Information processing device, and information processing method

The information processing device uses predictive modeling to identify project deterioration early, reducing human resource costs by identifying key variables and optimizing monitoring resource allocation.

JP2024169876AActive Publication Date: 2024-12-06HITACHI SOCIAL INFORMATION SERVICES LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
JP2023086701
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-05-26
Publication Date
2024-12-06
Estimated Expiration
2043-05-26

AI Technical Summary

Technical Problem

Conventional wide-area monitoring systems struggle to detect project deterioration at an early stage and require significant human resources to determine which projects should be prioritized for intensive monitoring, often leading to inefficiencies and increased costs due to the investigation of numerous small-scale projects.

Method used

An information processing device and method that generates a predictive model using machine learning to forecast project cost overruns, providing a basis for early detection of project deterioration and reducing human resource costs by identifying key explanatory variables.

Benefits of technology

Enables early detection of project deterioration through wide-area monitoring, minimizing the need for extensive human intervention in determining priority monitoring targets and optimizing resource allocation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024169876000001_ABST
    Figure 2024169876000001_ABST
Patent Text Reader

Abstract

To detect a sign of worsening of a project earlier in wide area monitoring, and decrease a human cost for determining whether to make it a target of intensive monitoring.SOLUTION: The present invention discloses an information processing device 100 which includes: a generation unit 1 which generates a prediction model trained with monitoring information of a finished first project; a predicting unit 2 which inputs an explanation variable of a second project in process to the prediction model, and outputs a predicted value of estimate cost presumed exceedance of the second project and an explanation variable being a basis of the predicted value; and an integration unit 5 which creates an integrated project obtained by integrating the selected second project and a plurality of kinds of selected first project.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to an information processing device and an information processing method. [Background technology]

[0002] In recent years, there has been active development of technologies to promote Digital Transformation (DX), and as part of this, importance is being placed on status monitoring of projects such as software development. Status monitoring can be divided into two categories: focused monitoring and wide-area monitoring. Focused monitoring is monitoring of projects by the management department. Wide-area monitoring is monitoring of all projects using specified tools. In status monitoring, first, projects that are judged to have a high possibility of failure or a large impact in the event of failure in wide-area monitoring based on data such as costs entered into the tool are targeted for focused monitoring. Next, with support from the management department, efforts are made to prevent deterioration or improve the projects that are the subject of focused monitoring.

[0003] Conventional wide-area monitoring would identify projects after problems, such as costs exceeding estimates, become apparent. In light of the goal of leading a project to success, it is preferable to detect signs of project deterioration at an early stage before problems become apparent. However, conventional wide-area monitoring had the problem of making it difficult to detect signs of project deterioration at an early stage before problems become apparent.

[0004] Furthermore, in conventional wide-area monitoring, investigations are conducted to determine whether or not a project of concern should really be the subject of priority monitoring. The investigations include, for example, investigating the scale of the project and the amount of overruns in estimated costs. However, such investigations require a great deal of human resources. For this reason, projects with large order amounts and other projects that would be greatly affected if the situation were to worsen are given priority, and monitoring of all projects, including small-scale projects, is not conducted. In other words, conventional wide-area monitoring had the problem of requiring a large human resources cost to determine which projects should be the subject of priority monitoring.

[0005] In addition, in conventional wide-area monitoring, there are cases where the number of projects of concern extracted is too large, which leads to the problem of even greater personnel costs required for investigations to determine whether or not to make them the subject of priority monitoring. Also, when the project to be monitored is small-scale, the values ​​such as estimated cost overruns are so small that they cannot be investigated, which leads to the problem of extra personnel costs being required for the investigation of that project.

[0006] Patent Document 1 discloses a prediction device, a prediction method, and a program for predicting future data with high accuracy even when the amount of time-series data is small when predicting future data using the time-series data. [Prior art documents] [Patent documents]

[0007] [Patent Document 1] JP 2016-103243 A Summary of the Invention [Problem to be solved by the invention]

[0008] In view of the above circumstances, an object of the present invention is to detect early signs of deterioration in a project through wide-area monitoring, and to reduce the human cost of determining whether or not to make a project a target for priority monitoring. [Means for solving the problem]

[0009] The present invention solves the above problems, a generation unit for generating a predictive model trained on monitoring information of a completed first project; a prediction unit that inputs explanatory variables of a second project in process into the prediction model and outputs a predicted value of an estimated cost overrun of the second project and explanatory variables that are the basis of the predicted value; The information processing device includes: a summarizing unit that creates a summarizing project by summarizing the selected second project and the selected types of first projects.

