JP6945472B2 - Project evaluation device, project evaluation method, and project evaluation program - Google Patents

Description

The present invention relates to a project evaluation device and the like for evaluating a project.

For example, various devices for managing projects such as software development and system development are known. For example, Patent Document 1 discloses a device that analyzes text included in project information, extracts an expression pattern, and predicts a trouble occurrence probability of a project based on the expression pattern. Further, Patent Document 2 discloses a system that proposes countermeasures when a project work delay occurs.

Japanese Unexamined Patent Publication No. 2009-230351 Japanese Unexamined Patent Publication No. 2006-126988

In general, it is difficult to recognize whether a project is out of order in the middle of the project. For example, as an opportunity for an expert who has know-how of past projects to give advice to a project manager who has little experience, for example, there is a process meeting, but the process meeting is held once a month, for example. Due to the limited frequency of this, it is difficult to give timely advice to project managers.

In addition, every predetermined period (for example, quarterly), the cause of the project malfunction may be investigated and analyzed for the project completed during that period, and the result is sent to the individual project manager. Feedback is also costly and can be difficult to ensure. Also, since it targets completed projects, it is not possible to give timely advice to running projects.

The present invention has been made in view of the above circumstances, and an object of the present invention is to provide a technique capable of appropriately evaluating a project in progress.

In order to achieve the above object, the project evaluation device according to one viewpoint is a project evaluation device that evaluates a running project, and is an evaluation corresponding to the project data of the executed project and one or more evaluation items for the executed project. Based on the result and the project data of the running project, the evaluation estimation unit that estimates the evaluation result corresponding to one or more evaluation items of the running project, and the evaluation estimation unit that estimates the running project. It is provided with an evaluation result display processing unit for displaying evaluation results for one or more evaluation items.

According to the present invention, a running project can be appropriately evaluated.

FIG. 1 is an overall configuration diagram of a project prediction server according to an embodiment. FIG. 2 is a configuration diagram of a project data table according to an embodiment. FIG. 3 is a configuration diagram of basic project information according to one embodiment. FIG. 4 is a configuration diagram of profit / loss information according to one embodiment. FIG. 5 is a configuration diagram of progress information according to one embodiment. FIG. 6 is a block diagram of quality information according to an embodiment. FIG. 7 is a block diagram of a malfunction investigation data table according to an embodiment. FIG. 8 is a block diagram of the AI project data table according to the embodiment. FIG. 9 is a block diagram of evaluation information according to one embodiment. FIG. 10 is a block diagram of a malfunction investigation data table for AI according to an embodiment. FIG. 11 is a block diagram of factor pattern information according to one embodiment. FIG. 12 is a block diagram of a risk data table according to an embodiment. FIG. 13 is a configuration diagram of risk data according to one embodiment. FIG. 14 is a diagram showing a project evaluation result screen according to one embodiment. FIG. 15 is a flowchart of the evaluation estimation model learning process according to the embodiment. FIG. 16 is a flowchart of the malfunction factor estimation model learning process according to the embodiment. FIG. 17 is a flowchart of the project evaluation process according to the embodiment.

The embodiment will be described with reference to the drawings. It should be noted that the embodiments described below do not limit the invention according to the claims, and all of the elements and combinations thereof described in the embodiments are indispensable for the means for solving the invention. Is not always.

In the following description, the information may be described by the expression of "AAA table", but the information may be expressed by any data structure. That is, the "AAA table" can be called "AAA information" to show that the information does not depend on the data structure.

The processor may also include hardware circuits that perform some or all of the processing. The program may be installed from the program source into a device such as a calculator. The program source may be, for example, a program distribution server or a non-volatile storage medium readable by a computer. Further, in the following description, two or more programs may be realized as one program, or one program may be realized as two or more programs.

FIG. 1 is an overall configuration diagram of a project prediction server according to an embodiment.

The project prediction server 100 as an example of the project evaluation device is composed of, for example, a computer such as a server and a PC (Personal Computer), and includes a processor 210, a program memory 220, a display device 230, a keyboard 240, and pointing. It includes a device 250, a storage unit 255 as an example of an estimated malfunction factor storage unit, and a data memory 280.

