Information processing apparatus, information processing method, and information processing program

Abstract

To predict a project with risk with high accuracy.SOLUTION: An information processing apparatus 100 according to the present invention has an acquiring unit 122 for acquiring information of at least any one of an inquiry on a status of a project and information of labor time and information of balance of the project, a prediction unit 123 for predicting information relating to deficit of development of the project by using a learning model using, as an input, information of at least any one of the inquiry on the status of the project and information of labor time and information of the balance of the project both of which are acquired by the acquiring unit 122, and an output unit 124 for outputting information relating to the development deficit of the project predicted by the prediction unit 123.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and an information processing program.

Background Art

[0002] Conventionally, there is a technique for quantitatively and efficiently determining risks in a project and facilitating subsequent countermeasure studies (for example, Patent Document 1). For example, there is a technique for calculating the failure probability of a project and calculating the failure factors as the contribution rates of explanatory variables that contributed to the calculation of the project's failure probability.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The prior art has a problem that it is impossible to accurately predict a project with risks. For example, there may be cases where it is impossible to detect early signs of development deficits. Also, for example, there may be cases where information suitable for predicting a project with risks is not used.

[0005] The present invention has been made in view of the above, and an object thereof is to provide an information processing apparatus, an information processing method, and an information processing program that enable risk countermeasures using information on past similar cases.

Means for Solving the Problems

[0006] In order to solve the above-described problems and achieve the object, an information processing apparatus according to the present invention includes an acquisition unit that acquires any one or more pieces of information among questionnaire information on a project situation and labor time information, and information on the profit and loss of a project; a prediction unit that predicts information on a development deficit of the project using a learning model with, as input, any one or more pieces of information among the questionnaire information on the project situation and the labor time information acquired by the acquisition unit, and the information on the profit and loss of the project; and an output unit that outputs the information on the development deficit of the project predicted by the prediction unit.

Effects of the Invention

[0007] According to the present invention, it is possible to accurately predict a project in which risks exist.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

[0009] Hereinafter, embodiments of the information processing apparatus, information processing method, and information processing program according to the present application will be described in detail with reference to the drawings. Note that the present invention is not limited by this embodiment. Also, in the description of the drawings, the same parts are denoted by the same reference numerals, and duplicate explanations are omitted.

[0010] [First Embodiment] [1. Outline] First, an outline of processing performed by the information processing apparatus 100 will be described with reference to FIG. 1. FIG. 1 is a diagram for explaining an outline of the outline of processing performed by the information processing apparatus 100.

[0011] Conventionally, there has been a technology for quantitatively and efficiently determining risks in a project and facilitating subsequent countermeasure studies, but there are cases where a project with risks cannot be accurately predicted. For example, in the prior art, there are cases where a sign of a development deficit cannot be detected early. Also, for example, there are cases where information suitable for predicting a project with risks is not used.

[0012] Therefore, the information processing apparatus 100 according to the embodiment uses, as input, one or more pieces of information among information on a questionnaire regarding the project situation and labor time information, and information regarding the project's revenue and expenditure, and predicts and outputs information regarding the development deficit of the project using a learning model.

[0013] For example, as shown in FIG. 1, the information processing apparatus 100 according to the embodiment acquires a regular questionnaire on the project situation, labor time information of developers, and project revenue and expenditure information, inputs them into a learning model, predicts the probability of a deficit occurring, and outputs information on the probability of a development deficit occurring for each project.

[0014] As described above, the information processing apparatus 100 according to the present embodiment inputs one or more pieces of information among information on a questionnaire regarding the project situation and labor time information, and information regarding the project's revenue and expenditure into a learning model, and predicts the probability of a development deficit occurring, thereby achieving the effect of being able to accurately predict projects with risks.

[0015] [2. Configuration of the Information Processing Apparatus] Next, an example of the configuration of the information processing apparatus 100 will be described with reference to FIG. 2. FIG. 2 is a diagram showing an example of the functional configuration of the information processing apparatus 100. As shown in FIG. 2, the information processing apparatus 100 includes a communication unit 110, a control unit 120, and a storage unit 130. Note that these units may be held distributively by a plurality of devices. Hereinafter, the processing of each of these units will be described.

[0016] (Communication Unit 110) The communication unit 110 is realized by a NIC (Network Interface Card) or the like, and enables communication between the control unit 120 and an external device via a telecommunication line such as a LAN (Local Area Network) or the Internet. For example, the communication unit 110 transmits and receives information to and from the terminal device 200.

[0017] (Storage Unit 130) The storage unit 130 is implemented by a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 2, the storage unit 130 includes a learning data storage unit 131, a project information storage unit 132, and a prediction information storage unit 133.

[0018] The learning data storage unit 131 stores information used by the learning unit 121 described later for learning a predetermined learning model. For example, the learning data storage unit 131 stores a questionnaire regarding the project situation, comments regarding the project situation, labor hours, information regarding the project's profit and loss, and information regarding the development deficit of the actual project. Note that the development deficit refers to a state where the gross profit is equal to or less than a predetermined threshold. More specifically, the development deficit refers to a state where the gross profit is -1,000,000 yen or less.

[0019] (Learning data storage unit 131) The information stored in the learning data storage unit 131 will be described with reference to FIGS. 3 and 4. FIG. 3 is an example of a questionnaire regarding the project situation. The questionnaire regarding the project situation is the result of answers to questions such as whether the personnel participating in the project feel there are problems with the project. In the questionnaire regarding the project situation, for example, as shown in FIG. 3, there are instructions such as "Regarding the project, do you feel the following problems? Please select one applicable item." and items such as "1. Due to a shortage of required personnel and skills for the project, there are quality defects and delays in progress (insufficient system)". The personnel participating in the project perform a stage evaluation for each item such as "1. I think so, 2. Somewhat think so, 3. Somewhat don't think so, 4. Don't think so". Note that the above description is merely an example, and the content of the questionnaire regarding the project situation is not limited to this.

