WO2018168193A1 - 業務改善支援装置および業務改善支援方法 - Google Patents

業務改善支援装置および業務改善支援方法 Download PDF

Info

Publication number
WO2018168193A1
WO2018168193A1 PCT/JP2018/001532 JP2018001532W WO2018168193A1 WO 2018168193 A1 WO2018168193 A1 WO 2018168193A1 JP 2018001532 W JP2018001532 W JP 2018001532W WO 2018168193 A1 WO2018168193 A1 WO 2018168193A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
business
business data
group
improvement support
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2018/001532
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
泰介 高柳
浩仁 矢野
健一郎 岡田
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hitachi Ltd
Original Assignee
Hitachi Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hitachi Ltd filed Critical Hitachi Ltd
Priority to US16/332,178 priority Critical patent/US20190265679A1/en
Priority to EP18767101.1A priority patent/EP3499437A4/en
Publication of WO2018168193A1 publication Critical patent/WO2018168193A1/ja
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Program-control systems
    • G05B19/02—Program-control systems electric
    • G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/20—Administration of product repair or maintenance
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Z—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR
    • G16Z99/00—Subject matter not provided for in other main groups of this subclass
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Definitions

  • the present invention relates to a business improvement support apparatus and a business improvement support method.
  • a railway business management system is composed of 100 or more subsystems (see Non-Patent Document 1).
  • a causal structure model in which a causal relationship between business data is expressed by a directed graph is useful for extracting the business that is the key to KPI improvement.
  • linear multiple regression analysis is often used when estimating the above-mentioned causal structure model from a large amount of data.
  • a regression equation of Y is calculated by using data Y corresponding to KPI as an objective variable and other data X1, X2,... Xn as explanatory variables.
  • the explanatory variable included in the regression equation is used as a new objective variable, and the multiple regression analysis is sequentially repeated to estimate the causal structure model of the entire data.
  • linear multiple regression analysis is a technique for quantitatively analyzing the correlation between Y and X1, X2,..., Xn, and it is inherently difficult to automatically estimate the causal relationship. This is because in the linear multiple regression analysis, the regression equation of the objective variable Y is expressed by a linear combination of explanatory variables.
  • JP 2006-65598 A Japanese Unexamined Patent Publication No. 2016-31714 Japanese Patent Laid-Open No. 5-233011
  • the regression equation of Y shows various nonlinearities with respect to the explanatory variables.
  • non-linearity include time integration in addition to time differentiation of explanatory variables.
  • the square of the explanatory variable and the product of the explanatory variables are representative.
  • the square root of the explanatory variable is hardly seen empirically. In such a case, in the data analysis using the linear multiple regression, it is considered difficult to estimate the accurate regression equation even if the conventional technique (eg, the method shown in Patent Document 2) is applied.
  • an object of the present invention is to provide a technique that can easily and accurately estimate causal relationships between predetermined data in consideration of nonlinearity between the data.
  • the business improvement support apparatus of the present invention that solves the above problem is an apparatus that estimates a causal structure model between business data based on predetermined business data, calculates a nonlinear value for the business data, and A nonlinear term addition unit that adds a value to the business data, a multiple regression analysis unit that calculates a regression equation for each of the business data by linear multiple regression, and the presence or absence of a linear term in the calculated regression equation is determined.
  • Data group setting unit for setting predetermined data constituting a term and objective variable of regression equation to the same group, and explanatory variable candidate selection for selecting business data excluding the predetermined data as explanatory variable candidates for linear multiple regression analysis And a section.
  • a business improvement support device that estimates a causal structure model between business data based on predetermined business data calculates a nonlinear value for the business data, and calculates the nonlinear value. Processing to add to the business data, processing to calculate a regression equation for each of the business data by linear multiple regression, determination of the presence or absence of a linear term in the calculated regression equation, and regression with predetermined data constituting the linear term A process of setting the objective variable of the formula in the same group and a process of selecting business data excluding the predetermined data as explanatory variable candidates for linear multiple regression analysis are executed.
  • the causal relationship between predetermined data can be estimated with high accuracy and easily in consideration of the non-linearity between the data.
  • FIG. 1A is a network configuration diagram including the business improvement support apparatus 100 of the present embodiment.
  • the work improvement support apparatus 100 shown in FIG. 1 is a computer apparatus that can easily and accurately estimate causal relationships between predetermined data in consideration of nonlinearity between the data.
  • the business improvement support apparatus 100 illustrated in FIG. 1A is connected to a database (hereinafter referred to as a business management system) 20 that stores business data 5 via a predetermined network 1 so as to be communicable.
  • the business management system 20 collects business data 4 in a social infrastructure system including a plurality of subsystems 30 and manages it as a business data group 5.
  • An example of the business data group 5 and the business data 4 constituting the business data group 5 in the first embodiment is shown in FIG. 1B.
  • the business data group 5 is an aggregate of a plurality of types of business data 4 obtained from each subsystem 30.
  • the business management system 20 is connected to each subsystem 30, and collects and records the business data 4 held in each subsystem 30.
  • the business improvement support apparatus 100 may include the configuration and functions of the business management system 20 described above.
  • the business improvement support apparatus 100 includes a storage device 101 configured by an SSD, a hard disk drive, or a memory, a processor 103 such as a CPU that reads and executes the program 102 from the storage device 101, and the processing results of the processor 103.
  • the hardware configuration includes a display device 104 such as a display to display, an input interface 105 such as a keyboard and a mouse that accepts instructions from the user, and a communication device 106 that accesses the network 1 and executes communication processing. ing. These are connected to each other by internal wiring such as a bus.
  • the business improvement support apparatus 100 described above implements each functional unit shown in FIG. 1C by executing the program 102 in the processor 103.
  • the information acquisition unit 110 acquires the business data group 5 from the business management system 20 in response to an instruction from the operator received through the input interface 105, and performs all business operations.
