System, computer and data production method

Abstract

The object is to provide a system that can support the creation of a system. [Solution] In this invention, a storage device of one or more computers stores first information regarding one or more first functions provided by a software platform and second information regarding one or more second functions provided by each of one or more plug-ins available in the software platform. The system proposal data indicates whether the one or more functions required for the generation system can be realized by the first function, the second function, or a third function. A control device of the one or more computers generates third information related to input data from the first information and the second information, and causes a machine learning model to generate the system proposal data for the generation system based on the input data and the third information.

Description

[Technical Field]

[0001] The present invention relates to a system, a computer and a data production method. [Background technology]

[0002] As an invention relating to a conventional system, for example, the platform described in Non-Patent Document 1 is known. This platform can create a business system for customer management, for example. The platform also has multiple plug-ins available. Users can extend the functionality of the platform by using the plug-ins. [Prior art documents] [Non-patent literature]

[0003] [Non-Patent Document 1] Cybozu, Inc., "kintone extension", [online], [searched October 1, 2023], Internet<URL:https: / / kintone-sol.cybozu.co.jp / integrate / search / > Summary of the Invention [Problem to be solved by the invention]

[0004] System integrators (SIers) undertake a series of processes, including the design, development, implementation, operation, and maintenance of information systems used by companies. When implementing an information system using the above platform, SIers must understand the functions of the platform and then consider which plug-ins to use and whether or not to develop new programs.

[0005] SUMMARY OF THE INVENTION It is therefore an object of the present invention to provide a system, a computer and a data production method that can assist in the creation of a system. [Means for solving the problem]

[0006] The first form is A system for generating system proposal data used in a software platform that supports the creation of a generation system, The system comprises one or more computers; a storage device of the one or more computers storing first information about one or more first functions provided by the software platform and second information about one or more second functions provided by each of one or more plug-ins available for the software platform; the software platform is capable of adding the first functionality to the production system; the plug-in is capable of adding the second functionality to the production system; the system proposal data indicates whether the one or more functions required for the generation system can be realized by the one or more first functions, the one or more second functions, or the one or more first functions and a third function other than the one or more second functions; the one or more computers are equipped with a machine learning model; the one or more computer control devices Takes input data containing text, generating third information related to the input data from the first information and the second information; causing the machine learning model to generate system proposal data for the generation system based on the input data and the third information; It is a system.

[0007] The second form is the one or more computer control devices generating the input data in which the speech is converted into text based on speech data representing speech in a conference; In the process of acquiring the input data, the input data obtained by converting the voice into text is acquired. The system according to the first aspect.

[0008] The third form is the one or more computer control devices generating the input data by sequentially converting the speech into text in response to acquisition of the speech data during the conference; The system is described in the second aspect.

[0009] The fourth form is the one or more computer control devices generating emotion information relating to emotions of speakers in the conference based on the voice data; generating the input data in which the speech is converted into text based on the speech data and the emotion information; The system according to the second or third aspect.

[0010] The fifth form is the one or more computer control devices generating overall explanation data that explains a system configuration of the generation system realized by at least one of the first function, the second function, and the third function based on the system proposal data; The system is according to any one of the first to fourth aspects.

[0011] The sixth form is the one or more computer control devices causing the machine learning model to generate second explanation data that explains the plug-in of the second function that can realize one or more functions required for the generation system based on the system proposal data; The system is according to any one of the first to fifth aspects.

[0012] The seventh form is the one or more computer control devices causing the machine learning model to generate third explanation data that explains one or more functions required for the generation system that can be realized by the third function, based on the system proposal data; The system is according to any one of the first to sixth aspects.

[0013] The eighth form is the third description data includes a description of a generating application that implements the third function. The system according to the seventh aspect.

[0014] The ninth form is The machine learning model is a trained model that has undergone machine learning using data related to the data output by the machine learning model as training data. The system according to any one of the first to eighth aspects.

[0015] The tenth form is A first computer used in a system for generating system proposal data used in a software platform for supporting the creation of a generation system, the system includes the first computer and a second computer; a storage device of the first computer stores first information about one or more first functions provided by the software platform and second information about one or more second functions provided by each of one or more plug-ins available for the software platform; the software platform is capable of adding the first functionality to the production system; the plug-in is capable of adding the second functionality to the production system; the system proposal data indicates whether the one or more functions required for the generation system can be realized by the one or more first functions, the one or more second functions, or the one or more first functions and a third function other than the one or more second functions; the second computer includes a machine learning model; The control device of the first computer Takes input data containing text, generating third information related to the input data from the first information and the second information; instructing the second computer to generate system proposal data of the generation system in the machine learning model based on the input data and the third information; This is the first computer.

