Cooperation management device and cooperation management method

Abstract

To provide a cooperation management device and a cooperation management method, capable of easily and appropriately determining the goal or operation of an individual system being a low-order system so as to improve the goal of the entire system in which a plurality of individual systems cooperate with each other, the entire system being a host system.SOLUTION: In a multiple system integration operation system, a cooperation management system cooperatively operating a plurality of individual systems as one overall system includes an individual KPI / operation parameter search program which, using a relation model, searches for and determines conditions for individual indexes for improving an entire index or operation parameters. The relation model represents a relationship between the entire index being an evaluation index on the entire system and operation parameters of an individual index being an evaluation index on each individual system or each individual system controlling the individual index. The cooperation management system also includes an individual KPI / operation parameter notification program which notifies each individual system of the determined conditions for the individual indexes or operation parameters.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to an association management apparatus and an association management method.

Background Art

[0002] There is a system in which a plurality of individual systems cooperate to operate as one system. Such a system is called a System of Systems, and while having an index to be achieved by the entire system of cooperating systems (hereinafter referred to as the entire system), each individual system also has an index to be achieved independently.

[0003] As an example of the entire system, there is a supply chain management system. Regarding supply chain management, for example, an information processing apparatus that generates action rules for a plurality of companies constituting a supply chain so that important performance evaluation indexes in the entire supply chain become optimal is disclosed in Patent Document 1. Specifically, Patent Document 1 discloses that "the action rule pattern generation unit generates a plurality of patterns of action rule information in which a first company constituting the supply chain is associated with an action logic according to the state of a second company constituting the supply chain of the first company. The simulation unit calculates important performance evaluation indexes in the entire supply chain for each of the plurality of patterns of action rule information. The optimal action rule selection unit selects action rule information to be applied to the supply chain based on the important performance evaluation indexes."

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, in the above-described prior art, based on a plurality of patterns of candidate action rules generated in advance based on the candidate action rules of each company input by the user, a pattern that maximizes the key performance evaluation index of the entire supply chain is selected, and there is no description regarding selecting other action rules that can further improve the key performance evaluation index of the entire supply chain. Also, the pattern of the action rule of each company selected here is selected from limited candidates based on user input, but it is not necessarily the one that maximizes the key performance evaluation index of the entire supply chain.

[0006] Moreover, as the number of companies constituting the supply chain increases, there is a problem that the calculation for selecting the pattern of the action rule that maximizes the key performance evaluation index becomes complicated and enormous.

[0007] The present invention has been made in view of the above, and in an overall system in which a plurality of individual systems cooperate, it is an object to easily and appropriately determine the goals or operations of individual systems, which are lower-level systems, so as to better the goals of the overall system, which is a higher-level system.

Means for Solving the Problem

[0008] To solve the above-described problems, in one aspect of the present invention, there is provided a cooperation management system that operates a plurality of individual systems in cooperation as one overall system, and uses a relationship model between an overall index that is an evaluation index for the overall system and an individual index that is an evaluation index for each individual system or an operation parameter of each individual system that controls the individual index to search for and determine the condition of the individual index or the operation parameter for which the overall index improves, and a notification unit that notifies each individual system of the condition of the individual index or the operation parameter determined by the search unit.

Effects of the Invention

[0009] According to one aspect of the present invention, in an overall system in which a plurality of individual systems cooperate, the goals or operations of the individual systems, which are lower-level systems, can be easily and appropriately determined so as to better the goals of the overall system, which is the higher-level system.

Brief Description of the Drawings

[0010]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Best Mode for Carrying Out the Invention

[0011] Hereinafter, embodiments of the present invention will be described with reference to the drawings. It should be noted that the embodiments described below are merely examples including the drawings, and do not limit the invention according to the claims. Also, not all of the elements and combinations thereof described in the embodiments are essential for the solution means of the invention. Also, for configurations that are essential for the configuration of the invention but are well known, illustration and description may be omitted.

[0012] In the following description, the "program" may be used as the subject to describe the processing. Since the program performs the defined processing by being executed by a processor, using the storage unit and / or interface etc. as appropriate, the subject of the processing may be the processor (or a device such as a controller having that processor). That is, the subject of the processing of "XXX program" may be "XXX unit".

[0013] The program may be installed in a device such as a computer, or may be, for example, in a program distribution server or a computer-readable (for example, non-transitory) recording medium. Also, in the following description, two or more programs may be realized as one program, or one program may be realized as two or more programs.

[0014] Also, there is one or more "processors". The processor is typically a microprocessor such as a CPU (Central Processing Unit), but may also be another type of processor such as a GPU (Graphics Processing Unit). Also, the processor may be single-core or multi-core. Also, the processor may be a processor in a broad sense such as a hardware circuit (for example, FPGA (Field-Programmable Gate Array) or ASIC (Application Specific Integrated Circuit)) that performs part or all of the processing.

[0015] In the following description, an identification number is used as identification information for various objects, but identification information of other types (for example, an identifier including letters or symbols) may be adopted. In the following description, "#Y" represents number Y. For example, "XXX#Y" represents XXX identified by number Y.

[0016] In the following description, when describing elements of the same type without distinction, reference signs (or common signs among the reference signs) are used, and when describing elements of the same type separately, the identification numbers (or reference signs) of the elements may be used. Also, the number of each element shown in each figure is an example and is not limited to the illustration.

[0017] In the following description, the notation "A / B" means "one or both of A and B".

[0018] (Overview of the Embodiment) FIG. 1 is a diagram for explaining the overview of the embodiment. The multiple-system integrated operation system S according to the present embodiment includes a cooperation management system 1 and a plurality of individual systems 2 (individual system #1 (individual system 2-1), individual system #2 (individual system 2-2), ···, individual system #N (individual system 2-N)). The cooperation of the plurality of individual systems 2 to share some information is managed by the cooperation management system 1 connected via a communication line.

[0019] An index representing a goal to be achieved is defined for the multiple-system integrated operation system S. Also, an index representing a goal to be achieved is defined for each individual system 2. In the present embodiment, the index representing the goal is KPI (Key Performance Indicators). Hereinafter, the KPI is assumed to include not only general KPIs such as sales, profit, quality, and cost but also constraint conditions such as resource limitations and delivery dates.