[0010] The present invention also provides a method for producing a semiconductor device comprising the steps of: An information processing device, generating a predictive model trained on monitoring information of the completed first project; inputting explanatory variables of a second project in process into the prediction model, and outputting a predicted value of an estimated cost overrun of the second project and explanatory variables that are the basis of the predicted value; creating a combined project that combines the selected second project and the selected plurality of types of first projects. Effect of the Invention

[0011] According to the present invention, it is possible to detect early signs of deterioration in a project through wide-area monitoring, and to reduce the human cost of determining whether or not to make a project a target for priority monitoring. [Brief description of the drawings]

[0012] [Figure 1] FIG. 2 is a diagram illustrating an example of a functional configuration of an information processing device according to the present embodiment. [Diagram 2] 13 is a screen example of output information from a prediction unit. [Diagram 3] 4 is an example of a flowchart illustrating a process according to the present embodiment. [Figure 4] 13 is an example of a flowchart illustrating a consolidation process. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] First Embodiment [composition] The information processing device 100 shown in FIG. 1 is a computer that detects signs of deterioration in a project in progress through wide-area monitoring. The information processing device 100 includes hardware such as an input unit, an output unit, a control unit, and a storage unit. For example, when the control unit is configured with a CPU (Central Processing Unit), information processing by a computer including the control unit is realized by program execution processing by the CPU. Furthermore, the storage unit included in the computer stores various programs for realizing the functions of the computer according to instructions from the CPU. This realizes collaboration between software and hardware. The programs can be provided by recording them on a recording medium or via a network. The output unit may include a function of a display unit that displays on a screen.

[0014] A project is a task to achieve a specific purpose. Projects can be classified into past projects that have been completed and projects that are in progress. In this embodiment, past projects are called "first projects" and projects that are in progress are called "second projects." In addition, when there is no need to distinguish between past projects and projects that are in progress, they are simply called "projects."

[0015] 1, the information processing device 100 includes a generation unit 1, a prediction unit 2, and a compilation unit 5. The information processing device 100 also stores a first project DB 3 and a second project DB 4. The compilation unit 5 will be described later.

[0016] The generation unit 1 generates a prediction model for predicting the actual estimated cost of the second project by machine learning. The actual estimated cost is an estimated value of the cost that will occur by the end of the second project. There are multiple types of cost, such as manufacturing cost and sales cost, but in this embodiment, the cost is defined as an economic resource consumed to achieve a specific purpose, measured in monetary terms, and is described as a term that includes manufacturing cost, sales cost, etc. The prediction unit 2 uses the prediction model generated by the generation unit 1 to predict the actual estimated costs of the second project. The first project DB3 is a database that stores the monitoring information of the first project for each first project. The second project DB4 is a database that stores the monitoring information of the second project for each second project.

[0017] <Project monitoring information> The project monitoring information is information for monitoring the status of the project. The first project monitoring information can be composed of, for example, production number information, explanatory variables, and objective variables.

[0018] The production number information is information for identifying the first project. For example, the production number information includes, but is not limited to, a production number, a progress rate (%), and a production number name. The production number is an identifier for the first project and can be expressed, for example, as an alphanumeric string. The progress rate is a parameter that quantitatively indicates the progress of the first project. The project name is the name of the first project and can be expressed in a conceivable word, for example.

[0019] The explanatory variables are variables that express the state of the first project. There are multiple types of explanatory variables. Examples of explanatory variables include, but are not limited to, the start time of work, the end time of work, actual cost, forecast cost, estimated cost, person in charge, work time, and actual man-hours. For example, Boruta can be used to extract explanatory variable candidates, and the optimal explanatory variable can be selected from them, but the method of selecting explanatory variables is not limited to this. The work start time is the start time (year, month, day) of the first project. The work completion date is the completion date (year, month, and date) of the first project. The actual cost is the cost incurred from the start of the work to a specified time. Projected costs are costs that are expected to occur from a specified time until the end of the work. The estimated cost is the cost expected to be incurred from the start of the work to the end of the work. The person in charge is the person(s) in charge of the first project. The working time is the time each person in charge spent working on the first project from the start of the work to a specified time. The actual man-hours are the man-hours that have been completed from the start of work to a specified time out of the total man-hours that make up the first project. The predetermined time is any time between the start time and the end time of the work.

[0020] The objective variable is a variable that depends on the explanatory variables. The objective variable can be, for example, the final actual cost, which is the actual cost at the end of the first project, but is not limited to this.

[0021] (Progress rate) The progress rate can be calculated, for example, based on a time standard. For example, if the period from when work on a project starts to when it ends is 30 days and the target period is the 15th day from when work starts, the progress rate is 50%. Since the first project is a past project that has been completed, the progress rate at the current time is 100%. Here, the explanatory variables of the first project can be values ​​that change depending on the progress rate. The monitoring information of the first project can be configured as a collection of explanatory variables for each progress rate.

[0022] For example, the actual cost as an explanatory variable is a set of actual costs at all progress rates between 0% and 100%. The actual cost at a progress rate of X% is the cost incurred between the start of work and the time corresponding to the progress rate of X%. Furthermore, the forecast cost as an explanatory variable is a set of forecast costs at all progress rates between 0% and 100%. The forecast cost at a progress rate of X% is the cost expected to be incurred between the time corresponding to the progress rate of X% and the time the work is completed. Note that there are explanatory variables that do not change depending on the progress rate, such as the start and end of work, but it is preferable to treat such explanatory variables as constants that take the same value depending on the progress rate.

[0023] On the other hand, the monitoring information of the second project can be composed of, for example, production number information and explanatory variables.