[0016] The 11th form is A second computer used in a system for generating system proposal data used in a software platform for supporting the creation of a generation system, The system includes a first computer and the second computer, a storage device of the first computer stores first information about one or more first functions provided by the software platform and second information about one or more second functions provided by each of one or more plug-ins available for the software platform; the software platform is capable of adding the first functionality to the production system; the plug-in is capable of adding the second functionality to the production system; the system proposal data indicates whether the one or more functions required for the generation system can be realized by the one or more first functions, the one or more second functions, or the one or more first functions and a third function other than the one or more second functions; the second computer includes a machine learning model; The control device of the first computer Takes input data containing text, generating third information related to the input data from the first information and the second information; The control device of the second computer causing the machine learning model to generate system proposal data for the generation system based on the input data and the third information; This is the second computer.

[0017] The 12th form is A data production method for generating system proposal data used in a software platform that supports the creation of a production system, comprising: The system comprises one or more computers, a storage device of the one or more computers storing first information about one or more first functions provided by the software platform and second information about one or more second functions provided by each of one or more plug-ins available for the software platform; the software platform is capable of adding the first functionality to the production system; the plug-in is capable of adding the second functionality to the production system; the system proposal data indicates whether the one or more functions required for the generation system can be realized by the one or more first functions, the one or more second functions, or the one or more first functions and a third function other than the one or more second functions; the one or more computers are equipped with a machine learning model; a controller for the one or more computers; Let it take input data containing text, generating third information related to the input data from the first information and the second information; causing the machine learning model to generate system proposal data for the generation system based on the input data and the third information; It is a data production method. [Effects of the Invention]

[0018] According to the present invention, it is possible to assist in creating a system. [Brief explanation of the drawings]

[0019] [Figure 1] FIG. 1 is an explanatory diagram of the system 1. [Figure 2] FIG. 2 is a block diagram of the user terminal 10. [Figure 3] FIG. 3 is a block diagram of the server 110. [Figure 4] FIG. 4 is a block diagram of the server 210. [Figure 5] FIG. 5 shows the minutes data D2. [Figure 6] FIG. 6 is a diagram showing the standard function table T1, which is the first information. [Figure 7] FIG. 7 is a diagram showing the plug-in table T2, which is the second information. [Figure 8] 8 to 10 are diagrams showing the system proposal data D3. [Figure 9] 8 to 10 are diagrams showing the system proposal data D3. [Figure 10] 8 to 10 are diagrams showing the system proposal data D3. [Figure 11] FIG. 11 is a flowchart executed by the control device 12 of the user terminal 10. [Figure 12] FIG. 12 is a flowchart executed by the control device 112 of the server 110 and the control device 212 of the server 210 in the system 1. [Figure 13] FIG. 13 is a diagram of the functional requirement document indicated by the functional requirement document data D5. [Figure 14] FIG. 14 is a diagram of the non-functional requirements document indicated by the non-functional requirements document data D6. [Figure 15] FIG. 15 is a business process flow diagram indicated by the business process flow diagram data D7. [Figure 16] FIG. 16 is a diagram of the application design document indicated by the application design document data D8. [Figure 17] FIG. 17 is a diagram of a plug-in proposal indicated by the plug-in proposal data D9. [Figure 18]FIG. 18 is a diagram of the control item list indicated by the control item list data D10. [Figure 19] FIG. 19 is an ER diagram indicated by the ER diagram data D11. [Figure 20] FIG. 20 is a system configuration diagram indicated by the system configuration diagram data D12. DETAILED DESCRIPTION OF THE INVENTION

[0020] (Embodiment) A system 1 according to an embodiment of the present disclosure will be described with reference to the drawings.

[0021] [System 1 Configuration] First, the overall configuration of the system 1 will be described with reference to the drawings. Fig. 1 is an explanatory diagram of the system 1. Fig. 2 is a block diagram of the user terminal 10. Fig. 3 is a block diagram of the server 110. Fig. 4 is a block diagram of the server 210.

[0022] 1 includes a user terminal 10 (one or more computers), a server 110 (one or more computers), and a server 210 (one or more computers). The user terminal 10, the server 110, and the server 210 can communicate with each other via a communication network. The network may be the Internet, an intranet, or the like.

[0023] The user terminal 10 is an information processing device used by a user. The user terminal 10 is, for example, a smartphone, a tablet terminal, or a personal computer. As shown in Fig. 2, the user terminal 10 includes a control device 12, a storage device 14, a network interface 16, a graphics processing unit 18, a display 20, an operation unit 26, and a touch panel 28.

[0024] The storage device 14 stores programs and data and is, for example, a combination of a read-only memory (ROM), a random access memory (RAM), and a storage (for example, a flash memory or a hard disk).

[0025] The programs include, for example, the following programs: OS (Operating System) programs - Programs for applications that process information (e.g., web browsers or target apps described below)

[0026] The data includes, for example, the following data: Databases referenced in information processing Data obtained by performing information processing (i.e., the results of performing information processing)

[0027] The control device 12 executes the programs stored in the storage device 14 to realize the functions of the user terminal 10. The control device 12 is, for example, at least one of the following: ·CPU(Central Processing Unit) ·GPU(Graphic Processing Unit) ·ASIC(Application Specific Integrated Circuit) ·FPGA(Field Programmable Array)

[0028] The control device 12 includes a text conversion means 30 as a functional block.

[0029] The network interface 16 controls communication between the user terminal 10 and external devices. The external devices are servers 110 and 210.