[0020] The overall KPI (kpi) that the multiple system integrated operation system S should achieve and the individual KPI (kpin_k) that each individual system #n should achieve have a correlation relationship represented by a function with kpi as the objective variable and kpin_k as the explanatory variable as shown in the following formula (1). n = 1, 2, ···, N, k = 1, 2, ··· are indices for identifying the kpi#k of the individual system #n. kpi = F(kpi1_k1(Θ1), kpi2_k2(Θ2), kpi3_k3(Θ3), …, kpiN_kN(ΘN)) ···(1) However, kpin_k is a function of Θn. Also, Θn is an operation parameter of the individual system #n.

[0021] For the function F in formula (1), for example, a relationship model generated by learning the data of kpi and kpin_k can be applied.

[0022] Here, although there are multiple individual KPIs (kpin_k) and operation parameters Θn of the individual system #n, it is limited to only those that strongly affect the overall KPI (kpi) of the upper-level multiple system integrated operation system S. As shown in Figure 1, when the individual KPIs that strongly affect the overall KPI among the individual KPIs of the individual system #n (n = 1~N) are kpin_kn (n = 1, 2, 3, ···) respectively, formula (1) is generated based on kpin_kn.

[0023] Then, based on the current latest state of the multiple system integrated operation system S, the cooperation management system 1 solves a search problem with formula (1) as the objective function or evaluation function under predetermined constraint conditions to determine the individual KPI (kpin_kn) / operation parameter Θn of each individual system #n that optimizes the overall KPI (kpi). The cooperation management system 1 notifies each individual system #n of the determined individual KPI (kpin_kn) / operation parameter Θn.

[0024] Each individual system #n sets the individual KPI (kpin_kn) / operation parameter Θn notified from the cooperation management system 1 to its own system, and operates autonomously in accordance with the individual goals within the conditions of the individual KPI (kpin_kn) / operation parameter Θn.

[0025] In this way, the cooperation management system 1 determines the individual KPI / operation parameter so as to optimize the overall KPI, and notifies the individual system #n. The individual system #n can optimize the overall KPI while achieving the goals of each individual system #n by operating autonomously to become the notified individual KPI or operating in accordance with the notified operation parameter.

[0026] (Configuration of the integrated operation system S for multiple systems) Next, with reference to FIG. 2, the configuration of the integrated operation system S for multiple systems will be described.

[0027] FIG. 2 is a diagram showing the configuration of the integrated operation system S for multiple systems according to the embodiment. The integrated operation system S for multiple systems includes a cooperation management system 1 and a plurality of individual systems 2-1, ···, 2-N. The cooperation management system 1 and the plurality of individual systems 2 are connected via a communication line.

[0028] The cooperation management system 1 includes a CPU 11, a memory 12, a communication device 13, a program storage device 14, and a data storage device 18. The CPU 11 reads out the program described later from the program storage device 14 and executes each process in cooperation with the memory 12 and the communication device 13. The communication device 13 is an interface for the cooperation management system 1 to perform data transmission and reception with the individual system 2.

[0029] The data storage device 18 includes a relational model database 181 and an individual system setting / operation database 182. The individual system setting / operation database 182 stores the setting information and actual operation data of each individual system 2 collected from each individual system 2.

[0030] The program storage device 14 stores a KPI relationship model generation module 15, an individual system operation parameter determination module 16, and a data input / output module 17.

[0031] The KPI relationship model generation module 15 includes an overall KPI calculation program 151, an individual system data collection program 152, an individual KPI / operation parameter selection program 153, and a KPI / operation parameter relationship model generation program 154.

[0032] The overall KPI calculation program 151 calculates the overall KPI based on the above formula (1). The individual system data collection program 152 periodically collects various data related to each individual system 2 from each individual system 2. The various data related to each individual system 2 includes the data used in each process of the cooperation management system 1 of the present embodiment.

[0033] The individual KPI / operation parameter selection program 153 selects operation parameters that can control the individual KPI of each individual system 2. The individual KPI / operation parameter selection program 153 may, for example, receive an input or notification from the outside (such as each individual system 2) and select operation parameters that can control the individual KPI of each individual system 2. Or the individual KPI / operation parameter selection program 153 may select operation parameters that can control the individual KPI of each individual system 2 from the setting information of the individual system 2 held in the cooperation management system 1.

[0034] Furthermore, the individual KPI / operation parameter selection program 153 respectively selects individual KPI / operation parameters that have a strong influence on the overall KPI from the individual KPI / operation parameters for each individual system 2. For example, one individual KPI / operation parameter with the largest correlation coefficient with the overall KPI may be selected for each individual system 2, or multiple individual KPI / operation parameters with a correlation coefficient of a certain value or more may be selected for each individual system 2.

[0035] The operation parameters that can control the individual KPIs of each individual system 2 selected by the individual KPI / operation parameter selection program 153 and that have a strong influence on the overall KPI are called "target individual KPI / operation parameters".

[0036] The KPI / operation parameter relationship model generation program 154 learns the relationship between each data of the overall KPI and the individual KPI / operation parameters for each individual system 2 collected by the individual system data collection program 152, and generates a relationship model. The KPI / operation parameter relationship model generation program 154 stores the generated relationship model in the relationship model database 181.

[0037] The individual system operation parameter determination module 16 stores a search problem setting program 161, an individual KPI / operation parameter search program 162, an individual system state acquisition program 163, and an individual KPI / operation parameter notification program 164.

[0038] The search problem setting program 161 reads the relationship model from the relationship model database 181 and sets a search problem for searching and determining the individual KPI / operation parameters for each individual system 2 that optimizes the overall KPI. The search problem is set as a problem of searching for the individual KPI (kpin_k) conditions / operation parameters Θn for each individual system 2 that optimizes the objective function / evaluation function with the overall KPI (kpi) in the above formula (1) as the objective function / evaluation function. The individual KPI conditions include the value, upper limit, lower limit, and range of the individual KPI.

[0039] The individual KPI / operation parameter search program 162 searches for and determines the solution to the search problem set by the search problem setting program 161, that is, the individual KPI conditions / operation parameters for each individual system 2 that optimize the overall KPI under the constraint conditions.

