Project support system

Abstract

To facilitate forming project execution plans.SOLUTION: A project support system 10 is configured to execute, by at least one processor, first processing s1 for acquiring requirements data 100, which records information related to requirement contents of a project, and second processing s2 for identifying departments most closely related to the requirement contents recorded in the requirements data 100.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a project support system. [Background technology]

[0002] Japanese Patent Laid-Open Publication No. 2005-293403 discloses a design work support device that displays a business process template indicating design work procedures on an operation screen and supports the provision of design information and the accumulation of design results in a database in accordance with the design work procedures indicated in the business process template. The design work support device includes an automatic utilization history recording means that records, as a utilization history for each piece of design information, association information between the design work procedures and the design information provided for the design work procedures or generated as a design result in the design work procedures, and a design information utilization history database that stores and manages the utilization history. This design work support device is said to be able to accumulate the utilization history of design information without requiring the user's effort and to facilitate the reuse of design results.

[0003] International Publication No. 2023 / 218659 discloses a software development support device. The software development support device disclosed in this publication includes a similar task extraction unit configured to calculate a similarity between a workflow of a plurality of first tasks, for which software corresponding to each task has already been developed, and a workflow of a second task, for which software corresponding to each task has not yet been developed, and to extract some of the first tasks from the plurality of first tasks based on the similarity, and a software output unit configured to output a group of software corresponding to the extracted first task workflows. This reduces software development costs. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2005-293403 [Patent Document 2] International Publication No. 2023 / 218659 Summary of the Invention [Problem to be solved by the invention]

[0005] The inventors of the present invention would like to make it easier to create project execution plans. [Means for solving the problem]

[0006] The project support system disclosed here includes a department ID recording unit that records department IDs assigned to departments in charge of projects, and a processing unit. The processing unit is configured to be executed by at least one processor: a first process of acquiring request data in which information regarding the request content required for the project is recorded; and a second process of identifying the responsible department that is highly related to the request content recorded in the request data.

[0007] This project support system identifies the departments that are most relevant to the requirements of a project, making it easier to create an execution plan for the project. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a block diagram of the project support system 10 proposed herein. [Figure 2] FIG. 2 is a diagram showing an example of the request data 100 required in the project acquired in the first process s1. [Figure 3] FIG. 3 is a diagram showing an example of output data 200 to be output. [Figure 4] FIG. 4 is a schematic diagram of a deep learning model 300. [Figure 5] FIG. 5 is a schematic diagram of a deep learning model 300A according to another embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] An embodiment of the technology disclosed herein will be described below with reference to the drawings. The embodiment described here is, of course, not intended to limit the present invention. The drawings are schematic and do not necessarily reflect the actual product. Furthermore, the same reference numerals are appropriately used for components and parts that perform the same function, and redundant explanations will be omitted where appropriate.

[0010] <Project Support System 10> Figure 1 is a block diagram of the project support system 10 proposed here. Here, a project refers to a series of activities that are systematically carried out to achieve a specific goal, and is a plan that is executed by assigning people to multiple departments. The project support system 10 is a system that outputs information to facilitate the allocation of people to multiple departments when planning the execution of a project.

[0011] Here, the project support system 10 is typically embodied by a computer. The computer embodying the project support system 10 may include, for example, an interface (I / F) for receiving data from external devices, a central processing unit (CPU) for executing program instructions, a ROM for storing the program executed by the CPU, a RAM used as a working area for expanding the program, and a storage device (recording medium) such as a memory for storing the program and various data. Each function of the project support system 10 may be realized by cooperation with a computer (hardware) that executes a predetermined program (software). Although not shown in the figure, the project support system 10 may also be one in which multiple control devices cooperate with each other. The project support system 10 may also be realized, for example, by cooperative processing of multiple computers connected via a network.

[0012] The program for executing the various functions of the project support system 10 may be stored, for example, in a non-transitory computer readable medium. The program may also be supplied to a computer through such a non-transitory computer readable medium. Examples of non-transitory computer readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), CD-ROMs (Read Only Memory), etc. The program may also be installed in a computer via a network such as the Internet. The program may also be executed by multiple processors.

[0013] As shown in FIG. 1, the project support system 10 includes a recording unit 11, a processing unit 12, an input unit 21, and an output unit 22. The input unit 21 receives project requirement data. The output unit 22 is configured to present, after processing by the project support system 10, a number of departments highly relevant to the requirement content recorded in the requirement data input by the input unit 21. The project here is not particularly limited, but may be, for example, a project such as new product development. In this case, the requirement content may include the required specifications and target specifications of the new product.