[0030] The graphics processing unit 18 displays an image on the display 20 based on the image data generated by the control device 12. The display 20 is a liquid crystal display or an organic EL (Electro Luminescence) display.

[0031] The operation unit 26 generates an operation signal based on a user's operation on the touch panel 28 and outputs the operation signal to the control device 12 .

[0032] The server 110 is a first computer. The server 110 is a Retrieval-Augmented Generation (RAG) server. Therefore, the server 110 searches a database or a knowledge base for information related to a query from a user. The server 110 then generates a context based on the query and the information related to the query, and outputs the context to the server 210. As shown in FIG. 3 , the server 110 includes a control device 112, a storage device 114, and a network interface 116.

[0033] The storage device 114 stores programs and data and is, for example, a combination of a read-only memory (ROM), a random access memory (RAM), and a storage device (for example, a flash memory or a hard disk).

[0034] The control device 112 executes a program stored in the storage device 114 to realize the functions of the server 110. The control device 112 is, for example, at least one of the following: ·CPU(Central Processing Unit) ·GPU(Graphic Processing Unit) ·ASIC(Application Specific Integrated Circuit) ·FPGA(Field Programmable Array)

[0035] The control device 112 includes, as functional blocks, an input data acquisition means 120, a third information generation means 122, and a system proposal data generation instruction means 124.

[0036] The network interface 116 controls communication between the server 110 and external devices, which are the user terminal 10 and the server 210.

[0037] The server 210 is a second computer. The server 210 is a so-called machine learning server. The server 210 generates an answer based on the context generated by the server 110. As shown in FIG. 4 , the server 210 includes a control device 212, a storage device 214, and a network interface 216.

[0038] The storage device 214 stores programs and data and is, for example, a combination of a read-only memory (ROM), a random access memory (RAM), and a storage device (for example, a flash memory or a hard disk).

[0039] The control device 212 executes the programs stored in the storage device 214 to realize the functions of the server 210. The control device 212 is, for example, at least one of the following: ·CPU(Central Processing Unit) ·GPU(Graphic Processing Unit) ·ASIC(Application Specific Integrated Circuit) ·FPGA(Field Programmable Array)

[0040] The control device 212 includes a system proposal data generating means 220, an overall explanation data generating means 222, a second explanation data generating means 226, and a third explanation data generating means 228 as functional blocks.

[0041] The network interface 216 controls communication between the server 210 and external devices, such as the user terminal 10 and the server 110.

[0042] The server 210 (one or more computers) also includes a machine learning model 250. The machine learning program is a program for executing a machine learning algorithm to find certain rules from training data and generate a trained machine learning model 250 that expresses the found rules. The control device 212 of the server 210 executes the machine learning program, whereby multiple training data are machine-learned and parameters of the inference program are adjusted. As a result, the trained machine learning model 250 is generated. The machine learning model 250 is a trained model that has undergone machine learning using data related to the data output by the machine learning model 250 as training data. Examples of data related to the data output by the machine learning model 250 include, for example, some or all of the following: minutes data D2, system proposal data D3, functional requirements data D5, non-functional requirements data D6, business flow diagram data D7, application design data D8, plug-in proposal data D9, management item data D10, entity relationship diagram data D11, and system configuration diagram data D12, which will be described later.

[0043] The machine learning algorithm is not particularly limited as long as it is supervised learning, and may be, for example, a decision tree, a nearest neighbor method, a naive Bayes classifier, a support vector machine, or a neural network. Therefore, the trained machine learning model 250 includes a decision tree, a nearest neighbor method, a naive Bayes classifier, a support vector machine, or a neural network. Backpropagation may be used in the machine learning used to generate the trained machine learning model 250.

[0044] For example, a neural network includes an input layer, one or more hidden layers, and an output layer. Specifically, the neural network is a deep neural network, a recurrent neural network, or a convolutional neural network, and performs deep learning. The deep neural network includes, for example, an input layer, multiple hidden layers, and an output layer.

[0045] [System 1 operation] Next, the operation of the system 1 will be described with reference to the drawings. Fig. 5 is a diagram showing minutes data D2. Fig. 6 is a diagram showing standard function table T1, which is the first information. Fig. 7 is a diagram showing plug-in table T2, which is the second information. Figs. 8 to 10 are diagrams showing system proposal data D3.

[0046] First, an overview of the operation of system 1 will be described. System 1 generates system proposal data D3 to be used in platform K (software platform) that supports the creation of system A (generation system). More specifically, the user is the developer of system A. The user holds a conference with a client about the creation of system A. At this time, system 1 acquires video data D1 of the conference. System 1 generates minutes data D2 shown in FIG. 5 based on the video data D1. The minutes data D2 is the minutes of the conference about system A. The minutes data D2 describes requirements for system A. Specifically, the minutes data D2 describes a method for realizing system A and the functions that are desired to be realized in system A.