  • the list information of the data 4 is displayed on the display device 104, and the operator selects the business data 4 as KPI data from the business data 4 indicated in the list information.
  • Related business data is automatically extracted by a predetermined algorithm and stored in the storage device 101.
  • the nonlinear term adding unit 111 calculates a nonlinear value for each business data in the business data group 5 obtained from the business management system 20 and adds the nonlinear value to the business data group 5 described above.
  • the business data group 5 referred to here is a collection of various business data 4 obtained from each subsystem 30.
  • the multiple regression analysis unit 112 calculates a regression equation for each of the business data 4 included in the business data group 5 by linear multiple regression. Specific contents of this calculation will be described later.
  • the data group setting unit 113 determines the presence or absence of a linear term in the regression equation calculated by the multiple regression analysis unit 112 described above, and sets the predetermined data constituting the linear term and the objective variable of the regression equation in the same group. It is to set.
  • the explanatory variable candidate selection unit 114 selects the business data 4 excluding the above-described predetermined data handled by the data group setting unit 113 as an explanatory variable candidate for linear multiple regression analysis.
  • the correlation coefficient calculation unit 115 calculates a correlation coefficient for one or more combinations of the business data 4 described above.
  • the data group setting unit 113 sets business data in which the correlation coefficient calculated by the correlation coefficient calculation unit 115 exceeds a preset threshold value in the same group.
  • the explanatory variable candidate selection unit 114 selects arbitrary business data 4 one by one from each of the groups including the business data whose correlation coefficient exceeds the preset threshold as the explanatory variable candidates for the linear multiple regression analysis. Will be.
  • the data distance setting unit 116 sets the distance between the business data for each of the business data 4.
  • the explanatory variable candidate selection unit 114 selects the business data 4 having a distance longer than the objective variable as an explanatory variable candidate for linear multiple regression analysis.
  • the data distance setting unit 116 may determine the distance between the business data 4 based on the structure of the data table such as the ER diagram of each of the various business data 4.
  • the data distance setting unit 116 may include a similar word table 1161 in which keyword groups that are determined to be similar or identical to each other are described for each group.
  • the data distance setting unit 116 in this case includes a keyword determination unit 1162 that determines whether the name of the business data 4 includes the keyword described in the similar word table 1161, and a keyword that is determined to be included in the business data 4 by this determination.
  • a data classifying unit 1163 for classifying the business data 4 for each affiliation table, and the distance between the business data 4 is determined based on the result of the classification.
  • the group information display unit 117 displays a business model belonging to the same group set by the data group setting unit 113 for each business data 4 in the user interface for displaying the estimated causal structure model on the display device 104.
  • the information of data 4 is displayed.
  • the group information display unit 117 described above displays the information of the business data 4 belonging to the same group as described above for each of the business data 4 and replaces the selected business data 4 with other information belonging to the group. It is preferable to accept user instructions for selecting the business data 4 as the selection target.
  • the group information display unit 117 described above corresponds to one selected business data 4 in the causal structure model when displaying the information of the business data 4 belonging to the same group as described above for each business data 4. It is also preferable that the nodes and the nodes corresponding to the other business data 4 belonging to the group are displayed together.
  • the group information display unit 117 described above displays predetermined instruction means (for example, a user interface) output from the display device 104 when displaying the information of the business data 4 belonging to the same group as described above for each business data 4. : A cursor or the like) may display a node corresponding to another business data 4 belonging to the group when the node corresponding to the selected one business data 4 approaches a predetermined distance range. .
  • predetermined instruction means for example, a user interface
  • the group information display unit 117 described above displays the selected business data 4 in the causal structure model.
  • the corresponding node and the node corresponding to the other business data 4 belonging to the group are displayed together, and the node corresponding to the other business data 4 described above corresponds to the one selected business data 4 described above.
  • the above selection is performed. It is also preferable to select the above-described other business data 4 in place of one business data.
  • the group information display unit 117 described above may display, in a predetermined form, a node corresponding to the other business data 4 directly connected at the edge in the causal structure model with respect to the predetermined business data 4 received the user instruction. Is preferred.
  • the above-described group information display unit 117 displays the estimated causal structure model
  • a regression equation related to the corresponding business data 4 between the nodes corresponding to each business data 4 in the causal structure model is displayed. It is preferable to further arrange nodes indicating information.
  • FIG. 2 is a diagram showing a flow example 1 of the business improvement support method in the present embodiment. Here, a series of flows relating to the automatic estimation of the causal structure model is shown, and the processing of the work improvement support apparatus 100 in the first embodiment of the present invention will be described.
  • the operator of the business improvement support apparatus 100 starts a predetermined program in the business improvement support apparatus 100, analyzes the causal relationship between the business data 4 in the business data group 5, and contributes to the improvement of the predetermined KPI. I am trying to extract business and plan appropriate business improvement measures. At this time, it is assumed that the information acquisition unit 110 of the business improvement support device 100 displays a predetermined screen on the display device 104.
  • the information acquisition unit 110 of the business improvement support apparatus 100 acquires the business data group 5 from the business management system 20 in response to the above-described pressing, and displays the list information of all the business data 4 on the display device 104 (step 201). ).
  • the above-mentioned operator browses the list information of the business data 4 on the display device 104, operates the input interface 105, and selects each of the business data 4 indicated by the list information from the KPI (Railway Maintenance Example). In this case, one item (hereinafter referred to as KPI data) to be a maintenance cost is selected.
