Configuration task support system, configuration task support method, and program

Abstract

To support the configuration tasks of databases created using no-code or low-code.SOLUTION: A configuration operation identification unit (202) of a configuration task support system (1) identifies a configuration operation performed by a user in order to set up a database created using no-code or low-code. A machine learning model storage unit (200) stores a machine learning model which has been trained using training data generated on the basis of the configuration for training. A configuration task support unit (203) supports a database configuration task by a user on the basis of configuration operations and the machine learning model.SELECTED DRAWING: Figure 5

Description

Technical Field

[0001] The present disclosure relates to a setting work support system, a setting work support method, and a program.

Background Art

[0002] Conventionally, databases created with no-code or low-code are known. For example, Non-Patent Document 1 describes a help page of an app that is an example of a database created with no-code or low-code. In the app of Non-Patent Document 1, a user can freely specify settings such as fields. The user can also change the settings of a prepared sample app according to their preferences.

Prior Art Documents

Non-Patent Documents

[0003]

Non-Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the app of Non-Patent Document 1, there are cases where a user does not know what settings should be specified. For example, a user may be confused about specifying the field type, which is the type of field in the app. This is not limited to the app of Non-Patent Document 1, and the same applies to other databases created with no-code or low-code. While databases created with no-code or low-code can be easily used by users, there are cases where users do not know what settings should be specified. Therefore, there is a need to support users who perform setting work for databases created with no-code or low-code.

[0005] One of the objectives of the present disclosure is to assist in setting up databases created with no-code or low-code.

Means for Solving the Problems

[0006] A setting work support system according to an aspect of the present disclosure includes a setting operation specifying unit that specifies a setting operation performed by a user for setting up a database created with no-code or low-code, a machine learning model storage unit that stores a machine learning model in which training data created based on the training settings has been learned, and a setting work support unit that supports the user's database setting work based on the setting operation and the machine learning model.

Advantages of the Invention

[0007] According to the present disclosure, it is possible to assist in setting up databases created with no-code or low-code.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Embodiments for Carrying Out the Invention

[0009] [1. Hardware Configuration] An example of an embodiment of a setting work support system, a setting work support method, and a program according to the present disclosure will be described. FIG. 1 is a diagram showing an example of the hardware configuration of the setting work support system. For example, the setting work support system 1 includes a learning terminal 10, a server 20, and a user terminal 30. Each of the learning terminal 10, the server 20, and the user terminal 30 is connected to a network N such as the Internet or a LAN.

[0010] The learning terminal 10 is a computer that performs learning of a machine learning model described later. For example, the learning terminal 10 is a personal computer, a tablet terminal, or a smartphone. For example, the learning terminal 10 includes a control unit 11, a storage unit 12, a communication unit 13, an operation unit 14, and a display unit 15. The control unit 11 includes at least one processor. The storage unit 12 includes at least one of a volatile memory such as a RAM and a non-volatile memory such as a flash memory. The communication unit 13 includes at least one of a communication interface for wired communication and a communication interface for wireless communication. The operation unit 14 is an input device such as a mouse or a touch panel. The display unit 15 is a liquid crystal or organic EL display.

[0011] The server 20 is a server computer. For example, the server 20 includes a control unit 21, a storage unit 22, and a communication unit 23. The hardware configurations of the control unit 21, the storage unit 22, and the communication unit 23 may be the same as those of the control unit 11, the storage unit 12, and the communication unit 13, respectively.

[0012] The user terminal 30 is the user's computer. For example, the user terminal 30 is a personal computer, a tablet terminal, or a smartphone. For example, the user terminal 30 includes a control unit 31, a storage unit 32, a communication unit 33, an operation unit 34, and a display unit 35. The hardware configurations of the control unit 31, the storage unit 32, the communication unit 33, the operation unit 34, and the display unit 35 may be the same as those of the control unit 11, the storage unit 12, the communication unit 13, the operation unit 14, and the display unit 15, respectively.