[0047] Here, we will explain System A. System A is the system A used by the secretariat of the Umeda Yukata Festival. System A performs processes for sending surveys, collecting surveys, aggregating and analyzing the surveys, and contacting survey respondents. System A is created using Platform K. Platform K can create System A for customer management. Platform K is a no-code application that allows users to create systems by using a visual-based interface. Platform K is, for example, kintone (registered trademark) made by Cybozu, Inc.

[0048] Platform K can realize one or more first functions and one or more second functions. The one or more first functions are standard functions provided by platform K (software platform). Platform K (software platform) can add the first function to system A (generation system). The first function is, for example, a process for collecting questionnaires. The second function is a function provided by each of one or more plug-ins available in platform K (software platform). The plug-ins can add the second function to system A (generation system). The second function is, for example, a process for contacting survey respondents. Furthermore, a function that is not one or more of the first functions or one or more second functions is defined as a third function. The third function is, for example, a process for creating a questionnaire response form or a process for sending the questionnaire form by email, fax, etc.

[0049] The storage device 114 of the server 110 (one or more computers) stores first information regarding one or more first functions and second information regarding one or more second functions. More specifically, the storage device of the server 110 stores a standard function table T1 shown in FIG. 6 and a plug-in table T2 shown in FIG. 7. The standard function table T1 is the first information. The standard function table T1 includes descriptions of first functions that can be realized by standard functions provided in the platform K. The plug-in table T2 is the second information. The plug-in table T2 includes descriptions of second functions that can be realized by plug-ins available for the platform K.

[0050] Based on the minutes data D2, the system 1 causes the machine learning model 250 to generate the system proposal data D3 shown in FIGS. 8 to 10. The system proposal data D3 indicates whether one or more first functions, one or more second functions, or a third function can realize one or more functions required for the system A (generated system). Specifically, the system proposal data D3 includes a use case table 300. The user can design and develop the system A based on this system proposal data D3.

[0051] Next, details of the operation of the system 1 will be described with reference to the drawings. Fig. 11 is a flowchart executed by the control device 12 of the user terminal 10. Fig. 12 is a flowchart executed by the control device 112 of the server 110 and the control device 212 of the server 210 in the system 1.

[0052] The control device 12 of the user terminal 10 reads out the programs stored in the storage device 14, which cause the control device 12 of the user terminal 10 to execute the operations described below. The programs cause the control device 12 to execute the text conversion means 30.

[0053] When the control device 112 of the server 110 reads out the programs stored in the storage device 114, these programs cause the control device 112 of the server 110 to execute the operations described below. The programs cause the control device 112 to execute input data acquisition means 120, third information generation means 122, and system proposal data generation instruction means 124.

[0054] When the control device 212 of the server 210 reads out the programs stored in the storage device 214, these programs cause the control device 212 of the server 210 to execute the operations described below. The programs cause the control device 212 to execute a system proposal data generation means 220, an overall explanation data generation means 222, a second explanation data generation means 226, and a third explanation data generation means 228.

[0055] First, a user holds a Web conference with a client. A Web conference server (not shown) generates video data D1 for the Web conference and stores the video data D1. In parallel with the generation and storage of video data D1 by the Web conference server, the control device 12 of the user terminal 10 downloads the video data D1 from the Web conference server. As a result, the control device 12 of the user terminal 10 acquires the video data D1 (step S201).

[0056] The control device 12 (text conversion means 30) of the user terminal 10 generates minutes data D2 (input data; see FIG. 5 ) by converting speech into text based on the video data D1 of the conference (step S202). In this embodiment, the control device 12 (text conversion means 30) of the user terminal 10 generates minutes data D2 (input data) by successively converting speech into text in response to acquisition of video data D1 (audio data) during the conference. Note that the video data D1 contains speech, and therefore corresponds to audio data indicating speech. Note that the processing of step S202 can be realized, for example, by Google Cloud's Speech-to-Text (manufactured by Google). Successive conversion means that the control device 12 of the user terminal 10 converts speech into text while acquiring the video data D1. In successive conversion, the control device 12 of the user terminal 10 operates so as to minimize the delay between acquiring the video data D1 and converting speech into text.

[0057] Next, the control device 12 of the user terminal 10 transmits the minutes data D2 to the server 110 via the network interface 16 (step S203). In response, the network interface 116 of the server 110 receives the minutes data D2 and outputs the minutes data D2 to the control device 112. As a result, the control device 112 (input data acquisition means 120) of the server 110 (one or more computers) acquires the minutes data D2 (input data) in which the speech has been converted into text (step S101). In this way, the control device 112 (input data acquisition means 120) of the server 110 (one or more computers) acquires the minutes data D2 (input data) including text as shown in FIG. 5.

[0058] Next, the control device 112 (third information generating means 122) of the server 110 generates a context D4 (third information) related to the minutes data D2 (input data) from the standard function table T1 (first information) shown in Fig. 6 and the plug-in table T2 (second information) shown in Fig. 7 (step S102). The context D4 includes the result of the control device 112 of the server 110 searching for information related to the minutes data D2 based on the standard function table T1 and the plug-in table T2.