[0020] Comments on the project status are the results of written answers to questions such as whether the personnel participating in the project feel that there are problems with the project. For example, as shown in Figure 3, comments on the project status are the results of answers to questions such as "If you feel uneasy when proceeding with the project, please write it down. If there is no item to write, please write 'None in particular'." Specific examples include "I have not been able to confirm whether it operates normally when viewed as a whole" and "The work content for ○○ month is unclear."

[0021] Also, Figure 4 is a table diagram showing an example of learning data according to the embodiment. As shown in Figure 4, the information stored in the learning data storage unit 131 is stored in a list format having items such as "No", "Variable name", and "Calculation method / Content". For example, in the example of Figure 4, the questionnaire on the project status is information such as "No: 16", "Variable name: Health check", "Calculation method / Content: PJ average of the ratio of answering 'Yes' or 'Rather yes' to PJ health check Q1 - Q10".

[0022] Also, in the example of Figure 4, the working hours are information such as "No: 20", "Variable name: Difference in average overtime hours by department", "Calculation method / Content: Difference between the average overtime hours per department and the 3 - month moving average overtime hours of the project". Also, for example, information regarding the project's revenue and expenditure includes the project's sales profit, the project's customer name, the project's execution month, and the project's outsourcing costs. In the example of Figure 4, information regarding the project's revenue and expenditure is information such as "No: 9", "Variable name: Plan difference - outsourcing cost vs. labor cost", "Calculation method / Content: Plan difference - cost of goods sold - outsourcing cost calculation ÷ Plan difference - cost of goods sold - labor cost".

[0023] In addition, for example, information regarding the development deficit of an actual project is the measured value of information regarding the project's revenue and expenditure, and includes the project's sales profit, the name of the project's customer, the month of project execution, and the outsourcing costs of the project. In the example of FIG. 4, information regarding the development deficit of an actual project is information such as "No: 9", "Variable name: planned difference between outsourcing costs and labor costs", "Calculation method / content: planned difference in cost of goods sold - outsourcing costs calculation ÷ planned difference in cost of goods sold - labor costs". Note that the items shown in FIG. 4 are merely examples, and the items stored in the learning data storage unit 131 are not limited to these.

[0024] (Project Information Storage Unit 132) The project information storage unit 132 stores a questionnaire regarding the project situation, comments regarding the project situation, labor hours, information regarding the project's revenue and expenditure, and information regarding the development deficit predicted by the prediction unit 123 described later.

[0025] (Control Unit 120) The control unit 120 is implemented using a CPU (Central Processing Unit), NP (Network Processor), FPGA (Field Programmable Gate Array), etc., and executes a processing program stored in a memory. As shown in FIG. 2, the control unit 120 includes a learning unit 121, an acquisition unit 122, a prediction unit 123, and an output unit 124. Hereinafter, each unit included in the control unit 120 will be described.

[0026] (Learning Unit 121) The learning unit 121 learns a learning model using, as correct data, any one or more pieces of information among questionnaire information on the project status and labor hour information, information on the project's revenue and expenditure, and information on the development deficit of the actual project. For example, the learning unit 121 learns the relationship among any one or more pieces of information among questionnaire information on the project status and labor hour information, information on the project's revenue and expenditure, and information on the development deficit of the actual project, and learns a learning model that takes, as inputs, any one or more pieces of information among questionnaire information on the project status and labor hour information and information on the project's revenue and expenditure, and outputs information on the development deficit of the project.

[0027] In this embodiment, the learning unit 121 is described on the premise of performing learning using LightGBM (Light Gradient Boosting Machine), but is not limited as long as it is a learning model capable of predicting information on the development deficit of the project. Further, the learning unit 121 can learn a supervised learning model, an unsupervised learning model, a reinforcement learning model, and the like.

[0028] Here, an example of the learning process according to the embodiment will be described with reference to FIG. 5. FIG. 5 is a diagram showing an example of the learning process according to the embodiment. In the example shown in FIG. 5, out of 21,669 pieces of all data, 80% was used as learning data and 20% was used as test data for learning. Further, in order to prevent the conditions of the learning data and the test data from varying, multiple random divisions were performed, and the division method with the smallest difference in the standardized main items was adopted.

[0029] Then, the learning data was divided into groups by k-fold cross-validation (k-fold Cross Validation), and the accuracy of the model was obtained from the average value of the predictions of the model for the test data created in each group. In the example of FIG. 5, the test data is the data used for accuracy evaluation, the learning data is the data used during the learning of each fold, and the validation data is the data used for parameter adjustment during the learning of each fold.

[0030] In addition, when training the model, the learning unit 121 can perform data processing. For example, when targeting training data, it excludes a small amount of loss or profit data. More specifically, when the definition of development loss is "gross profit is -1 million yen or less" and the target variable is "development loss occurs more than once in the next three months", data within the range of -1 million yen < gross profit < 0 for all three months, or data where the gross profit for two months is within the range of -1 million yen < gross profit < 0 and does not include months with development losses, or data where the gross profit for one month is within the range of -1 million yen < gross profit < 0 and does not include months with development losses are excluded from the training data.

[0031] In addition, for example, it corrects the imbalance in the training data. More specifically, it randomly excludes a large amount of data to match the small amount of data so that the number of data with the target variable of 1 and the number of data with the target variable of 0 are approximately the same. Also, for example, for the training data and test data, it excludes data where all the income and expenditure items such as "sales - sales plan, cost of sales - cost of sales plan, cost of sales - labor costs, cost of sales - subcontracting costs plan, gross profit" are 0 regarding the planned difference, the current month's forecast, and the initial plan.