[0013] Note that the programs stored in the storage units 12, 22, and 32 may be supplied via the network N. The hardware configurations of each of the learning terminal 10, the server 20, and the user terminal 30 are not limited to the example in FIG. 1. For example, at least one of the learning terminal 10, the server 20, and the user terminal 30 may include at least one of a reading unit (e.g., a memory card slot) for reading a computer-readable information storage medium and an input / output unit (e.g., a USB terminal) for directly connecting to an external device. The program stored in the information storage medium may be supplied to at least one of the learning terminal 10, the server 20, and the user terminal 30 via at least one of the reading unit and the input / output unit.

[0014] Also, the setting work support system 1 may include at least one computer. The computer included in the setting work support system 1 is not limited to the example in FIG. 1. For example, the setting work support system 1 may include only the learning terminal 10 and the server 20. In this case, the user terminal 30 exists outside the setting work support system 1. The setting work support system 1 may include only the server 20. In this case, the learning terminal 10 and the user terminal 30 exist outside the setting work support system 1. The setting work support system 1 may include the server 20 and another server computer.

[0015] [2. Outline of the Setting Work Support System] In this embodiment, the user performs database setting operations created with no-code or low-code. A database created with no-code is a database in the database development infrastructure where the user does not need to input codes such as database languages or programming languages. For example, when the user specifies database settings, the setting operation support system 1 creates a database based on the specified settings. All the codes required for creating the database are prepared by the setting operation support system 1 side.

[0016] A database created with low-code is a database in the database development infrastructure where the user only needs to input the minimum necessary codes. For example, when the user inputs the minimum necessary codes and specifies database settings, the setting operation support system 1 creates a database based on the minimum necessary codes and the specified settings. The remaining codes required for creating the database are prepared by the setting operation support system 1 side.

[0017] Note that those skilled in the art involved in database development can understand the meanings of no-code and low-code based on the common general knowledge in the art at the time of filing. Each of no-code and low-code may be a known meaning understandable by those skilled in the art based on the common general knowledge in the art at the time of filing. In the following description, the places described as databases mean databases created with no-code or low-code. Creating a database can also be referred to as developing or constructing a database.

[0018] In this embodiment, an example is given where the groupware application corresponds to a database. Groupware is a program that supports the user's work. Groupware can be either cloud-based or on-premises. The application has not only functions as a database but also other functions related to work support. For example, the application has at least one of communication functions, file management functions, email management functions, and other functions. The functions of the application may be known functions.

[0019] In the following description, wherever the term "application" is used, it can be read as "database". In this embodiment, an example where the application is created without code is given, but the application may also be created with code. For example, when a user logs in to groupware, the user can use the applications of the organization such as the company to which the user belongs. When the user selects an arbitrary application, the user terminal 30 causes the display unit 35 to display an application screen indicating the application.

[0020] FIG. 2 is a diagram showing an example of an application screen. In this embodiment, as an example of the application, an application for managing access to a website will be described. For example, as shown in the upper part of FIG. 2, the application screen SC1 includes a record list L10 showing a list of records that are units of each piece of data in the application. The record list L10 shows the values of fields that are each item constituting the record. A field may also be called by another name such as a cell. The first row of the record list L10 indicates the field name which is the name of the field.

[0021] For example, when the user selects an arbitrary record from the record list L10, as shown in the lower part of FIG. 2, the user terminal 30 causes the display unit 35 to display an application screen SC1 showing the details of the record. The user can input a value corresponding to the field type which is the type of the field of the record from the application screen SC1 in the lower part of FIG. 2. The field type can also be referred to as the data type of the field. The field type may be a type used in known applications. For example, the field type may be a numerical value, calculation, string (one line), string (multiple lines), date and time, link, or lookup.

[0022] For example, the field types of the fields of the field names "number of sessions" and "number of page views" are numerical values. The user can input any numerical value into these fields. The field type of the field with the field name "number of page views per session" is a calculation. In this field, a calculation formula is set indicating that the numerical value entered in the field with the field name "number of page views" is divided by the numerical value entered in the field with the field name "number of sessions". Other fields also have some defined field types.

