Machine learning device, WBS creation device, machine learning method
The machine learning device addresses the complexity of WBS creation by integrating standard and project-specific information to generate a consistent WBS through supervised and reinforcement learning, enhancing compliance and consistency in software development projects.
Patent Information
- Application Number
- JP2023576619
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Priority Date
- 2022-01-31
- Filing Date
- 2022-10-19
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2042-10-19
Smart Images

Figure 0007584684000001 
Figure 0007584684000002 
Figure 0007584684000003
Abstract
Description
[Technical Field]
[0001] The present disclosure relates to a machine learning device, a WBS creation device, and a machine learning method. [Background technology]
[0002] A product development project is an activity to create a product that meets the quality, price, and deadline required by the customer. However, in projects, especially software development, it is difficult to determine whether the activities are being carried out in a planned manner that meets the quality, price, and deadline required by the customer until the product is incorporated into the system. In software development, which faces such challenges, it has been suggested to utilize a WBS (Work Breakdown Structure).
[0003] The WBS is a system that allows you to identify all work from the start of a project to its completion without any omissions. However, in recent projects, the number of WBS work packages has increased, and the connections between them have become more complex. Furthermore, within the same organization, products with different quality characteristics may be produced in parallel. Differences in compliance with standards, particularly those related to performance and scalability, operation and maintainability, and system environment and ecology, among other quality characteristics, make it difficult to create a WBS for a project.
[0004] Various technologies have been proposed to solve these problems. For example, Patent Document 1 proposes a technology in which a management ID is assigned to a deliverable, trace information is attached to the management ID, and the trace information is registered in a traceability ID recording terminal. Patent Document 2 proposes supervised learning that uses state variables and judgment data as training data. [Prior art documents] [Patent documents]
[0005] [Patent Document 1] Japanese Patent Application Publication No. 2018-5802 [Patent Document 2] Japanese Patent Application Laid-Open No. 2017-188030 Summary of the Invention [Problem to be solved by the invention]
[0006] Traditionally, experts have analyzed customer requirements and created the basis of a WBS from the most suitable reusable assets extracted from the organization's past project performance. However, this method relies heavily on the skills of the experts, and it is difficult to incorporate customer requirements into the WBS while ensuring consistency in compliance with standards within a limited time frame.
[0007] To address this issue, it is possible to conduct learning based on information from standards, but there is a problem in that an appropriate WBS cannot be created using only information from standards.
[0008] Therefore, the present disclosure has been made in consideration of the above-mentioned problems, and aims to provide a technology that enables creation of an appropriate general-purpose WBS. [Means for solving the problem]
[0009] The machine learning device according to the present disclosure includes an acquisition unit that acquires first information about a WBS work package of a standard, second information about a WBS work package of a project corresponding to the standard, and third information about a process diagnosis result of the project corresponding to the standard, and an acquisition unit that performs learning about the WBS work package based on the first information, the second information, and the third information, thereby associating the first information, the second information, and the third information. It was used to create the WBS. and a learning control unit that generates related information. [Effects of the Invention]
[0010] According to the present disclosure, related information is generated by learning about the WBS work packages based on first information about the WBS work packages of the standard, second information about the WBS work packages of the project corresponding to the standard, and third information about the process diagnosis results of the project corresponding to the standard. With this configuration, an appropriate general-purpose WBS can be created.