[0032] (Acquisition unit 122) The acquisition unit 122 acquires one or more pieces of information from among the questionnaire on the project situation and the labor time information, and information on the project's income and expenditure. For example, the acquisition unit 122 acquires the questionnaire information "health check" on the project situation, the labor time information "overtime hours", and the information on the project's income and expenditure "project sales profit, project customer name, project execution month, project subcontracting costs".

[0033] The acquisition unit 122 periodically collects a questionnaire regarding the project status, information on working hours, and information regarding the project's revenue and expenditure. For example, the acquisition unit 122 collects a questionnaire regarding the project status, information on working hours, and information regarding the project's revenue and expenditure every three months. Note that three months is an example, and the acquisition unit 122 can collect information at any period according to the purpose.

[0034] (Prediction unit 123) The prediction unit 123 uses the learning model to predict information regarding the development deficit of the project, taking as input any one or more pieces of information from among the questionnaire regarding the project status and the information on working hours acquired by the acquisition unit 122, and the information regarding the project's revenue and expenditure.

[0035] For example, the prediction unit 123 inputs any one or more pieces of information from among the questionnaire regarding the project status and the information on working hours acquired by the acquisition unit 122, and the information regarding the project's revenue and expenditure, into a learning model that outputs information regarding the development deficit of the project, thereby predicting the information regarding the development deficit of the project.

[0036] The prediction unit 123 uses a learning model with a questionnaire on the project status, labor hour information, and information on the project's revenue and expenditure as inputs to predict the probability of a project incurring a deficit (unprofitability coefficient). For example, the prediction unit 123 inputs a questionnaire on the project status, labor hour information, and information on the project's revenue and expenditure into a learning model that outputs the probability of a deficit for the project, and thereby predicts the probability of a deficit. For example, the prediction unit 123 predicts the probability that a development deficit will occur within a predetermined period in the target project. More specifically, the prediction unit 123 predicts the probability that a development deficit will occur within three months in the target project.

[0037] As information on the project's revenue and expenditure, the prediction unit 123 uses one or more of the project's sales profit, the project's customer name, the project's execution month, and the project's outsourcing cost as inputs and uses a learning model to predict information related to the deficit.

[0038] For example, the prediction unit 123 uses one or more of the information "health check" of the questionnaire on the project status acquired by the acquisition unit 122 and the information "overtime hours" of the labor hours, and as information on the project's revenue and expenditure, one or more of the project's sales profit "total sales profit", the project's customer name "customer name", the project's execution month "number of months", and the project's outsourcing cost "outsourcing cost", and uses a learning model to predict information related to the deficit.

[0039] Here, an example of the prediction process according to the embodiment will be described with reference to FIG. 6. FIG. 6 is a diagram showing an example of the prediction process according to the embodiment. Note that the prediction method shown in FIG. 6 is merely a conceptually described content of regression analysis based on a learning model, and the actual prediction method is not limited.

[0040] As shown in FIG. 6, the prediction unit 123 performs regression analysis based on the learned model (LightGBM) learned by the learning unit 121, and calculates the probability of deficit occurrence. For example, the prediction unit 123 determines whether the condition that the "total operating profit for the current month's forecast" input in the first layer satisfies "XXXXXX yen or less" is met.

[0041] If the above-mentioned condition is satisfied, then subsequently, the prediction unit 123 determines whether the condition that the "planned difference_against total sales_operating profit rate" input in the next layer satisfies "XX% or less" is met. In this way, the prediction unit 123 repeats the determination in multiple layers and calculates the probability of deficit occurrence (for example, 98%, etc.). At this time, an uneconomic label "1" indicating that it is predicted that a deficit will occur for cases where the probability of deficit occurrence is 50% or more may be attached, and for cases where the probability of deficit occurrence is less than 50%, an uneconomic label "0" indicating that it is predicted that no deficit will occur may be attached.

[0042] (Output unit 124) The output unit 124 outputs information regarding the development deficit of the project predicted by the prediction unit 123. For example, as information regarding the development deficit of the project predicted by the prediction unit 123, the output unit 124 outputs, for each project, an uneconomic coefficient (probability of deficit occurrence) indicating the probability that the project will become uneconomic and an uneconomic label indicating whether the project will become uneconomic.

[0043] Here, an example of the output process according to the embodiment will be described with reference to FIG. 7. FIG. 7 is a diagram showing an example of the output process according to the embodiment. As shown in FIG. 7, the output unit 124 outputs information such as business unit "*****", department "*****", PJ aggregation ID "*****", PJ name "*****", customer name "*****", uneconomic coefficient "0.998", and uneconomic label "1" to the user's terminal device 200 or the like.

[0044] At this time, the output unit 124 can perform output processing by ranking based on any item. For example, the output unit 124 outputs the deficit occurrence probability in the order of projects with a high deficit occurrence probability predicted by the prediction unit 123. For example, the output unit 124 outputs the business unit, department, PJ aggregation ID, PF name, customer name, uneconomical coefficient, and uneconomical label in the order of projects with a high uneconomical coefficient predicted by the prediction unit 123.

[0045] The output unit 124 outputs information on the deficit predicted by the prediction unit 123, together with the results of the questionnaire on the project status collected by the acquisition unit 122, a list of the working hours of the persons participating in the project, and the output of information on the profit and loss of the project. For example, the output unit 124 outputs, as the results of the questionnaire on the project status collected by the acquisition unit 122, the negative response rate for each question, the average overtime hours of the persons participating in the project, the number of persons whose overtime hours exceed 60 hours, and the information on the period profit and loss of the project, together with the uneconomical coefficient predicted by the prediction unit 123.

