Project plan adjustment tool and project plan adjustment method

Abstract

To provide a project plan adjustment tool for adjusting a plan value parameter of a project.SOLUTION: A project plan adjustment tool includes a plan value parameter input unit that accepts input of a first plan value parameter for each of phases into which a project is divided, a past result information storage unit that stores result value parameters and result evaluation values of phases of a plurality of past projects, a past result information analysis unit that conducts analysis while associating the result value parameters and the result evaluation values of the phases of the past projects, and generates a project prediction model, a project result prediction unit that predicts a result evaluation value from the first plan value parameter using the prediction model, and a plan value parameter adjustment unit that redistributes the first plan value parameters to the phases and outputs a second plan value parameter having undergone adjustment.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a project plan optimization tool that optimizes planned value parameters based on project result predictions when planning a project. [Background technology]

[0002] In software development projects, data is being utilized to analyze and make decisions based on the performance values ​​of accumulated project management data, which can efficiently advance project plans and detect risks early using predictive technology.

[0003] When planning a project, project outcome prediction technology has been developed that compares the planned values ​​with accumulated actual values ​​and predicts the results. There are various prediction methods, but one method searches through accumulated project management data for past projects that are similar to or have similar trends to the new project to be predicted, and predicts the project's evaluation value based on the management data of the past projects found.

[0004] At this time, the accumulated data includes explanatory variables used to find similarities and objective variables, which are the items to be predicted. The explanatory variables are values ​​based on the nature of the project and the development content, such as the product category and the scale of development. On the other hand, the objective variables are evaluation values ​​that indicate the results of the development project, such as the labor hours and costs determined at the end of past projects.

[0005] The relationship between explanatory variables and objective variables can be viewed as a causal relationship based on rules, and in project outcome prediction technology, the relationship between explanatory variables and objective variables is treated as a prediction model. In project outcome prediction technology, a prediction model receives input of explanatory variables for the project to be predicted, and outputs a predicted result evaluation value as the objective variable. Prediction technology can be applied at the start of a project, but there are explanatory variables that are difficult to determine at the start of a project, and some are input as planned values.

[0006] The following prior art is included as background art in this technical field. Patent Document 1 (JP Patent Publication 2022-32115 A) discloses a project sign detection device that includes a storage device that stores information on the contents and profit and loss of each past project, a process for extracting each piece of information on each past project from the storage device, and generating a decision tree for each explanatory variable by machine learning, with the values ​​of one or more predetermined items in the contents of each piece of information as explanatory variables and the profit and loss situation of each piece of information as a target variable, and a calculation device that extracts values ​​of items corresponding to the explanatory variables of the decision tree from the information on the contents of the target project, inputs them into the corresponding decision trees, and executes a process of calculating the failure probability of the target project by a random forest algorithm. [Prior art documents] [Patent documents]

[0007] [Patent Document 1] Patent Publication No. 2022-32115 Summary of the Invention [Problem to be solved by the invention]

[0008] The above project outcome prediction technology is used to create project plans. By planning a project based on appropriate planned values ​​that produce favorable results using project outcome prediction technology, the validity of the plan can be confirmed. For example, results based on planned values ​​created by humans can be checked using project outcome prediction technology to see if the plan is unrealistic. Furthermore, if necessary, the planned values ​​can be updated and predicted again, allowing adjustments to be made to obtain better predicted results.

[0009] On the other hand, in many cases, development projects are managed by dividing them into multiple phases, which are separated by the time of development and release. When planning a project, a new requirement is to allocate the planned values ​​of the development scale, period, budget, personnel, etc. to each phase. Project outcome prediction technology can be applied to each phase. In this case, explanatory variables for each phase are input, and a predicted result evaluation value can be output as the objective variable for each phase. When looking at the project plan as a whole for one objective variable, it is possible to confirm the progress of each phase throughout the project. For example, prediction results can be obtained from the perspective of which phase is likely to incur a burden. Based on these results, it is necessary to adjust the planned values ​​and take measures such as smoothing out the burden between phases and taking risk countermeasures for each phase.