  • the information acquisition unit 110 of the business improvement support device 100 receives the selection content of the KPI data by the above-described operator (step 202).
  • the information acquisition unit 110 of the business improvement support apparatus 100 that has received the selection of KPI data by the operator, from all the business data 4 obtained in step 201, business data related to the KPI data ( Hereinafter, related data) is automatically extracted by a predetermined algorithm and stored in the storage device 101 (step 203).
  • the information acquisition unit 110 may correct and process the related data automatically extracted as described above into a data format suitable for later-described analysis.
  • business data 4 recorded in the same table can be assumed as relevant business data, that is, related data.
  • different tables for example, a table storing work data for track maintenance costs and a table storing work data for the number of workers
  • a common key for example, data acquisition date and time.
  • Business data 4 can also be assumed.
  • business data 4 obtained by the same subsystem 30 can be assumed.
  • n pieces of related data (X1, X2, X3,... Xn) are extracted from the business management system 20.
  • the nonlinear term adding unit 111 of the business improvement support apparatus 100 calculates a nonlinear value X ′ for the related data (step 204).
  • the following data square is considered as an example of the nonlinear value. ----- (Formula 1)
  • the nonlinear term adding unit 111 stores the calculated nonlinear value X ′ in the storage device 101 as new related data (Xn + 1,... Xm).
  • the related data Xi indicates a nonlinear value of the original data extracted from the business management system 20.
  • the square of data (Formula 1) is taken as an example of the above-described nonlinear value, but an arbitrary nonlinear value may be calculated according to the social infrastructure of interest and added to the related data. For example, as another example of the nonlinear value, a product of the following two data can be considered. ----- (Formula 2)
  • a predetermined button for example, a causal structure model estimation start button
  • the work improvement support apparatus 100 starts estimating the causal structure model related to the above-described KPI data.
  • the business improvement support apparatus 100 uses the above-mentioned KPI data as the target variable Y and the predetermined number of related data (X1, X2, X3,... Xn,... Xm) as explanatory variable candidates, for example, in the storage device 101.
  • FIG. 3 shows a detailed method for selecting explanatory variable candidates in step 205 described above.
  • the business improvement support apparatus 100 correlation coefficient calculation unit 115 performs a single regression analysis between the related data (X1, X2, X3,... Xm) with a combination of all the related data (step 301). ).
  • the data group setting unit 113 groups related data groups having a correlation coefficient obtained by the above-described single regression analysis that are a certain level or more as the same collinearity group (step 302).
  • the explanatory variable candidate selection unit 114 arbitrarily selects one related data for each group obtained in step 302 described above, and stores information in the storage device 101 as an explanatory variable candidate.
  • the explanatory variable candidate selection unit 114 records the information of the related data not selected here in the storage device 101 as a collinearity group associated with each explanatory variable candidate (step 3). In the example of FIG. 3, information that “Xm” and “Xi + 1” are included in the collinearity group of “X1” is recorded in the storage device 101.
  • the multiple regression analysis unit 112 of the business improvement support apparatus 100 performs multiple regression analysis on each of the related data described above (step 206), and calculates a regression equation of the objective variable Y (step 207).
  • the regression equation of the objective variable Y is expressed by the following Equation 4.
  • aA, aB, and aC are coefficients of each explanatory variable, and C is a constant.
  • the right side is defined as the cause and the left side is defined as the result. ----- (Formula 4)
  • the business improvement support device 100 determines whether or not the regression equation calculated in step 207 described above satisfies a preset completion condition (step 208).
  • step 208: No when the corresponding regression equation does not satisfy the completion condition (eg, related data preset by the operator is extracted as an explanatory variable) (step 208: No), the work improvement support apparatus 100 , Explanatory variables XA, XB, and XC are set as new objective variables Y, and related data (X1, X2, X3,... Xn, except for the objective variables themselves) are used as explanatory variable candidates.
  • Each regression equation is estimated by linear multiple regression analysis (step 205). As described above, the multiple regression analysis is sequentially repeated to automatically estimate the entire causal structure model related to the KPI data.
  • the business improvement support device 100 ends the multiple regression analysis of the business data, and thus the estimated causal structure model (that is, , The regression equation of each data) is stored in the storage device 101 (step 209), and the process is terminated.
  • the regression equation of the objective variable Y is represented by a linear combination of explanatory variables. Therefore, even if the true causal relationship is expressed by the following expression 5 (that is, the right side XA is the result because of Y on the right side), if the data Y is calculated as the objective variable, the expression 4 is derived. Is done. In other words, it is possible to evaluate the correlation, but automatic causal estimation is difficult. ----- (Formula 5)
  • Equation 4 is expressed by Equation 6 below. ----- (Formula 6)
  • Equation 7 shown below is obtained. ----- (Formula 7)
  • Equation 7 includes the square root and takes a form that is not empirically found in business management of social infrastructure. Further, even if the business improvement support apparatus 100 is used, the formula 7 cannot be derived by the linear multiple regression analysis (the business improvement support apparatus 100 can derive only the formula 6 by the linear multiple regression analysis). That is, the work improvement support apparatus 100 can uniquely specify the causal relationship between the objective variable Y and the explanatory variables Xa, Xb, and Xc. Therefore, in the first embodiment, the causal relationship between data can be automatically estimated accurately. In the first embodiment, since the nonlinear regression equation can be calculated based on the linear multiple regression analysis in this way, a causal structure model between business data can be estimated with high accuracy and easily.
  • step 206 in the flow of FIG. 2 will be described below using the flow of FIG.
  • the multiple regression analysis unit 112 of the business improvement support apparatus 100 performs multiple regression analysis using the explanatory variable candidates set in step 205 (step 401), and calculates a temporary regression equation of the objective variable Y. (Step 402).
  • the variable increase / decrease method is adopted as an algorithm for the multiple regression analysis, but it is not dependent only on the algorithm.
  • the data group setting unit 113 of the business improvement support device 100 determines whether or not a linear term is included in the provisional regression equation (step 403).