[0059] Next, the control device 112 of the server 110 transmits the minutes data D2 and the context D4 to the server 210 via the network interface 116 (step S103). That is, in step S103, the control device 112 (system proposal data generation instruction means 124) of the server 110 instructs the server 210 (second computer) to generate system proposal data D3 (see FIGS. 8 to 10) for system A (generation system) in the machine learning model 250 based on the minutes data D2 (input data) and the context D4 (third information). In response, the network interface 216 of the server 210 receives the minutes data D2 and the context D4 and outputs the minutes data D2 and the context D4 to the control device 212. As a result, the control device 212 of the server 210 acquires the minutes data D2 and the context D4 (step S1).

[0060] Next, the control device 212 (system proposal data generation means 220) of the server 210 causes the machine learning model 250 to generate system proposal data D3 for system A (generation system) based on the minutes data D2 (input data) and the context D4 (third information) (step S2). As shown in FIGS. 8 to 10, the system proposal data D3 indicates the specifications of system A described in the minutes data D2. Specifically, the system proposal data D3 includes a purpose, main functions 303, system configuration, benefits, and others 302, a business flow 301, a use case table 300, and supplementary information 304.

[0061] The Main Functions 303 column lists the functions required for System 1. The Other 302 column describes information other than the functions required for System A. The Work Flow 301 column describes the work performed by those involved in System A (the secretariat, respondent, and system).

[0062] Use case table 300 is a table that indicates whether one or more first functions, one or more second functions, or a third function can realize one or more functions required of system A (generation system). The use case column describes the function. The classification column describes whether the function in the use case column can be realized by the first function, the second function, or the third function. A standard function corresponds to the first function. A plugin corresponds to the second function. Customization means that a user customizes a standard function, and corresponds to the third function. An external service corresponds to the third function.

[0063] Supplementary information is described in the column of supplementary information 304. In this embodiment, the supplementary information 304 describes a second function and a third function that cannot be realized by the standard function (first function) of platform K.

[0064] Next, the control device 212 of the server 210 causes the machine learning model 250 to generate functional requirement document data D5 based on the system proposal data D3 (step S3). Figure 13 is a diagram of the functional requirement document indicated by the functional requirement document data D5. As shown in Figure 13, the functional requirement document corresponds to the use case table 300 of the system proposal data D3.

[0065] Next, the control device 212 of the server 210 causes the machine learning model 250 to generate non-functional requirements data D6 based on the system proposal data D3 (step S4). FIG. 14 is a diagram of the non-functional requirements indicated by the non-functional requirements data D6. As shown in FIG. 14, the non-functional requirements describes information other than the functions required for system A. The non-functional requirements describes the number of users expected for system A, the number of data items, etc. The non-functional requirements corresponds to other 302 in the system proposal data D3.

[0066] Next, the control device 212 of the server 210 causes the machine learning model 250 to generate business process flow diagram data D7 based on the system proposal data D3 (step S5). FIG. 15 is a business process flow diagram indicated by the business process flow diagram data D7. As shown in FIG. 15, the business process flow diagram illustrates the business process flow of the system proposal data D3. In this manner, the control device 212 (overall explanation data generation means 222) of the server 210 generates overall explanation data that explains the system configuration of system A (generated system) realized by at least one of the first function, the second function, and the third function, based on the system proposal data D3. In this embodiment, the overall explanation data is the business process flow diagram data D7. The business process flow diagram corresponds to the business process flow 301 of the system proposal data D3.

[0067] Next, the control device 212 (third explanation data generation means 228) of the server 210 causes the machine learning model 250 to generate application design specification data D8 (third explanation data) that explains one or more functions required for system A (generated system) that can be realized by the third function, based on the system proposal data D3 (step S6). In step S6, the control device 112 of the server 110 generates a context based on the system proposal data D3. The control device 212 of the server 210 generates application design specification data D8 based on the system proposal data D3 and the context. The application design specification data D8 (third explanation data) includes a description of the generated application that realizes the third function. FIG. 16 is a diagram of the application design specification indicated by the application design specification data D8. As shown in FIG. 16, the application design specification describes the functions required for the system to realize the third function. The application design specification corresponds to the use case table 300 and supplemental information 304 of the system proposal data D3. The application design document also includes information about a first function that can be realized by a standard function of platform K and a second function that can be realized by a plug-in available for platform K.

[0068] Next, the control device 212 (second explanation data generation means 226) of the server 210 causes the machine learning model 250 to generate plugin proposal data D9 (second explanation data) that describes a plugin of a second function that can realize one or more functions required for system A (generation system) based on the system proposal data D3 (more precisely, the functional requirements data D5) (step S7). In step S7, the control device 112 of the server 110 generates a context based on the system proposal data D3 (functional requirements data D5). The control device 212 of the server 210 generates plugin proposal data D9 based on the system proposal data D3 (functional requirements data D5) and the context. FIG. 17 is a diagram of a plugin proposal indicated by the plugin proposal data D9. As shown in FIG. 17, the plugin proposal describes a list of plugins having the second function described as being realizable by the plugin in the functional requirements document shown in FIG. 13. The plugin proposal corresponds to the use case table 300 and supplemental information 304 of the system proposal data D3.