[0023] In this embodiment, the setting work support system 1 supports the setting work of the user who creates the application shown in FIG. 2. In the following description, it is assumed that the application shown in FIG. 2 has not been created yet. That is, it is assumed that the user will newly create the application shown in FIG. 2. For example, when the user logs in to the groupware and performs an operation for creating an application, the user terminal 30 causes the display unit 35 to display a setting screen for the user to specify the application settings.

[0024] FIGS. 3 and 4 are diagrams showing an example of the setting screen. For example, the setting screen SC2 includes a display area A20 showing a list of forms that the user can arrange on the application screen SC1. The user can specify a field of the field type indicated by the image by moving the image displayed in the display area A20 to the display area A21 with the cursor C. The user can specify other settings (for example, field name, form layout, form width, graph, or access right setting) other than the field type from the setting screen SC2.

[0025] Hereinafter, the setting of a field is referred to as field setting. When there is no need to distinguish between field setting and other settings other than field setting, it is simply referred to as setting. For example, as shown in the upper part of FIG. 3, when the user moves an image indicating the field type "numerical value" from the display area A20 to the display area A21, as shown in the lower part of FIG. 3, the form of the field of the field type "numerical value" is arranged in the display area A21. The layout of the form in the display area A21 becomes the layout of the form on the lower side of the application screen SC1 in FIG. 2. The user sequentially moves images from the display area A20 to the display area A21 so as to achieve the desired settings.

[0026] In the present embodiment, the setting work support system 1 supports the setting work of the application by the user based on a machine learning model in which the settings of the training application are learned. Details of the learning method of the machine learning model will be described later. Here, it is assumed that the machine learning model has learned the field settings of the training application. For example, the machine learning model predicts the field type in which the user will next place the form based on the field type of the form placed by the user in the display area A21.

[0027] For example, as shown in the upper part of FIG. 4, assume that the user has moved an image indicating the field type "numerical value" from the display area A20 to the display area A21. When there are two fields of the field type "numerical value", the machine learning model predicts the field type (recommended field type) in which the user will next place the form. If the machine learning model predicts that the user will next place a form of the field type "calculation", as shown in the lower part of FIG. 4, the user terminal 30 uses the placeholder function to display the form of the field type "calculation" in the display area A21. The user terminal 30 may also display a message for proposing the form in the display area A21.

[0028] For example, when the user selects the form of the field type "Calculation" displayed in the display area A21, the user terminal 30 arranges the form in the display area A21. If the user does not select the form of the field type "Calculation" displayed in the display area A21, the user terminal 30 deletes the form from the display area A21. When a message proposing the form is displayed in the display area A21, the user terminal 30 deletes the message.

[0029] For example, every time the user specifies or deletes some settings of the application, the machine learning model predicts the settings that the user will specify next based on the learned training settings of the application that it has learned. The user terminal 30 displays the prediction result of the machine learning model on the setting screen SC2 until the user completes the settings of the application being created. The setting work support system 1 of the present embodiment can support the user's application setting work based on such a machine learning model. Hereinafter, the details of the setting work support system 1 will be described.

[0030] [3. Functions realized by the setting work support system] FIG. 5 is a diagram showing an example of the functions realized by the setting work support system 1.

[0031] [3-1. Functions realized by the learning terminal] For example, the learning terminal 10 includes a machine learning model storage unit 100, a database storage unit 101, and a learning unit 102. The machine learning model storage unit 100 and the database storage unit 101 are realized by the storage unit 12. The learning unit 102 is realized by the control unit 11.

[0032] [Machine learning model storage unit] The machine learning model storage unit 100 stores the machine learning model M. The machine learning model M is a model created based on machine learning techniques. The machine learning model M can be any type of model. For example, the machine learning model M can be a model of supervised learning, semi-supervised learning, or unsupervised learning.