  • the data group setting unit 113 sets the objective variable Y and the explanatory variable (equation 8) constituting the linear term.
  • Xa is defined as the same causal group
  • Xi is removed from the explanatory variable candidates (step 404), and the process transitions to step 401.
  • the data group setting unit 113 stores the history of the data removed in step 404 in the storage device 101 as a causal group of the objective variable Y (step 405).
  • the data group setting unit 113 stores the history of the data removed in step 404 in the storage device 101 as a causal group of the objective variable Y (step 405).
  • Equation 8 information that Xa is included in the causal group of Y is recorded in the storage device 101.
  • Equation 10 is finally derived as a regression equation of the objective variable Y by linear multiple regression. ----- (Formula 10)
  • Xd and Xe are original data (X1,... Xd,... Xe,... Xn) extracted from the business management system 20.
  • the inverse function of Equation 10 includes a square root on the right side (cause) for any explanatory variable, and takes a form that is not empirically found in business management of social infrastructure. Even if the business improvement support apparatus 100 is used, the inverse function of Equation 10 cannot be derived by linear multiple regression analysis. In the business improvement support apparatus 100, only Equation 10 can be derived by linear multiple regression analysis. Therefore, although the derived regression equation (Equation 10) does not include information of the data Xi, the business improvement support device 100 can automatically and correctly estimate the causal relationship between the data.
  • the business improvement support device 100 determines the presence or absence of a linear term in the regression equation obtained by the linear multiple regression analysis.
  • the objective variable Y and the explanatory variable that constitutes the linear term are defined as the same causal group, and the explanatory variable is removed from the explanatory variable candidates.
  • the regression equation of the objective variable Y not including the linear term is derived by sequentially repeating the reselection of the explanatory variable candidates and the multiple regression analysis.
  • the business improvement support apparatus 100 automatically automatically corrects the causal relationship between the data. Can be estimated.
  • the business improvement support apparatus 100 displays the estimated causal structure model on the display device 104 based on the information stored in the storage device 101. Become.
  • the business improvement support device 100 displays the entire causal structure model on the display device 104 by tracing the causal relationship in reverse by using the KPI data as a starting point.
  • FIG. 5 shows a display example of the causal structure model 601.
  • each vertex 602 represents the business data 4 used in the multiple regression analysis described above.
  • data that is in a causal relationship with each business data 4 (that is, the relationship between the objective variable and the explanatory variable) is connected by a symbol 603 (edge) such as an arrow.
  • the direction of the arrow 603 indicates the direction from the explanatory variable (cause) to the objective variable (result).
  • the business improvement support apparatus 100 uses the business data 4 corresponding to each vertex 602 based on information stored in the storage device 101 in association with each business data 4. Can be displayed. Further, the business improvement support apparatus 100 can display a corresponding regression equation coefficient 604 in the vicinity of each arrow 603.
  • the group information display unit 117 of the business improvement support apparatus 100 displays the details 605 of the business data 4 based on the information stored in the storage device 101 in association with the business data 4 selected by the operator. Displayed together with the display column of the model 601.
  • the details 605 of the data include a business data name 606 indicating the business data 4 selected by the operator, and a display 607 of the regression equation. Further, the regression equation display 607 includes a coefficient display 608 and an explanatory variable display 609.
  • the above-mentioned operator can extract the key job most dominant in determining the KPI by confirming the displayed causal structure model 601 and the regression equation 607 for each job data (for example, the value of the coefficient 604). Because a large explanatory variable can be determined to have a large effect on the KPI, it is possible to determine that the business corresponding to the explanatory variable, that is, business data, is a key business).
  • the business improvement support apparatus 100 uses the data details 605 described above to store business data belonging to the same causal group based on information stored in the storage device 101 in association with the business data 4 selected by the operator. A list 610 is displayed. Further, the business improvement support apparatus 100 displays a list 611 of business data belonging to the same collinearity group in the data details 605.
  • the display form of the data details 605 is not limited to the example shown in FIG. 5, and a form that is written in the vicinity of each vertex 602 or a form that displays a list on a separate screen using a tab or the like is adopted. Also good.
  • examples of such other display modes will be described with reference to the drawings.
  • causal structure model 601 of FIG. 6 when the operator selects an arbitrary vertex 602 in the causal structure model 601 using the input interface 105, the causal group display 610 and the collinear group display 611 are clearly displayed in a pop-up 612. Display form.
  • the business improvement support apparatus 100 that has received this selection operation replaces the data with the vertex 602 and the causal structure. Addition of data to the model 601 is executed.
  • causal structure model 601 of FIG. 6 only the causal group display 610 and the collinear group display 611 are displayed in the pop-up 612, but are stored in the storage device 101 in association with the selected business data 4. Based on the information, all of the detailed data display 605 shown in FIG. 5 may be displayed on the pop-up 613. Thus, since detailed information is not displayed when the operator does not select the vertex 602, the causal structure model 601 can be displayed large on the same screen, and the causal structure model 601 can be easily understood. Can do.
  • the causal structure model 601 in FIG. 7 has a display form in which business data (hereinafter referred to as group data) 701 belonging to the same causal group and collinearity group is written around each vertex 602.
  • group data business data
  • the group data 701 and each vertex 602 are distinguished by color and size, but the present invention is not necessarily limited to this.
  • the business improvement support apparatus 100 writes all or part of the group data 701 around the apex 602, so that an operator who views this data is assumed to need correction. It is possible to confirm at a glance the location to be done.
  • the business improvement support apparatus 100 displays detailed information such as the name of the data in a pop-up 702.
  • the operator can select replacement of data with the vertex 602 or addition of data to the causal structure model 601 from the pop-up 702.
  • FIG. 8 shows an operation example related to a similar example of the display form shown in FIG. In this case, similarly to the case of FIG. 7, the business improvement support apparatus 100 shows a process of writing the group data 701 around each vertex 602.