[0069] Next, the control device 212 of the server 210 causes the machine learning model 250 to generate management item data D10 based on the application design specification data D8 and the plug-in proposal data D9 (step S8). In step S8, the control device 112 of the server 110 generates a context based on the application design specification data D8 and the plug-in proposal data D9. The control device 212 of the server 210 generates management item data D10 based on the application design specification data D8, the plug-in proposal data D9, and the context. FIG. 18 is a diagram of the management item indicated by the management item data D10. As shown in FIG. 18, the management item lists details of information managed in a standard function for realizing a first function, a plug-in for realizing a second function, and a system for realizing a third function.

[0070] Next, the control device 212 of the server 210 causes the machine learning model 250 to generate ER (Entry Relationship) diagram data D11 based on the management item document data D10 (step S9). FIG. 19 is an ER diagram indicated by the ER diagram data D11. As shown in FIG. 19, the ER diagram describes the structure of data exchanged in system A. In this embodiment, the ER diagram describes the structure of data exchanged in the transmission and reception of questionnaires and responses.

[0071] Next, the control device 212 of the server 210 causes the machine learning model 250 to generate system configuration diagram data D12 based on the application design document data D8 (step S10). FIG. 20 is a system configuration diagram indicated by the system configuration diagram data D12. As shown in FIG. 20, the system configuration diagram visually represents the components and their interrelationships in a system in which system A is used. Specifically, the components are an administrator (user), system A, a facility, and a parent facility. The system configuration diagram also describes the exchange of data between the administrator (user) and system A. In this manner, the control device 212 (overall explanation data generation means 222) of the server 210 generates overall explanation data that explains the system configuration of system A (generated system) realized by at least one of the first function, the second function, and the third function, based on the system proposal data D3. In this embodiment, the overall explanation data is the system configuration diagram data D12.

[0072] Next, the control device 212 of the server 210 transmits the system proposal data D3, the functional requirements data D5, the non-functional requirements data D6, the business flow diagram data D7, the application design data D8, the plug-in proposal data D9, the management item data D10, the ER diagram data D11, and the system configuration diagram data D12 to the server 110 via the network interface 216 (step S11). In response, the network interface 116 of the server 110 receives the system proposal data D3, the functional requirements document data D5, the non-functional requirements document data D6, the business flow diagram data D7, the application design document data D8, the plug-in proposal data D9, the management item data D10, the ER diagram data D11, and the system configuration diagram data D12, and outputs the system proposal data D3, the functional requirements document data D5, the non-functional requirements document data D6, the business flow diagram data D7, the application design document data D8, the plug-in proposal data D9, the management item data D10, the ER diagram data D11, and the system configuration diagram data D12 to the control device 112. As a result, the control device 112 of the server 110 acquires the system proposal data D3, the functional requirements document data D5, the non-functional requirements document data D6, the business flow diagram data D7, the application design document data D8, the plug-in proposal data D9, the management item data D10, the ER diagram data D11, and the system configuration diagram data D12 (step S104).

[0073] Next, the control device 112 of the server 110 transmits the system proposal data D3, the functional requirements document data D5, the non-functional requirements document data D6, the business flow diagram data D7, the application design document data D8, the plug-in proposal data D9, the management item document data D10, the ER diagram data D11, and the system configuration diagram data D12 to the user terminal 10 via the network interface 116 (step S105). In response, the user terminal 10 receives the system proposal data D3, the functional requirements document data D5, the non-functional requirements document data D6, the business flow diagram data D7, the application design document data D8, the plug-in proposal data D9, the management item document data D10, the ER diagram data D11, and the system configuration diagram data D12. This allows the user to operate the user terminal 10 to view system proposal data D3, functional requirements data D5, non-functional requirements data D6, business flow diagram data D7, application design data D8, plug-in proposal data D9, management item data D10, ER diagram data D11, and system configuration diagram data D12.

[0074] [effect] System 1 can assist in the creation of system A. More specifically, system 1 aims to generate system proposal data D3. The system proposal data D3 indicates whether one or more functions required for system A can be realized by one or more first functions, one or more second functions, or one or more first functions and one or more third functions other than the second functions. The storage device 114 of the server 110 stores a standard function table T1 related to one or more first functions provided by platform K and a plugin table T2 related to one or more second functions provided by each of one or more plugins available on platform K. This allows the control device 112 of the server 110 to determine whether the function required for system A in the minutes data D2 corresponds to the first function, the second function, or the third function. The control device 112 of the server 110 generates a context D4 related to the minutes data D2 from the standard function table T1 and the plugin table T2. The context D4 includes information for determining whether the function required of system A in the minutes data D2 corresponds to the first function, the second function, or the third function. This allows the control device 212 of the server 210 to generate system proposal data D3 for system A in the machine learning model 250 based on the minutes data D2 and the context D4. As described above, the user can create system A using the system proposal data D3, and the system 1 can therefore assist in the creation of system A.