[0010] After predicting the results for each phase into which a project is divided, adjusting the input values ​​of the explanatory variables so that the predicted result evaluation values ​​for each phase are values ​​that are desirable to the user requires a large amount of trial and error, and a technology is needed to perform this optimization automatically. [Means for solving the problem]

[0011] A representative example of the invention disclosed in the present application is as follows: That is, a project plan optimization tool that outputs information on improvement proposals for a business plan of a project is configured by a computer having a calculation device that executes calculation processing and a storage device accessible by the calculation device, and is characterized by comprising: a planned value parameter input unit to which a first planned value parameter for each of a plurality of phases into which the project is divided is input, a past performance information accumulation unit that accumulates a performance value parameter and a result evaluation value of each phase of a plurality of past projects, a past performance information analysis unit that associates and analyzes the performance value parameter and the result evaluation value of each phase of the past projects to generate a prediction model for the project, a project result prediction unit that predicts the result evaluation value from the first planned value parameter using the prediction model, and a planned value parameter optimization unit that reallocates the first planned value parameter between the phases and outputs an optimized second planned value parameter. Effect of the Invention

[0012] According to one aspect of the present invention, it is possible to optimize the planned value parameters of a project. Problems, configurations, and effects other than those described above will become apparent from the following description of the embodiments. [Brief description of the drawings]

[0013] [Figure 1] FIG. 1 is a diagram showing an overall configuration of a project plan optimization tool according to an embodiment of the present invention. [Diagram 2] 11 is a flowchart of an optimization process according to an embodiment of the present invention. [Diagram 3] FIG. 2 is a diagram showing multiple phases constituting a project according to an embodiment of the present invention. [Figure 4] FIG. 1 is a diagram illustrating definitions of project plan values ​​and result forecasts for each phase in an embodiment of the present invention. [Diagram 5] FIG. 13 is a diagram showing an example of the configuration of a migration rule table according to the embodiment of the present invention. [Figure 6] FIG. 13 is a diagram illustrating an example of a configuration of a goal definition table according to the embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] <Example 1> FIG. 1 is a diagram showing the overall configuration of a project plan optimization tool 100 according to the present embodiment.

[0015] The project plan optimization tool 100 includes a project result prediction unit 101, a planned value parameter optimization unit 102, a past performance information analysis unit 103, and a user interface unit 110. The user interface unit 110 has a function of presenting the execution results of a program to a user via a display device or an input device and receiving input from the user, and includes a planned value parameter input unit 111, a project forecast result output unit 112, a movement rule input unit 113, an optimization goal definition input unit 114, and an optimization result output unit 115. The past performance information analysis unit 103 is connected to a past performance information accumulation unit 120, refers to project performance information 121, and holds a prediction model 104 that is an analysis result.

[0016] The project result prediction unit 101 has a function of predicting the result of a project by simulating the project, and predicts a prediction result evaluation value based on the planning value parameters input to the planning value parameter input unit 111, based on the prediction model 104. The predicted prediction result evaluation value is displayed in the project prediction result output unit 112.

[0017] The planned value parameter optimization unit 102 optimizes the prediction result by reallocating the planned value parameters to the prediction result by the project result prediction unit 101. The constraint conditions of the planned value parameters in optimization are acquired from the movement rule input unit 113, and the goal conditions for optimization are acquired from the optimization goal definition input unit 114. The optimization result by the planned value parameter optimization unit 102 is output from the optimization result output unit 115.

[0018] A past performance information analysis unit 103 analyzes project performance information 121 stored in a past performance information accumulation unit 120, and generates and stores a prediction model 104.

[0019] To give a more specific example assuming a software development project, the past performance information stores a wide range of information such as the period, development scale (number of lines of development, number of requirements), product category, distinction between new development and derivative development, safety / security level, and execution environment (OS, CPU) that can be explanatory variables of the prediction model as project parameters. In addition, the final labor hours, cost (amount), quality (defect information), delivery date, etc. are stored as result information that can be objective variables. The past performance information analysis unit 103 models the causal relationships in these explanatory variables and objective variables, generates and holds the prediction model 104. Machine learning technology can be used as one of the generation methods. Generally, in such cases, supervised machine learning regression analysis is used, and the explanatory variables and objective variables are learned as supervised data to generate a prediction model.