[0014] <Recording Section 11> The recording unit 11 is a part that records various data of the project support system 10. The recording unit 11 includes a department ID recording unit 11a. The recording unit 11 may also include a recording unit that records various data other than the department ID recording unit 11a.

[0015] <Department ID recording section 11a> The department ID recording unit 11a is a memory in which department IDs are recorded. The department IDs are individual identifiers (Identifications) assigned to multiple departments in charge of a project. The departments in charge to which department IDs are assigned may include not only departments that have handled projects in the past, but also departments that may handle projects in the future and newly established departments. In the project support system 10, it is preferable that the department ID recording unit 11a stores the individual identifiers assigned to the multiple departments in association with the departments in charge. In addition, the project support system 10 may be configured to have a computer execute a process for recording the individual identifiers in the department ID recording unit 11a in association with the departments in charge.

[0016] Processing section 12 The processing unit 12 is a part configured to have at least one processor execute predetermined processes of the project support system 10. The processes executed by the processing unit 12 include the following first process s1 and second process s2.

[0017] <First process s1> The first process s1 is a process of acquiring requirement data in which information regarding the requirements required for a project is recorded. Here, the requirement required for a project is, for example, if the project is related to product development, detailed content such as required specifications and target specifications related to product development, broken down by item. The requirement data in which information regarding the requirement is recorded may preferably have the information regarding the requirement recorded as computer-readable information.

[0018] FIG. 2 is a diagram illustrating an example of requirement data 100 required for a project acquired in the first process s1. In the example illustrated in FIG. 2, the requirement data 100 required for the project is represented in a spreadsheet. Here, a requirement ID is assigned to each piece of requirement data 100 required for the project. In FIG. 2, the requirement ID column 101 may be assigned an individual identifier, such as ABC0001...ABC0011..., for each required content in each project. The required content column 102 may be different for each project. FIG. 2 illustrates an example of requirement content for a development project to develop a new lithium-ion secondary battery. The department column 103 lists departments that may be responsible for the project in order. The responsible department column 103 may list the responsible departments recorded in the department ID recording unit 11a in order, as shown in FIG. 2. In such a spreadsheet, for each requirement content linked to a requirement ID, the relationship between the multiple responsible departments corresponding to the project can be recorded in the corresponding cell. Here, the content of the request may change for each project, and the multiple departments in charge of each project may also change for each organization corresponding to the project.

[0019] In the example shown in Figure 2, the requirements for a lithium-ion secondary battery development project include mass production timing, storage temperature, operating environment, power supply voltage, dimensions, peak output current during use, detected SOC accuracy, vibration resistance, noise resistance, transmission of battery temperature information to the ECU, opening of a protection switch in the event of a battery abnormality, advance notification of changes in materials or parts, warranty period, ensuring traceability during production, and advance notification of changes in the production process. Here, the storage temperature refers to the required environmental temperature for storing the manufactured lithium-ion secondary batteries. The operating environment refers to the required environmental temperature for using the manufactured lithium-ion secondary batteries. Thus, in the form shown in Figure 2, the requirements are listed by category, covering various requirements for the manufactured lithium-ion secondary batteries. The department column may be listed according to the organization responsible for the project, such as systems, mechanisms, electrical components, circuits, software, procurement, quality assurance, production technology, or factory. Each department may be assigned a department ID as a computer-identifiable identifier.

[0020] In the first process s1, the requirements data 100, which records information about the requirements required for the project, may be acquired. In the project support system 10, the requirements data 100 may be recorded in a spreadsheet, each linked to a requirement ID, as shown in FIG. 2. The spreadsheet may also have multiple cells corresponding to multiple departments responsible for each requirement. In this way, the requirements data 100 may be, for example, data on the requirements specifications and target specifications related to development, organized by item.

[0021] <Second process s2> The second process s2 is a process of identifying a responsible department that is highly relevant to the request content recorded in the request data 100. The request data 100 shown in FIG. 2 can be input data for the process of identifying a responsible department that is highly relevant to the request content. A responsible department that is highly relevant to the request content recorded in the request data 100 can be, for example, a department that has a track record of responding to the request content in past projects, or a department whose items that the department is scheduled to be responsible for match or are close to the items in the request content. In this way, the second process s2 can be a means of assigning a responsible department to each item of the request specifications or target specifications recorded in the request data 100.