  • the group information display unit 117 of the business improvement support device 100 has a predetermined distance range 805 in which a cursor 804 operated by the operator via the input interface 105 is located around any vertex 602. Is determined every predetermined time. In normal times, that is, when the cursor 804 operated by the operator via the input interface 105 is away from a certain vertex 602 (step 801), the group information display unit 117 of the business improvement support device 100 displays Without changing the form, each vertex 602 is displayed as usual, and nothing is written around each vertex 602.
  • the group information display unit 117 of the business improvement support device 100 displays the group data 701 around the vertex 602. It is displayed (step 802).
  • the group information display unit 117 of the business improvement support apparatus 100 displays detailed information such as the name of the data in the pop-up 702 as in FIG. .
  • the operator selects replacement of the vertex 602 with the vertex of other business data of the corresponding group or addition of data to the causal structure model 601. Can do. If the business improvement support apparatus 100 generates a complicated causal structure model 601 with a large amount of business data 4, the display becomes complicated if group data 701 is always displayed around each vertex 602 as shown in FIG. . In this case, there is a possibility that the operator may not understand the causal structure model 601.
  • the group data 701 is not displayed on the screen at normal times, so that the operator can easily understand the complicated causal structure model 601. In addition, the operator can easily confirm a place where correction is considered necessary.
  • the color of the group data 701 is changed based on which of the causal group and the collinearity group to support the understanding of the operator, but this is not necessarily limited thereto. It is not a thing.
  • FIG. 9 illustrates an intuitive operation regarding the replacement of data between the vertex 602 and the group data 701 and the addition of the group data 701 to the causal structure model 601 in the display example of the group data 701 illustrated in FIGS. 7 and 8. An example of the enabling steps is shown.
  • the step of exchanging data between the vertex 602 and the group data 701 will be described. It is assumed that the operator operates the cursor 804 via the input interface 105, selects and drags the group data 701 written in the vicinity of the vertex 602, and drops it on the vertex 602.
  • the group information display unit 117 of the business improvement support apparatus 100 detects this operation event (step 901), and exchanges the group data 701 and the vertex 602 selected by the operator (step 902).
  • the causal structure model 601 requires adjustment of the causal structure around the exchanged vertex 602. That is, the operator needs to adjust the regression equation having the replaced vertex 602 as the objective variable and the coefficient of the regression equation having the vertex 602 as the explanatory variable.
  • an adjustment method there are a method in which an operator determines a coefficient and inputs it through the input interface 105, and a method in which the coefficient is updated using the multiple regression analysis function (step 401) of the business improvement support apparatus 100. .
  • step 903 determines whether the distance between the group data 701 selected by the operator and the vertex 602 has reached a preset value, and sets the distance to a preset value. When it reaches, the line 905 visually connecting the vertex 602 and the group data 701 is cut, and the selected group data 701 is added to the causal structure model 601.
  • the causal structure model 601 needs to adjust the causal structure around the added vertex 602. That is, the operator sets the explanatory variable of the added vertex 602 and the objective variable having the vertex 602 as the explanatory variable. Further, the operator adjusts the regression equation having the added vertex 602 as an objective variable and the coefficient of the regression equation having the vertex 602 as an explanatory variable.
  • an adjustment method there are a method in which an operator determines a coefficient and inputs it through the input interface 105, and a method in which the coefficient is updated using the multiple regression analysis function (step 401) of the business improvement support apparatus 100. .
  • the causal structure model 601 can be easily corrected by a more intuitive operation.
  • the group information display unit 117 of the business improvement support apparatus 100 uses the vertex 602 and the edge 604 for the vertex 602 that is the target of the cursor 1004 by the operator's operation. Display control may be performed in which information is clearly indicated only for other vertexes 602 directly connected, that is, at least one of an objective variable and an explanatory variable.
  • the vertices 602 and the edges 604 only the explicit ones are displayed as solid lines, and the others are displayed as broken lines.
  • the causal structure model 601 emphasizes only the explanatory relationship and the objective variable for the vertex 602 (node) selected by the operator, that is, the explanatory variable and the objective variable for the vertex 602. In this case, the visibility of the complicated causal structure model 601 is improved.
  • the group information display unit 117 uses the relationship between the vertices 602, that is, the information on the regression equation that defines the corresponding data, as the new vertices 650. Display control arranged between them may be performed.
  • a causal structure model is automatically obtained by linear multiple regression analysis even when time precedence information between business data is not clear by using a non-linear relationship between business data. It can be estimated.
  • the business data and the other business data (explanatory variable) that make up the linear term are the same.
  • an accurate causal structure model can be automatically estimated by linear multiple regression analysis.
  • by clearly indicating to the operator other business data belonging to the same causal group as the business data concerned it is possible to easily and more accurately correct the automatically estimated causal structure model by focusing on only a limited number of data. Can be updated.
  • the operator analyzes the causal relationship between the business data 4 accumulated by the business management system 20, extracts key business that contributes to the improvement of KPI, and attempts to formulate appropriate business improvement measures.
  • the information acquisition unit 110 of the business improvement support device 100 acquires all the business data 4 stored in the business management system 20, and displays the list information on the display device 104 (step 201).
  • the above-mentioned operator selects one piece of data (hereinafter referred to as KPI data) that becomes KPI (maintenance costs, etc., taking railroad maintenance as an example) from the displayed list of business data 4.
  • KPI data one piece of data
  • the information acquisition unit 110 of the business improvement support apparatus 100 accepts selection of KPI data (step 202).
  • the information acquisition unit 110 of the business improvement support apparatus 100 performs a business related to the KPI data from all the business data 4 stored in the business management system 20.
  • Data (hereinafter referred to as related data) is automatically extracted by a predetermined algorithm and stored in the storage device 101 (step 203).