[0011] The objects, features, aspects and advantages of the present disclosure will become more apparent from the following detailed description and the accompanying drawings. [Brief explanation of the drawings]
[0012] [Figure 1] FIG. 1 is a block diagram showing an example of the configuration of a machine learning device according to a first embodiment. [Figure 2] 4 is a flowchart illustrating an example of machine learning processing according to the first embodiment. [Figure 3] FIG. 2 is a diagram showing an example of an ID management table according to the first embodiment; [Figure 4] 4 is a flowchart illustrating an example of machine learning processing according to the first embodiment. [Figure 5] FIG. 3 is a diagram showing an example of a term management table according to the first embodiment. [Figure 6] 4 is a flowchart illustrating an example of machine learning processing according to the first embodiment. [Figure 7] FIG. 2 is a diagram showing an example of a general-purpose WBS task table according to the first embodiment. [Figure 8] FIG. 2 is a diagram showing an example of a general-purpose WBS link table according to the first embodiment. [Figure 9] FIG. 3 is a diagram showing an example of a link type according to the first embodiment. [Figure 10] FIG. 1 is a diagram illustrating an example of the configuration of a neural network. [Figure 11] FIG. 10 is a block diagram showing an example of the configuration of a WBS creation device according to a second embodiment. [Figure 12]FIG. 10 is a diagram showing an example of an input screen of an information input unit according to the second embodiment. [Figure 13] FIG. 10 is a diagram showing an example of an output screen of an information output unit according to the second embodiment. [Figure 14] FIG. 10 is a diagram showing an example of an output screen of an information output unit according to the second embodiment. [Figure 15] FIG. 10 is a block diagram showing a hardware configuration of a machine learning device according to another modified example. [Figure 16] FIG. 10 is a block diagram showing a hardware configuration of a machine learning device according to another modified example. DETAILED DESCRIPTION OF THE INVENTION
[0013] <First Embodiment> Fig. 1 is a block diagram showing an example of the configuration of a machine learning device according to the first embodiment. The machine learning device of Fig. 1 includes a specifications management unit 101, a general-purpose WBS control unit 105, an asset management unit 111, and a diagnosis management unit 121. At least one of the specifications management unit 101, the general-purpose WBS control unit 105, the asset management unit 111, and the diagnosis management unit 121 may be provided on a single terminal or may be distributed across multiple terminals. The machine learning device of Fig. 1 may also be provided on a cloud server.
[0014] The standard management unit 101 manages first information related to the WBS work packages of the standard. The asset management unit 111 manages second information related to the WBS work packages of the project corresponding to the standard. The diagnosis management unit 121 manages third information related to the evaluation results of the process diagnosis results of the project corresponding to the standard. Projects corresponding to the standard include, for example, projects that reuse standards. In the following description, projects corresponding to the standard may be simply referred to as "projects." The first information may include the WBS work packages of the standard themselves, and the second information may include the WBS work packages of the project themselves.
[0015] The general-purpose WBS control unit 105 generates related information that associates the first information, second information, and third information by learning about the WBS work package based on the first information, second information, and third information managed by the specifications management unit 101 and the asset management unit 111. The learning about the WBS work package may be the learning of the WBS work package itself.
[0016] The related information generated by this learning is used to create a general-purpose WBS, etc. The related information according to the first embodiment includes at least one of the ID management table 106, the term management table 107, the general-purpose WBS task table 108, and the general-purpose WBS link table 109. However, the related information is not limited to these, and may include, for example, tables other than these tables.
[0017] The standards management unit 101 manages, for example, a standards information table 102, a standards terminology table 103, and a standards association table 104 as first information. The standards information table 102 registers WBS work packages including technical process activities, management process activities, and support process activities based on information defined in the standards. The standards terminology table 103 registers the meanings of terms defined in the standards. The standards association table 104 registers the names of standards and the names of other related standards.
[0018] The asset management unit 111 manages, for example, an asset information table 112, an asset terminology table 113, and an asset association table 114 as second information. The asset information table 112 registers WBS work packages including technical process activities, management process activities, and support process activities that were executed in past projects. The asset terminology table 113 registers the meanings of terms defined in the project. The asset association table 114 registers the names of projects generated by reusing standards that the project complies with.
[0019] The diagnostic management unit 121 manages, for example, a diagnostic information table 122, a diagnostic terminology table 123, and a diagnostic association table 124 as third information. The diagnostic information table 122 registers assessment results including technical process activities, management process activities, and support process activities diagnosed in past projects. The diagnostic terminology table 123 registers the meanings of terms defined in the project. The diagnostic association table 124 registers the names of projects generated by reusing standards that the project complies with.
[0020] The general-purpose WBS control unit 105 includes an acquisition unit 105a and a learning control unit 105b. The acquisition unit 105a acquires first information from the specifications management unit 101, acquires second information from the asset management unit 111, and acquires third information from the diagnosis management unit 121. The acquisition unit 105a may also acquire the first information, second information, and third information from a network.