[0033] In this embodiment, an example is given where the machine learning model M is a model created by the method of LDA (Latent Dirichlet Allocation). LDA is a type of topic model mainly used for clustering purposes. A topic model is a model for identifying the topics of a text. The topic model performs clustering so that texts of the same topic belong to the same cluster. The cluster itself is sometimes referred to as a topic. The topic model may be a model using known methods. The machine learning model M may be another topic model other than LDA. For example, it may be LSA (Latent Semantic Analysis), NMF (Non-Negative Matrix Factorization), or HDP (Hierarchical Dirichlet Process).

[0034] Note that the machine learning model M is not limited to a topic model. For example, the machine learning model M may be of various known method types. In this embodiment, since the machine learning model M is used for clustering, the machine learning model M may be created by other methods used in clustering. For example, the machine learning model M may be a model created by k-Means clustering, hierarchical clustering, DBSCAN (Density-Based Spatial Clustering of Applications with Noise), or other methods. For example, the machine learning model M may be a neural network. The machine learning model M may perform other processes other than clustering. An example of other processes will be described in the modified example below.

[0035] For example, the machine learning model M includes parameters adjusted by learning and a program for calculating an embedded representation and the like. The parameters of the machine learning model M are referred to by the program of the machine learning model M. For example, the parameters are weight coefficients and biases. The program of the machine learning model M includes code indicating the internal processing of the machine learning model M. For example, the program of the machine learning model M includes an intermediate layer that calculates an embedded representation and generates data for the output layer, and an output layer that performs a final output based on the data. The program and parameters of the machine learning model M may be various known programs and parameters. The machine learning model storage unit 100 may also store other data such as a learning program indicating a series of processes during learning. Assume that the calculation formula of the loss function calculated during learning is also shown in the learning program.

[0036] [Database storage unit] The database storage unit 101 stores data necessary for the learning of the machine learning model M. For example, the database storage unit 101 also stores a training database DB1 necessary for learning and a topic database DB2 obtained as a result of learning.

[0037] FIG. 6 is a diagram showing an example of the training database DB1. The training database DB1 is a database in which training data necessary for the learning of the machine learning model M is stored. In the present embodiment, since LDA, which is a type of unsupervised learning, corresponds to the machine learning model M, the training data is assumed to be unannotated. When a machine learning model M of supervised learning or semi-supervised learning is used, the training data is annotated. The training data may be prepared manually or by using a known tool.

[0038] For example, the training data is created based on the settings of the training app. The training app is the app used in generating the training data. For example, the training app may be a virtual app prepared by the creator who creates the machine learning model M (for example, a person in charge of a company that provides groupware to users), or may be an app actually used in groupware. The training data can indicate any setting of the training app. In the present embodiment, the training data is assumed to indicate the field settings of the training app.

[0039] For example, the training data indicates each of a plurality of field types and the number of fields of the corresponding field type in the training app. That is, the training data indicates, for each field type, the number of fields of the corresponding field type in the training app. For example, assuming that the number of field types is n (n is a natural number), the training data is represented as an n-dimensional vector. Each element of each dimension of the vector is the number of fields of the field type corresponding to that dimension.

[0040] In the example of FIG. 6, for the first training app, the number of fields of each of the field types "numerical value", "calculation", "one-line string", "multiple-line string", and "date" is 3, 1, 0, 2, and 0, respectively. The training data also indicates the number of other field types. Similarly, for the second and subsequent training apps, the training data indicates the number of fields of each field type.

[0041] Note that the training data may be in any format. The format of the training data is not limited to a vector. For example, the training data may be represented as an array, a matrix, a combination of multiple numerical values, a single numerical value, a character, or other symbols. In the example of FIG. 6, the number of each field type in the training app may be indicated in the training data in another format such as an array.

[0042] When the training data is annotated, the training data includes an input part that is input to the machine learning model M during learning and an output part that becomes the correct answer during learning. The combination of the input part and the output part may be any combination according to the setting work supported by the machine learning model M. For example, the input part of the training data indicates the field settings of the training application. The output part of the training data indicates the cluster to which the training application belongs. A cluster can also be called a label.