  • n pieces of related data (X1, X2, X3,... Xn) are extracted from the business management system 20.
  • step 203 the data distance setting unit 116 of the business improvement support apparatus 100 according to the second embodiment calculates a distance (data distance) from the KPI data for each related data, and stores it in the storage device 101.
  • FIG. 12 shows an ER diagram of the business data 4 accumulated by the business management system 20.
  • the business data 4 is stored in a plurality of data tables.
  • the business improvement support apparatus 100 according to the second embodiment has a distance “1” for related data included in the same data table (table 1) as the KPI data, and a table (for example, date and time) that is common to the table 1 (for example, date and time).
  • the related data included in the table 2) is defined as the distance “2”
  • the related data included in the table (table 3) including the key common to the table 2 is defined as the distance “3”, and the like.
  • step 204 is the same as that in the first embodiment, description thereof is omitted.
  • the business improvement support device 100 sets KPI data as the objective variable Y and related data (X1, X2, X3,... Xn,... Xm) as explanatory variable candidates, as in the first embodiment. (Step 205).
  • the work improvement support apparatus 100 in this step 205 executes a single regression analysis between related data (X1, X2, X3,... Xm) with a combination of all the related data (Ste 301), data groups having a correlation coefficient equal to or greater than a certain value are grouped as the same collinearity group (step 302). Furthermore, the business improvement support apparatus 100 arbitrarily selects one data for each group and adds it to the explanatory variable candidates. Further, the business improvement support apparatus 100 records the data not selected above in the storage device 101 as a collinearity group associated with each explanatory variable candidate (step 303).
  • the explanatory variable candidate selection unit 114 of the business improvement support device 100 uses the distance information of each data stored in the storage device 101 as an explanatory variable candidate for data having a distance shorter than the distance of the objective variable Y. Remove from. That is, it can be the cause of the objective variable Y (estimated that the distance is long and the relevance to the KPI data is low), but not the result (estimated that the distance is short and the relevance to the KPI data is high). , Remove the estimated data.
  • the business improvement support apparatus 100 uses only business data that can cause the objective variable Y as explanatory variable candidates for linear multiple regression analysis. Therefore, steps 403, 404 and 405 shown in FIG. 4 are not necessary, and a causal structure graph can be automatically extracted in a shorter time. Further, it is possible to reduce the trouble of correcting / updating the causal structure graph by the operator.
  • Third embodiment In the third embodiment, a technique is shown in which the causal relationship between the business data 4 accumulated by the business management system 20 can be easily estimated with high accuracy based on the name of the business data 4.
  • the apparatus configuration and the like of the business improvement support apparatus 100 in the third embodiment are the same as those in the first embodiment, and a description thereof will be omitted.
  • the explanatory variable candidate selection unit 114 of the business improvement support apparatus 100 in the third embodiment is based on the distance information of each data stored in the storage device 101 in step 205 shown in the flow of FIG.
  • the data having a distance shorter than the distance of the objective variable Y is removed from the explanatory variable candidates.
  • the distance of the related data from the KPI data is defined based on the data table structure of the business management system 20, but in the third embodiment, the distance of the data is determined based on the name of the data. Define.
  • FIG. 13 shows an example of a registration screen 1100 for the similar word table 1161.
  • the operator creates a similar word table 1161 using the input interface 105 on the registration screen 1100 and presses a registration button 1110 to perform a registration operation on the business improvement support apparatus 100.
  • the work improvement support apparatus 100 stores the similar word table 1161 in the storage device 101.
  • the operator performs an operation for adding the keyword 1103 determined to be similar or homogeneous to each keyword group 1102.
  • the operator can also add and create a new group by pressing a new group creation button 1111.
  • the operator sets the distance between the groups by selecting an appropriate interface such as a pull-down menu 1115 or 1116, for example. Taking FIG. 13 as an example, the operator sets the distance between group 1 and group 2 and group 1 and group 3 to “2” and “3”, respectively.
  • the operator analyzes the causal relationship between the business data 4 accumulated by the business management system 20 to extract key business for KPI improvement and to plan appropriate business improvement measures.
  • the information acquisition unit 110 of the business improvement support device 100 acquires information on all the business data 4 stored in the business management system 20, and displays the list information on the display device 104 (step 201).
  • the above-mentioned operator browses the list information of the business data on the display device 104, and data (hereinafter referred to as KPI data) serving as KPI (maintenance costs, etc. in the case of railway maintenance) from the list. Select one.
  • KPI data serving as KPI (maintenance costs, etc. in the case of railway maintenance) from the list. Select one.
  • the information acquisition unit 110 of the business improvement support apparatus 100 accepts this selection (step 202).
  • the information acquisition unit 110 of the business improvement support apparatus 100 selects a business related to the KPI data from all the business data 4 stored in the business management system 20.
  • Data (hereinafter referred to as related data) is automatically extracted by a predetermined algorithm and stored in the storage device 101 (step 203).
  • n pieces of related data (X1, X2, X3,... Xn) are extracted from the business management system 20.
  • step 203 the data distance setting unit 116 of the business improvement support apparatus 100 calculates a distance (data distance) from the KPI data for each related data 4, and stores this value in the storage device 101. Save to.
  • the keyword determination unit 1162 of the business improvement support device 100 determines which keyword 1103 of the similar word table 1161 is included in the names (column names) of the KPI data and each related data using natural language processing or the like. .
  • the data classification unit 1163 of the business improvement support apparatus 100 classifies related data for each group 1102 to which the corresponding keyword 1103 belongs.
  • the data classification unit 1163 of the business improvement support apparatus 100 sets the related data belonging to the same keyword group 1102 as the KPI data as the distance “1”, the related data belonging to the keyword group 1102 as the distance “2” as the distance “2”, and the distance “ Assume that the related data belonging to the keyword group 1102 of “3” is the distance “3”.
  • Step 204 is the same as that in the first embodiment, and a description thereof will be omitted.