The processor 210 is, for example, a CPU (Central Processing Unit), and executes various processes according to a program stored in the program memory 220. In the present embodiment, the processor 210 executes the program stored in the program memory 220 to execute the learning processing unit 211, and the prediction processing unit 212 as an example of the evaluation estimation unit, the malfunction factor estimation unit, and the risk identification unit. The evaluation result display processing unit, the malfunction factor display processing unit, and the display processing unit 213 as an example of the risk display processing unit are configured.

The program memory 220 is, for example, a RAM (RANDOM ACCESS MEMORY) and stores various programs executed by the processor 210. In the present embodiment, the program memory 220 stores the project evaluation program that constitutes the learning processing unit 211, the prediction processing unit 212, and the display processing unit 213 by being executed by the processor 210.

The storage unit 255 is, for example, a hard disk drive, an SSD (Solid State Drive), or the like, and stores a program executed by the processor 210 and various data used by the processor 210. In the present embodiment, the storage unit 255 includes a project data table 60, a malfunction investigation data table 120, a project data table 260 for AI (Artificial Intelligence), a malfunction investigation data table 270 for AI, and a risk data table 290. The meeting material data 70 and the log file 300 are stored. In the meeting material data 70, project data related to the project being executed (execution project) is stored. The evaluation result log 300 stores upset factors that are evaluation results related to the project being executed, countermeasures, and the like.

The data memory 280 is, for example, a RAM, which stores data used in a program executed by the processor 210. In the present embodiment, the data memory 280 stores AI project data 261 read from the storage unit 255 as the program is executed, AI malfunction investigation data 271, risk data 291 and the like. In the present embodiment, as shown in FIG. 1, the tables and data stored in the data memory 280 and the storage unit 255 are for predicting the evaluation items of the project (evaluation prediction) and predicting the cause of the malfunction. It can be roughly divided into those for doing.

The display device 230 is, for example, a liquid crystal display and displays various information (for example, a project evaluation result screen (see FIG. 14)). The keyboard 240 and the pointing device 250 receive various inputs from the user of the project prediction server 100.

Next, the project data table 60 will be described.

FIG. 2 is a configuration diagram of a project data table according to an embodiment.

The project data table 60 stores entries (project data 61) for each executed project. The project data 61 includes project basic information 281 (see FIG. 3) which is basic information about the project, profit / loss information 282 (see FIG. 4) regarding the profit and loss of the project, and progress information 283 (see FIG. 5) regarding the progress with the project. ) And quality information 284 (see FIG. 6) regarding the quality of the project. The project data of the running project included in the meeting material data 70 has the same structure as the project data 61 of the executed project.

Next, the project basic information 281 will be described.

FIG. 3 is a configuration diagram of basic project information according to one embodiment. Note that "{}" in FIG. 3 (also in FIGS. 6 and 11) indicates that any one of the numerical values in {} is selected and set.

The project basic information 281 is basic information of the project, and has fields (members) such as introduction form 281-1, business form 281-2, commercial distribution form 281-3, and management level 281-4. The introduction form of the project is stored in the introduction form 281-1. The business form of the project is stored in the business form 281-2. The distribution form of the product of the project is stored in the commercial distribution form 281-3. The management level 281-4 stores the management level for the project.

Next, the profit and loss information 282 will be described.

FIG. 4 is a configuration diagram of profit / loss information according to one embodiment. “9” in the field in FIG. 4 (also in FIGS. 6, 8, 9, and 10) means that a numerical value is set.

The profit / loss information 282 is information on the profit / loss of the project, and has fields (members) such as sales 282-1, manufacturing cost 282-2, gross profit 282-3, and sales profit / loss 282-4. The sales amount of the project is stored in the sales amount 282-1. The manufacturing cost of the project is stored in the manufacturing cost 282-2. The gross profit of the project is stored in the gross profit 282-3. The sales profit / loss of the project is stored in the sales profit / loss 282-4.

Next, the progress information 283 will be described.

FIG. 5 is a configuration diagram of progress information according to one embodiment.