[0021] The learning control unit 105b has a machine learning function and generates related information that relates the first information, the second information, and the third information by performing learning on the WBS work package based on the first information, the second information, and the third information. The related information according to the first embodiment includes at least one of the ID management table 106, the term management table 107, the general WBS task table 108, and the general WBS link table 109.
[0022] The ID management table 106 is a table that records an identifier for identifying a standard or a project, an identifier for the associated standard or project, the name of the standard or project, and version management. In other words, the ID management table 106 includes the name of at least one of the standard and the project.
[0023] The terminology management table 107 is a table that records an identifier for identifying a standard or a project, an identifier for identifying other standards or projects that use the same term, and the defined term. In other words, the terminology management table 107 includes at least one term of a standard or a project.
[0024] The general WBS task table 108 is a table that records the identifiers for identifying the WBS work packages used in the general WBS, the identifiers of the standards in which the WBS work packages used in the general WBS are defined, and the contents of the WBS work packages used in the general WBS. In other words, the general WBS task table 108 includes the contents of the WBS work packages.
[0025] The general WBS link table 109 is a table that records the link types between WBS work packages used in the general WBS, the identifiers of the WBS work packages used in the link source general WBS, and the identifiers of the WBS work packages used in the link destination general WBS. In other words, the general WBS link table 109 includes trace information that associates WBS work packages with each other.
[0026] The learning control unit 105b generates the ID management table 106 by performing supervised learning using the standards information table 102 and the standards association table 104. The learning control unit 105b also strengthens the ID management table 106 by performing reinforcement learning using the asset information table 112 and the asset association table 114. The learning control unit 105b also strengthens the ID management table 106 by performing reinforcement learning using the diagnostic information table 122 and the diagnostic association table 124.
[0027] The learning control unit 105b generates the term management table 107 by performing supervised learning using the standard terminology table 103 and the standard association table 104. The learning control unit 105b also strengthens the term management table 107 by performing reinforcement learning using the asset terminology table 113 and the asset association table 114. The learning control unit 105b also strengthens the term management table 107 by performing reinforcement learning using the diagnostic terminology table 123 and the diagnostic association table 124.
[0028] The learning control unit 105b generates a general-purpose WBS task table 108 by performing supervised learning using the ID management table 106, the terminology management table 107, and the contents of the standard WBS work packages recorded in the standards information table 102. The learning control unit 105b also strengthens the general-purpose WBS task table 108 by performing reinforcement learning using the ID management table 106, the terminology management table 107, and the contents of the WBS work packages of the projects recorded in the asset information table 112. The learning control unit 105b also strengthens the general-purpose WBS task table 108 by performing reinforcement learning using the ID management table 106, the terminology management table 107, and the contents of the process diagnosis results of the projects recorded in the diagnosis information table 122.
[0029] The learning control unit 105b generates a general-purpose WBS link table 109 by performing supervised learning using the ID management table 106, the terminology management table 107, and correlation information of standard WBS work packages recorded in the specifications information table 102. The learning control unit 105b also strengthens the general-purpose WBS link table 109 by performing reinforcement learning using the ID management table 106, the terminology management table 107, and correlation information of WBS work packages of projects recorded in the asset information table 112. The learning control unit 105b also strengthens the general-purpose WBS link table 109 by performing reinforcement learning using the ID management table 106, the terminology management table 107, and correlation information of process diagnosis results of projects recorded in the diagnosis information table 122.
[0030] If there is insufficient general WBS information in the general WBS task table 108 and the general WBS link table 109, the missing information may be manually registered. Also, in the above description, supervised learning may be performed instead of reinforcement learning.
[0031] Fig. 2 is a flowchart for explaining an example of machine learning processing by the learning control unit 105b regarding the ID management table 106. An example of the ID management table 106 is shown in Fig. 3.
[0032] Although not shown, when machine learning processing for the ID management table 106 starts, the acquisition unit 105a acquires the name of a standard or project from the standard-related table 104, the asset-related table 114, or the diagnosis-related table 124. In the following description, the name acquired by the acquisition unit 105a will be referred to as the "acquired name."