[0040] The individual system state acquisition program 163 acquires the latest system state from each individual system 2. The latest system state includes information that can be the input value or setting value of the search problem when the search problem is set by the search problem setting program 161.

[0041] The individual KPI / operation parameter notification program 164 notifies each individual system 2 of the individual KPI conditions / operation parameters for each individual system 2 determined by the individual KPI / operation parameter search program 162.

[0042] The data input / output module 17 includes a data input / output program for the KPI relationship model generation module 15 and the individual system operation parameter determination module 16 to transmit and receive data with the individual system 2.

[0043] Each of the individual systems 2 (2-1, …, 2-N) has a CPU 21, a memory 22, a communication device 23, a program storage device 24, and a data storage device 28. The CPU 21 reads out the programs described later from the program storage device 24 and executes each process in cooperation with the memory 22 and the communication device 23. The communication device 23 is an interface for the individual system 2 to transmit and receive data with the cooperation management system 1.

[0044] The program storage device 24 stores an individual system operation module 25 and a parameter notification module 26.

[0045] The individual system operation module 25 includes an individual system operation program 251 and an individual KPI calculation program 252.

[0046] The individual system operation program 251 controls the system operation to achieve the purpose of its own system. The individual KPI calculation program 252 calculates the individual KPI of its own system.

[0047] The parameter notification module 26 includes a controllable parameter notification program 261 and an individual KPI acceptance notification program 262.

[0048] The controllable parameter notification program 261 notifies the cooperation management system 1 of the individual KPI / operation parameters among the individual KPI / operation parameters of its own system that can control the overall KPI.

[0049] The individual KPI acceptance notification program 262 determines whether the individual KPI of its own system can achieve the target of its own system when accepting the individual KPI conditions / operation parameters that optimize the overall KPI received from the cooperation management system 1.

[0050] When the individual KPI can achieve the target of its own system, the individual KPI acceptance notification program 262 notifies the cooperation management system 1 that the received individual KPI conditions / operation parameters can be accepted. When the individual KPI cannot achieve the purpose of its own system, the individual KPI acceptance notification program 262 notifies the cooperation management system 1 that the received individual KPI conditions / operation parameters cannot be accepted, together with the additional conditions required for the individual KPI to achieve the purpose of its own system.

[0051] When the search problem setting program 161 of the cooperation management system 1 is notified from each individual system 2 that the individual KPI conditions / operation parameters cannot be accepted and the additional conditions, it additionally sets the additional conditions to the search problem. Then, the individual KPI / operation parameter search program 162 re-executes the search and determination of the solution to the search problem with the additional conditions additionally set.

[0052] FIG. 3 is a functional block diagram showing the configuration of the multi-system integrated operation system S according to the embodiment.

[0053] As shown in FIG. 3, the cooperation management system 1 includes a KPI relationship model generation processing unit 101, an individual KPI / operation parameter determination processing unit 102, and a data input / output processing unit 103. The cooperation management system 1 is also connected to a terminal device 5 including a display screen.

[0054] The KPI relationship model generation processing unit 101 is realized by the execution of a KPI relationship model generation module 15 by a CPU 11 (FIG. 2). The individual KPI / operation parameter determination processing unit 102 is realized by the execution of an individual system operation parameter determination module 16 by the CPU 11.

[0055] The data input / output processing unit 103 is realized by the execution of a data input / output module 17 by the CPU 11. The data input / output processing unit 103 performs data input / output processing for the KPI relationship model generation processing unit 101 and the individual KPI / operation parameter determination processing unit 102 to perform data transmission and reception with the individual system 2.

[0056] Each of the individual systems 2 (2-1,..., 2-N) includes an individual system operation processing unit 201, a parameter notification processing unit 202, and a data input / output processing unit 203.

[0057] The individual system operation processing unit 201 is realized by the execution of an individual system operation module 25 (FIG. 2) by a CPU 21 (FIG. 2). The parameter notification processing unit 202 is realized by the execution of a parameter notification module 26 (FIG. 2) by the CPU 21.

[0058] The data input / output processing unit 203 is realized by the execution of a data input / output module (not shown) by the CPU 21. The data input / output processing unit 203 performs data input / output processing for the individual system operation processing unit 201 and the parameter notification processing unit 202 to perform data transmission and reception with the cooperation management system 1.

[0059] The KPI relationship model generation processing unit 101 of the cooperation management system 1 generates a relationship model between the overall KPI and individual KPIs / operation parameters, and stores it in the relationship model database 181. The individual KPI / operation parameter determination processing unit 102 obtains individual KPIs / operation parameters that optimize the overall KPI as a solution to the search problem based on the relationship model read from the relationship model database 181, and notifies each individual system 2.

[0060] The parameter notification processing unit 202 of each individual system 2 accepts the individual KPI / operation parameters notified from the cooperation management system 1 when they achieve the goals of the local system, and notifies the cooperation management system 1 that they are unacceptable together with additional conditions when they do not achieve the goals of the local system.

[0061] When the cooperation management system 1 is notified of the unacceptability of the individual KPI / operation parameters and additional conditions from the individual system 2, it adds the notified additional conditions to the search problem, re-executes the search for the solution, obtains individual KPIs / operation parameters that optimize the overall KPI, and notifies each individual system 2 again.

[0062] The cooperation management system 1 repeats the execution of the search for the solution of the search problem until a predetermined condition (such as a predetermined time, a predetermined number of times, or notification of the acceptability of the individual KPI / operation parameters from the individual system 2) is satisfied.

[0063] (Relationship model generation process of the cooperation management system 1) FIG. 4 is a flowchart showing the relationship model generation process of the cooperation management system 1 according to the embodiment. The KPI relationship model generation processing unit 101 of the cooperation management system 1 executes the relationship model generation process at the specified schedule or the timing of the user's execution instruction.

[0064] First, in step S11, the individual KPI / operation parameter selection program 153 executes the individual KPI / operation parameter selection process. The details of the individual KPI / operation parameter selection process will be described later with reference to FIG. 5.