The progress information 283 is information on the progress of the project, and has fields (members) such as a plan 283-1, a basic design 283-2, a detailed design 283-3, and an operation support 283-4. The plan 283-1 stores data (days data) indicating the number of days indicating the difference between the planned date when the project plan ends and the actual date. In the basic design 283-2, the number of days data indicating the difference between the scheduled date when the basic design of the project is completed and the actual date is stored. The detailed design 283-3 stores the number of days data indicating the difference between the scheduled date when the detailed design of the project is completed and the actual date. The operation support 283-4 stores the number of days data indicating the difference between the scheduled date when the operation support of the project ends and the actual date.

Next, the quality information 284 will be described.

FIG. 6 is a block diagram of quality information according to an embodiment.

The quality information 284 is information on the quality of the project, and has fields (members) such as a development amount 284-1, a development language 284-2, a checklist number 284-3, and a bug number 284-4. The development amount in the project is stored in the development amount 284-1. The development language 284-2 stores the code indicating the development language in the project. The number of checklists in the project is stored in the number of checklists 284-3. The number of bugs 284-4 stores the number of bugs that have occurred in the project.

Next, the malfunction investigation data table 120 will be described.

FIG. 7 is a block diagram of a malfunction investigation data table according to an embodiment.

The malfunction investigation data table 120 stores entries (fault investigation data) for each executed project. The malfunction investigation data includes fields of project basic information 281 which is basic information about the project, profit / loss information 282 about the profit and loss of the project, factor 287, problem 288, and countermeasure 289. The basic project information 281 and the profit / loss information 282 are the same as those having the same reference numerals as those already described.

For the project that ended in failure, the factor 287 stores the factor that caused the project to fail (disorder factor). The cause of the malfunction is, for example, obtained by analysis by an expert in the analysis of the project based on the project data or the like. Examples of malfunction factors include low estimation accuracy, insufficient project planning, ambiguous specifications, shortage of employees, and insufficient business knowledge. The problem 288 stores a problem when there is a malfunction factor of the factor 287. This problem was set, for example, by an expert in the analysis of the project. Countermeasure 289 stores possible countermeasures against the malfunction factor of factor 287. This measure is, for example, set by an expert in the analysis of the project.

Next, the project data table 260 for AI will be described.

FIG. 8 is a block diagram of the AI project data table 260 according to the embodiment.

The AI project data table 260 stores an entry (AI project data 261) for each executed project. The AI project data 261 is used as teacher data for learning from an estimation model (evaluation estimation model) for evaluating evaluation items by AI. The AI project data 261 includes basic project information 281, profit / loss information 282, progress information 283, quality information 284, and evaluation information 285 (profit / loss evaluation 285-1, progress evaluation 285-2, quality evaluation 285-3). Includes fields with.

The evaluation information 285 stores the evaluation results for one or more evaluation items (in this embodiment, profit / loss, progress, and quality) in the project.

Next, the evaluation information 285 will be described.

FIG. 9 is a block diagram of evaluation information according to one embodiment.

The evaluation information 285 has fields (members) of a profit / loss evaluation 285-1, a progress evaluation 285-2, and a quality evaluation 285-3. The profit / loss evaluation 285-1 stores the evaluation result regarding the profit / loss of the project. The evaluation result regarding profit and loss is, for example, the result of evaluation by an expert on the evaluation of the project based on the profit and loss information 282 of the project data. The progress evaluation 285-2 stores the evaluation result regarding the progress of the project. The evaluation result regarding the progress is, for example, the result of the evaluation by an expert on the evaluation of the project based on the progress information 283 of the project data. The quality evaluation 285-3 stores the evaluation result regarding the quality of the project. The quality evaluation result is, for example, the result of an expert on the project evaluation based on the quality information 284 of the project data.

Next, the malfunction investigation data table 270 for AI will be described.

FIG. 10 is a block diagram of the AI malfunction investigation data table 270 according to the embodiment.

The AI malfunction investigation data table 270 stores an entry (AI malfunction investigation data 271) for each executed project. The AI malfunction survey data 271 is used as teacher data for learning the estimation model (disorder factor estimation model) for predicting the malfunction factor of the project by AI. The AI malfunction investigation data 271 includes fields of project basic information 281, profit / loss information 282, and factor pattern information 286.