[0033] In step S1, the learning control unit 105b determines whether a name that matches the acquired name is registered in data 303 and data 304 of the ID management table 106. If it is determined that they match, the processing in FIG. 2 ends, and if it is determined that they do not match, the processing proceeds to step S2.
[0034] In step S2, the learning control unit 105b registers the acquired name in data 303 and data 304. For example, the nickname of the acquired name is registered in the master of data 303, and the version of the acquired name is registered in the slave of data 304.
[0035] In step S3, the learning control unit 105b generates an identifier for identifying the acquired name and registers it in the data 301.
[0036] In step S4, the learning control unit 105b determines whether a past standard or project related to the standard or project indicated by the acquired name is registered in the ID management table 106. For example, if the learning control unit 105b determines, based on the standard information table 102, that the standard indicated by the acquired name reuses a past standard, the standard indicated by the acquired name is determined to be related to the past standard. For example, if the learning control unit 105b determines, based on the standard information table 102, the asset information table 112, and the diagnosis information table 122, that the project indicated by the acquired name reuses a past project, the project indicated by the acquired name is determined to be related to the past project.
[0037] If it is determined that the standard or project indicated by the acquired name is related to a past standard or project, the process proceeds to step S5. If it is determined that the standard or project indicated by the acquired name is not related to a past standard or project, the process of FIG. 2 ends.
[0038] In step S5, the learning control unit 105b registers the identifier of the past standard or project in the associated acquired name data 302. Then, the processing in Fig. 2 ends. As the learning control unit 105b performs learning, the determination in step S4, for example, is optimized, and the ID management table 106 in Fig. 3 is optimized.
[0039] Fig. 4 is a flowchart for explaining an example of machine learning processing of the learning control unit 105b regarding the term management table 107. An example of the term management table 107 is shown in Fig. 5.
[0040] The machine learning process of the learning control unit 105b for the terminology management table 107 is performed, for example, on the standard or project for which an identifier was generated in step S3 of Fig. 2. Although not shown, when the machine learning process starts, the acquisition unit 105a acquires terms used in the standard or project for which an identifier was generated in step S3 from the standard terminology table 103, the asset terminology table 113, or the diagnostic terminology table 123. In the following description, the terms acquired by the acquisition unit 105a will be referred to as "acquired terms."
[0041] In step S11, the learning control unit 105b determines whether a term whose meaning matches the acquired term is registered in the data 503 of the term management table 107. If it is determined that they match, the process proceeds to step S12, and if it is determined that they do not match, the process proceeds to step S13.
[0042] In step S12, the learning control unit 105b obtains, from the data 501 of the terminology management table 107, the identifiers of past standards or projects that use the terms determined in step S11 to have the same meaning as the obtained term.
[0043] 2 in data 501. If the processing of step S12 has been performed, the learning control unit 105b registers the identifier acquired in step S12 in data 502.
[0044] In step S14, the learning control unit 105b registers the acquired terms in data 503. After that, the processing in Fig. 4 ends. As the learning control unit 105b performs learning, for example, the determination in step S11 is optimized, and the term management table 107 in Fig. 5 is optimized.
[0045] Fig. 6 is a flowchart for explaining an example of machine learning processing by the learning control unit 105b regarding the general WBS task table 108 and the general WBS link table 109. Note that Fig. 7 shows an example of the general WBS task table 108, and Fig. 8 shows an example of the general WBS link table 109.
[0046] The machine learning process of the learning control unit 105b for the general WBS task table 108 and the general WBS link table 109 is performed, for example, on the standard or project for which an identifier was generated in step S3 of Figure 2. Although not shown, when the machine learning process starts, the acquisition unit 105a acquires the WBS work packages used in the standard or project for which an identifier was generated in step S3 from the standard information table 102, asset information table 112, or diagnostic information table 122. In the following description, the WBS work packages acquired by the acquisition unit 105a will be referred to as "acquired packages."