[0046] Here, an example of the output processing according to the embodiment will be described with reference to FIG. 8. FIG. 8 is a diagram showing an example of the output processing according to the embodiment. For example, as shown in FIG. 8, the output unit 124 outputs, to the user's terminal device 200 or the like, information on the transition of the uneconomical coefficient of a specific project predicted by the prediction unit 123 (FIG. 8(1)), the transition of the period profit and loss of the specific project (FIG. 8(2)), the transition of the average overtime hours of the persons participating in the specific project and the number of persons whose overtime hours exceed 60 hours (FIG. 8(3)), and the transition of the negative response rate for each question as the questionnaire on the project status (PJ health check) of the specific project (FIG. 8(4)).

[0047] (Terminal device 200) The terminal device 200 is an information processing terminal that receives the information output from the information processing device 100 and displays it to the user or the like. Note that the terminal device 200 according to the present embodiment may be, for example, a smartphone, a PDA (Personal Digital Assistant), a tablet terminal, a notebook PC (Personal Computer), etc., and is not limited thereto.

[0048] [3. Flowchart] Next, an example of the processing flow by the information processing device 100 will be described with reference to FIG. 9. FIG. 9 is a flowchart showing an example of the processing flow by the information processing device 100 according to the embodiment. Note that each of the following steps can be executed in a different order, and there may be processes that are omitted.

[0049] First, the acquisition unit 122 acquires one or more pieces of information from among the questionnaire on the project status and the labor time information, and the information on the project's revenue and expenditure (step S101). For example, the acquisition unit 122 acquires the questionnaire information "health check" on the project status, the labor time information "overtime hours", and the information on the project's revenue and expenditure "project sales profit, project customer name, project execution month, project outsourcing cost".

[0050] Subsequently, the prediction unit 123 uses the learning model to predict the information on the development deficit for the project by inputting one or more pieces of information from among the questionnaire on the project status and the labor time information acquired by the acquisition unit 122, and the information on the project's revenue and expenditure (step S102).

[0051] For example, the prediction unit 123 inputs any one or more pieces of information among the questionnaire for the project status and the labor hour information acquired by the acquisition unit 122, and the information regarding the profit and loss of the project, into a learning model that outputs information regarding the development deficit of the project, and predicts the information regarding the development deficit of the project.

[0052] Subsequently, the prediction unit 123 determines whether information regarding the development deficit has been predicted for all projects (step S103). Here, if it is determined by the prediction unit 123 that information regarding the development deficit has not been predicted for all projects (step S103: No), the process of step S102 is performed again.

[0053] On the other hand, if it is determined by the prediction unit 123 that information regarding the development deficit has been predicted for all projects (step S103: Yes), the output unit 124 outputs the information regarding the development deficit of the project predicted by the prediction unit 123 (step S104). For example, the output unit 124 outputs the uneconomic coefficient and the uneconomic label of the project as the information regarding the development deficit of the project predicted by the prediction unit 123 to the user's terminal device 200 for each project.

[0054] Subsequently, the output unit 124 determines whether a selection of a project from the user has been received (step S105). Here, if it is determined by the output unit 124 that a selection of a project from the user has not been received (step S105: No), the process of step S105 is performed again.

[0055] On the other hand, when it is determined by the output unit 124 that the selection of a project from the user has been received (step S105: Yes), the output unit 124 outputs information regarding the deficit predicted by the prediction unit 123, together with the results of the questionnaire on the project status, the list of working hours of the persons participating in the project, and the information on the profit and loss of the project, for the selected project (step S106).

[0056] For example, the output unit 124 outputs to the user's terminal device 200, for the selected project, the negative response rate for each question as the result of the questionnaire on the project status, the average overtime hours of the personnel participating in the project and the number of persons whose overtime hours exceed 60 hours, and the information on the period profit and loss of the project, together with the non - profitability coefficient predicted by the prediction unit 123.

[0057] [4. Effects] The information processing apparatus 100 according to the embodiment includes an acquisition unit 122 that acquires any one or more pieces of information among the questionnaire on the project status and the working - hour information, and the information on the profit and loss of the project; a prediction unit 123 that predicts information regarding the development deficit of the project using a learning model with any one or more pieces of information among the questionnaire on the project status and the working - hour information acquired by the acquisition unit 122 and the information on the profit and loss of the project as inputs; and an output unit 124 that outputs the information regarding the development deficit of the project predicted by the prediction unit 123.

[0058] Thereby, the information processing apparatus 100 inputs information suitable for predicting the occurrence of a development deficit, such as the questionnaire on the project status, the working hours, and the information on the profit and loss of the project, into the learning model to predict the information regarding the development deficit of the project, so that it can detect the sign of the occurrence of a deficit at an early stage and accurately predict the projects with risks.

[0059] That is, the information processing apparatus 100 can accurately predict the probability of development deficit occurrence for each project by performing prediction using, as input, elements with a high degree of influence on the occurrence of development deficit.

[0060] The information processing apparatus 100 according to the embodiment further includes a learning unit 121 that learns a learning model using, as correct data, any one or more pieces of information among the questionnaire on the project status and the labor time information, the information on the project's revenue and expenditure, and the information on the development deficit of the actual project.

[0061] Thereby, the information processing apparatus 100 can accurately predict a project with risks by performing learning of the learning model using, as correct data, any one or more pieces of information among the questionnaire on the project status and the labor time information, the information on the project's revenue and expenditure, and the information on the development deficit of the actual project.

[0062] The prediction unit 123 of the information processing apparatus 100 according to the embodiment predicts the probability of deficit occurrence of the project using a learning model with, as input, a questionnaire on the project status, the labor time information, and the information on the project's revenue and expenditure, and the output unit 124 outputs the probability of deficit occurrence in the order of projects with a high probability of deficit occurrence predicted by the prediction unit 123.