[0024] The production number information is information for identifying the second project. For example, the production number information includes, but is not limited to, a production number, a progress rate (%), and a production number name. The production number is an identifier of the second project and can be expressed, for example, as an alphanumeric string. The progress rate is a parameter that quantitatively indicates the progress of the second project. The project number is the name of the second project and can be expressed, for example, in a conceivable word.

[0025] The explanatory variables are variables that express the state of the second project. There are multiple types of explanatory variables. Examples of explanatory variables include, but are not limited to, the start time of work, the end time of work, actual cost, forecast cost, estimated cost, person in charge, work hours, and actual man-hours. For example, it is possible to extract explanatory variable candidates using Boruta and select the optimal explanatory variable from among them, but the method of selecting explanatory variables is not limited to this. The work start date is the start date of the second project. The work completion date is the completion date (year, month, and date) of the second project. The actual cost is the cost incurred from the start of the work to a specified time. Projected costs are costs that are expected to occur from a specified time until the end of the work. The estimated cost is the cost expected to be incurred from the start of the work to the end of the work. The person in charge is the person(s) in charge of the second project. The working time is the time each person in charge spent working on the second project from the start of the work to the specified time. The actual man-hours are the man-hours that are completed from the start of work to a specified time out of the total man-hours that make up the second project. The predetermined time is the present time between the work start time and the work end time. As already explained, the actual estimated cost of the second project is the sum of the actual cost and the forecast cost of the second project.

[0026] The progress rate of the second project can be calculated as the ratio of the period from the start of work to the end of work to the period from the start of work to the present. The actual cost of a progress rate of X%, which corresponds to the present, is the cost incurred from the start of work to the present. Furthermore, the forecasted cost of a progress rate of X%, which corresponds to the present, is the cost expected to be incurred from the present to the end of work. Note that there are explanatory variables that do not change depending on the progress rate, such as the start and end of work, but it is preferable to treat such explanatory variables as constants that take the same value depending on the progress rate.

[0027] <Prediction model> (training) The generation unit 1 can generate a prediction model by combining, for example, multiple decision trees used in a random forest. A random forest is a machine learning algorithm, and is an ensemble learning algorithm that uses multiple decision trees and makes predictions by majority vote. The decision tree can be configured as a tree-like logic that combines, for example, judgment conditions using explanatory variables. The judgment conditions can be designed as appropriate, and can be, for example, whether or not the average daily working hours of a person in charge are 5 hours or more.

[0028] The generation unit 1 can train the prediction model using the monitoring information of the first project as training data. For example, for each first project, explanatory variables at a time point corresponding to a progress rate of 50% in the monitoring information of the first project can be used as input to the prediction model. Also, a value based on the objective variable of the monitoring information of the first project can be used as output of the prediction model. For example, the estimated cost overrun value obtained by subtracting the estimated cost from the final actual cost of the first project can be used as output of the prediction model. The generation unit 1 trains the prediction model using monitoring information of a predetermined number of first projects.

[0029] Here, the generating unit 1 prepares a plurality of prediction models, and can output the prediction models in a plurality of stages. For example, the generating unit 1 prepares a first prediction model and a second prediction model. The input of the first prediction model targets the monitoring information of all the first projects, and can be an explanatory variable of the monitoring information at a time when the progress rate is 50%. The output of the first prediction model can be whether or not there is an estimated cost overrun (greater than 0M (0 yen)) obtained by subtracting the estimated cost from the final actual cost of the first project. Next, the input of the second prediction model targets the monitoring information of the first project in which there is an estimated cost overrun in the output of the first prediction model, and can be an explanatory variable of the monitoring information at a time when the progress rate is 50%. The output of the second prediction model can be whether or not the estimated cost overrun is 1M (1 million yen) or more. As a result, the output of the prediction model can be classified into three values: the estimated cost overrun is 0M or less, greater than 0M and less than 1M, and 1M or more.

[0030] (prediction) The prediction unit 2 uses the trained prediction model to predict the actual estimated cost of the second project to be predicted. For example, the prediction unit 2 inputs explanatory variables from the monitoring information of the second project, that is, at the present time, i.e., at a time corresponding to a predetermined progress rate (preferably 50% or more, but may be less than 50%), into the prediction model. The prediction unit 2 can then obtain a value based on the actual estimated cost as the output of the prediction model. For example, the prediction unit 2 can obtain a value of the estimated cost overrun, which is obtained by subtracting the estimated cost from the actual estimated cost.

[0031] When the prediction model is the first prediction model or the second prediction model described above, the prediction unit 2 inputs the current explanatory variables from the monitoring information of the second project to be predicted into the first prediction model. Then, the prediction unit 2 can obtain a value indicating whether or not there has been an estimated cost overrun (greater than 0M (0 yen)) as the output of the first prediction model. If there has been an estimated cost overrun, the prediction unit 2 inputs the current explanatory variables from the monitoring information of the second project into the second prediction model. Then, the prediction unit 2 can obtain a value indicating whether or not the estimated cost overrun is 1M (1 million yen) or more as the output of the second prediction model. As a result, the estimated cost overrun can be classified into three values: 0M or less, greater than 0M and less than 1M, and 1M or more. Note that 1M and 0M are merely examples, and the value may be greater than 1M or greater than 0M, or may be less than 1M or less than 0M.