[0043] FIG. 7 is a diagram showing an example of the topic database DB2. The topic database DB2 is a database in which topic data indicating individual topics obtained when the learning of the machine learning model M is completed is stored. For example, the topic database DB2 stores a topic ID that is an ID for identifying an individual topic and topic data. The number of topics may be specified by the creator of the machine learning model M or may be determined by a program for learning the machine learning model M.

[0044] In the example of FIG. 7, the topic data of each individual topic shows the utilization rate of each field type in the training application belonging to the topic. The utilization rate of a certain field type is a value obtained by dividing the number of training applications in which the field of the field type is used by the total number of training applications belonging to the topic. For example, when the utilization rate of a certain field type is 90%, it indicates that the field of the field type is used in 90% of the training applications in the topic.

[0045] Note that the data stored in the database storage unit 101 is not limited to the examples of the present embodiment. The database storage unit 101 may store data necessary for learning the machine learning model M. For example, the database storage unit 101 may store a database in which various data of the training application is stored. It is assumed that data indicating various settings of the training application is stored in the database. The training data may be created based on the database.

[0046] [Learning Department] The learning department 102 executes learning of the machine learning model M based on each of a plurality of pieces of training data stored in the training database DB1. In the present embodiment, an example is given in which the learning department 102 executes learning of the machine learning model M based on an algorithm of unsupervised learning. The learning algorithm may be a known algorithm described above. The learning department 102 may execute learning of the machine learning model M based on an algorithm of supervised learning, semi-supervised learning, or unsupervised learning.

[0047] For example, the learning department 102 learns the machine learning model M by adjusting parameters so that training data having similar characteristics belong to the same cluster based on an algorithm of unsupervised learning. In the present embodiment, the learning department 102 executes learning of the machine learning model M based on a known LDA algorithm. When another topic model other than LDA is used, the learning department 102 executes learning of the machine learning model M based on an algorithm of another known topic model. When another machine learning method other than the topic model is used, the learning department 102 executes learning of the machine learning model M based on an algorithm of another machine learning method.

[0048] In the present embodiment, the learning department 102 executes a series of learning processes by executing a learning program stored in the database storage unit 101. The learning department 102 records the learned machine learning model M in the database storage unit 101. The database storage unit 101 may store both the machine learning model M before learning and the learned machine learning model M. The learning department 102 transmits the learned machine learning model M to the server 20. The learned machine learning model M transmitted to the server 20 is provided for user use.

[0049] For example, the learning unit 102 generates a topic database DB2 based on the processing results of the learned machine learning model M and records it in the database storage unit 101. The learning unit 102 generates the topic database DB2 by calculating the utilization rate of each field type based on the field settings of the training apps belonging to the topic for each topic. The learning unit 102 transmits the topic database DB2 to the server 20. The topic database DB2 transmitted to the server 20 is provided for user use.

[0050] When a supervised learning or semi-supervised learning model is used, the learning unit 102 adjusts the parameters of the machine learning model M based on the algorithms of these models so that when the input part of the training data is input to the machine learning model M, the output part of the training data is output from the machine learning model M, and thus the learning of the machine learning model M can be executed. For example, the learning unit 102 executes the learning of the machine learning model M based on a known algorithm such as the error backpropagation method or the gradient descent method.

[0051] [Functions Implemented by the Server] For example, the server 20 includes a machine learning model storage unit 200, a database storage unit 201, a setting operation identification unit 202, and a setting work support unit 203. Each of the machine learning model storage unit 200 and the database storage unit 201 is realized by the storage unit 22. Each of the setting operation identification unit 202 and the setting work support unit 203 is realized by the control unit 21.

[0052] [Machine Learning Model Storage Unit] The machine learning model storage unit 200 stores the machine learning model M that has learned the training data created based on the training settings. For example, the machine learning model storage unit 200 stores the machine learning model M whose learning has been completed by the learning terminal 10. The learning of the machine learning model M may also be executed by the server 20. In this case, the server 20 has the same functions as the learning unit.