[0047] In step S21, the learning control unit 105b determines whether a WBS work package to which the acquired package is linked is registered in the general WBS task table 108 and the general WBS link table 109. If it is determined that a WBS work package to which the acquired package is linked is registered, the process proceeds to step S23, and if it is determined that a WBS work package to which the acquired package is linked is not registered, the process proceeds to step S22.
[0048] In step S22, the learning control unit 105b determines whether a WBS work package whose activity is the same as the acquired package is registered in the general WBS task table 108 and the general WBS link table 109. If it is determined that a WBS work package whose activity is the same as the acquired package is registered, the process proceeds to step S23; if it is determined that a WBS work package whose activity is the same as the acquired package is not registered, the process in FIG. 6 ends.
[0049] In step S23, the learning control unit 105b generates a task ID and registers it in the data 701, and registers the identifier generated in step S3 of FIG.
[0050] In step S24, the learning control unit 105b registers the contents of the acquired package in the data 703.
[0051] In step S25, the learning control unit 105b registers the link type in data 801 based on the task information of the WBS work package. The learning control unit 105b also registers the task ID of the WBS work package that is the link destination in data 701 in data 802, and registers the task ID of the WBS work package that is the link source in data 701 in data 803. The processing in FIG. 6 then ends. As the learning control unit 105b performs learning, the registration in step S24, for example, is optimized, and the general WBS task table 108 in FIG. 7 and the general WBS link table 109 in FIG. 8 are optimized.
[0052] Fig. 9 is a diagram for explaining an example of the link types in Fig. 8. A link type of 0 indicates that the link destination is the next process for the link source. A link type of 1 indicates that the link destination and the link source are the same process. A link type of 2 indicates that the link destination is a part of the process of the link source.
[0053] The processes of steps S1 to S5 in Fig. 2, steps S11 to S14 in Fig. 4, and steps S21 to S25 in Fig. 6 are repeated until the general-purpose WBS work package is fully learned. Note that it is preferable that the WBS work package of a standard or project is implemented using multiple link type patterns.
[0054] FIG. 10 is a diagram illustrating an example of a neural network configuration. The machine learning of the learning control unit 105b may, for example, learn design review achievement prediction according to a neural network model. As illustrated in FIG. 10, the neural network includes an input layer including one neuron x1, x2, x3, ..., x1, an intermediate layer (hidden layer) including m neurons y1, y2, y3, ..., ym, and an output layer including n neurons z1, z2, z3, ..., zn. While the example of the neural network configuration in FIG. 10 includes only one intermediate layer, two or more intermediate layers may be provided. Furthermore, a general-purpose computer or processor may be used for the machine learning (neural network) of the learning control unit 105b, but faster processing is possible by applying a large-scale PC cluster or the like.
[0055] The neural network may learn the ID management table 106, terminology management table 107, general WBS task table 108, or general WBS link table 109 associated with the general WBS work package, i.e., learn related information. The neural network may learn related information that associates standards and project WBS work packages, etc., through so-called "supervised learning" according to verification results based on a combination of related information and judgment data indicating whether the related information is correct or incorrect. Here, "supervised learning" refers to learning that can inductively acquire the relationship between input and result by providing a learning device with a large number of pairs of input and result (label) to learn the features present in those verification results and create a model that infers the result from the input, i.e., the relationship between input and result.
[0056] The machine learning performed by the learning control unit 105b is not limited to "supervised learning." For example, a neural network may be used to accumulate correct related information, i.e., only the ID management table 106, terminology management table 107, general WBS task table 108, or general WBS link table 109 that correctly meets the verification criteria, and the general WBS work package may be learned by so-called "unsupervised learning." For example, if the verification results of the ID management table 106, terminology management table 107, general WBS task table 108, or general WBS link table 109 are extremely accurate, the "unsupervised learning" method is considered effective.
[0057] Here, "unsupervised learning" refers to learning that can compress, classify, reshape, etc. input data by providing a large amount of input data and learning how the input data is distributed without providing corresponding supervised data. This type of learning enables clustering, which classifies similar verification results. Using this result, some kind of criterion can be set to assign outputs that optimize the data, making it possible to predict the output.