The factor pattern information 286 stores a pattern (factor pattern 286-1) indicating a malfunction factor in the project.

Next, the factor pattern information 286 will be described.

FIG. 11 is a block diagram of factor pattern information according to one embodiment.

The factor pattern information 286 has a field (member) of the factor pattern 286-1. In the factor pattern 286-1, a pattern (factor pattern: here, the corresponding numerical value) corresponding to the cause of the malfunction (disorder factor) generated in the project is stored. The factor pattern is a factor pattern corresponding to the malfunction factor evaluated for the project data by an expert in the evaluation of the project.

Next, the risk data table 290 will be described.

FIG. 12 is a block diagram of a risk data table according to an embodiment. FIG. 13 is a configuration diagram of risk data according to one embodiment.

The risk data table 290 is a table that manages risks, problems, countermeasures, etc. corresponding to the upset factors indicated by the factor patterns, and the entries for each upset factor (risk data 291) are the factor pattern 290-1 and the risk. It has fields (members) of problem (event) 290-2, risk / problem (root cause) 290-3, and countermeasure 290-4. The factor pattern 290-1 stores the factor pattern of the malfunction factor. The risk / problem (event) 290-2 stores a risk or a problematic event for the factor pattern corresponding to the risk data 291. The risk / problem (root cause) 290-3 stores the risk or the root cause of the problem with respect to the factor pattern corresponding to the risk data 291. Countermeasure 290-4 stores countermeasures for factor patterns corresponding to risk data 291. Each risk data 291 in the risk data table 290 is preset by an expert on risks / problems of malfunction factors and countermeasures.

Next, the project evaluation result screen will be described.

FIG. 14 is a project evaluation result screen according to the embodiment.

The project evaluation result screen 700 is a screen displayed on the display device 230 by the display processing unit 213. On the project evaluation result screen 700, a profit / loss evaluation result area 701, a progress evaluation result area 702, a quality evaluation result area 703, a malfunction factor area 704, a risk / problem, a countermeasure display area 705, and a malfunction factor statistical information are displayed. The display area 706 is displayed.

The profit / loss evaluation result of the project to be evaluated is displayed in the profit / loss evaluation result area 701. The progress evaluation result of the project to be evaluated is displayed in the progress evaluation result area 702. The quality evaluation result of the project to be evaluated is displayed in the quality evaluation result area 703.

In the malfunction factor area 704, when the project to be evaluated is determined to be malfunctioning (for example, when all of the profit and loss evaluation, the progress evaluation, and the quality evaluation are below the standard (less than the predetermined standard value)). , The estimated upset factor is displayed. In the risk / problem display area 705, risks / problems, countermeasures, etc. due to the malfunction factor displayed in the malfunction factor area 704 are displayed. In the malfunction factor statistical information 706, statistical information regarding the malfunction factor displayed in the malfunction factor 704 is displayed. The statistical information is generated by the display processing unit 213 based on the evaluation result log of the log file 300. Specifically, the display processing unit 213 generates the number of projects in which the same malfunction factor as the malfunction factor displayed in the malfunction factor display area 704 is estimated, the ratio of the same malfunction factor to the whole, and the like.

Next, the processing operation by the project prediction server 100 according to the embodiment will be described.

First, the evaluation estimation model learning process in which an estimation model (evaluation estimation model) for evaluating each evaluation item of the running project is constructed by learning will be described.

FIG. 15 is a flowchart of the evaluation estimation model learning process according to the embodiment.

The evaluation estimation model learning process is executed, for example, before the project evaluation process (see FIG. 17) is executed.

First, the learning processing unit 211 acquires the project data 61 from the project data table 60 (S411). If the project data table 60 does not exist in the project prediction server 100, it may be acquired from another device that manages the project data table 60.

Next, the learning processing unit 211 performs a process of normalizing or digitizing a predetermined value in the project data 61 (S412). For example, the learning processing unit 211 converts the value stored in the project data 61 in the character format into a numerical value corresponding to this value. If the project data 61 is composed only of values that do not need to be normalized or quantified, it is not necessary to execute this step.