[0020] The project plan optimization tool 100 of this embodiment is configured by a computer having a processor (CPU), a memory, an auxiliary storage device, a communication interface, an input interface, and an output interface.

[0021] The processor is a computing device that executes programs stored in a memory. The processor executes various programs to realize the functions of the functional units (e.g., project result prediction unit 101, planned value parameter optimization unit 102, past performance information analysis unit 103, etc.) of the project plan optimization tool 100. Note that some of the processes performed by the processor executing the programs may be executed by other computing devices (e.g., hardware such as ASIC and FPGA).

[0022] Memory includes ROM, which is a non-volatile storage element, and RAM, which is a volatile storage element. ROM stores unchanging programs (e.g., BIOS), etc. RAM is a high-speed, volatile storage element such as DRAM (Dynamic Random Access Memory), and temporarily stores programs executed by a processor and data used when executing the programs.

[0023] The auxiliary storage device is, for example, a large-capacity non-volatile storage device such as a magnetic storage device (HDD) or a flash memory (SSD). The auxiliary storage device also stores data used by the processor when executing a program, and the program executed by the processor. That is, the program is read from the auxiliary storage device, loaded into the memory, and executed by the processor to realize each function of the project plan optimization tool 100.

[0024] The communication interface is a network interface device that controls communications with other devices according to a predetermined protocol.

[0025] The input interface is an interface that receives input from a user, such as a keyboard or a mouse. For example, the input interface receives input of a file in which cost data is recorded and stored in an auxiliary storage device. The input interface may also provide a GUI and receive input of cost data from a user.

[0026] The output interface is an interface that outputs the execution result of a program in a format that can be viewed by a user, such as a display device or a printer. For example, the output interface outputs the execution result of a program. The output interface may also be a data output port that outputs the execution result of a program in a format that can be viewed by a user.

[0027] A terminal connected to the computer via a network may provide the input interface and the output interface.

[0028] The programs executed by the processor are provided to the computer via removable media (CD-ROM, flash memory, etc.) or a network, and are stored in a non-volatile auxiliary storage device, which is a non-transitory storage medium. For this reason, the computer should have an interface for reading data from removable media.

[0029] The project plan optimization tool 100 is a computer system configured on one physical computer, or on multiple logically or physically configured computers, and may operate on a virtual computer constructed on multiple physical computer resources. For example, the project result prediction unit 101, the planned value parameter optimization unit 102, and the past performance information analysis unit 103 may each operate on separate physical or logical computers, or multiple units may be combined to operate on a single physical or logical computer.

[0030] FIG. 2 is a flowchart of the optimization process of this embodiment.

[0031] The optimization process shown in FIG. 2 starts in a state where the prediction model 104, which is the premise of the process, has been generated by the past performance information analysis unit 103 (201).

[0032] When the process starts, in step 202, input of plan value parameters of each phase constituting the project is received from the plan value parameter input unit 111.

[0033] In step 203, the project result prediction unit 101 predicts the result evaluation value for the planned value parameters using the prediction model 104, and predicts the project result. The project result is predicted for each phase, and a series of predicted values ​​for one type of prediction target objective variable is output for the number of phases constituting the project.

[0034] In step 204, the predicted result evaluation value is presented to the user to confirm whether or not it is necessary to continue the optimization process. If it is not necessary to continue the optimization process, the process ends (205).

[0035] In step 206, a planned value parameter movement rule is received from the movement rule input unit 113 as a user input, and an optimization goal definition is received from the optimization goal definition input unit 114.

[0036] In step 207, the degree of deviation of the series of predicted values ​​generated in step 203 or step 210 described later is evaluated with respect to the input goal definition of optimization. For example, for a numerical sequence for which the goal definition can be changed, the deviation can be determined based on the difference with the corresponding predicted value. In this case, the phase with the largest deviation is selected and stored as the selected phase for the subsequent step.

[0037] In step 208, the possibility of moving the planned value parameters of the selected phase is evaluated according to the plan value parameter moving rules between phases, and candidates for the planned value parameters after the movement are prepared. This process is performed for all applicable movement rules, and the planned value parameter groups obtained by combining the planned value parameter candidates are listed as patterns and stored.