[0032] The prediction unit 2 can output information including the output of the prediction model. For example, the display unit of the information processing device 100 can display the output information of the prediction unit 2 on a screen as shown in Fig. 2. As shown in Fig. 2, the output information of the prediction unit 2 can be in a table format with "prediction result", "production number information", and "explanatory variables and features of the prediction result" as columns, and the second project as rows.

[0033] The "prediction result" indicates the output content of the prediction model. The "prediction result" is composed of an "item number", a "predicted value", and a "confidence factor". "Item number" is the line number assigned to each second project. "Predicted value" is the result according to a three-value classification of estimated cost overruns when the forecast model is a combination of the first and second forecast models already explained. "1: Overrun by 1 million yen" corresponds to 1 million or more. "2: Overrun by less than 1 million yen" corresponds to greater than 0 million and less than 1 million. "3: No problem" corresponds to 0 million or less. "Confidence" is the reliability of the prediction and is indicated by a value between 0% and 100%. For example, the confidence can be calculated using bagging, but is not limited to this.

[0034] The "production number information" is the same as the production number information in the monitoring information of the second project. "Explanatory variables and features of prediction results" shows the explanatory variables that contribute to the "prediction results." "Explanatory variables and features of prediction results" consists of a "list of explanatory variables" and a "feature ranking." The "List of explanatory variables" is the same as the explanatory variables for the monitoring information of the second project. The "feature ranking" indicates the rank of explanatory variables that contribute to the "prediction result". The higher the rank, the greater the contribution rate of that explanatory variable to the output of the predicted value. For example, the contribution rate of each variable can be calculated using the Shapley Additive exPlanations (SHAP) algorithm, but is not limited to this.

[0035] According to the first embodiment, it is possible to extract second projects whose estimated cost exceeds the estimated cost by 1M or more. Therefore, it is possible to detect early signs of deterioration of a project through wide-area monitoring.

[0036] (Decision on whether to subject to intensive monitoring) The management department, having obtained the output information in Figure 2, decides whether or not to make the second project, which has an estimated cost overrun of 1M yen, a target for intensive monitoring. Conventionally, even if AI detected signs of deterioration in a project, the basis for the AI's prediction results was a black box. For this reason, it was not easy for the management department to track down the causes of the signs of deterioration in the project based on the AI's prediction results, and it required a large amount of human resources to decide whether or not to make it a target for intensive monitoring.

[0037] The "Feature Ranking" in Figure 2 can be said to show the reason why the estimated cost overrun became 1M or more. By referring to the "Feature Ranking", the management department can easily identify the explanatory variables that contributed greatly to the prediction that the estimated cost overrun became 1M or more. As a result, it becomes easier to decide whether or not to subject the second project to intensive monitoring, and the human cost of deciding whether or not to subject it to intensive monitoring can be reduced.

[0038] [process] The process executed by the information processing device 100 is as shown in Fig. 3. That is, first, the generating unit 1 generates a prediction model (step S1). Next, the generating unit 1 trains the prediction model using monitoring information of the first project at a predetermined progress rate (step S2). Next, the predicting unit 2 uses the prediction model to output a predicted value of the estimated cost overrun of the target second project and explanatory variables contributing to the predicted value as prediction grounds (step S3). The management department judges, based on the prediction grounds, whether or not to target the second project showing signs of deterioration as a target for intensive monitoring.

[0039] Second Embodiment In explaining the second embodiment, differences from the first embodiment will be explained, and overlapping points will be omitted. In the first embodiment, the explanatory variables of the monitoring information of the first project, which is the training data, were explanatory variables at a time when the progress rate was equivalent to 50%. In the second embodiment, the time of the explanatory variables of the first project used for the training data is periodic.

[0040] For example, if the duration of the first project, i.e., the period from the start of work to the end of work, is several months, the period of the explanatory variables used in the training data, i.e., the training date (learning date), is set to the 25th of each month. Therefore, if work on the first project of work number A starts on 4 / 15 and ends on 6 / 30, the training dates for the first project of work number A will be 4 / 25, 5 / 25, and 6 / 25. In other words, from the monitoring information for the first project of work number A, the explanatory variables on 4 / 25 (explanatory variables with a progress rate equivalent to 4 / 25), the explanatory variables on 5 / 25 (explanatory variables with a progress rate equivalent to 5 / 25), and the explanatory variables on 6 / 25 (explanatory variables with a progress rate equivalent to 6 / 25) for a total of three times will be input into the prediction model. Also, if the work start date for the first project of work number B is 5 / 1 and the work end date is 9 / 15, the training dates for the first project of work number B will be 5 / 25, 6 / 25, 7 / 25, and 8 / 25. In other words, from the monitoring information for the first project of work number B, the explanatory variables on 5 / 25 (explanatory variables with a progress rate equivalent to 5 / 25), the explanatory variables on 6 / 25 (explanatory variables with a progress rate equivalent to 6 / 25), the explanatory variables on 7 / 25 (explanatory variables with a progress rate equivalent to 7 / 25), and the explanatory variables on 8 / 25 (explanatory variables with a progress rate equivalent to 8 / 25) for a total of four times will be input into the prediction model. In addition, if the work start date for the first project of work number C is 6 / 1 and the work end date is 7 / 10, the training date for the first project of work number C will be 6 / 25. In other words, the explanatory variables for 6 / 25 (explanatory variables with a progress rate equivalent to 6 / 25) from the monitoring information for the first project of work number C are used as input for the prediction model for one session.