[0022] The process for realizing the second process s2 can include, for example, various processes configured to determine, based on the request content recorded in the request data 100, a department in charge that is highly related to the request content.

[0023] The second process s2 may be, for example, a process of using the machine learning model 40 to identify a responsible department highly related to the request content recorded in the requested content column 102 of the request data 100. The machine learning model may include an input layer to which the request data 100 obtained in the first process s1 is input, and an output layer to which the department ID of the responsible department highly related to the request content recorded in the requested content column 102 of the request data 100 is output. In this case, the machine learning model may be configured to previously learn, by machine learning, the correlation between the request content recorded in the request data 100 and information on the performance of each department in dealing with the request content in past projects and information on the items that the department is scheduled to be responsible for. The machine learning model may then be configured to output a responsible department highly related to the request content recorded in the request data 100.

[0024] In the second process s2, the requirements data obtained in the first process s1 may be input to an input layer of a machine learning model, and the department IDs of departments highly relevant to the requirements data may be obtained from an output layer. The machine learning model may be a trained model trained based on the requirements data, which records information about the requirements required for the project, and training data, which records correlations between the requirements data and predetermined departments corresponding to the project. Existing technologies can be applied to machine learning. For example, a neural network model may be used as the machine learning model. Furthermore, the machine learning model may include a deep learning model with multiple intermediate layers of a neural network. Deep learning also includes GUI (Graphical User Interface) tools that can be operated without writing code. By training appropriate training data, deep learning can more accurately present multiple departments highly relevant to the requirements required for the project as candidates without human intervention.

[0025] FIG. 3 is a diagram illustrating an example of output data 200. As illustrated in FIG. 3, the output data 200 may be output in the form of a spreadsheet, for example. In the form illustrated in FIG. 3, the output data 200 may be in the form of a spreadsheet in the same format as the input data (requirement data 100). The requirement ID column 201 of the output data 200 is assigned the same ID as the requirement data 100. In the department column 203 of the output data 200, multiple departments highly relevant to the requirement content required for the project listed in the requirement content column 202 are marked. For the requirement content required for the project, cells corresponding to the departments are marked with "◎" or "○" in descending order of relevance. This output data allows the user to grasp the relationship between the requirement content required for the project and the departments at a bird's-eye view. Based on this output, the user can easily determine the department responsible for the requirement content required for the project.

[0026] Here, Fig. 4 is a schematic diagram of a deep learning model 300. As shown in Fig. 4, the deep learning model 300 receives the requirement data 100 shown in Fig. 2 as input data, and outputs output data 200 (see Fig. 3) in which, in a department column 203, multiple departments that are highly relevant to the requirement content required for the project listed in a requirement content column 202 are marked. Note that, although Fig. 4 illustrates a deep learning model 300, the deep learning model 300 can be understood as one form of a machine learning model or a neural network model, and can be replaced with a machine learning model or a neural network model as appropriate, provided that this is acceptable.

[0027] Here, the project support system 10 may be configured such that the process of updating the machine learning model is executed by at least one processor, as shown in Fig. 4. Fig. 4 illustrates a deep learning model 300 as an example of the machine learning model. The accuracy of a machine learning model such as the deep learning model 300 improves with repeated learning.

[0028] Here, the learning data for the deep learning model 300 as a machine learning model may be information describing the relationship between the request content recorded in the request data 100 and departments highly related to the request content. For example, it may be possible to learn information prepared in the past that describes the relationship between the request content recorded in the request data 100 and departments highly related to the request content. An example of such learning data is a document 280 that was created manually in the past to assign responsibilities to each department.

[0029] The project support system 10 does not necessarily have to make the final decision on the department responsible for the request details recorded in the request data 100 of the project. The person who decides the department responsible for the request details of the project may be a user (person). From this perspective, the project support system 10 may present the user with reference materials to help the person decide the department responsible for the request details recorded in the request data. As shown in FIG. 4, the teaching data used by the deep learning model 300 to learn may be correction data 301 obtained by a person correcting the relationship between the request details recorded in the request data presented by the project support system 10 and the responsible department.

[0030] In this way, the project support system 10 may be configured so that at least one processor executes a process of acquiring corrected data 301 in which the relationship with the responsible department output from the output layer of the deep learning model 300 (machine learning model) is corrected, and a process of updating the deep learning model 300 by learning the corrected data 301 as teaching data. By using the manually corrected corrected data 301 as additional learning data, the accuracy of the deep learning model 300 is improved.