[0038] In step 209, for all patterns of the set of planned value parameters, the result evaluation values ​​are predicted in sequence by the project result prediction unit 101. A series of predicted result evaluation values ​​for all patterns is obtained.

[0039] In step 210, the closest outcome of all predicted outcome measures is recorded against the optimization goal definition.

[0040] In step 211, it is determined whether sufficient optimization has been performed. This determination may be made by determining the closeness to the optimization goal definition in the comparison in step 210 using a predetermined threshold, or it may be determined that sufficiency has been met based on the number of repetitions since step 207. As a result, if the optimization is insufficient, the process returns to step 207 and repeats the process.

[0041] If it is determined in step 211 that the optimization is sufficient, the optimized planned value parameters, which are the results of the optimization, are presented to the user in step 212, and the process ends (213).

[0042] 3 and 4, a specific example of the process performed in the project result prediction unit 101 will be described. This process is executed in steps 203 and 209.

[0043] Figure 3 is a diagram showing the multiple phases that make up a project. The horizontal axis is the timeline of the project, and four phases are defined on the timeline. Each phase exists by dividing the project along the timeline, but the period of each phase is not clearly separated by a certain date, and there may be overlapping periods between adjacent phases, or conversely, there may be gaps between phases.

[0044] FIG. 4 is a diagram showing definitions of project plan values ​​and result forecasts for each phase shown in FIG.

[0045] In step 202 , the planned value parameters of each phase, which are composed of an input value table 401 and a planned value parameter table 402 , are input to the planned value parameter input unit 111 .

[0046] In step 209, multiple patterns of planned value parameter groups corresponding to the input value table 401 and the planned value parameter table 402 are created according to the movement rule. These become candidates for optimization. The results of prediction using these are stored in the same data structure as the result prediction table 403.

[0047] In step 210, the input value table 401, the planned value parameter table 402, and the result prediction table 403 are stored for use in subsequent processing, using the set of planned value parameters that have resulted in the appropriate result at that point in time. If optimization is to be continued, the values ​​in the stored tables are used in steps 207 and 208. If the process proceeds to step 212, the values ​​in the stored tables are used.

[0048] The input value table 401 holds planned value parameters for each phase. Each planned value parameter is structured like the planned value parameter table 402, and the planned value is stored in the definition item. A different instance of the planned value parameter table 402 is created for each row of the input value table 401, and holds information for each phase.

[0049] The project result prediction unit 101 acquires information held in the input value table 401 and the planned value parameter table 402 for each phase, predicts the project result (man-hours, quality) using the prediction model 104, and stores the predicted values ​​in the result prediction table 403. When there are multiple types of objects to be predicted, a predicted value is stored for each prediction object. Fig. 4 shows an example of prediction for two types of prediction objects, man-hours and quality.

[0050] With reference to FIG. 5, the movement rule table 500 will be described.

[0051] A movement rule table 500 in which movement rules for planned value parameters are defined includes planned value parameters 501 and their movement rules 502, and the movement rules input by the user to the movement rule input unit 113 are recorded for each type of planned value parameter as shown in the following example rules. The movement rule table 500 is stored in the memory of the computer in which the project plan optimization tool 100 is implemented.

[0052] In the example shown in the first line, the planned value parameter "LOC" has two rules: "It can be moved up to 30% from the initial state" and "The distance of the moving phase is limited to one line ahead or behind." LOC is an abbreviation for Line of Code and represents the number of lines. The former rule specifies the maximum amount by which the planned value parameter LOC is moved in step 208, and for example, the planned value initially entered in step 202 is 1000 lines, and the rule states that it can be moved up to 30% ahead or behind, i.e., up to 300 lines, by optimization.

[0053] The latter is a rule regarding the range of destination phases that allows the planned value parameters to be moved only to adjacent phases before and after the selected phase when considering the movement of the planned value parameters in step 208 for the selected phase in step 207.

[0054] In the example shown in the second row, the planned value parameter "end date" is not movable, and is not subject to consideration of the possibility of moving in step 208. Among the project planned values, there are some planned value parameters that cannot be changed due to their nature or organizational reasons. Such rules can also be defined.