[0053] [Database Storage Unit] The database storage unit 201 stores data necessary for supporting the setting work. For example, the database storage unit 201 stores the topic database DB2. The machine learning model storage unit 200 stores the topic database DB2 generated by the learning terminal 10. The database storage unit 201 stores, in addition to the topic database DB2, an app database DB3 in which various data of the app are stored.

[0054] FIG. 8 is a diagram showing an example of the app database DB3. For example, the app database DB3 stores an app ID which is an ID for identifying each app, and app setting data indicating specific setting contents of the app. Arbitrary data may be stored in the app database DB3, and the data stored in the app database DB3 is not limited to the example of FIG. 8. For example, record data indicating details of each record may be stored in the app database DB3.

[0055] In the present embodiment, the app setting data indicates field settings. For example, the field setting is the field type of the field in the app. The field setting may be any setting of the field. The field setting is not limited to the field type. For example, the field setting may be a field name (column name), an order of fields (order of columns), a layout of a form for a user to input a value of the field, a calculation formula set for the field, or other settings.

[0056] Note that the app setting data is not limited to the field settings. The app setting data may indicate any setting of the app. For example, the app setting data may be an app name, a memo for the app administrator, a display format of the record list L10, a setting of a graph displayed in the app, an icon of the app, a design of the entire app, an access right, or other settings. When the user creates an app, the server 20 associates the app ID of the app with the app setting data indicating the settings of the app and stores them in the app database DB3.

[0057] Note that the data stored in the database storage unit 201 is not limited to the above example. The database storage unit 201 can store any data. For example, the database storage unit 201 may store a user database in which various data of the user is stored. The user database stores data such as user IDs and passwords for logging in to groupware. The database storage unit 201 may store data of each screen such as the application screen SC1 or the setting screen SC2. For example, the database storage unit 201 may store a program for enabling the creation of an application by no-code or low-code. The program shows codes that the user does not need to input. The application is created based on the settings specified by the user and the codes of the program. The creation of the application may be performed by the server 20 or by another computer other than the server 20.

[0058] [Setting operation specifying unit] The setting operation specifying unit 202 specifies the setting operation performed by the user for the setting of the application. The setting operation is an operation different from the operation in which the user inputs a character string indicating a code. For example, the setting operation may be an operation of selecting an image (image for setting the application) displayed on the setting screen SC2, an operation of specifying a specific value for the setting of the application, or an operation in which the user inputs a character string other than the code. The setting operation may be any operation related to some setting of the application.

[0059] In this embodiment, an example is given where the setting operation is an operation for the user to specify settings. That is, an operation in which the user specifies the specific settings of the application itself corresponds to the setting operation. Examples of other setting operations will be described in the modified examples below. For example, when the user performs a setting operation on the user terminal 30, the user terminal 30 transmits setting operation data indicating the content of the setting operation to the server 20. The server 20 receives the setting operation data from the user terminal 30. The setting operation specifying unit 202 specifies the setting operation by referring to the setting operation data. In this embodiment, the setting operation specifying unit 202 specifying the setting operation corresponds to specifying the content of the setting specified by the user.

[0060] In this embodiment, the setting operation data indicates the field settings specified by the user through the setting operation. In the examples of FIGS. 3 and 4, an operation in which the user moves an image showing a form of a certain specific field type from the display area A20 to the display area A21 corresponds to the setting operation. The setting operation data indicates the field type (the field type indicated by the image that the user has moved from the display area A20 to the display area A21) specified by the setting operation. The setting operation data also indicates the content of other settings such as the layout of the form.

[0061] Note that the setting operation may be a user operation on the setting screen SC2. The setting operation is not limited to an operation in which the user moves an image indicating the field type from the display area A20 to the display area A21. For example, the setting operation may be an operation in which the user inputs text indicating the field name, an operation in which the user changes the layout of the form of the field, or an operation in which the user swaps the order of the fields. The setting operation may be an operation in which the user specifies the field settings by other methods.