[0063] Thereby, the information processing apparatus 100 predicts the probability of deficit occurrence of the project from the questionnaire on the project status, the labor time information, and the information on the project's revenue and expenditure, and outputs in the order of high probability of deficit occurrence, facilitating the grasping of projects with risks and reducing the burden on the user.

[0064] The prediction unit 123 of the information processing apparatus 100 according to the embodiment predicts information on deficit using a learning model with, as input, any one or more of the project's sales profit, the project's customer name, the project's execution month, and the project's outsourcing cost as the information on the project's revenue and expenditure.

[0065] Accordingly, the information processing apparatus 100 inputs information suitable for predicting the occurrence of development deficit, such as a questionnaire on the project status, labor hours, and information on the project's revenue and expenditure (project sales profit, project customer name, project execution month, project outsourcing cost), into the learning model to predict information on the project's development deficit, thereby enabling highly accurate prediction of projects with risks.

[0066] The acquisition unit 122 of the information processing apparatus 100 according to the embodiment periodically collects a questionnaire on the project status, information on labor hours, and information on the project's revenue and expenditure, and the output unit 124 outputs the result of the questionnaire on the project status collected by the acquisition unit 122, a list of the labor hours of the persons participating in the project, and the output of the information on the project's revenue and expenditure, together with the information on the deficit predicted by the prediction unit 123.

[0067] Accordingly, the information processing apparatus 100 can prevent the obsolescence of the information used for prediction by periodically collecting information suitable for predicting the occurrence of development deficit, and can highly accurately predict projects with risks. Further, the information processing apparatus 100 presents materials for the user who has viewed the prediction result to judge whether a development deficit is likely to actually occur by displaying the detailed information of the project together with the development deficit occurrence probability, thereby reducing the burden on the user.

[0068] [Second Embodiment] In the first embodiment, an example of predicting information related to a development deficit of a project was described by using, as inputs to a learning model, one or more pieces of information among questionnaire information on the project situation, labor time information, and information on the project's revenue and expenditure. In the subsequent second embodiment, an example of predicting information related to a development deficit of a project will be described by using, as an input to the learning model, the result of clustering information on comments on the project situation. Note that descriptions of content common to the first embodiment will be omitted as appropriate.

[0069] [1. Overview] First, an overview of the processing performed by the information processing apparatus 100 will be described with reference to FIG. 10. FIG. 10 is a diagram for explaining the overview of the processing performed by the information processing apparatus 100. As shown in FIG. 10, the information processing apparatus 100 according to the embodiment predicts the probability of occurrence of a development deficit by using information on a questionnaire on the project situation, labor time information of developers, project revenue and expenditure information, and information on comments on the project situation.

[0070] For example, the information processing apparatus 100 vectorizes the information on comments on the project situation and performs clustering on the comments to classify the comments into predetermined groups (clusters) (in the example of FIG. 10, BP (Business Partner) dissatisfaction, management dissatisfaction, etc.), and calculates the probability that the comments belong to each group. Then, the information processing apparatus 100 predicts the probability of occurrence of a development deficit by using, as inputs, the questionnaire on the project situation, the labor time information, the project revenue and expenditure information, and the clustering result of the comments on the project situation.

[0071] As described above, the information processing apparatus 100 according to the present embodiment inputs one or more pieces of information among the questionnaire on the project status and the labor time information, the information on the project's revenue and expenditure, and the result of clustering the comments on the project status into the learning model, and predicts the probability of occurrence of a development deficit, thereby reflecting the opinions of the personnel participating in the project in the prediction and being able to more accurately predict the projects with risks.

[0072] [2. Configuration of Information Processing Apparatus] Next, an example of the configuration of the information processing apparatus 100 will be described with reference to FIG. 11. FIG. 11 is a diagram showing an example of the functional configuration of the information processing apparatus 100. As shown in FIG. 11, the information processing apparatus 100 includes a communication unit 110, a control unit 120, and a storage unit 130. Note that each of these units may be held by a plurality of devices in a distributed manner. Hereinafter, the processing of each of these units will be described.

[0073] (Control Unit 120) The control unit 120 is realized by using a CPU, NP, FPGA, etc., and executes a processing program stored in a memory. As shown in FIG. 11, the control unit 120 includes a learning unit 121, an acquisition unit 122, a prediction unit 123, an output unit 124, and a calculation unit 125. Hereinafter, each unit included in the control unit 120 will be described.

[0074] (Learning Unit 121) The learning unit 121 learns a learning model using, as correct data, any one or more pieces of information among the questionnaire on the project status and the labor time information, the information on the project's revenue and expenditure, the comments on the project status, and the information on the development deficit of the actual project. For example, the learning unit 121 learns the relationship between any one or more pieces of information among the questionnaire on the project status and the labor time information, the information on the project's revenue and expenditure, the comments on the project status, and the information on the development deficit of the actual project, and uses any one or more pieces of information among the questionnaire on the project status and the labor time information, the information on the project's revenue and expenditure, and the comments on the project status as input to learn a learning model that outputs the information on the development deficit of the project.

[0075] (Acquisition unit 122) The acquisition unit 122 further acquires comments on the project status. For example, the acquisition unit 122 acquires the labor time information "overtime hours", the information on the project's revenue and expenditure "project sales profit, project customer name, project execution month, project outsourcing cost", and the comment on the project status "unease about the project".

[0076] (Calculation unit 125) The calculation unit 125 classifies the comments acquired by the acquisition unit 122 into a plurality of groups and calculates the probability that each comment belongs to a group. For example, the calculation unit 125 classifies the comments acquired by the acquisition unit 122 into four groups A, B, C, and D, and calculates the probability that each comment belongs to the groups A, B, C, and D respectively.