[0055] In the example shown in the third row, a rule is defined for the planned value parameter "number of tests" that "it moves in proportion to LOC." The planned value parameters are not independent and may have a correlation with each other. In such a case, it is desirable to maintain the relationship of the planned value parameters when considering the amount of movement in step 208. In this example, LOC and the number of tests are considered to be proportional, and the rule is to consider the possibility of moving both planned value parameters, the LOC value and the number of tests, while maintaining their proportional relationship. Such interrelationships may be three or more.

[0056] In the example shown in the fourth line, a numerical range specific to the planned value parameter is defined. In the example shown in Fig. 3, the upper limit of the number of developers is set to N people per unit time, and in step 208, a movement of the planned value that does not exceed this number is considered.

[0057] As described above, four examples have been shown in the transfer rule table 500, and in this format, the rules for transferring the planned value parameters between phases can be specified in step 206.

[0058] The example shown in Figure 5 is written in natural language, but it is a good idea to prepare a template for such rules in advance on the user interface and implement it in a format such as selecting the template and specifying the details using numbers. The template shows the rule definition in a format such as "Can move X% from the initial state" or "Move in proportion to X", and after selecting the template on the user interface, the numerical value of X or the target is entered. This template can be prepared without depending on any specific planned value parameters.

[0059] The user generates a migration rule table 500 in which migration rules are defined by sequentially assigning rules to each planned parameter. It is also assumed that rules are applied in a somewhat fixed manner depending on the organization. In such a case, a migration rule defined in a previously prepared table may be read, and the read migration rule may be customized for use.

[0060] Based on the definition of the movement rule table 500 shown in FIG. 5, in step 209, a pattern of parameter movement is generated. For example, if the movement rule is "can move up to 30% from the initial state", candidates for the amount of movement are selected within 30%. There are several possible approaches, but if it is performed collectively within a range, the possible range of the amount of movement is divided into equal intervals (for example, 10 equal parts) to create a group of candidates. Furthermore, according to the rule "up to one movement phase forward or backward", combinations of the amount of movement forward and backward are created as a group of candidates. In step 209, candidates are similarly created for the subsequent movement rules, prediction is performed using the prediction model 104 for all patterns of the planned value parameter group derived by the combination of candidates, and appropriate planned value parameters are found in step 210. It is good to evaluate all combinations, but as the number of combinations increases, an increase in the amount of calculation is expected, so it is good to suppress the increase in the amount of calculation by a method of selectively evaluating patterns using random numbers, etc., or by preferentially incorporating candidates with fewer differences from the initial state into the patterns. In addition, by using information on causal relationships in the prediction model 104, the priority of explanatory variables that have an influence according to the target goal definition may be grasped, and a pattern may be created according to that order.

[0061] The goal definition table 600 will be described with reference to FIG.

[0062] The goal definition table 600 records the contents of the goal definition input by the user in step 206. The goal definition table 600 includes a goal definition name 601, which is a name for identifying the goal definition, and its contents 602. In step 210, the goal definition is compared with the prediction result to evaluate the degree of achievement of optimization.

[0063] In the example of effort smoothing shown in the first line, the goal is to make the effort predicted for each phase as the objective variable uniform throughout the project. When the user inputs the goal definition, it is preferable that the goal definition can be specified in natural language as shown in content 602 or in a template similar to the above-mentioned movement rule. When evaluating in step 210, the objective variable specified in the goal definition content 602 is re-expressed as a numerical value as a result of the sequence for each phase. In effort smoothing, the goal is reached when the predicted result of the effort for each phase falls within a specified error range with the average effort for each phase. In step 210, the predicted result that minimizes the difference in effort for each phase and the planned value parameters after movement at that time are selected.

[0064] In the example of quality improvement shown in the second line, the goal is for quality to improve the later the phase in the chronological order. In this goal definition, unlike the example of effort mentioned above, a goal numerical value is defined that slopes according to the position of each phase on the time axis. The slope of the numerical value may be an implicitly specified value, or it may be specified by the user. When bug density or number of bugs are used as quality indicators, it is desirable for the quality indicators to decrease as time progresses toward completion. It is advisable to calculate the quality indicators of each phase as goal numerical values ​​based on the expected quality indicators for the entire project (bug density, number of bugs) and the specified slope.