[0041] As a result, explanatory variables at multiple types of progress rates are input to the prediction model for most of the first project. Using the prediction model trained in this way, the prediction unit 2 predicts the actual estimated cost of the second project. In this case, even if the progress rate of the second project is low (e.g., about 30%) and explanatory variables at a period equivalent to the low progress rate are input to the prediction model, it has been confirmed that the confidence level of the predicted value output by the prediction unit 2 (see FIG. 2) is sufficiently high.

[0042] According to the second embodiment, the training date can be set to a regular date, and explanatory variables for multiple types of progress rates for the same first project can be input to the prediction model. This allows for earlier prediction of the actual estimated cost of the second project. In addition, by regularizing the training dates, the input to the predictive model for all primary projects can be systematized, simplifying the processing required for training.

[0043] <<Summary work>> As mentioned above, the production number included in the production number information constituting the project monitoring information is an identifier for the project, and is assigned to each project. A project can be divided into multiple types of work, and can be treated as a collection of multiple types of work. A production number can be assigned to each work, and each work can be identified by the assigned production number. The production number assigned to a project can be associated with the production numbers assigned to the multiple types of work into which the project is divided.

[0044] The information processing device 100 can equate projects with work when it comes to processing signs of deterioration. Work may be called a small-scale project. In this embodiment, past work is called a "first work" and work in progress is called a "second work". Furthermore, when there is no need to distinguish between past work and work in progress, they are simply called "work". The information processing device 100 can store a database that stores work monitoring information for each work, similar to the first project DB3 and the second project DB4 (however, this is not shown in FIG. 1).

[0045] The information processing device 100 can set monitoring information for tasks as well as projects. Task monitoring information is information for monitoring the status of a task. The monitoring information for a first task can be composed of, for example, production number information, explanatory variables, and objective variables. The monitoring information for a second task can be composed of, for example, production number information and explanatory variables.

[0046] The consolidation unit 5 shown in FIG. 1 consolidates a plurality of types of work into one to create a consolidation work. A "consolidation work" is a collection of a plurality of types of work. The plurality of types of work that are consolidated into a consolidation work can be appropriately selected by, for example, the operator of the information processing device 100, but is not limited to this. For example, the plurality of types of work that are consolidated into a consolidation work may be work that constitutes the same project, or may be work that constitutes different projects.

[0047] The information processing device 100 can equate a consolidation task with a project or task in terms of processing a deterioration sign. In this embodiment, the consolidation task of consolidating multiple types of past tasks into one is called a "first consolidation task," and the consolidation task of consolidating multiple types of tasks including at least one task in progress into one is called a "second consolidation task." In addition, when there is no distinction between the consolidation task of consolidating multiple types of past tasks into one and the consolidation task of consolidating multiple types of tasks including at least one task in progress into one, they are simply called "consolidation tasks." The information processing device 100 can store monitoring information of the consolidation task in a database (not shown in FIG. 1) that stores task monitoring information for each task.

[0048] Similar to the project monitoring information and task monitoring information, the consolidation unit 5 can set monitoring information for the consolidation task. The consolidation task monitoring information is information for monitoring the status of the consolidation task, and the first consolidation task monitoring information can be composed of, for example, production number information, explanatory variables, and objective variables. The second consolidation task monitoring information can be composed of, for example, production number information and explanatory variables.

[0049] The value of the explanatory variable for the combining task can be calculated using the values ​​of explanatory variables for multiple types of tasks that are combined into the combining task. For example, if the explanatory variables are amounts such as cost, profit and loss, and estimates, the value of the explanatory variables for the grouping task can be calculated as the sum of the explanatory variables for the multiple tasks that are grouped together as the grouping task. Instead of the sum, the average, median, maximum, or minimum value may be used. In addition, for example, when the explanatory variable is a time such as task time, the value of the explanatory variable of the summing up task can be calculated as the sum of the explanatory variables of the multiple types of tasks that are summed up as the summing up task. Instead of the sum, the average, median, maximum, or minimum value may be used. Furthermore, for example, when the explanatory variables are numerical values ​​such as actual man-hours, the value of the explanatory variables for a grouping task can be calculated as the sum of the values ​​of the explanatory variables for the multiple types of tasks that are grouped together as the grouping task. Furthermore, for example, if the explanatory variables are times such as the start time and end time of a task, the value of the explanatory variables of the combining task can be calculated as the minimum or maximum value of the explanatory variables of the multiple tasks that are combined into the combining task. The earliest start time among the start times of the multiple tasks that are combined into the combining task can be set as the start time of the combining task. The latest end time among the end times of the multiple tasks that are combined into the combining task can be set as the end time of the combining task. Also, for example, if the explanatory variables are non-numeric variables such as a person in charge, the value of the explanatory variables for the consolidation task can be calculated as the union of the values ​​of the explanatory variables for the multiple types of tasks that are consolidated into the consolidation task. Each person in charge of the multiple types of tasks that are consolidated into the consolidation task can be set as the person in charge of the consolidation task.