[0058] In addition, generic WBS work packages can be trained using a method called "semi-supervised learning," which is an intermediate method between "unsupervised learning" and "supervised learning." "Semi-supervised learning" is effective when, for example, only some input and output data pairs exist and the rest of the data is input only.
[0059] <Summary of the First Embodiment> According to the first embodiment described above, related information is generated by learning about WBS work packages based not only on first information about standard WBS work packages but also on second information about the project's WBS work packages and third information about the project's process diagnosis results. This configuration allows, for example, the second or third information to supplement content that is lacking in the first information, thereby enabling appropriate learning about WBS work packages and generating related information that can create an appropriate, general-purpose WBS. In other words, even when the factors that improve the achievement of verification results are complex and it is difficult to pre-determine the project's WBS work packages, it is possible to generate a predictive model that can create a highly accurate WBS.
[0060] The learning control unit 105b may learn the WBS work package by learning the ID management table 106, the terminology management table 107, the general WBS task table 108, or the general WBS link table 109. The learning control unit 105b may also learn the WBS work package based on first information, second information, and third information acquired from multiple standard management units 101, multiple asset management units 111, and multiple diagnostic management units 121 operating at the same development site. The learning control unit 105b may also learn the WBS work package based on first information, second information, and third information acquired from multiple standard management units 101, multiple asset management units 111, and multiple diagnostic management units 121 operating independently at different development sites. Any of the standard management unit 101, asset management unit 111, and diagnostic management unit 121 may be added to or removed from the target from which the first information, second information, and third information are acquired.
[0061] Verification results may be shared (commonly used) among multiple general-purpose WBS control units 105. As a first example, the same neural network model may be shared among multiple general-purpose WBS control units 105. Specifically, each weighting coefficient of the network for reflecting differences among multiple general-purpose WBS control units 105 may be transmitted using a communication means. As a second example, machine learning weights and the like may be shared by sharing verification results of the input and output of the neural network. As a third example, a pre-prepared database may be accessed to load a more appropriate neural network model, thereby sharing the state so that similar models are used. The sharing of verification results among multiple general-purpose WBS control units 105 is not limited to the first to third examples.
[0062] <Embodiment 2> 11 is a block diagram showing an example of the configuration of a WBS creation device according to the second embodiment. Hereinafter, the WBS creation device according to the second embodiment will be described as a specific WBS creation device that creates a WBS work package specific to a project. In the following, among the components according to the second embodiment, components that are the same as or similar to the components described above will be assigned the same or similar reference numerals, and different components will be mainly described.
[0063] As shown in Figure 11, the WBS creation device of this embodiment 2 has the same configuration as the machine learning device of Figure 1 described in embodiment 1, with the addition of an information input unit 1101, a unique WBS control unit 1102, and an information output unit 1103.
[0064] The information input unit 1101 acquires the current project or a standard specification corresponding to the current project as input information. The specific WBS control unit 1102 acquires related information, such as a general WBS work package created by machine learning from the general WBS control unit 105 based on the input information. The specific WBS control unit 1102 creates a specific WBS work package or a specific WBS for the current project based on the input information and related information, according to the development scale and degree of change of the project. The information output unit 1103 outputs the specific WBS work package or specific WBS created by the specific WBS control unit 1102.
[0065] In this embodiment 2, the project from which the second information used in machine learning is obtained may be a past project as in embodiment 1, or it may be a current new project input into the information input unit 1101.
[0066] Furthermore, a neural network model may be used in a configuration for creating a specific WBS work package as in the second embodiment. For example, the output layer may calculate the affinity between the verification results input to the input layer of the neural network and information indicating whether the general WBS work package is successful or not, or the WBS work package that is deemed valid. Then, based on the affinity, the output layer may output information indicating whether the general WBS work package is successful or not, or the WBS work package that is deemed valid.
[0067] 12 is a diagram showing an example of the input screen of the information input unit 1101. A main WBS selection screen 1201 displays selectable project names obtained from the ID management table 106 of the general WBS control unit 105. The project names may be displayed in a list of all projects, or in a pull-down format.