[0065] As shown in Fig. 6, goal definitions are determined individually for multiple objective variables. Therefore, in the judgment of step 211, the closeness between the calculated objective variables and each goal definition shown in the goal definition table 600 is evaluated. Most simply, it is advisable to select as the solution the case in which the average difference between the calculated objective variables and each goal definition value is the smallest. The goal definition may be defined by a combination of multiple conditions.

[0066] Alternatively, a priority may be assigned to each goal definition, and a weighted average based on the priority may be used, allowing step 210 to select a solution that prioritizes goal definitions with higher priorities.

[0067] As described above, according to the project plan optimization tool of the embodiment of the present invention, the planned value parameters can be reallocated between the phases by moving the planned values ​​between the multiple phases that make up the project, and the planned value parameters can be optimized. In addition, the plan value movement rules can provide appropriate planned value parameters that ensure the validity of the planned values. Furthermore, the user inputs the shape of the planned value transition desired as a target goal, and the target goal is approached within the range permitted by the movement rules, so that the planned value parameters that derive the project results desired by the user can be obtained.

[0068] <Example 2> In the first embodiment, a candidate group for reallocation of planned value parameters is generated using the movement rule shown in FIG. 3 as a constraint condition, and the search for a planned value parameter that derives an appropriate prediction result is limited to the candidate group under this constraint condition. However, even when some constraints are released, a calculated value parameter that derives an appropriate prediction result may exist. In this case, if the released constraint is permissible, the optimized calculated value parameter obtained therein can also be used. In this embodiment, when listing possible patterns of parameter movement in step 208, it is possible to intentionally deviate from the movement rule, for example, to search for a combination of parameters that are optimized within a range of 50% rule deviation conditions for the movement rule in the range of "30% from the initial state" in FIG. 5, and it is considered that a more appropriate result can be obtained than when complying with the movement rule.

[0069] If a suitable result is found by deviating from such a movement rule, in the result display of step 212, the result of deviating from the movement rule and the result that complies with the movement rule are displayed together with the deviated movement rule, and the user can decide whether or not to deviate from the movement rule.

[0070] Note that among the movement rules, there are some strict ones that do not allow deviation, and some that allow deviation. By adding a specification of whether to allow attempts that deviate from the movement rules to the definition of the movement rules shown in Figure 3, it becomes possible to search for solutions without waste.

[0071] The present invention is not limited to the above-described embodiments, and includes various modified examples and equivalent configurations within the spirit of the appended claims. For example, the above-described embodiments have been described in detail to clearly explain the present invention, and the present invention is not necessarily limited to those including all of the configurations described. Furthermore, a part of the configuration of one embodiment may be replaced with the configuration of another embodiment. Furthermore, the configuration of another embodiment may be added to the configuration of one embodiment. Furthermore, a part of the configuration of each embodiment may be added, deleted, or replaced with another configuration.

[0072] In addition, each of the above-mentioned configurations, functions, processing units, processing means, etc. may be realized in hardware, for example by designing some or all of them as an integrated circuit, or may be realized in software by a processor interpreting and executing a program that realizes each function.

[0073] Information such as programs, tables, and files that realize each function can be stored in a storage device such as a memory, a hard disk, or an SSD (Solid State Drive), or in a recording medium such as an IC card, an SD card, or a DVD.