[0077] Here, with reference to FIG. 12, an example of the calculation process according to the embodiment will be described. FIG. 10 is a diagram for explaining an example of the calculation process according to the embodiment. The calculation unit 125 classifies comments on the situation of a certain project into a plurality of groups, and calculates the probability that each comment belongs to each of the classified groups. For example, as shown in FIG. 12, the calculation unit 125 predicts that the probability that a comment "Most of the main functions of the business have been determined ~" belongs to each cluster (group) is "A: 0.1, B: 0.2, C: 0.88, D: 0.2, E: 0.1, F: 0.1, F: 0.1, G: 0.2, H: 0.2".

[0078] Note that the calculation unit 125 can receive inputs from the user or an external device and perform labeling of each group. For example, when the user interprets the classification result by the calculation unit 125 and receives an input of the correspondence between the group name and the label such as "Group A: BP dissatisfaction", "Group B: Management dissatisfaction", each group is labeled.

[0079] Further, the calculation unit 125 vectorizes the comments acquired by the acquisition unit 122 using the frequency of occurrence or the distributed representation of the words included in the comments, and classifies the vectorized comments into a plurality of groups by clustering. Here, as a method of vectorizing using the frequency of occurrence of the words included in the comments, TF-IDF (Term Frequency-Inverse Document Frequency) is cited as an example. Also, here, as a method of vectorizing using the distributed representation of the words included in the comments, Word2Vec (Word to Vector) and BERT (Bidirectional Encoder Representations from Transformers) are cited as examples.

[0080] In addition, dimensionality reduction performed on vectorized comments is carried out by methods such as PCA (Principal Component Analysis), t-SNE (t-Distributed Stochastic Neighbor Embedding), and UMAP (Uniform Manifold Approximation and Projection). Examples of clustering algorithms include the K-Means method and HDBSCAN (Hierarchical Density Based Spatial Clustering of Applications with Noise).

[0081] Here, with reference to FIG. 13, an example of the calculation process according to the embodiment will be described. FIG. 13 is a diagram for explaining an example of the calculation process according to the embodiment. For example, the calculation unit 125 vectorizes the comments acquired by the acquisition unit 122 using BERT. Subsequently, the calculation unit 125 performs dimensionality reduction on the vectorized comments using UMAP, and then clusters them using HBDSCAN to classify them into a plurality of groups. For example, as shown in FIG. 13, the calculation unit 125 classifies the comments into 62 groups.

[0082] Then, the calculation unit 125 reduces the number of groups by classifying the comments classified into 62 groups into 40, 20, and 10 groups. Here, the number of groups for classifying the comments can be arbitrarily changed according to the purpose. Note that the vectorization method, dimensionality reduction method, and clustering method are not limited to the above, and known methods can be combined and used according to the characteristics and purpose of the data.

[0083] (Prediction Unit 123) The prediction unit 123 predicts information regarding a development deficit of the project by using a learning model with, as input, any one or more pieces of information among the questionnaire for the project status and the labor time information acquired by the acquisition unit 122, information regarding the project's profit and loss, and the probability that a comment calculated by the calculation unit 125 belongs to a predetermined group.

[0084] For example, the prediction unit 123 inputs any one or more pieces of information among the questionnaire for the project status and the labor time information acquired by the acquisition unit 122, information regarding the project's profit and loss, and the probability that a comment calculated by the calculation unit 125 belongs to a predetermined group into a learning model that outputs information regarding the development deficit of the project with the above-mentioned information as input, thereby predicting information regarding the development deficit of the project.

[0085] [3. Flowchart] Next, an example of the processing flow by the information processing apparatus 100 will be described with reference to FIG. 14. FIG. 14 is a flowchart showing an example of the processing flow by the information processing apparatus 100 according to the embodiment. Note that each of the following steps can be executed in a different order, and some processing may be omitted.

[0086] First, the acquisition unit 122 acquires any one or more pieces of information among the questionnaire for the project status and the labor time information, information regarding the project's profit and loss, and comments on the project status (step S201). For example, the acquisition unit 122 acquires the questionnaire information "health check" for the project status, the labor time information "overtime hours", the information regarding the project's profit and loss "project sales profit, project customer name, project execution month, project outsourcing cost", and the comment on the project status "unease about the project".

[0087] Subsequently, the calculation unit 125 vectorizes the comment acquired by the acquisition unit 122 (step S202). For example, the calculation unit 125 vectorizes the comment acquired by the acquisition unit 122 using Word2Vec.

[0088] Subsequently, the calculation unit 125 compresses the dimension of the vectorized comment (step S203). For example, the calculation unit 125 compresses the dimension of the vectorized comment using UMAP. Subsequently, the calculation unit 125 classifies the vectorized comment into a plurality of groups by clustering and calculates the probability of belonging to a predetermined group (step S204). For example, the calculation unit 125 clusters the vectorized comment using HBDSCAN, classifies it into a plurality of groups, and calculates the probability of belonging to a predetermined group.

[0089] Subsequently, the calculation unit 125 labels each group classified as a result of clustering (step S205). For example, the calculation unit 125 receives the content interpreted by the user about the result of clustering and labels each group.

[0090] Subsequently, the prediction unit 123 uses, as inputs, any one or more pieces of information among the questionnaire for the project status acquired by the acquisition unit 122, the information on the working hours, the information on the profit and loss of the project, and the probability that the comment calculated by the calculation unit 125 belongs to a predetermined group, and predicts information on development deficit for the project using a learning model (step S206).

[0091] For example, the prediction unit 123 inputs, as input, any one or more pieces of information among the questionnaire for the project status and the labor hour information acquired by the acquisition unit 122, the information regarding the profit and loss of the project, and the probability that the comment calculated by the calculation unit 125 belongs to a predetermined group, into a learning model that outputs information regarding the development deficit of the project, and thereby predicts the information regarding the development deficit of the project.