[0068] The integration target WBS selection screen 1202 displays selectable names of standards obtained from the ID management table 106 of the general-purpose WBS control unit 105. The standard names may be displayed in a list of all project names, or in a pull-down menu. Furthermore, when a project is displayed on the main WBS selection screen 1201, the integration target WBS selection screen 1202 may display standards associated with the project (e.g., standards to which the project conforms) pre-checked. Furthermore, the integration target WBS selection screen 1202 may add or delete standards associated with the project as needed.
[0069] 13 is a diagram showing an example of an output screen of the information output unit 1103. The specific WBS control unit 1102 acquires the standard specifications associated with the project selected in the information input unit 1101 from the general WBS work package registered in the general WBS task table 108 and the general WBS link table 109 of the general WBS control unit 105. The specific WBS control unit 1102 then creates a specific WBS based on the input information and the acquired standard specifications, and the specific WBS output screen 1301 displays the created specific WBS.
[0070] If a WBS work package is newly added to the project, the unique WBS output screen 1301 may highlight the added WBS work package. Also, if multiple WBS work packages are newly added to the project, the information output unit 1103 may be configured to allow the user to select one WBS work package from among them.
[0071] The unique WBS output screen 1302 is a button for starting output of the project of the selected WBS work package. The output format may be text or a file format compatible with other application tools.
[0072] In the second embodiment, the information input section 1101 and the information output section 1103 are configured to be selectively displayed on one screen, and the unique WBS output screen 1303 is a button for returning to the display of Fig. 12. The unique WBS output screen 1304 is a button for terminating the operation of the WBS creation device.
[0073] 14 is a diagram showing an example of an output screen of the information output unit 1103, specifically a diagram showing an example of a selection screen when there are multiple WBS work packages newly added to a project. The main WBS confirmation screen 1401 displays the name of the project, etc. selected on the main WBS selection screen 1201 of the information input unit 1101.
[0074] The WBS work package selection screen 1402 displays, for example, a list of selectable names of multiple WBS work packages that correspond to the selected project. When a project is displayed on the main WBS confirmation screen 1401, the WBS work package selection screen 1402 may display multiple WBS work packages that have been newly added to the project with a check mark next to them.
[0075] In actual operation, there may be cases where a newly added WBS work package does not exist in a project. In such cases, the WBS work package selection screen 1402 may display other standards that are similar to the standard associated with the project, or WBS work packages of other projects. The WBS work package selection screen 1402 allows a user to select a work package to be used in the project from multiple WBS work packages.
[0076] <Summary of the second embodiment> In the second embodiment, a WBS for a current project is created based on information about the current project and related information. With this configuration, an appropriate unique WBS can be created.
[0077] <Other variations> The acquisition unit 105a and learning control unit 105b in FIG. 1 are hereinafter referred to as the "acquisition unit 105a, etc." The acquisition unit 105a, etc. are realized by a processing circuit 81 shown in FIG. 15. That is, the processing circuit 81 includes an acquisition unit 105a that acquires first information about a WBS work package of a standard, second information about a WBS work package of a project corresponding to the standard, and third information about a process diagnosis result of the project corresponding to the standard, and a learning control unit 105b that performs learning about the WBS work package based on the first information, the second information, and the third information, thereby generating association information that associates the first information, the second information, and the third information. The processing circuit 81 may be implemented by dedicated hardware, or may be implemented by a processor that executes a program stored in memory. Examples of the processor include a central processing unit, a processing unit, an arithmetic unit, a microprocessor, a microcomputer, and a DSP (Digital Signal Processor).
[0078] When the processing circuit 81 is dedicated hardware, the processing circuit 81 may be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a combination thereof. The functions of each unit such as the acquisition unit 105a may be realized by a circuit in which processing circuits are distributed, or the functions of each unit may be realized together by a single processing circuit.