[0065] Next, in step S12, the KPI / operation parameter relationship model generation program 154 executes a KPI / operation parameter relationship model generation process. Details of the KPI / operation parameter relationship model generation process will be described later with reference to FIG. 6.

[0066] In the relationship model generation process, data on the overall KPI, individual KPIs, and operation parameters of the individual systems 2 that can control them are acquired, and their relationships are modeled in a data-driven manner. Also, data collection is limited to data on individual KPIs that affect fluctuations in the overall KPI. Also, controllable operation parameters can be acquired by querying the individual systems 2. Also, as the basis of the relationship model, a relationship graph given by the user may be used. Also, it may be modeled not only as a direct relationship between the overall KPI and individual KPIs, but also as a relationship in which intermediate variables are interposed.

[0067] (Individual KPI / Operation Parameter Selection Process) FIG. 5 is a flowchart showing the individual KPI / operation parameter selection process in step S11 (FIG. 4).

[0068] First, in step S11a, the individual KPI / operation parameter selection program 153 acquires a set of data on the overall KPI and the individual KPI / operation parameters of any one of the individual systems 2. The operation parameters are pre-filtered to be operation parameters that can control the individual KPIs of each individual system 2. Here, the overall KPI may be replaced with any index used in the calculation of the overall KPI. Also, the set of data to be acquired may be actual operation data or simulation data.

[0069] Next, in step S11b, the individual KPI / operation parameter selection program 153 calculates a numerical value, such as a correlation coefficient, representing the relationship between the overall KPI and any individual KPI / operation parameter based on the set of data acquired in step S11a.

[0070] Next, in step S11c, the individual KPI / operation parameter selection program 153 selects individual KPI / operation parameters for which the overall KPI and the numerical value representing the relationship calculated in step S11b satisfy a predetermined condition, for example, the correlation coefficient is equal to or greater than a certain value.

[0071] Next, in step S11d, the individual KPI / operation parameter selection program 153 lists and outputs the individual KPI / operation parameters selected in step S11c as target individual KPI / operation parameters whose influence degree on the overall KPI is equal to or greater than a certain value.

[0072] Note that the selection of the target individual KPI / operation parameters may be specified by an external input regardless of the individual KPI / operation parameter selection process. In this case, the individual KPI / operation parameter selection process is omitted.

[0073] (KPI / Operation Parameter Relationship Model Generation Process) FIG. 6 is a flowchart showing the KPI / operation parameter relationship model generation process in step S12 (FIG. 4).

[0074] First, in step S12a, the KPI / operation parameter relationship model generation program 154 acquires a set of data of the overall KPI and the target individual KPI / operation parameters selected by the individual KPI / operation parameter selection process (FIG. 5) or an external input. Similar to step S11a (FIG. 5), the overall KPI may be any index used for calculating the overall KPI. The set of data to be acquired may be actual operation data or simulation data.

[0075] Next, in step S12b, the KPI / operation parameter relationship model generation program 154 selects the model format of the relationship model to be generated for the data pairs of the overall KPI obtained in step S12a and the individual KPI / operation parameters of any individual system 2. The model formats of the relationship model include a linear model and a non-linear model. If the search problem for embedding the relationship model is a linear programming problem, the linear model is selected; if it is a simulation-based search problem, the one with higher accuracy among the linear model and the non-linear model is selected.

[0076] Next, in step S12c, the KPI / operation parameter relationship model generation program 154 performs machine learning on the parameters (coefficients) of the relationship model with the overall KPI as the target variable and the individual KPI / operation parameters as the explanatory variables in the format of the relationship model selected in step S12b. In addition to the individual KPI / operation parameters, numerical values representing the system state, for example, may be added to the explanatory variables of the relationship model to improve the model accuracy.

[0077] Next, in step S12d, the KPI / operation parameter relationship model generation program 154 outputs the relationship model data (model format and parameters) learned in step S12c.

[0078] (Individual KPI / operation parameter determination process according to the embodiment) FIG. 7 is a flowchart showing the individual KPI / operation parameter determination process according to the embodiment. The individual KPI / operation parameter determination processing unit 102 of the cooperation management system 1 executes the individual KPI / operation parameter determination process at the specified schedule or the execution instruction timing of the user. The individual KPI / operation parameter determination process is executed at a timing independent of or synchronized with the relationship model generation process (FIG. 4).

[0079] First, in step S13, the search problem setting program 161 executes the search problem setting process. The details of the search problem setting process will be described later with reference to FIG. 8.

[0080] Next, in step S14, the individual KPI / operation parameter search program 162 executes an individual KPI / operation parameter search process. Details of the individual KPI / operation parameter search process will be described later with reference to FIG. 9.

[0081] Next, in step S15, the individual KPI / operation parameter notification program 164 executes an individual KPI / operation parameter notification process. Details of the individual KPI / operation parameter notification process will be described later with reference to FIG. 10.

[0082] Next, in step S16, the individual KPI / operation parameter notification program 164 determines whether it has received from the individual system 2 in step S15 an indication that the operation parameters are acceptable. If the individual KPI / operation parameter notification program 164 has received an indication of acceptability (step S16 YES), it ends the individual KPI / operation parameter determination process; if it has received an indication of non-acceptance (step S16 NO), it transfers the process to step S17.

[0083] In step S17, the individual KPI / operation parameter notification program 164 adds the additional conditions regarding the individual KPI / operation parameters received together with the individual KPI / operation parameters determined to be non-acceptable in step S16 to the search problem set in step S13, and returns the process to step S14. In step S14, to which the process is transferred from step S17, the individual KPI / operation parameter search program 162 re-executes the search process for the individual KPI / operation parameters in the search problem including the additional conditions additionally set in step S17.

[0084] In the individual KPI / operation parameter determination process, the relationship models between the overall KPI and individual KPIs and between individual KPIs and controllable operation parameters are reflected in the limitation of the search range, constraint definition, and objective function / reward definition of the linear programming problem to determine the parameters of the individual system that improve the overall KPI. Also, the relationships among the overall KPI, individual KPIs, and controllable operation parameters are introduced by converting them into the constraints of the linear programming problem. Further, the relationships among the overall KPI, individual KPIs, and controllable operation parameters are introduced into the objective function calculation formula of the linear programming problem. Additionally, the relationships among the overall KPI, individual KPIs, and controllable operation parameters are introduced by converting them into the calculation model of the simulator used for optimal solution search. Moreover, the relationships among the overall KPI, individual KPIs, and controllable operation parameters may be introduced into the reward calculation formula of reinforcement learning.