Next, the learning processing unit 211 accepts the input of the evaluation for each evaluation item of the project data 61 and sets it as the AI project data 261 (S413). In this embodiment, the evaluation items are profit / loss, progress, quality, and the like. The AI project data 261 becomes teacher data used for learning the evaluation estimation model described later. Next, the learning processing unit 211 sorts the AI project data 261 into data (learning data) for each evaluation item (S414). Specifically, the learning processing unit 211 sorts the AI project data 261 into profit / loss information 282, progress information 283, and quality information 284 as learning data.

Next, the learning processing unit 211 repeatedly executes the loop A processing (S415) for each of the evaluation items. Specifically, the learning processing unit 211 learns and learns an evaluation estimation model that evaluates the evaluation items using the learning data sorted for the evaluation items for the evaluation items to be processed. Information (various set values) of the evaluation estimation model is stored in the storage unit 255 (S415). In the present embodiment, the evaluation estimation model is, for example, a multi-layer neural network model, and the learning method is, for example, deep learning.

The learning processing unit 211 executes the processing of the loop A for all the evaluation items, then exits the loop A and ends the processing. According to this evaluation estimation model learning process, each evaluation estimation model for evaluating each evaluation item is created.

Next, the prediction processing model learning process in which the malfunction factor estimation model (prediction processing model) for estimating the malfunction factor of the project data is constructed by learning will be described.

FIG. 16 is a flowchart of the malfunction factor estimation model learning process according to the embodiment.

The malfunction factor estimation model learning process is executed, for example, before the project evaluation process (see FIG. 17) is executed.

First, the learning processing unit 211 acquires the malfunction investigation data from the malfunction investigation data table 120 (S421). If the malfunction investigation data table 120 does not exist in the project prediction server 100, it may be acquired from another device that manages the malfunction investigation data table 120.

Next, the learning processing unit 211 performs a process of normalizing or quantifying a predetermined value in the malfunction investigation data (S422). For example, the learning processing unit 211 converts the character string indicating the factor stored in the factor 287 of the malfunction investigation data into the numerical value of the factor pattern corresponding to this character string. If the malfunction investigation data consists only of values that do not need to be normalized or quantified, it is not necessary to execute this step.

Next, the learning processing unit 211 generates AI malfunction investigation data 271 to which a factor pattern is added for each malfunction investigation data (S423). The AI malfunction survey data 271 becomes teacher data used for learning the malfunction factor estimation model described later. Next, the learning processing unit 211 learns the malfunction factor estimation model using the AI malfunction investigation data 271, and stores the learned malfunction factor estimation model information (various set values) in the storage unit 255 (S424). ), End the malfunction factor estimation model learning process. In the present embodiment, the malfunction factor estimation model is, for example, a multi-layer neural network model, and the learning method is, for example, deep learning.

According to this malfunction factor estimation model learning process, a malfunction factor estimation model for evaluating the malfunction factor is created.

Next, the project evaluation process for evaluating the evaluation items for the running project will be described.

FIG. 17 is a flowchart of the project evaluation process according to the embodiment.

Before executing this project evaluation process, it is necessary that the evaluation estimation model learning process and the malfunction factor estimation model learning process have been executed.

First, the prediction processing unit 212 extracts the project data of the executing project to be evaluated from the conference material data 70 (S511). The running project to be evaluated may be a project specified by the user, or may be all running projects included in the conference material data 70. When a plurality of running projects are to be evaluated, the project evaluation process of FIG. 17 is executed for each running project.

Next, the prediction processing unit 212 performs a process of normalizing or quantifying a predetermined value in the acquired project data (S512). For example, the prediction processing unit 212 converts the value stored in the project data in the character format into the corresponding numerical value. If the project data consists only of values that do not need to be normalized or quantified, it is not necessary to execute this step.

Next, the prediction processing unit 212 sorts the project data into data for each evaluation item (evaluation data) in order to execute inference processing for each evaluation item (S513). Specifically, the forecast processing unit 212 describes the project data with profit / loss information (information similar to profit / loss information 282), progress information (information similar to progress information 283), and quality information (information similar to quality information 284). ) And.