[0079] When the processing circuitry 81 is a processor, the functions of the acquisition unit 105a and the like are realized in combination with software and the like. Software and the like may include, for example, software, firmware, or software and firmware. The software and the like are written as a program and stored in memory. As shown in FIG. 16, the processor 82 applied to the processing circuitry 81 realizes the functions of each unit by reading and executing a program stored in memory 83. That is, the machine learning device includes a memory 83 for storing a program that, when executed by the processing circuitry 81, results in the following steps: acquiring first information about a WBS work package of a standard, second information about a WBS work package of a project corresponding to the standard, and third information about a process diagnosis result of the project corresponding to the standard; and generating associated information that associates the first information, the second information, and the third information by performing learning about the WBS work package based on the first information, the second information, and the third information. In other words, this program can be said to cause a computer to execute the procedures and methods of the acquisition unit 105a and the like. Here, the memory 83 may be, for example, a non-volatile or volatile semiconductor memory such as RAM (Random Access Memory), ROM (Read Only Memory), flash memory, EPROM (Erasable Programmable Read Only Memory), EEPROM (Electrically Erasable Programmable Read Only Memory), an HDD (Hard Disk Drive), a magnetic disk, a flexible disk, an optical disk, a compact disk, a mini disk, a DVD (Digital Versatile Disc), a drive device for any of these, or any storage medium to be used in the future.
[0080] The above describes a configuration in which each function of the acquisition unit 105a, etc. is realized either by hardware or software, etc. However, this is not limited to this, and a configuration in which part of the acquisition unit 105a, etc. is realized by dedicated hardware and another part is realized by software, etc. For example, the function of the acquisition unit 105a can be realized by dedicated hardware such as a processing circuit 81, an interface, and a receiver, and the other functions can be realized by the processing circuit 81 as a processor 82 reading and executing a program stored in a memory 83.
[0081] As described above, the processing circuitry 81 can realize the above-mentioned functions by hardware, software, or a combination of these.
[0082] It should be noted that the embodiments and modifications may be freely combined, and the embodiments and modifications may be modified or omitted as appropriate.
[0083] The above description is illustrative in all respects and is not restrictive. It is understood that countless variations not illustrated can be envisioned. [Explanation of symbols]
[0084] 105a: Acquisition unit; 105b: Learning control unit.
Claims
1. An acquisition unit that acquires first information on a WBS work package of a standard, second information on a WBS work package of a project corresponding to the standard, and third information on a process diagnosis result of the project corresponding to the standard; a learning control unit that performs learning on a WBS work package based on the first information, the second information, and the third information, thereby generating associated information used for creating a WBS, which associates the first information, the second information, and the third information; A machine learning device comprising:
2. The machine learning device according to claim 1 , The relevant information includes the contents of the WBS work packages.
3. The machine learning device according to claim 1 or 2, A machine learning device, wherein the association information includes trace information that associates the WBS work packages with each other.
4. The machine learning device according to claim 1 or 2, The machine learning device, wherein the related information includes at least one of terms and names of the standard and / or the project.
5. The machine learning device according to claim 1 or 2, A machine learning device, wherein the related information includes at least one of a term and a name of the diagnostic information.
6. The machine learning device according to claim 1 or 2, The acquisition unit acquires the first information and the second information from a network.
7. The machine learning device according to claim 1 or 2, The project from which the second information is obtained includes a current project.
8. The machine learning device according to claim 1 or 2, The machine learning device is provided on a cloud server.
9. The machine learning device according to claim 1 or 2, A WBS creation device creates a WBS for the current project based on information about the current project and the related information.
10. An acquisition unit acquires first information on a WBS work package of a standard, second information on a WBS work package of a project corresponding to the standard, and third information on a process diagnosis result of the project corresponding to the standard; A machine learning method in which a learning control unit learns about a WBS work package based on the first information, the second information, and the third information, thereby generating associated information used to create a WBS that associates the first information, the second information, and the third information.
Citation Information
Patent Citations
Work decomposition structure WBS template recommendation method
CN112069417A
WBS automatic construction method and system based on highway engineering design information
CN112685804A
System for performing process management, process management method and program
JP2009176010A
Machine learning device for learning failure prediction of main axis or motor driving main axis and machine learning method, and failure prediction device having machine learning device and failure prediction system
JP2017188030A
Traceability id recording device
JP2018005802A