[0092] Subsequently, the prediction unit 123 determines whether information regarding the development deficit has been predicted for all projects (step S207). Here, if it is determined by the prediction unit 123 that information regarding the development deficit has not been predicted for all projects (step S207: No), the process of step S206 is performed again.

[0093] On the other hand, if it is determined by the prediction unit 123 that information regarding the development deficit has been predicted for all projects (step S207: Yes), the output unit 124 outputs the information regarding the development deficit of the project predicted by the prediction unit 123 (step S208). For example, the output unit 124 outputs, for each project, the uneconomic coefficient of the project and the uneconomic label as the information regarding the development deficit of the project predicted by the prediction unit 123 to the user's terminal device 200.

[0094] Subsequently, the output unit 124 determines whether a selection of a project from the user has been received (step S209). Here, if it is determined by the output unit 124 that a selection of a project from the user has not been received (step S209: No), the process of step S209 is performed again.

[0095] On the other hand, when it is determined by the output unit 124 that the selection of a project from the user has been received (step S209: Yes), the output unit 124 outputs information on the deficit predicted by the prediction unit 123, together with the results of the questionnaire on the project status, the list of working hours of the persons participating in the project, and the information on the project's revenue and expenditure, for the selected project (step S210).

[0096] For example, the output unit 124 outputs to the user's terminal device 200, for the selected project, the negative response rate for each question as the result of the questionnaire on the project status, the average overtime hours of the persons participating in the project and the number of persons whose overtime hours exceed 60 hours, and the information on the project's period profit and loss, together with the unprofitability coefficient predicted by the prediction unit 123.

[0097] [4. Effect] The acquisition unit 122 of the information processing apparatus 100 according to the embodiment further acquires comments on the project status, classifies the comments acquired by the acquisition unit 122 into a plurality of groups, and further has a calculation unit 125 that calculates the probability that a comment belongs to a predetermined group among the plurality of groups. The prediction unit 123 uses, as inputs, any one or more pieces of information among the questionnaire on the project status and the working hour information acquired by the acquisition unit 122, the information on the project's revenue and expenditure, and the probability that a comment calculated by the calculation unit 125 belongs to a predetermined group, and predicts information on the development deficit of the project using a learning model.

[0098] Thereby, when predicting information on the development deficit, the information processing apparatus 100 can use, as an input to the model, information obtained by quantifying the characteristics of each comment, so as to reflect the opinions of the persons participating in the project in the prediction and more accurately predict projects with risks.

[0099] The calculation unit 125 of the information processing apparatus 100 according to the embodiment vectorizes the comment acquired by the acquisition unit 122 using the frequency of appearance or the distributed representation of the words included in the comment, and classifies the vectorized comment into a plurality of groups by clustering.

[0100] Thereby, when predicting information related to development deficit, the information processing apparatus 100 further uses, as an additional input, the result of clustering the comments vectorized by the method using the frequency of appearance or the distributed representation of the words, and can more accurately predict the projects in which risks exist.

[0101] [Others] [1. Hardware Configuration] Next, a hardware configuration example of the information processing apparatus 100 according to the embodiment will be described. FIG. 15 is a block diagram showing a hardware configuration example of the information processing apparatus 100 according to the embodiment. Referring to FIG. 15, the information processing apparatus 100 includes, for example, a processor 801, a ROM 802, a RAM 803, a host bus 804, a bridge 805, an external bus 806, an interface 807, an input device 808, an output device 809, a storage 810, a drive 811, a connection port 812, and a communication device 813. Note that the hardware configuration shown here is an example, and some of the components may be omitted. Also, the information processing apparatus 100 may further include components other than those shown here.

[0102] (Processor 801) The processor 801 functions as, for example, an arithmetic processing unit or a control unit, and controls the overall operation or a part of the operations of each component based on various programs recorded in the ROM 802, the RAM 803, the storage 810, or the removable recording medium 901.

[0103] (ROM 802, RAM 803) The ROM 802 is a means for storing programs to be read by the processor 801, data used for calculations, and the like. In the RAM 803, for example, programs to be read by the processor 801, various parameters that change as appropriate when executing the programs, and the like are stored temporarily or permanently.

[0104] (Host bus 804, bridge 805, external bus 806, interface 807) The processor 801, ROM 802, and RAM 803 are interconnected via, for example, a host bus 804 capable of high-speed data transmission. On the other hand, the host bus 804 is connected to an external bus 806 with a relatively low data transmission speed via, for example, a bridge 805. Further, the external bus 806 is connected to various components via an interface 807.

[0105] (Input device 808) For the input device 808, for example, a mouse, keyboard, touch panel, button, switch, lever, and the like are used. Further, as the input device 808, a remote controller (hereinafter referred to as a remote control) capable of transmitting a control signal using infrared rays or other radio waves may be used. Also, the input device 808 includes a voice input device such as a microphone.

[0106] (Output device 809) The output device 809 is a device capable of visually or auditorily notifying the user of the acquired information, such as a display device such as a CRT (Cathode Ray Tube), LCD, or organic EL, an audio output device such as a speaker or headphones, a printer, a mobile phone, or a facsimile. Also, the output device 809 according to the present embodiment includes various vibration devices capable of outputting a tactile stimulus. Also, the output device 809 may include an AI speaker or a wearable device.

[0107] (Storage 810) Storage 810 is a device for storing various types of data. As the storage 810, for example, a magnetic storage device such as a hard disk drive (HDD), a semiconductor storage device, an optical storage device, or a magneto-optical storage device is used.

[0108] (Drive 811) Drive 811 is a device that reads information recorded on a removable recording medium 901 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, or writes information to the removable recording medium 901.

[0109] (Connection port 812) Connection port 812 is a port for connecting an external connection device 902 such as, for example, a USB (Universal Serial Bus) port, an IEEE1394 port, a SCSI (Small Computer System Interface), an RS-232C port, or an optical audio terminal.