[0085] (Search problem setting process) Figure 8 is a flowchart showing the search problem setting process of step S13 (Figure 7).

[0086] First, in step S13a, the search problem setting program 161 sets the type of the search problem. If the form of the relationship model generated in the KPI / operation parameter relationship model generation process (Figure 6) is a "linear model", "linear programming problem" or "simulation-based search problem" can be set. If the form of the relationship model is a "non-linear model", a "simulation-based search problem" can be set. In the case of a "linear model", similar to step S12b (Figure 6), the one with higher model accuracy between the "linear programming problem" and the "simulation-based search problem" is set as the problem type. Note that the problem types set in step S13a are exemplified by the "linear programming problem" and the "simulation-based search problem", but are not limited to these, and other problem types may also be used.

[0087] Next, in step S13b, if the type of the search problem set in step S13a is a "linear programming problem", the search problem setting program 161 transfers the process to step S13c, and if it is a "simulation-based search problem", it transfers the process to step S13g.

[0088] In step S13c, the search problem setting program 161 sets the calculation formula of the overall KPI in the objective function of the linear programming problem. Next, in step S13d, the search problem setting program 161 sets the target individual KPI, individual KPI conditions, and operation parameters in the decision variables of the linear programming problem. Next, in step S13e, the search problem setting program 161 sets predetermined constraint conditions. Next, in step S13f, the search problem setting program 161 sets the relationship model of the target individual KPI / operation parameters in the calculation formula of the constraint conditions or the objective function of the linear programming problem. When step S13f ends, the search problem setting program 161 transfers the process to step S13j.

[0089] On the other hand, in step S13g, the search problem setting program 161 sets the calculation formula of the overall KPI in the evaluation function of the simulation-based search problem. Next, in step S13h, the search problem setting program 161 sets the target individual KPI, individual KPI conditions, and operation parameters in the search target variables of the simulation-based search problem. Next, in step S13i, the search problem setting program 161 sets the relationship model of the target individual KPI / operation parameters in the calculation model within the simulation or the calculation formula of the evaluation function. When step S13i ends, the search problem setting program 161 transfers the process to step S13j.

[0090] In step S13j, the search problem setting program 161 outputs the search problem set in the above process.

[0091] (Individual KPI / Operation Parameter Search Process) FIG. 9 is a flowchart showing the individual KPI / operation parameter search process of step S14 (FIG. 7).

[0092] First, in step S14a, the individual KPI / operation parameter search program 162 receives the input of the search problem set by the search problem setting process (Figure 7). Next, in step S14b, for any set of individual KPIs related to the search problem, a trade-off (for example, the correlation coefficient is negative) relationship is identified by correlation analysis.

[0093] Next, in step S14c, the individual KPI / operation parameter search program 162 determines whether a trade-off relationship was identified in step S14b. If the individual KPI / operation parameter search program 162 has a trade-off relationship (step S14c YES), it transfers the process to step S14d. If there is no trade-off relationship (step S14c NO), it transfers the process to step S14e.

[0094] In step S14d, for the individual KPIs having a trade-off relationship, the individual KPI / operation parameter search program 162 adds the conditions of the upper limit, lower limit, or range of the individual KPI / operation parameter considering the trade-off as conditions to the search problem. The upper limit, lower limit, or range of the individual KPI / operation parameter is queried to the individual system 2, etc.

[0095] In step S14e, the individual KPI / operation parameter search program 162 receives the data input of the state of each individual system 2.

[0096] Next, in step S14f, the individual KPI / operation parameter search program 162 sets or inputs the latest state of the individual system obtained by the individual system state acquisition program 163 to the search problem. Next, in step S14g, the individual KPI / operation parameter search program 162 determines whether there are multiple target overall KPIs. If there are multiple target overall KPIs (step S14g YES), the individual KPI / operation parameter search program 162 transfers the process to step S14h. If there is one target overall KPI (step S14g NO), it transfers the process to step S14j.

[0097] In step S14h, the individual KPI / operation parameter search program 162 determines the priorities of a plurality of overall KPIs. The priorities may be in the order of importance according to the purpose of the multi-system integrated operation system S.

[0098] Next, in step S14i, the individual KPI / operation parameter search program 162 selects one overall KPI in order from the highest priority and sets it to the objective function / evaluation function.

[0099] Next, in step S14j, the individual KPI / operation parameter search program 162 calculates the individual KPI conditions / operation parameters for which the objective function / evaluation function is optimal (for example, maximum).

[0100] In the case where there are multiple overall KPIs, if the search problem is a linear programming problem, the weighted sum of the multiple KPIs can be used as the objective function, or the optimal solution range can be gradually narrowed while applying each overall KPI one by one when solving the search problem. In the case where there are multiple overall KPIs and the search problem is simulation-based optimization, it can also be adopted as a solution candidate only when all the overall KPIs satisfy the specified conditions in the simulation results.

[0101] Next, in step S14k, the individual KPI / operation parameter search program 162 determines whether all the overall KPIs have been processed. When the individual KPI / operation parameter search program 162 has processed all the overall KPIs (step S14k YES), the process proceeds to step S14l, and when there are unprocessed overall KPIs (step S14k NO), the process proceeds to step S14m. When there is one overall KPI (step S14g NO), step S14k becomes YES.

[0102] In step S14l, the individual KPI / operation parameter search program 162 outputs the individual KPI conditions / operation parameters.

[0103] In one step S14m, the individual KPI / operation parameter search program 162 adds the range of the objective function / evaluation function or the range of the individual KPI conditions / operation parameters calculated in step S14j to the search problem as a condition for limiting the search range. When step S14m ends, the individual KPI / operation parameter search program 162 transfers the process to step S14i. In step S14i to which the process is transferred from step S14m, the process is executed for the overall KPI with the next highest priority after the previously selected overall KPI.