[0050] Depending on the type of explanatory variable, the values ​​of the explanatory variables of the multiple types of tasks that are combined into a combining task may be used as they are for the explanatory variable values ​​of the combining task, or may not be used for the explanatory variable values ​​of the combining task. In the same manner as in the case of the explanatory variables, the value of the objective variable for the consolidation task can be calculated using the values ​​of the objective variables for the multiple types of tasks (mainly the first task) that are consolidated into the consolidation task.

[0051] (Summary Code) The summarizing unit 5 can assign summarizing codes to the tasks and the summarizing tasks. The summarizing code identifies multiple types of tasks that can be summarized as a summarizing task. The summarizing code may be included in the monitoring information of the tasks, or may be included in the monitoring information of the summarizing task. The summarizing unit 5 creates a summarizing task for multiple types of tasks selected by the operator. The summarizing unit 5 can assign the same summarizing code, for example, "code A", to multiple types of tasks and the summarizing tasks. The information processing device 100 can manage the relationship between the summarizing tasks and the multiple types of tasks that can be summarized as a summarizing task by referring to "code A".

[0052] (prediction) In the same way as the prediction of the second project already described, the prediction unit 2 can predict the actual estimated cost of the second work to be predicted using the trained prediction model. However, there are cases where the second work to be predicted is small-scale, the period from the start of the work to the end of the work is extremely short, and the amounts of the cost, profit and loss, estimate, etc. are extremely small. In such cases, the output value of the prediction model may be extremely small or may not be outputtable, resulting in a problem of reduced prediction accuracy of the actual estimated cost.

[0053] To solve such a problem, the operator selects multiple types of work including the second work to be predicted, and the summarizing unit 5 can create a summarizing work by summarizing the selected works. The selected work can be, for example, the second work to be predicted and multiple types of first work. The summarizing unit 5 can use the sum of the explanatory variable values ​​of the selected works as the explanatory variable value of the summarizing work. The prediction unit 2 can predict the actual estimated cost for the summarizing work including the second work to be predicted. By using the sum, the period from the start time of the work to the end time of the work can be sufficiently large, and the amounts of the cost, profit and loss, estimate, etc. can be sufficiently large. Therefore, the prediction accuracy of the prediction unit 2 can be improved to a desired level or higher.

[0054] In addition, by including the wrap-up work in the prediction target, the prediction unit 2 may simultaneously predict the second work of the original prediction target. In this case, there is a high possibility that the prediction accuracy for the second work of the original prediction target can be improved. In addition, when there are other second tasks in addition to the second task to be predicted, the summarizing unit 5 may select the other second tasks to create a summarizing task. The prediction unit 2 can predict the actual estimated cost even when there are multiple prediction targets.

[0055] (Example 1 of summary task usage) Project P1 as the second project is divided into multiple types of work W1 as the first work and work W2 as the second work. If the operator wants to predict the actual estimated cost of work W2, but work W2 is small-scale, the operator selects work W1 and work W2. The consolidation unit 5 can create a consolidation work T1 that consolidates the work W2 to be predicted and the selected multiple types of work W1. The consolidation unit 5 also assigns the same consolidation code "code A" to the selected work W1, W2, and consolidation work T1. Then, the prediction unit 2 can predict the actual estimated cost with the created consolidation work T1 as the prediction target. As a result, the actual estimated cost of work W2, which is the original prediction target, can be predicted based on the prediction result of the consolidation work T1. For example, the actual estimated cost of work W2 can be predicted by referring to the actual cost of the selected work W1.

[0056] The procedure for predicting the summarizing work can be the same as the procedure for predicting the second project, which has already been described. Specifically, the summarizing unit 5 calculates explanatory variables for the summarizing work using explanatory variables for the selected second work and explanatory variables for the selected multiple types of first work. The prediction unit 2 inputs the calculated explanatory variables for the summarizing work into a prediction model, and outputs a predicted value of the estimated cost overrun for the summarizing work and explanatory variables that are the basis for the predicted value.

[0057] In addition, the operator may combine all or some of the multiple types of work W1 belonging to the project P1 into a merging work. By including the merging work in the prediction target, the prediction unit 2 may also make a prediction for the second work of the original prediction target at the same time.

[0058] (Example 2 of summary task usage) Project P1 as the second project includes subprojects P11 and P12 as the second project. Subproject P11 is divided into multiple types of work W1 as the first work and work W2 as the second work. Subproject P12 is divided into multiple types of work W3 as the first work and work W4 as the second work.

[0059] If the operator wishes to predict the actual estimated cost of task W2 in subproject P11, but task W2 is small-scale, the operator selects tasks W1 and W2. The consolidation unit 5 can create a consolidation task T1 that consolidates the task W2 to be predicted and the selected tasks W1. The consolidation unit 5 also assigns the same consolidation code "code A" to the selected tasks W1, W2, and consolidation task T1. The prediction unit 2 can then predict the actual estimated cost of the created consolidation task T1 as the prediction target. As a result, the prediction unit 2 can predict the actual estimated cost of task W2, which is the original prediction target, based on the prediction results of the consolidation task T1. For example, the actual estimated cost of task W2 can be predicted by referring to the actual cost of the selected task W1.