[0110] (Communication device 813) Communication device 813 is a communication device for connecting to a network, and is, for example, a communication card for wired or wireless LAN, Bluetooth (registered trademark), or WUSB (Wireless USB), a router for optical communication, a router for ADSL (Asymmetric Digital Subscriber Line), or a modem for various types of communication.

[0111] (Removable recording medium 901) Removable recording medium 901 is, for example, a DVD medium, a Blu-ray (registered trademark) medium, an HD DVD medium, various types of semiconductor storage media, etc. Of course, the removable recording medium 901 may be, for example, an IC card equipped with a non-contact type IC chip, or an electronic device.

[0112] (External connection device 902) The external connection device 902 is, for example, a printer, a portable music player, a digital camera, a digital video camera, or an IC recorder.

[0113] Note that the storage unit 130 is realized by the ROM 802, the RAM 803, and the storage 810. Further, the control unit 120 realized by the processor 801 reads and executes each control program (for example, the information processing program according to the embodiment) for realizing the learning unit 121, the acquisition unit 122, the calculation unit 125, the prediction unit 123, and the output unit 124 from the ROM 802, the RAM 803, etc.

[0114] [2. Others] Among the above-described processes, all or part of the processes described as being automatically performed may be performed manually. Also, all or part of the processes described as being performed manually may be automatically performed by a known method. In addition, regarding the processing procedures, specific names, and information including various data and parameters shown in the above documents and drawings, they can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

[0115] Also, each component of each illustrated device is a functional concept, and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of the distribution and integration of each device is not limited to that shown in the figure. Also, each component may be functionally or physically distributed and integrated in any unit according to various loads and usage situations, etc., in whole or in part. Also, the above-described processes may be executed in appropriate combination within a non-contradictory range.

[0116] As described above, the embodiments of the present application have been described in detail based on several drawings, but these are examples, and the present invention can be implemented in other forms with various modifications and improvements based on the knowledge of those skilled in the art, starting from the aspects described in the column of the disclosure of the invention.

Explanation of Reference Numerals

[0117] 100 Information Processing Device 110 Communication Unit 120 Control Unit 121 Learning Unit 122 Acquisition Unit 123 Prediction Unit 124 Output Unit 125 Calculation Unit 130 Memory Unit 131 Learning Data Memory Unit 132 Project Information Memory Unit 200 Terminal Device

Claims

1. An acquisition unit that acquires any one or more pieces of information among questionnaire information on project status, labor time information, and information on the project's revenue and expenditure; A prediction unit that predicts information on the development deficit of the project using a learning model with, as input, any one or more pieces of information among the questionnaire on project status and the labor time information acquired by the acquisition unit, and information on the project's revenue and expenditure; An output unit that outputs information on the development deficit of the project predicted by the prediction unit An information processing apparatus characterized by comprising the above.

2. A learning unit that learns the learning model using, as correct data, any one or more pieces of information among the questionnaire on project status and the labor time information, information on the project's revenue and expenditure, and information on the development deficit of an actual project The information processing apparatus according to claim 1, further comprising the above.

3. The prediction unit: Predicts the probability of deficit occurrence of the project using a learning model with, as input, the questionnaire on the project status, the labor time information, and information on the project's revenue and expenditure; The output unit outputs the probability of deficit occurrence in order of the projects with a high probability of deficit occurrence predicted by the prediction unit The information processing apparatus according to claim 1, characterized by the above.

4. The prediction unit: Predicts information on the development deficit of the project using a learning model with, as input, any one or more of the project's sales profit, the project's customer name, the project's execution month, and the project's outsourcing cost as information on the project's revenue and expenditure; The information processing apparatus according to claim 1, characterized by the above.

5. The acquisition unit periodically collects the questionnaire on project status, the labor time information, and information on the project's revenue and expenditure; The output unit: Outputs the result of the questionnaire on project status collected by the acquisition unit, a list of the labor times of the persons participating in the project, information on the project's revenue and expenditure, and information on the development deficit of the project predicted by the prediction unit; The information processing apparatus according to claim 1, characterized by the above.

6. The acquisition unit further acquires comments on the project status A calculation unit that classifies the comments acquired by the acquisition unit into a plurality of groups and calculates the probability that each comment belongs to the group further comprising the prediction unit uses the learning model to predict information regarding a development deficit of the project, with as input any one or more pieces of information among the questionnaire regarding the project situation acquired by the acquisition unit and the information on the working hours, information regarding the project's revenue and expenditure, and the probability calculated by the calculation unit The information processing apparatus according to claim 1, characterized in that

7. the calculation unit vectorizes the comments acquired by the acquisition unit using the frequency of appearance or distributed representation of words included in the comments, and classifies the vectorized comments into the plurality of groups by clustering The information processing apparatus according to claim 6, characterized in that

8. A method executed by an information processing apparatus, comprising an acquisition step of acquiring any one or more pieces of information among a questionnaire regarding a project situation and information on working hours, and information regarding the project's revenue and expenditure a prediction step of predicting information regarding a development deficit of the project using a learning model, with as input any one or more pieces of information among the questionnaire regarding the project situation acquired by the acquisition step and the information on the working hours, and information regarding the project's revenue and expenditure an output step of outputting the information regarding the development deficit of the project predicted by the prediction step An information processing method, characterized by including

9. an acquisition step of acquiring any one or more pieces of information among a questionnaire regarding a project situation and information on working hours, and information regarding the project's revenue and expenditure a prediction step of predicting information regarding a development deficit of the project using a learning model, with as input any one or more pieces of information among the questionnaire regarding the project situation acquired by the acquisition step and the information on the working hours, and information regarding the project's revenue and expenditure an output step of outputting the information regarding the development deficit of the project predicted by the prediction step An information processing program, characterized by causing a computer to execute

Images