[0104] (Individual KPI / Operation Parameter Notification Process) FIG. 10 is a flowchart showing the individual KPI / operation parameter notification process of step S15 (FIG. 7).

[0105] First, in step S15a, the individual KPI / operation parameter notification program 164 notifies each individual system 2 of the respective individual KPI / operation parameters of each individual system 2, which are the search results by the individual KPI / operation parameter search process (FIG. 9). Next, in step S15b, the individual KPI / operation parameter notification program 164 receives from each individual system 2 the acceptability of the notified respective individual KPI / operation parameters of each individual system 2 and additional conditions (range of individual KPI, range of operation parameters).

[0106] In the individual KPI / operation parameter determination process described with reference to FIGS. 7 to 10, although the type of search problem to which one relationship model is applied is set to either a linear programming problem or a simulation problem, it is not limited to this. That is, one relationship model may be set for all types of search problems, and the type of search problem that can obtain better results for the overall KPI may be adopted.

[0107] (Display Screen 500 of Terminal Device 5) FIG. 11 is a diagram showing a display screen 500 of a terminal device 5 connected to the cooperation management system 1. In the example of FIG. 11, for individual systems other than the individual system #1, although they are the same except that the individual KPIs and operation parameters are different, the illustration is appropriately omitted.

[0108] The display screen 500 includes an optimal solution calculation button 50, overall KPIs and priorities 51, and individual KPIs and operation parameters 52, 53,... of individual systems. When the optimal solution calculation button 50 is pressed, an individual KPI / operation parameter determination process (FIG. 7) is executed.

[0109] The overall KPIs and priorities 51 display the overall KPIs and priorities. In the example of FIG. 11, there are overall KPIs 1, 2, 3, and their respective priorities are 3, 7, 5, and overall KPI 1 has the highest priority.

[0110] The individual KPI and operation parameter 52 of the individual system #1 includes an individual KPI 521 and an operation parameter 522. In the example of FIG. 11, the individual KPI 521 includes individual KPIs 1-1, 1-2, 1-3. The operation parameter 522 includes operation parameters 1-1, 1-2, 1-3.

[0111] Also, the individual KPI and operation parameter 52 includes an overall KPI correlation coefficient 52a, a target applicable or not 52b, an optimal value 52c, an acceptance possible or not 52d, a current value 52e, a trade-off 52f, and a constraint 52g for each individual KPI and operation parameter.

[0112] The overall KPI correlation coefficient 52a represents the correlation coefficient between the corresponding individual KPI / operation parameter of the individual system #1 and the overall KPI used to calculate the corresponding individual KPI / operation parameter. In the example of FIG. 11, it is shown that the correlation coefficient of the individual KPI 1-1 of the individual system #1 is "0.76".

[0113] The applicability flag 52b shows "○" when the value of the overall KPI correlation coefficient 52a is equal to or greater than the threshold value and the corresponding individual KPI / operation parameter is subject to optimization by search problem solving, and shows a blank when it does not apply. In the example of Fig. 11, the individual KPI1-1 of the individual system #1 is shown as "○".

[0114] The optimal value 52c represents the optimal value of the corresponding individual KPI / operation parameter, and for example, the value of the corresponding individual KPI / operation parameter optimized by search problem solving is displayed. In the example of Fig. 11, the optimal value of the individual KPI1-1 of the individual system #1 is shown as "3.6".

[0115] The acceptance flag 52d represents the result of determining the acceptance or non-acceptance of the corresponding individual KPI / operation parameter optimized by search problem solving by the individual system #1. "Acceptable" is shown when it is acceptable, and a blank is shown when it is not acceptable. In the example of Fig. 11, the individual KPI1-1 of the individual system #1 is shown as "Acceptable".

[0116] The current value 52e is the current value of the corresponding individual KPI / operation parameter. In the case of an individual KPI, it is a value calculated taking into account the current state of the individual system #1, and in the case of an operation parameter, it is the current setting value. In the example of Fig. 11, the current value of the individual KPI1-1 of the individual system #1 is shown as "3.4".

[0117] The trade-off 52f represents other individual KPI / operation parameters with which the corresponding individual KPI / operation parameter has a trade-off relationship. In the example of Fig. 11, it is shown that the individual KPI1-1 of the individual system #1 has a trade-off relationship with the individual KPI21 of the individual system #2, and the operation parameter 1-1 of the individual system #1 has a trade-off relationship with the individual KPI23 of the individual system #2.

[0118] Constraint 52g is the upper limit, lower limit, or range condition of the corresponding individual KPI / operation parameter. The upper limit, lower limit, or range condition of this individual KPI may be set as a condition for not causing a trade-off relationship, or may be set as a prerequisite condition to be satisfied. In the example of FIG. 11, it is shown that the individual KPI1-1 of the individual system #1 is restricted to a value of "from 3 to 7". Also, the operation parameter 1-1 of the individual system #1 is shown to be restricted to a value "less than 26".

[0119] (Effect of Embodiment) According to the above-described embodiment, a relationship model between the overall KPI of the multi-system integrated operation system S and the individual KPI of each individual system 2 or the operation parameter of each individual system 2 that controls the individual KPI is used. Then, the individual KPI conditions or operation parameters that improve the overall KPI are searched for and determined, and the determined individual KPI conditions / operation parameters are notified to each individual system. Therefore, each individual system can be appropriately operated without prior input of candidates for the conditions and operation parameters of the individual KPI so that the overall KPI of the multi-system integrated operation system S is further improved.

[0120] Also, while operating the multi-system integrated operation system S, a relationship model of the overall KPI of the multi-system integrated operation system S, the individual KPI of each individual system 2 that affects the overall KPI, and the controllable operation parameter that affects the individual KPI is constructed and sequentially updated. Therefore, based on the model reflecting the situation of the latest system, the individual KPI conditions / operation parameters for controlling the individual system 2 can be determined.

[0121] Also, by selecting an operation parameter that can control the individual KPI and using minimal information, even if the number of individual systems 2 and operation parameters becomes extremely large, the individual KPI conditions / operation parameters can be easily and appropriately determined.