[0074] In addition, the control lines and information lines shown are those considered necessary for the explanation, and do not necessarily show all the control lines and information lines necessary for implementation. In reality, it can be considered that almost all components are connected to each other. [Explanation of symbols]

[0075] 100 Project Planning Optimization Tools 101 Project Outcome Forecasting Department 102 Planned value parameter optimization unit 103 Past Performance Information Analysis Department 104 Predictive Model 110 User Interface Section 111 Planned value parameter input section 112 Project forecast result output section 113 Movement rule input section 114 Optimization goal definition input section 115 Optimization result output unit 120 Past Performance Information Storage Unit 121 Project performance information 401 Input Value Table 402 Planned Value Parameter Table 403 Result Prediction Table 500 Movement Rules Table 600 Goal Definition Table

Claims

1. A project plan optimization tool that outputs information regarding improvement proposals for a project's business plan, The present invention is configured as a computer having a computing device that executes arithmetic processing and a storage device that can be accessed by the computing device, a plan value parameter input unit to which a first plan value parameter for each of a plurality of phases into which the project is divided is input; a past performance information storage unit that stores performance value parameters and result evaluation values ​​of each phase of a plurality of past projects; a past performance information analysis unit that analyzes the performance parameter and the result evaluation value of each phase of the past project in association with each other to generate a prediction model for the project; a project result prediction unit that predicts a result evaluation value from the first plan value parameter by using the prediction model; and a planned value parameter optimization unit that reallocates the first planned value parameter among the phases and outputs an optimized second planned value parameter.

2. 2. The project plan optimization tool according to claim 1, The past performance information analysis unit Analyzing the performance value parameters and the result evaluation values ​​stored in the past performance information storage unit by machine learning for each phase; A project plan optimization tool that generates a prediction model that learns the causal relationship between the performance value parameters and the result evaluation values.

3. 2. The project plan optimization tool according to claim 1, The project result prediction unit calculates a plurality of result evaluation values ​​by simulating a plurality of projects using a plurality of planned value parameters; A project plan optimization tool characterized in that the planned value parameter optimization unit selects a result evaluation value that is close to a goal definition set in accordance with the project's objectives, and outputs a second planned value parameter corresponding to the selected result evaluation value.

4. 4. The project plan optimization tool according to claim 3, The project plan optimization tool is characterized in that the planned value parameter optimization unit determines that optimization is completed by selecting a result evaluation value within a predetermined error range in accordance with the goal definition, and outputs a second planned value parameter corresponding to the selected result evaluation value.

5. 4. The project plan optimization tool according to claim 3, The goal definition is defined by a combination of a plurality of conditions, and a priority is assigned to the plurality of conditions.

6. 4. The project plan optimization tool according to claim 3, A project planning optimization tool, characterized in that the goal definition is a transition of evaluation values ​​depending on the position of each phase on the timeline of the project.

7. 2. The project plan optimization tool according to claim 1, The planned value parameter optimization unit Based on the movement rules preset for each type of planned value parameter, an appropriate result evaluation value is derived, and a combination of movement of the planned value parameters between phases is searched for; A project plan optimization tool that outputs a second plan value parameter based on the combination found.

8. The project plan optimization tool according to claim 7, A project plan optimization tool characterized in that the movement rules can specify at least one of whether or not a planned value parameter can be moved, the amount by which the planned value parameter can be moved, the range of phases to which the planned value parameter is moved, and the numerical range of the planned value parameter after the movement.

9. The project plan optimization tool according to claim 7, The project plan optimization tool according to the present invention is characterized in that the movement rules include rules for maintaining relationships between multiple correlated planned value parameters.

10. The project plan optimization tool according to claim 7, The planned value parameter optimization unit Searching for a combination of reallocation of the planned value parameters in a range that deviates from the movement rule; A project plan optimization tool comprising: a second planned value parameter having a movement rule deviation condition attached thereto;

11. A project plan optimization method executed by a project plan optimization tool that outputs information regarding improvement proposals for a project's business plan, comprising: The project plan optimization tool is configured by a computer having a calculation device that executes calculation processing and a storage device that can be accessed by the calculation device, the storage device includes a past performance information storage unit that stores performance value parameters and result evaluation values ​​of each phase of a plurality of past projects; The project plan optimization method includes: a planned value parameter input step of inputting a first planned value parameter for each of a plurality of phases into which the project is divided; a past performance information analysis step of analyzing performance parameters and result evaluation values ​​of each phase of the past project in association with each other to generate a prediction model for the project; a project outcome forecasting step of forecasting an outcome evaluation value from the first planned value parameter using the forecasting model; and a planned value parameter optimization procedure for reallocating the first planned value parameter among the phases to output an optimized second planned value parameter.

Images