[0031] In the deep learning model 300, the computer itself learns which part of the requirements data 100 to focus on and output the highly relevant departments. The deep learning model 300 eliminates the need for a human to instruct which part of the requirements data 100 to focus on and output the highly relevant departments. Furthermore, the accuracy of the computer improves as it learns. For this reason, the use of the deep learning model 300 in the project support system 10 is expected to significantly simplify the amount of human effort required.

[0032] 5 is a schematic diagram of a deep learning model 300A according to another embodiment. As shown in FIG. 5, the process of updating the deep learning model 300A (machine learning model) may, for example, learn items highly relevant to the department in charge of the project based on information recorded in the database 400 of the department in charge of the project. From this perspective, the project support system 10 may be configured to execute a process of acquiring information recorded in the database 400 of the department in charge of the project.

[0033] For example, as shown in FIG. 5 , the project support system 10 may be configured to learn, using a machine learning model, the track record of each department and the items planned for each department as training data 302. The track record of each department and the items planned for each department may be information retrieved from a database 400 used by each department. That is, the database 400 used by each department records information 303 handled by each department. For example, the database 400 may record deliverable documents resulting from the work of each department for each department. The project support system 10 may be configured to be able to access the database 400 recording the information 303 handled by each department via a network. In this case, the project support system 10 may access the database 400 used by each department and acquire the information 303 handled by each department as training data 302. The information 303 handled by each department may include information such as drawings, structural design documents, circuit diagrams, circuit design documents, and test results.

[0034] In this case, deep learning model 300A learns items highly relevant to the department in charge of the project based on information recorded in database 400 of the department in charge of the project. In this way, deep learning model 300A learns based on information recorded in database 400 of the department in charge of the project, and information 303 handled by each department is updated appropriately. This allows deep learning model 300A to more accurately present departments highly relevant to the requirements required for the project.

[0035] In this case, as shown in FIG. 1, the project support system 10 may further include a department information storage unit 11b that obtains keywords from information recorded in a database 400 (see FIG. 5) of the department in charge of the project and records the keywords in association with the department ID. Keywords related to the department are recorded and accumulated in the department information storage unit 11b. For example, keywords may be extracted from information, drawings, structural design documents, circuit diagrams, circuit design documents, test results, etc. recorded in the database 400 of the department in charge of the project and recorded in association with the department ID. Keywords are highly important words for extracting highly relevant departments, and may be words, phrases, or coherent words.

[0036] The second process s2 for determining a department highly relevant to the request content recorded in the request data 100 may use a machine learning model configured, for example, to input the request data 100 obtained in the first process s1 to an input layer and obtain, from an output layer, department IDs of departments highly relevant to the request content recorded in the request data 100. The machine learning model may be a pre-trained machine learning model (e.g., deep learning model 300) that is trained in advance so as to determine a department highly relevant to the request content recorded in the request data 100 based on keywords stored in the department information storage unit 11b. Furthermore, the machine learning model may be configured to extract words included in the request data 100 or related words, and to determine a department highly relevant to the request data 100 based on the extracted words and the keywords stored in the department information storage unit 11b.

[0037] Here, deep learning models 300 and 300A are exemplified as machine learning models, but deep learning models 300 and 300A do not necessarily need to be used in project support system 10. Project support system 10 may include, for example, a means for storing deliverable documents resulting from the work of each department for each responsible department, and a means for accepting data on development-related requirement specifications and target specifications for each item, and a means for assigning a responsible department to each item of requirement specifications and target specifications based on the degree of relevance between the deliverable documents stored for each responsible department and the requirement specifications or target specifications. From this perspective, not only deep learning models but also machine learning models can be used as the means for assigning a responsible department to each item of requirement specifications and target specifications based on the degree of relevance between the deliverable documents stored for each responsible department and the requirement specifications or target specifications.

[0038] From this perspective, in the project support system 10, the relevance may be linked by focusing on words in the items of the requirement specifications or target specifications. For example, the relevance may be linked by focusing on the relationship between multiple words in the items of the requirement specifications or target specifications. The relevance may be weighted according to the words.

[0039] According to the project support system 10, a highly relevant department is identified for each requirement content required in a project using a machine learning model such as a neural network model or deep learning models 300 and 300A. Therefore, by examining the output data 200, it becomes easy to, for example, create an execution plan for the project.