[0122] Also, by selecting individual KPIs or operation parameters whose correlation with the overall KPI is above a certain level and using minimal information, even if the number of overall KPIs, individual KPIs, and operation parameters becomes extremely large, the individual KPI conditions / operation parameters can be easily and appropriately determined.

[0123] Also, since the above-described relationship model is applied to the search problem of exploring individual KPI conditions / operation parameters that improve the overall KPI, the individual KPI conditions / operation parameters determined by the search problem to which the relationship model is applied are reliable and trustworthy based on the past performance of the multiple system integrated operation system S and the individual system 2.

[0124] Also, since the characteristics of the search problem are selected by the method of formulating the relationship model, the characteristics of the search problem can be controlled, and a search problem with more appropriate characteristics for the problem can be used.

[0125] Also, for the individual system 2, inquire whether the individual KPI conditions / operation parameters determined by the search problem can be executed. If the answer is no, add the constraints received from the individual system 2 together with the negative notification to the search problem and re-search for the individual KPI conditions / operation parameters. Thus, the inconvenience of reducing the individual KPI by improving the overall KPI can be avoided.

[0126] Also, even if there are multiple overall KPIs, the individual KPI conditions / operation parameters can be determined and each individual system 2 can be appropriately controlled.

[0127] Also, the range of the individual KPI conditions / operation parameters determined for the overall KPI with the first priority among the multiple overall KPIs is used as a condition to limit the search range when determining the individual KPI conditions / operation parameters for the overall KPI with the second priority lower than the first priority. Thus, the individual KPI conditions / operation parameters can be determined so that the overall KPIs with higher priorities are prioritized and the multiple overall KPIs are improved respectively.

[0128] Also, when determining the presence or absence of conflicts for any arbitrary combination of individual KPIs and performing the determination of the operation parameters for controlling the individual KPI conditions / individual KPIs of the combination of individual KPIs with conflicts, additional conditions are set in advance. Thus, even if there are conflicts in the combination of individual KPIs, the individual KPI conditions / operation parameters for controlling the individual system 2 can be appropriately determined.

[0129] Also, when performing the search and determination of the operation parameters for controlling the individual KPI conditions / individual KPIs for the combination of individual KPIs with conflicts, the additional conditions added in advance are the upper limit, lower limit, or range of the individual KPI conditions / operation parameters. Thus, it is possible to efficiently search for the individual KPI conditions / operation parameters after narrowing down the search range in advance.

[0130] (Application Example of the Embodiment) FIG. 12 is a diagram showing an example in which the multi-system integrated operation system S of the embodiment is applied to the supply chain planning and operation system 1S.

[0131] The supply chain planning and operation system 1S is configured to include a procurement planning system 20A-1, a production planning system 20A-2, a transportation planning system 20A-3, a sales planning system 20A-4, and a supply chain overall planning system 10A that manages the cooperation of these subsystems. The supply chain overall planning system 10A can formulate a procurement plan, a production plan, a transportation plan, and a sales plan that optimize the overall plan (sales, costs, profits, etc.) in the supply chain planning and operation system 1S in a state where the latest demand is input.

[0132] FIG. 13 is a diagram showing an example in which the multi-system integrated operation system S of the embodiment is applied to the power grid maintenance management system 2S.

[0133] The power grid maintenance management system 2S is composed of the regional A system 20B-1, the regional B system 20B-2, the regional C system 20B-3, the regional D system 20B-4, and the power grid overall planning system 10B that manages the cooperation of these subsystems. In the power grid maintenance management system 2S with the latest external environment (power demand, weather conditions, etc.) input, the power grid overall planning system 10B can formulate maintenance management for each region to further improve the overall plan (power outage time, cost, etc.).

[0134] Also, as shown in FIG. 14, in the power grid maintenance management system 2S in the latest state with the latest external environment input, the power grid overall planning system 10C can formulate maintenance management for each risk factor to further improve the overall plan.

[0135] The present invention is not limited to the above-described embodiments and includes various modifications. For example, the above-described embodiments have been described in detail for easy understanding of the present invention, and are not necessarily limited to those having all the configurations described. Also, as long as there is no contradiction, it is possible to replace a part of the configuration of one embodiment with the configuration of another embodiment, or to add the configuration of another embodiment to the configuration of one embodiment. Also, it is possible to add, delete, replace, integrate, or disperse a part of the configuration of each embodiment. Also, the configurations and processes shown in the embodiments can be appropriately dispersed, integrated, or replaced based on processing efficiency or implementation efficiency.

Explanation of Reference Numerals

[0136] S: Multiple system integrated operation system, 1: Cooperation management system, 2: Individual system, 153: Individual KPI / operation parameter selection program, 154: KPI / operation parameter relationship model generation program, 161: Search problem setting program, 162: Individual KPI / operation parameter search program, 164: Individual KPI / operation parameter notification program, CPU11, 12: Memory

Claims

Claim 1. A cooperation management system that operates multiple individual systems in cooperation as one integrated system, using a relational model between an overall metric that is an evaluation metric for the integrated system and an individual metric that is an evaluation metric for each individual system or an operation parameter of each individual system that controls the individual metric, to search for and determine the conditions of the individual metric or the operation parameter under which the overall metric is improved; a search unit; a notification unit that notifies each individual system of the conditions of the individual metric or the operation parameter determined by the search unit; and a model generation unit that generates the relational model based on the overall metric and the individual metric or the operation parameter. A cooperation management system characterized by comprising the above.

2. In the cooperation management system according to Claim 1, a selection unit that selects an individual metric or an operation parameter that can control the overall metric. A cooperation management system further characterized by comprising the above.

3. In the cooperation management system according to Claim 2, the selection unit selects an individual metric or an operation parameter having a correlation with the overall metric of a certain level or more. A cooperation management system characterized by the above.

4. A cooperation management system that operates multiple individual systems in cooperation as one integrated system, using a relational model between an overall metric that is an evaluation metric for the integrated system and an individual metric that is an evaluation metric for each individual system or an operation parameter of each individual system that controls the individual metric, to search for and determine the conditions of the individual metric or the operation parameter under which the overall metric is improved; a search unit; a notification unit that notifies each individual system of the conditions of the individual metric or the operation parameter determined by the search unit; and a search problem setting unit that applies the relational model to a search problem of searching for the conditions of the individual metric or the operation parameter under which the overall metric is improved. The cooperation management system comprises: the search problem setting unit selects the characteristics of the search problem by the formulation method of the relational model. A cooperation management system characterized by the above.