Next, the prediction processing unit 212 repeatedly executes the loop B process (S514) for each of the evaluation items. Specifically, the prediction processing unit 212 inputs the evaluation data sorted for this evaluation item into the evaluation estimation model that has already been learned to evaluate the evaluation item to be processed. , The evaluation item to be processed is evaluated, and the evaluation result (for example, evaluation point) is stored in the data memory (S514).

The prediction processing unit 212 exits the loop B after executing the processing of the loop B for all the evaluation items. Next, the prediction processing unit 212 determines whether or not there is an evaluation item less than a predetermined reference point among the evaluation results of the plurality of evaluation items (S515). As a result, when there is no evaluation item below the reference point (S515: NO), it is considered that there is no malfunction factor in the project corresponding to the project data. The process proceeds to S519.

On the other hand, when there is an evaluation item less than the reference point (S515: YES), it means that there is a malfunction factor in the project corresponding to the project data, so that the prediction processing unit 212 has already learned the malfunction. By inputting the information in the project data (profit and loss information in this embodiment) into the factor estimation model, the factor pattern is evaluated and the factor pattern of the malfunction factor for the project is determined (S516).

Next, the prediction processing unit 212 selects risks / problems, countermeasures, etc. corresponding to the determined factor pattern with reference to the risk data in the risk data table 290 (S517), and selects the determined factor pattern and the selected risk. -The evaluation result log associated with the problems, countermeasures, etc. is stored in the log file 300 of the storage unit 255 (S518), and the process proceeds to S519.

In S519, the display processing unit 213 displays the project evaluation result screen 700 including the evaluation result on the display device 230, and ends the processing. For example, in the case of NO in S515, the display processing unit 213 sets the evaluation results (evaluation points) of each evaluation item obtained in S514 into the profit and loss evaluation result area 701, the progress evaluation result area 702, and the quality evaluation result area. It is displayed as 703. On the other hand, when S518 is executed, the display processing unit 213 displays the evaluation results (evaluation points) of each evaluation item obtained in S514 in the profit / loss evaluation result area 701, the progress evaluation result area 702, and the quality evaluation result area. Displayed in 703, the factor pattern determined in the evaluation of S516 and the malfunction factor corresponding to the factor pattern are displayed in the malfunction factor area 704, and the risks / problems, countermeasures, etc. selected in S517 are risk / problem. , The countermeasure display area 705 is displayed, and the malfunction factor statistical information display area 706 is displayed with statistical information related to the malfunction factor calculated based on the evaluation result log of the log file 300.

According to the above-mentioned project evaluation process, the evaluation result of each evaluation item for the running project can be displayed. In addition, it is possible to appropriately display the related upset factors for the running project (in the above example, the running project in which all the evaluation results are below the reference point) that are assumed to have upset factors. It is possible to display risks / problems corresponding to the malfunction factors and countermeasures corresponding to the malfunction factors.

The present invention is not limited to the above-described embodiment, and can be appropriately modified and implemented without departing from the spirit of the present invention.

For example, in the above embodiment, the evaluation items for the project and the malfunction factors in the project are evaluated using an estimation model (evaluation estimation model, malfunction factor estimation model) trained from the teacher data. However, the present invention is not limited to this, and the evaluation items for the project and the factors of the malfunction in the project may be evaluated according to a predetermined algorithm without using the estimation model.

Further, in the above embodiment, when any of a plurality of evaluation items for the project is less than the reference point, the malfunction factor is estimated and displayed, thereby reducing the process of estimating the malfunction factor and reducing the processing. Although it was attempted to prevent the user from displaying information that is less necessary (information on the cause of the disorder when it is considered that there is no cause of the disorder, etc.), the present invention is not limited to this, and all projects. The cause of the malfunction may be estimated and displayed. Further, the condition for estimating and displaying the malfunction factor is not limited to the case where any one of the plurality of evaluation items is less than the reference point, and may be an arbitrary condition as necessary.

Further, in the above embodiment, the project data table 60 is stored in the project prediction server 100, and the project prediction server 100 creates the AI project data 261 by associating the evaluation results with the project data 61. However, the present invention is not limited to this, and the project data for AI in which the evaluation result is associated with the project data may be acquired from another device.