[0060] Furthermore, if the operator wishes to predict the actual estimated cost of task W4 in subproject P12, but task W4 is small-scale, the operator selects tasks W3 and W4. The consolidation unit 5 can create a consolidation task T2 that consolidates task W4, which is the target of prediction, and the selected tasks W3. The consolidation unit 5 also assigns the same consolidation code "code B" to the selected tasks W3, W4, and consolidation task T2. The prediction unit 2 can then predict the actual estimated cost of the created consolidation task T2 as the prediction target. As a result, the actual estimated cost of task W4, which is the original prediction target, can be predicted based on the prediction results of the consolidation task T2. For example, the actual estimated cost of task W4 can be predicted by referring to the actual cost of the selected task W3.

[0061] In addition, the actual estimated cost of the entire project P1 can be predicted using the summary tasks T1 and T2. If the tasks W2 and W4 are small-scale, the operator selects the summary tasks T1 and T2. The summary unit 5 can create a summary task T3 by summarizing the summary tasks T1 and T2. The summary unit 5 also assigns the same summary code "code C" to the selected summary tasks T1, T2 and T3. Then, the prediction unit 2 can predict the actual estimated cost using the created summary task T3 as the prediction target. That is, the actual estimated cost of the entire project P1 can be predicted. More specifically, the actual estimated cost of the tasks W2 and W4, which are the original prediction targets, can be predicted based on the prediction result of the summary task T3. For example, the actual estimated cost of the tasks W2 and W4 can be predicted by referring to the actual costs of the selected tasks W1 and W3.

[0062] "Code C" has a function of consolidating multiple types of consolidation codes ("Code A" and "Code B" in the above example). There is a consolidation relationship between codes A to C in which code C is a higher-level consolidation code than codes A and B. The operator can specify such a relationship, and the information processing device 100 can store the specified relationship as an external parameter. For example, as in "Example 2 of Use of Consolidation Work", it is preferable to construct a consolidation relationship so as to correspond to the relationship between project P1 and subprojects P11 and P12. Note that the operator can also specify a consolidation relationship that excludes some of the multiple types of consolidation codes consolidated by the higher-level consolidation code.

[0063] The procedure for forecasting the finalizing task T3 can be the same as the procedure for forecasting the second project, which has already been described. Specifically, the finalizing unit 5 calculates explanatory variables for the finalizing task T3 using explanatory variables for the selected finalizing tasks T1 and T2. The forecasting unit 2 inputs the calculated explanatory variables for the finalizing task T3 into a forecasting model, and outputs a forecasted value of the estimated cost overrun for the finalizing task T3 and explanatory variables that are the basis for the forecasted value.

[0064] [process] The consolidation process executed by the information processing device 100 is as shown in FIG. 4. That is, first, the information processing device 100 acquires the work selected by the operator (step S11). Next, the consolidation unit 5 consolidates the selected work to create a consolidation work (step S12). At this time, the values ​​of the explanatory variables of the selected work are combined (or not combined) using a predetermined arithmetic expression to calculate the values ​​of the explanatory variables of the consolidation work. Next, the consolidation unit 5 assigns a consolidation code to the selected work and the created consolidation work (step S13). At this time, a consolidation code that consolidates the consolidation codes may be prepared and a consolidation relationship may be specified. With the above, the consolidation process is completed. After that, the prediction unit 2 predicts an estimated cost overrun for the consolidation work.

[0065] [Effects of consolidation work] In conventional wide-area monitoring, the prediction by the information processing device 100 may extract too many tasks (tasks of concern) with estimated cost overruns of 1M or more, which may lead to a problem that the personnel costs required for the investigation to determine whether or not to subject the task to priority monitoring are further increased. In addition, when the task to be monitored is small-scale, the value of the estimated cost overrun is too small to be investigated, so that there is a problem that extra personnel costs are required for investigating the task. Note that "when the task to be monitored is small-scale" refers to, for example, a case where the period from the start to the end of the task is extremely short, or a case where the value of the explanatory variable of the task is extremely small.

[0066] According to this embodiment, by creating multiple types of summary tasks including the task to be predicted, the number of tasks to be monitored in wide-area monitoring can be substantially reduced. In addition, the number of tasks with estimated cost overruns of 1M or more can be substantially reduced. Therefore, the personnel cost required for the investigation to determine whether or not to make the task a target of intensive monitoring can be reduced. Even if the task to be monitored is small-scale, the summary task including the task can be large-scale, so that the value of estimated cost overruns can be large enough to be investigated, and unnecessary personnel cost for investigating the task can be saved. Therefore, wide-area monitoring can detect early signs of deterioration in the project and reduce the personnel cost for determining whether or not to make the task a target of intensive monitoring. In addition, the system can output the estimated cost overrun prediction value for the summary task and the explanatory variables that are the basis for the prediction value. In other words, the summary task can be treated as equivalent to the tasks that make up the summary task. In addition, it is possible to obtain the prediction result of the task to be predicted from the prediction result of the summary task by using the other tasks that make up the summary task. In addition, since a combined task that combines multiple combined tasks can be created, the number of tasks that are the subject of wide-area monitoring can be substantially further reduced. In addition, the number of tasks that are extracted with an estimated cost overrun of 1M or more can also be substantially further reduced. This further reduces the personnel costs required for the investigation to determine whether or not to make it a subject of focused monitoring. In addition, since a combined task that combines multiple combined tasks becomes even larger in scale, it can be made larger to the extent that values ​​such as estimated cost overruns can be more reliably investigated, and unnecessary personnel costs for the investigation of the task can be further reduced.