[0075] In the system 1, the control device 12 of the user terminal 10 generates minutes data D2 in which the audio is converted into text based on video data D1 showing the audio of a conference. This allows the user to easily obtain the minutes data D2 including the text.

[0076] In the system 1, the control device 12 of the user terminal 10 generates minutes data D2 by sequentially converting speech into text in response to acquisition of video data D1 during a conference, thereby enabling the user to obtain the minutes data D2 at the end of the conference.

[0077] System 1 can assist in the creation of system A. More specifically, the control device 212 of server 210 generates, based on system proposal data D3, workflow diagram data D7 and system configuration diagram data D12 that explain the system configuration of system A realized by at least one of the first function, the second function, and the third function. As a result, system 1 allows the user to obtain workflow diagram data D7 and system configuration diagram data D12 in addition to the system proposal data D3. Therefore, the user can design and develop system A based on the system proposal data D3, workflow diagram data D7, and system configuration diagram data D12. Therefore, system 1 can assist in the creation of system A.

[0078] System 1 can assist in the creation of system A. More specifically, the control device 212 of the server 210 causes the machine learning model 250 to generate plug-in proposal data D9 that describes a second function plug-in that can realize one or more functions required for system A, based on the system proposal data D3. This allows the user in system 1 to obtain the plug-in proposal data D9 in addition to the system proposal data D3. Therefore, the user can design and develop system A based on the system proposal data D3 and the plug-in proposal data D9. Therefore, system 1 can assist in the creation of system A.

[0079] System 1 can assist in the creation of system A. More specifically, the control device 212 of the server 210 causes the machine learning model 250 to generate application design document data D8 that describes one or more functions required for system A that can be realized by the third function, based on the system proposal data D3. This allows the user in system 1 to obtain the application design document data D8 in addition to the system proposal data D3. Therefore, the user can design and develop system A based on the system proposal data D3 and the application design document data D8. Therefore, system 1 can assist in the creation of system A.

[0080] In the system 1, the machine learning model 250 is a trained model that has undergone machine learning using training data related to data output by the machine learning model 250. As a result, the machine learning model 250 trains every time the system 1 generates system proposal data D3. As a result, the system 1 can generate system proposal data D3 that meets the user's requirements.

[0081] (Other embodiments) The system according to the present invention is not limited to System 1, and can be modified within the scope of the gist thereof.

[0082] The control device 12 of the user terminal 10 may generate emotion information related to the emotion of the speaker in the conference based on the video data D1 (audio data). The control device 12 of the user terminal 10 generates the emotion information based on the content of the speaker's speech and the speaker's facial expression. Then, the control device 12 of the user terminal 10 generates minutes data D2 (input data) in which the speech is converted into text based on the video data D1 (audio data) and the emotion information. This allows the emotion of the speaker in the conference to be reflected in the minutes data D2. As a result, the user can obtain minutes data D2 that includes more information.

[0083] The system 1 may include one or more computers. Therefore, the server 110 and the server 210 may be implemented by a single computer. Furthermore, the user terminal 10, the server 110, and the server 210 may be implemented by a single computer.

[0084] The minutes data D2 may be created by the user operating the user terminal 10. In this case, the audio data is not required.

[0085] The control device 12 of the user terminal 10 may convert speech into text all at once after the conference, instead of converting speech into text successively during the conference.

[0086] The context D4 includes the search results for information related to the minutes data D2. However, the context D4 may include information corresponding to the minutes data D2 in addition to the search results for information related to the minutes data D2. In this case, the context D4 includes the third information and the minutes data D2.

[0087] It should be noted that audio data may be used instead of the video data D1.

[0088] The training data may be part or all of the minutes data D2, system proposal data D3, functional requirements data D5, non-functional requirements data D6, business flow diagram data D7, application design data D8, plug-in proposal data D9, management item data D10, ER diagram data D11, and system configuration diagram data D12. However, the training data may be part or all of the minutes data D2, system proposal data D3, functional requirements data D5, non-functional requirements data D6, business flow diagram data D7, application design data D8, plug-in proposal data D9, management item data D10, ER diagram data D11, and system configuration diagram data D12. The training data may also be context D4. [Explanation of symbols]

[0089] 1: System 10: User terminal 12: Control device 14:Storage device 16: Network interface 18: Graphics processing unit 20: Display 26:Operation unit 28: Touch panel 30: Text conversion method 110: Server 112: Control device 114: Storage device 116: Network interface 120: Input data acquisition means 122:Third information generation means 124: System proposal data generation instruction means 210: Server 212: Control device 214: Storage device 216: Network interface 220: System proposal data generation means 222: Overall explanation data generation means 226: Second explanation data generating means 228: Third explanation data generation means 250: Machine learning models 300: Use Case Table A: System D1: Video data D2: Minutes data D3: System proposal data D4: Context D5: Functional requirements data D6: Non-functional requirements data D7: Business flow diagram data D8: Application design data D9: Plug-in proposal data D10: Control item data D11: ER diagram data D12: System configuration diagram data K: Platform T1: Standard function table T2: Plug-in table