  • the explanatory variable candidate selection unit 114 of the business improvement support device 100 converts the KPI data into the objective variable Y and the related data (X1, X2, X3,... Xn,... Xm ) As an explanatory variable candidate.
  • Step 205 As shown in FIG. 3, in step 205 described above, the explanatory variable candidate selection unit 114 of the business improvement support device 100 performs a single regression analysis between the related data (X1, X2, X3,... Xm). Then, the process is executed with a combination of all the related data (step 301), and data groups having a correlation coefficient equal to or larger than a certain value are grouped as the same collinearity group (step 302).
  • the explanatory variable candidate selection unit 114 arbitrarily selects one data for each group and removes the rest from the explanatory variable candidates.
  • the explanatory variable candidate selection unit 114 records the unselected data in the storage device 101 as a collinearity group associated with each explanatory variable candidate (step 303).
  • the explanatory variable candidate selection unit 114 of the business improvement support device 100 converts the related data having a distance shorter than the distance of the objective variable Y based on the distance information about each related data stored in the storage device 101 into the explanatory variable. Remove from the candidate. That is, it can be the cause of the objective variable Y (estimated that the distance is long and the relevance to the KPI data is low), but not the result (estimated that the distance is short and the relevance to the KPI data is high). , Remove the relevant data estimated.
  • the business improvement support apparatus 100 in the third embodiment uses only business data that can cause the objective variable Y as explanatory variable candidates for linear multiple regression analysis. Therefore, steps 403, 404 and 405 shown in FIG. 4 are not necessary, and a causal structure graph can be automatically extracted in a shorter time. Further, it is possible to reduce the trouble of correcting / updating the causal structure graph by the operator.
  • the steps 403, 404 and 405 shown in FIG. 4 are not necessary, and the causal structure graph can be obtained in a shorter time. Can be automatically extracted. Further, it is possible to reduce the trouble of correcting and updating the causal structure graph by the operator.
  • the causal relationship between the predetermined data can be estimated with high accuracy and easily in consideration of the non-linearity between the data.
  • a group information display unit that displays information on the business data belonging to the same group for each of the business data It may be provided with.
  • a user such as a person in charge of business improvement can confirm the grouped data on the user interface as described above, and can perform predetermined work such as selection of explanatory variables with appropriate accuracy. .
  • the business improvement support apparatus further includes a correlation coefficient calculation unit that calculates a correlation coefficient with respect to one or more combinations of the business data, and the data group setting unit includes the calculated correlation coefficient.
  • Business data exceeding the preset threshold value are set in the same group, and the explanatory variable candidate selection unit is a business variable whose correlation coefficient exceeds the preset threshold value as an explanatory variable candidate for the linear multiple regression analysis.
  • Arbitrary business data is selected one by one from each group including data, and the group information display unit of the user interface displays information on business data belonging to the same group for each of the business data. It is good also as what is displayed.
  • the information can be included in the group and presented to the user, and can be determined by the user.
  • the business improvement support device further includes a data distance setting unit that sets a distance between the business data between the business data, and the explanatory variable candidate selection unit is longer than the objective variable.
  • Business data having a distance may be selected as explanatory variable candidates for the linear multiple regression analysis.
  • the data distance setting unit may determine the distance between the business data based on the data table structure of the business data.
  • the data distance setting unit includes a similar word table in which a group of keywords determined to be similar or identical to each other is described for each group, and the name of the business data.
  • a keyword determination unit that determines whether or not a keyword described in a similar word table is included, and a data classification unit that classifies the business data for each keyword affiliation table that is determined to be included in the business data by the determination The distance between each piece of business data may be determined based on the classification result.
  • the group information display unit displays information on business data belonging to the same group for each of the business data, and replaces the selected single business data.
  • the user instruction for selecting other business data belonging to the group may be accepted.
  • the group information display unit displays the selected 1 in the causal structure model when displaying the business data information belonging to the same group for each of the business data. Nodes corresponding to one business data and nodes corresponding to other business data belonging to the group may be displayed together.
  • the group information display unit displays predetermined business information in the user interface when displaying business data information belonging to the same group for each of the business data.
  • a node corresponding to another business data belonging to the group may be displayed.
  • the group information display unit displays the selected 1 in the causal structure model when displaying the business data information belonging to the same group for each of the business data.
  • a node corresponding to one business data and a node corresponding to another business data belonging to the group are displayed together, and a node corresponding to the other business data corresponds to the selected one business data.
  • the selected one business data is replaced.
  • the other business data may be the target of the selection.
  • the group information display unit predetermines a node corresponding to other business data directly connected by an edge in the causal structure model with respect to the predetermined business data received by the user. It may be displayed in a form.
  • the group information display unit displays the estimated causal structure model
  • a corresponding work is performed between nodes corresponding to the work data in the causal structure model.
  • a node indicating information on the regression equation between the data may be further arranged.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • Quality & Reliability (AREA)
  • Theoretical Computer Science (AREA)
  • Marketing (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Operations Research (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Manufacturing & Machinery (AREA)
  • Automation & Control Theory (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
PCT/JP2018/001532 2017-03-17 2018-01-19 業務改善支援装置および業務改善支援方法 Ceased WO2018168193A1 (ja)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US16/332,178 US20190265679A1 (en) 2017-03-17 2018-01-19 Work Improvement Support Device and Work Improvement Support Method
EP18767101.1A EP3499437A4 (en) 2017-03-17 2018-01-19 COMMERCIAL IMPROVEMENT ASSISTANCE DEVICE AND COMMERCIAL IMPROVEMENT ASSISTANCE METHOD