5. A cooperation management system that operates multiple individual systems in cooperation as one integrated system, Using a relational model of the overall metric, which is an evaluation metric for the entire system, and the individual metrics, which are evaluation metrics for each individual system, or the operation parameters of each individual system that control the individual metrics, a search unit searches for and determines the conditions of the individual metrics or the operation parameters for which the overall metric is improved. A notification unit notifies each individual system of the conditions of the individual metrics or the operation parameters determined by the search unit. It comprises: The notification unit receives from each individual system whether the conditions of the individual metrics or the operation parameters notified to each individual system can be accepted. In the case of non-acceptance, it receives the constraints of the individual metrics or the operation parameters from each individual system. Based on the constraints, the search unit re-executes the determination of the conditions of the individual metrics or the operation parameters. A cooperation management system characterized by the above. **Claim 6**: A cooperation management system that operates a plurality of individual systems in cooperation as one overall system, Using a relational model of the overall metric, which is an evaluation metric for the entire system, and the individual metrics, which are evaluation metrics for each individual system, or the operation parameters of each individual system that control the individual metrics, a search unit searches for and determines the conditions of the individual metrics or the operation parameters for which the overall metric is improved. A notification unit notifies each individual system of the conditions of the individual metrics or the operation parameters determined by the search unit. It comprises: There are a plurality of the overall metrics. The search unit determines the conditions of the individual metrics or the operation parameters such that a plurality of the overall metrics are improved. A cooperation management system characterized by the above. **Claim 7** In the cooperation management system according to Claim 6, The search unit sets the range of the conditions of the individual metrics or the operation parameters determined for the overall metric of the first priority among the plurality of the overall metrics as a condition for limiting the search range when determining the conditions of the individual metrics or the operation parameters for the overall metric of the second priority lower than the first priority. A cooperation management system characterized by the above. **Claim 8**: A cooperation management system that operates a plurality of individual systems in cooperation as one overall system, Using a relational model of the overall metric, which is an evaluation metric for the entire system, and the individual metrics, which are evaluation metrics for each individual system, or the operation parameters of each individual system that control the individual metrics, a search unit searches for and determines the conditions of the individual metrics or the operation parameters for which the overall metric improves. A notification unit that notifies each individual system of the conditions of the individual metrics or the operation parameters determined by the search unit having The search unit determines the presence or absence of conflict for combinations of the individual metrics, and sets additional conditions when determining the conditions of the individual metrics or the operation parameters that control the individual metrics for combinations of the individual metrics that have a conflict. A cooperation management system characterized by the above.

9. In the cooperation management system according to claim 8, The additional condition is an upper limit or a lower limit of the condition of the individual metric or the operation parameter. A cooperation management system characterized by the above.

10. A cooperation management method executed by a cooperation management system that operates a plurality of individual systems in cooperation as one overall system, Using a relational model of the overall metric, which is an evaluation metric for the entire system, and the individual metrics, which are evaluation metrics for each individual system, or the operation parameters of each individual system that control the individual metrics, search for and determine the conditions of the individual metrics or the operation parameters for which the overall metric improves. Notify each individual system of the determined conditions of the individual metrics or the operation parameters. Generate the relational model based on the overall metric, the individual metric, or the operation parameter. A cooperation management method characterized by having each process.

11. A cooperation management method executed by a cooperation management system that operates a plurality of individual systems in cooperation as one overall system, Using a relational model of the overall metric, which is an evaluation metric for the entire system, and the individual metrics, which are evaluation metrics for each individual system, or the operation parameters of each individual system that control the individual metrics, search for and determine the conditions of the individual metrics or the operation parameters for which the overall metric improves. Notify each individual system of the determined conditions of the individual metrics or the operation parameters. Apply the relational model to a search problem of searching for the conditions of the individual metrics or the operation parameters for which the overall metric improves. Select the characteristics of the search problem by the formulation method of the relational model. A cooperation management method characterized by having each process.

12. A cooperation management method executed by a cooperation management system that operates a plurality of individual systems in cooperation as one overall system, using a relationship model between an overall index that is an evaluation index for the overall system and an individual index that is an evaluation index for each individual system or an operation parameter of each individual system that controls the individual index, to search for and determine the conditions of the individual index or the operation parameter for which the overall index improves, notifying each individual system of the determined conditions of the individual index or the operation parameter, receiving from each individual system whether the conditions of the individual index or the operation parameter notified to each individual system can be accepted, and if not accepted, receiving from each individual system the constraints of the individual index or the constraints of the operation parameter, based on the constraints, re-executing the determination of the conditions of the individual index or the operation parameter A cooperation management method characterized by having each process.

13. A cooperation management method executed by a cooperation management system that operates a plurality of individual systems in cooperation as one overall system, using a relationship model between a plurality of overall indexes that are evaluation indexes for the overall system and an individual index that is an evaluation index for each individual system or an operation parameter of each individual system that controls the individual index, to search for and determine the conditions of the individual index or the operation parameter for which the overall index improves, notifying each individual system of the determined conditions of the individual index or the operation parameter, having each process, wherein the overall indexes are plural, determining the conditions of the individual index or the operation parameter so that a plurality of the overall indexes improve A cooperation management method characterized by this.

14. A cooperation management method executed by a cooperation management system that operates a plurality of individual systems in cooperation as one overall system, using a relationship model between an overall index that is an evaluation index for the overall system and an individual index that is an evaluation index for each individual system or an operation parameter of each individual system that controls the individual index, to search for and determine the conditions of the individual index or the operation parameter for which the overall index improves, notifying each individual system of the determined conditions of the individual index or the operation parameter, having each process, When determining the presence or absence of a contradiction for the combination of the individual indicators, and when executing the determination of the conditions of the individual indicators or the operation parameters for controlling the individual indicators of the combination of the individual indicators having a contradiction, additional conditions are set. A cooperation management method characterized by the above.

Images