation of the function obtained by the function calculating means and displaying the minimum and maximum errors determined by the determining means. . 5. The image processing apparatus according to claim 1, further comprising a maximum / minimum color setting unit configured to set a color to each of the minimum and maximum errors determined by the determination unit, wherein the display control unit includes: 5. The calculation apparatus according to claim 4, wherein a color list set by said maximum and minimum color setting means is added to the minimum and maximum errors to display a list of errors. 6. The apparatus according to claim 1, further comprising a percentage conversion means for converting the error calculated by said error calculation means into a percentage, wherein said display control means displays the error in a percentage converted by said percentage conversion means. The computing device according to claim 2. 7. A storage medium storing a program for calculating a function, comprising: a computer-executable program code for obtaining a function indicating a correlation between two sets each including a plurality of numerical values; A computer-executable program for calculating an error between a numerical value indicating an element forming one of the sets and a numerical value calculated by substituting the elements forming the other set into the obtained function A program including a code and a computer-executable program code for displaying a graph of the obtained function and displaying a symbol indicating the magnitude of the calculated error on the graph. A storage medium characterized by the above-mentioned. 8. A storage medium storing a program for calculating a function, comprising: a computer-executable program code for obtaining a function indicating a correlation between two sets each having a plurality of numerical values as elements; A computer-executable program for calculating an error between a numerical value indicating an element forming one of the sets and a numerical value calculated by substituting the elements forming the other set into the obtained function A code, a computer-executable program code for determining the minimum and maximum errors among the calculated errors, and an expression of the obtained function are displayed, and the determined minimum and maximum errors are calculated. A storage medium storing a program including: a computer-executable program code for displaying the program;