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2017-052115 2017-03-17
JP2017052115A JP6723946B2 (ja) 2017-03-17 2017-03-17 業務改善支援装置および業務改善支援方法

Publications (1)

Publication Number Publication Date
WO2018168193A1 true WO2018168193A1 (ja) 2018-09-20

Family

ID=63523434

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2018/001532 Ceased WO2018168193A1 (ja) 2017-03-17 2018-01-19 業務改善支援装置および業務改善支援方法

Country Status (4)

Country Link
US (1) US20190265679A1 (https=)
EP (1) EP3499437A4 (https=)
JP (1) JP6723946B2 (https=)
WO (1) WO2018168193A1 (https=)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2025004302A1 (ja) * 2023-06-30 2025-01-02 日本電気株式会社 情報処理装置、表示制御方法、および表示制御プログラム
WO2025004299A1 (ja) * 2023-06-30 2025-01-02 日本電気株式会社 情報処理装置、表示制御方法、および表示制御プログラム

Families Citing this family (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7107386B2 (ja) * 2018-11-27 2022-07-27 日本電気株式会社 情報処理装置
EP3683745A1 (en) * 2019-01-18 2020-07-22 Verint Americas Inc. Iva performance dashboard and interactive model and method
JP7267964B2 (ja) * 2019-03-14 2023-05-02 アクタピオ，インコーポレイテッド 生成装置、生成方法および生成プログラム
JP7313887B2 (ja) * 2019-04-23 2023-07-25 株式会社日立製作所 保全改善支援システム
KR102282982B1 (ko) * 2019-07-04 2021-07-27 연세대학교 산학협력단 다층모형 인터페이스 제공 장치 및 방법
EP4094202A1 (en) * 2020-01-23 2022-11-30 Umnai Limited Encoding and transmission of knowledge, data and rules for explainable ai
JP7333284B2 (ja) 2020-03-16 2023-08-24 株式会社日立製作所 保守支援システム及び保守支援方法
JP7519316B2 (ja) * 2021-02-25 2024-07-19 株式会社日立製作所 運転管理支援装置及び運転管理支援方法
JP7700624B2 (ja) * 2021-10-22 2025-07-01 住友金属鉱山株式会社 予測モデルの作成方法、操業プロセスの条件設定方法
JP7449982B2 (ja) * 2022-07-05 2024-03-14 株式会社日立製作所 施策策定支援システム、施策策定支援方法、および、施策策定支援プログラム
JP2024061314A (ja) * 2022-10-21 2024-05-07 株式会社日立製作所 業務施策評価装置、および、業務施策評価方法
JP2024167641A (ja) * 2023-05-22 2024-12-04 株式会社日立製作所 輸送計画管理装置及び輸送計画管理方法
WO2025104786A1 (ja) * 2023-11-13 2025-05-22 株式会社日立製作所 計算機システム及びデータ分析の支援方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH05233011A (ja) * 1992-02-18 1993-09-10 Nippon Telegr & Teleph Corp <Ntt> 独立要因抽出法
JP2006065598A (ja) * 2004-08-27 2006-03-09 Hitachi Ltd 生産管理システム
JP2015052862A (ja) * 2013-09-06 2015-03-19 株式会社東芝 生産管理装置および生産管理プログラム
JP2016031714A (ja) * 2014-07-30 2016-03-07 日本電信電話株式会社 重回帰分析装置および重回帰分析方法
WO2016079972A1 (ja) * 2014-11-19 2016-05-26 日本電気株式会社 要因分析装置、要因分析方法と記録媒体、及び、要因分析システム

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5108116B2 (ja) * 2009-01-14 2012-12-26 株式会社日立製作所 装置異常監視方法及びシステム

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH05233011A (ja) * 1992-02-18 1993-09-10 Nippon Telegr & Teleph Corp <Ntt> 独立要因抽出法
JP2006065598A (ja) * 2004-08-27 2006-03-09 Hitachi Ltd 生産管理システム
JP2015052862A (ja) * 2013-09-06 2015-03-19 株式会社東芝 生産管理装置および生産管理プログラム
JP2016031714A (ja) * 2014-07-30 2016-03-07 日本電信電話株式会社 重回帰分析装置および重回帰分析方法
WO2016079972A1 (ja) * 2014-11-19 2016-05-26 日本電気株式会社 要因分析装置、要因分析方法と記録媒体、及び、要因分析システム

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3499437A4 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2025004302A1 (ja) * 2023-06-30 2025-01-02 日本電気株式会社 情報処理装置、表示制御方法、および表示制御プログラム
WO2025004299A1 (ja) * 2023-06-30 2025-01-02 日本電気株式会社 情報処理装置、表示制御方法、および表示制御プログラム

Also Published As

Publication number Publication date
EP3499437A4 (en) 2020-01-01
JP2018156346A (ja) 2018-10-04
JP6723946B2 (ja) 2020-07-15
US20190265679A1 (en) 2019-08-29
EP3499437A1 (en) 2019-06-19

Similar Documents

Publication Publication Date Title
WO2018168193A1 (ja) 業務改善支援装置および業務改善支援方法
JP2018156346A5 (https=)
Asif et al. A composite index for measuring performance in higher education institutions
US20190236497A1 (en) System and method for automated model selection for key performance indicator forecasting
CN105260835A (zh) 多来源业务大数据的建模、分析、自我优化的方法
CN101583961A (zh) 业务分析程序以及业务分析装置
US11675756B2 (en) Data complementing system and data complementing method
CN114971710B (zh) 基于事件日志的多维度流程变体差异分析方法与系统
KR20190039758A (ko) 데이터 분석 지원 장치 및 데이터 분석 지원 시스템
JP2015141524A (ja) 合意形成支援方法、装置、及びプログラム
KR20150137704A (ko) 프로젝트 관리 시스템 및 방법
CN117435489A (zh) 基于需求文档自动分析软件功能点方法及系统
JP6760084B2 (ja) 分析用情報表示システム、方法およびプログラム
KR101138444B1 (ko) 입체/복합 개발사업의 리스크 관리 및 성과 관리 통합 시스템
JP2019032807A (ja) 要因分析システム、要因分析方法およびプログラム
JP5258832B2 (ja) 拠点分析システム
JPWO2017221856A1 (ja) 分析装置、分析方法、および記憶媒体
CN120542819A (zh) 一种基于大数据的企业管理优化方法及系统
JPH09101947A (ja) 時系列予測方法
WO2023223448A1 (ja) 情報処理装置、情報処理方法及びプログラム
JP6018852B2 (ja) 要因分析・表示方法及びシステム
WO2014162602A1 (ja) 指標設定支援装置及び指標設定支援方法
JP2021068331A (ja) 不動産価格分析装置、不動産価格分析モデル生成方法、不動産価格分析システム及び不動産価格分析プログラム
JP4663526B2 (ja) 帳票作成支援装置、帳票作成支援方法、および帳票作成支援プログラム
JP7673824B2 (ja) 推計システム、推計方法、及びプログラム

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18767101

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2018767101

Country of ref document: EP

Effective date: 20190311

NENP Non-entry into the national phase

Ref country code: DE