Claims

1. A system for generating system proposal data used in a software platform that supports the creation of a generation system, The system comprises one or more computers; a storage device of the one or more computers storing first information about one or more first functions provided by the software platform and second information about one or more second functions provided by each of one or more plug-ins available for the software platform; the software platform is capable of adding the first functionality to the production system; the plug-in is capable of adding the second functionality to the production system; the system proposal data indicates whether one or more functions required for the generation system can be realized by the one or more first functions, the one or more second functions, or the one or more first functions and a third function other than the one or more second functions, and indicates a specification of the generation system; the one or more computers are equipped with a machine learning model; the one or more computer controllers acquiring input data that is minutes of a meeting for the generation system and includes text; generating third information based on the first information and the second information, the third information including information for determining whether a function required of the generation system in the input data corresponds to the one or more first functions, the one or more second functions, or the third function; causing the machine learning model to generate system proposal data for the generation system based on the input data and the third information; system.

2. the one or more computer controllers generating the input data in which the speech is converted into text based on speech data representing speech in a conference; In the process of acquiring the input data, the input data obtained by converting the voice into text is acquired. The system of claim 1 .

3. the one or more computer controllers generating the input data by sequentially converting the speech into text in response to acquisition of the speech data during the conference; The system of claim 2 .

4. the one or more computer controllers generating emotion information relating to emotions of speakers in the conference based on the voice data; generating the input data in which the speech is converted into text based on the speech data and the emotion information; The system according to claim 2 or claim 3.

5. the one or more computer controllers generating overall explanation data that explains a system configuration of the generation system realized by at least one of the first function, the second function, and the third function based on the system proposal data; A system according to any one of claims 1 to 3.

6. the one or more computer controllers causing the machine learning model to generate second explanation data that explains the plug-in of the second function that can realize one or more functions required for the generation system based on the system proposal data; A system according to any one of claims 1 to 3.

7. the one or more computer controllers causing the machine learning model to generate third explanation data that explains one or more functions required for the generation system that can be realized by the third function, based on the system proposal data; A system according to any one of claims 1 to 3.

8. the third description data includes a description of a production application that implements the third function. The system of claim 7.

9. The machine learning model is a trained model that has undergone machine learning using data related to the data output by the machine learning model as training data. A system according to any one of claims 1 to 3.

10. A first computer used in a system for generating system proposal data used in a software platform for supporting the creation of a generation system, the system includes the first computer and a second computer; a storage device of the first computer stores first information on one or more first functions provided by the software platform and second information on one or more second functions provided by each of one or more plug-ins available for the software platform; the software platform is capable of adding the first functionality to the production system; the plug-in is capable of adding the second functionality to the production system; the system proposal data indicates whether one or more functions required for the generation system can be realized by the one or more first functions, the one or more second functions, or the one or more first functions and a third function other than the one or more second functions, and indicates a specification of the generation system; the second computer includes a machine learning model; The control device of the first computer acquiring input data that is minutes of a meeting for the generation system and includes text; generating third information based on the first information and the second information, the third information including information for determining whether a function required of the generation system in the input data corresponds to the one or more first functions, the one or more second functions, or the third function; instructing the second computer to generate system proposal data of the generation system in the machine learning model based on the input data and the third information; First computer.

11. a second computer used in a system for generating system proposal data used in a software platform for supporting the creation of a generation system, The system includes a first computer and the second computer, a storage device of the first computer stores first information on one or more first functions provided by the software platform and second information on one or more second functions provided by each of one or more plug-ins available for the software platform; the software platform is capable of adding the first functionality to the production system; the plug-in is capable of adding the second functionality to the production system; the system proposal data indicates whether one or more functions required for the generation system can be realized by the one or more first functions, the one or more second functions, or the one or more first functions and a third function other than the one or more second functions, and indicates a specification of the generation system; the second computer includes a machine learning model; The control device of the first computer acquiring input data that is minutes of a meeting for the generation system and includes text; generating third information based on the first information and the second information, the third information including information for determining whether a function required of the generation system in the input data corresponds to the one or more first functions, the one or more second functions, or the third function; The control device of the second computer causing the machine learning model to generate system proposal data for the generation system based on the input data and the third information; Second computer.

12. A data production method for generating system proposal data used in a software platform that supports the creation of a production system, comprising: The system comprises one or more computers, a storage device of the one or more computers storing first information about one or more first functions provided by the software platform and second information about one or more second functions provided by each of one or more plug-ins available for the software platform; the software platform is capable of adding the first functionality to the production system; the plug-in is capable of adding the second functionality to the production system; the system proposal data indicates whether one or more functions required for the generation system can be realized by the one or more first functions, the one or more second functions, or the one or more first functions and a third function other than the one or more second functions, and indicates a specification of the generation system; the one or more computers are equipped with a machine learning model; the one or more computer controllers; acquiring input data that is minutes of a meeting for the generation system and that includes text; generating third information based on the first information and the second information, the third information including information for determining whether a function required of the generation system in the input data corresponds to the one or more first functions, the one or more second functions, or the third function; causing the machine learning model to generate system proposal data for the generation system based on the input data and the third information; Data production method.

Images