Further, in the above embodiment, the evaluation result of the project is displayed as the project evaluation result screen 700, but the display mode of the evaluation result is not limited to this, and for example, the evaluation result is displayed together with the project data related to the project. You may try to do it.

Further, in the above embodiment, the risks / problems and countermeasures for the malfunction factors are selected by using the risk data table 290, but the present invention is not limited to this, and for example, the risks / problems for the malfunction factors are selected in advance. It is also possible to train a model for evaluating points and countermeasures, and use the model to select risks / problems and countermeasures for malfunction factors.

100 ... Project prediction server, 210 ... Processor, 211 ... Learning processing unit, 212 ... Prediction processing unit, 213 ... Display processing unit, 220 ... Program memory, 255 ... Storage unit, 280 ... Data memory

Claims (9)

A project evaluation device that evaluates a running project.
Corresponds to the one or more evaluation items of the running project based on the project data of the executed project, the evaluation result corresponding to one or more evaluation items for the executed project, and the project data of the running project. Evaluation estimation unit that estimates the evaluation result and
An evaluation result display processing unit that displays evaluation results for the one or more evaluation items of the running project estimated by the evaluation estimation unit, and an evaluation result display processing unit.
A malfunction factor estimation unit that estimates the malfunction factor of the running project based on the project data of the executed project, the malfunction factor of the executed project, and the project data of the executing project.
A malfunction factor display processing unit that displays information on malfunction factors estimated by the malfunction factor estimation unit, and a malfunction factor display processing unit.
Project evaluation device equipped with. The project evaluation device according to claim 1, wherein the one or more evaluation items include at least one of project profit / loss, project progress, and project quality. The evaluation estimation unit is executing the execution based on the evaluation estimation model learned by using the project data of the executed project and the evaluation result corresponding to the one or more evaluation items for the executed project as teacher data. The project evaluation device according to claim 1 or 2, which estimates the evaluation result corresponding to the one or more evaluation items of the project. The malfunction factor estimation unit is any one of claims 1 to 3 that estimates the malfunction factor of the running project when all the evaluation results evaluated by the evaluation estimation unit are below a predetermined standard. The project evaluation device described in the section. A risk identification unit that identifies at least one of the risks, problems, or countermeasures that correspond to the above-mentioned malfunction factors.
A risk display processing unit that displays the identified risks, problems, or countermeasures,
The project evaluation device according to any one of claims 1 to 4 , further comprising. It also has an estimated upset factor storage unit that stores a log of upset factors of the running project estimated by the upset factor estimation unit.
The upset factor display processor, together with the information of the estimated disorder factors, project according to any one of claims 1 to 5 for displaying the statistical information based on the log of the estimated malfunction factor Evaluation device. The malfunction factor estimation unit estimates the malfunction factor of the running project based on the malfunction factor estimation model learned by using the project data of the executed project and the malfunction factor for the executed project as teacher data. project evaluation device according to any one of claims 1 to 6 for. A project evaluation method using a project evaluation device that evaluates a running project.
Evaluation corresponding to the one or more evaluation items of the running project based on the project data of the executed project, the evaluation result corresponding to one or more evaluation items for the executed project, and the project data of the running project. Estimate the result,
Display the evaluation results for the one or more evaluation items of the estimated running project .
Based on the project data of the executed project, the malfunction factor of the executed project, and the project data of the running project, the malfunction factor of the executing project is estimated.
A project evaluation method for displaying information on the estimated upset factors. A project evaluation program that is executed by the computers that make up the project evaluation device that evaluates the project being executed.
The computer
Evaluation corresponding to the one or more evaluation items of the running project based on the project data of the executed project, the evaluation result corresponding to one or more evaluation items for the executed project, and the project data of the running project. Evaluation estimation unit that estimates the result and
A display result display unit that displays the evaluation results for the one or more evaluation items of the running project estimated by the evaluation estimation unit, and a display result display unit.
A malfunction factor estimation unit that estimates the malfunction factor of the running project based on the project data of the executed project, the malfunction factor of the executed project, and the project data of the executing project.
A malfunction factor display processing unit that displays information on malfunction factors estimated by the malfunction factor estimation unit, and a malfunction factor display processing unit.
A project evaluation program that works .

Images