[0040] The invention disclosed herein has been described in various ways. Unless otherwise specified, the embodiments described herein do not limit the present invention. Furthermore, the embodiments of the invention disclosed herein can be modified in various ways, and each component and each process described herein can be omitted or combined as appropriate, unless a particular problem arises.

[0041] As described above, this specification includes the disclosures set forth in the following sections.

[0042] Section 1: A first process of acquiring requirement data in which information regarding requirements content required in the project is recorded; A second process of identifying a department highly related to the request content recorded in the request data; configured to be executed by at least one processor, Project support system.

[0043] Section 2: the second processing is configured so that the request data obtained in the first processing is input to an input layer of a machine learning model, and a department in charge of a highly relevant piece of the request data is obtained from an output layer; Here, the machine learning model is a trained machine learning model that has been trained based on requirement data that records information about the requirements required for the project and teaching data that records the correlation with the predetermined responsible department corresponding to the project, in the project support system described in paragraph 1.

[0044] Section 3: Item 3. The project support system according to item 2, wherein the machine learning model is a deep learning model.

[0045] Section 4: A project support system as described in item 2, configured to have at least one processor execute a process of updating the machine learning model using modified data as additional learning data, in which the relationship with the responsible department output from the output layer of the machine learning model is modified.

[0046] Section 5: A process of acquiring information recorded in a database of a department in charge of the project; A process of learning items highly relevant to the department in charge of the project based on information recorded in the database of the department in charge, and updating the machine learning model. The project support system according to claim 2, configured to be executed by at least one processor.

[0047] Item 6: The system further includes a department information storage unit that stores keywords obtained from information recorded in a database of the department in charge of the project, in association with the department. The project support system described in item 1.

[0048] Section 7: the second processing is configured so that the request data obtained in the first processing is input to an input layer of a machine learning model, and a department in charge of a highly relevant piece of the request data is obtained from an output layer; Here, the machine learning model is a trained machine learning model that has been trained in advance to identify a responsible department that is highly relevant to the request content recorded in the request data based on keywords stored in the department information storage unit. The project support system described in Section 6.

[0049] Section 8: The machine learning model is configured to extract words contained in the request data or related words, and to identify a department that is highly related to the request data based on the extracted words and keywords stored in the department information storage unit. The project support system described in Section 7. [Explanation of symbols]

[0050] 10 Project Support System 11 Recording section 11a Department ID Record Section 11b Department information storage section 12 Processing section 21 Input section 22 Output section 40 Machine Learning Models 100 Request data (input data) 101 Request ID field 102 Required Contents Column 103 Department column 200 output data 201 Request ID field for output data 200 202 Request details column 203 Department column of output data 200 280 Materials 300,300A Deep Learning Model 301 Correction Data 302 Training Data 303 Information handled by each department 400 databases

Claims

1. a first process of acquiring requirement data in which information regarding requirements content required in a project is recorded; a second process of identifying a department highly related to the request content recorded in the request data; configured to be executed by at least one processor, Project support system.

2. the second processing is configured so that the request data obtained in the first processing is input to an input layer of a machine learning model, and a department in charge of a high degree of relevance of the request data is obtained from an output layer; Here, the machine learning model is a trained machine learning model that has been trained based on requirement data that records information regarding the requirements required for the project and teaching data that records the correlation with a predetermined responsible department corresponding to the project, as described in claim 1.

3. The project support system according to claim 2 , wherein the machine learning model is a deep learning model.

4. 3. The project support system of claim 2, wherein the machine learning model is updated by at least one processor using corrected data as additional learning data, the relationship with the responsible department output from the output layer of the machine learning model being corrected.

5. A process of acquiring information recorded in a database of a department in charge of the project; A process of learning items highly relevant to the department in charge of the project based on information recorded in the database of the department in charge, and updating the machine learning model. The project support system according to claim 2 , wherein the steps of:

6. The system further includes a department information storage unit that stores keywords obtained from information recorded in a database of the department in charge of the project, in association with the department.

2. A project support system according to claim 1.

7. the second processing is configured so that the request data obtained in the first processing is input to an input layer of a machine learning model, and a department in charge of a high degree of relevance of the request data is obtained from an output layer; Here, the machine learning model is a trained machine learning model that has been trained in advance to identify a responsible department that is highly relevant to the request content recorded in the request data based on keywords stored in the department information storage unit.

7. A project support system according to claim 6.

8. The machine learning model is The system is configured to extract words contained in the request data or related words, and to identify a department that is highly related to the request data based on the extracted words and keywords stored in a department information storage unit.

8. A project support system according to claim 7.

Images