[0067] In this embodiment, the summarizing unit 5 performs summarizing processing on the tasks to create a summarizing task. However, as already described, in terms of processing the deterioration signs, projects and tasks can be regarded as the same thing, so the summarizing unit 5 can also perform summarizing processing on projects and create a summarizing project that summarizes multiple types of projects. For example, the summarizing unit 5 can create a summarizing project that summarizes the selected second project to be predicted and the selected multiple types of first projects. The summarizing unit 5 can calculate explanatory variables of the summarizing project using explanatory variables of the selected second project and explanatory variables of the selected multiple types of first projects. The prediction unit 2 can input the calculated explanatory variables of the summarizing project to a prediction model and output a predicted value of the estimated cost overrun of the summarizing project and explanatory variables that are the basis of the predicted value. When a first summary project and a second summary project exist as summary projects, the summary unit can create a third summary project that summarizes the first summary project and the second summary project. The above-mentioned consolidation process can also be applied to multiple types of subprojects that make up a project.

[0068] [Variations] (a): In the first and second embodiments, the progress rate is calculated based on a time standard using the period of the project. However, for example, the progress rate may be calculated based on the degree of accomplishment of the work to be done in the project. (b): In the first embodiment, explanatory variables at a time point corresponding to a progress rate of 50% in the monitoring information of the first project were input to the prediction model for each first project. However, for example, explanatory variables at a time point corresponding to any same progress rate other than 50% may be input to the prediction model for each first project. Also, explanatory variables at a time point corresponding to a different progress rate for each first project may be input to the prediction model. (c): In the second embodiment, by regularizing the training days, multiple types of progress rates are substantially selected for the same first project, and explanatory variables at the selected progress rates are input to the prediction model. However, for example, a user of the information processing device 100 may operate the input unit to select multiple types of arbitrary progress rates for the same first project, and input explanatory variables at the selected progress rates to the prediction model. (d): In this embodiment, a summary task (or summary project) is created and used in the prediction stage. However, a summary task (or summary project) may be created and used in the training stage. By training a prediction model with a summary task (or summary project), the number of learning patterns can be increased, and the prediction accuracy can be improved. (e): In this embodiment, a summary task (or summary project) is created for a small-scale task (or project). However, the present invention does not prevent a summary task (or summary project) from being created for a large-scale task (or project).

[0069] (f): It is also possible to realize a technology that appropriately combines the various technologies described in this embodiment. (g) The software described in this embodiment can be realized as hardware, and vice versa. (h) In addition, the hardware, software, flow charts, etc. may be modified as appropriate without departing from the spirit and scope of the present invention. [Explanation of symbols]

[0070] 100 Information processing device 1 Generation part 2. Prediction Department 3. First Project DB 4. Second Project DB 5 Summary

Claims

1. a generation unit for generating a predictive model trained on monitoring information of a completed first project; a prediction unit that inputs explanatory variables of a second project in process into the prediction model and outputs a predicted value of an estimated cost overrun of the second project and explanatory variables that are the basis of the predicted value; a summarizing unit that creates a summarizing project by summarizing the selected second project and a selected plurality of types of first projects.

2. the summarizing unit calculates explanatory variables of the summary project using explanatory variables of the selected second project and explanatory variables of the selected plurality of types of first projects; The information processing device according to claim 1 , wherein the prediction unit inputs the calculated explanatory variables of the summary project into the prediction model, and outputs a predicted value of the estimated cost overrun of the summary project and the explanatory variables that serve as the basis for the predicted value.

3. The summary projects include a first summary project and a second summary project, The information processing apparatus according to claim 1 , wherein the summarizing unit creates a third summarization project by summarizing the first summarization project and the second summarization project.

4. An information processing device, generating a predictive model trained on monitoring information of the completed first project; inputting explanatory variables of a second project in process into the forecasting model, and outputting a forecast value of an estimated cost overrun of the second project and explanatory variables that are the basis of the forecast value; creating a combined project by combining the selected second project and a selected plurality of types of first projects.

Citation Information

Patent Citations

  • Synthesis and Deletion Processing Method and System for Optimized Outcome Derivation Workflow

    JP2003526158A

  • Profit / loss management system and management method, and program of the same

    JP2007041915A

  • Man-hour estimation device, man-hour estimation method, and man-hour estimation program

    JP2012181739A

  • Project sign detection apparatus and project sign detection method

    JP2022032115A

  • Information processing device and information processing method

    JP2022173656A