[0062] For example, the setting operation may be an operation in which the user specifies settings other than field settings. For example, the setting operation may be an operation in which the user inputs text indicating the application name, an operation in which the user inputs a memo for the administrator of the application, an operation in which the user specifies the display format of the record list L10, an operation in which the user specifies the settings of the graph displayed in the application, an operation in which the user specifies the application icon, an operation in which the user specifies the overall design of the application, an operation in which the user specifies access rights, or an operation in which the user specifies other settings. Even when these setting operations are performed, the setting operation data may be any data that enables the server 20 to identify what settings the user has specified by the setting operation.

[0063] [Setting Work Support Section] Based on the setting operation identified by the setting operation identification unit 202 and the machine learning model M, the setting work support unit 203 supports the user's work of setting the application. The setting work is the work that the user performs for setting the application. The setting operation is an example of the setting work. The user may perform other operations than the setting operation as the setting work. For example, the other operation may be an operation of deleting the settings specified by the user, an operation of copying the created application, or an operation of deleting the created application.

[0064] For the setting work support unit 203 to support the setting work means that the setting work support unit 203 executes processing for reducing the burden of the setting work by the user. For example, the setting work support unit 203 proposing the specific content of the setting work to the user, the setting work support unit 203 automatically executing all or part of the setting work, and the setting work support unit 203 automatically generating data indicating the settings of the application correspond to the setting work support unit 203 supporting the setting work. In the example of the setting screen SC2 on the lower side of FIG. 4, the setting work support unit 203 executing the display by the placeholder function and the display of a message indicating the next setting work corresponds to the setting work support unit 203 supporting the setting work.

[0065] In this embodiment, since the user designates the app settings themselves through a setting operation, the setting work support unit 203 supports the setting work based on the setting designated by the setting operation and the machine learning model M. For example, when the setting designated by the setting operation is a field setting, the machine learning model M has learned training data created based on the training field settings. The learning process is as described above. In this embodiment, the machine learning model M has learned training data created based on the training app.

[0066] In this embodiment, the setting work support unit 203 supports the setting work by proposing to the user the field setting designated by the next setting operation based on the field setting designated by the setting operation and the machine learning model M. The setting work support unit 203 proposes the field setting by performing a display related to the field setting predicted by the machine learning model M in a manner that can be visually recognized by the user on the setting screen SC2. The information is not limited to an image of a placeholder function such as the lower setting screen SC2 in FIG. 4. For example, the information may be a message such as the lower setting screen SC2 in FIG. 4, or may be an image such as an icon. The setting work support unit 203 may propose the field setting to the user by performing an effect such as blinking of an image within the display area A20.

[0067] For example, the setting work support unit 203 proposes to the user the field setting designated by the next setting operation based on the topic output from the machine learning model M and the topic database DB2. For example, the setting work support unit 203 proposes to the user the field settings that are used in the fields of the topic to which the app being set by the user belongs and that the user has not yet designated.

[0068] For example, when the field setting is a field type, the setting work support unit 203 supports the setting work by proposing to the user the field type specified by the next setting operation based on the field type specified by the setting operation and the machine learning model M. The setting work support unit 203 proposes to the user the field types that have not yet been specified by the user among the field types used in the topic to which the application being set by the user belongs.

[0069] For example, the setting work support unit 203 executes clustering of the application being set by the user based on the setting specified by the setting operation and the machine learning model M. The setting work support unit 203 represents the current setting specified by the user in the same format as the training data. In the example of FIG. 6, the setting work support unit 203 represents the current setting specified by the user in the form of vector data. The setting work support unit 203 executes clustering of the application being set by the user by inputting the data into the machine learning model M. The machine learning model M outputs the topic ID of the topic to which the application being set belongs.

[0070] The setting work support unit 203 identifies the topic to which the application being set by the user belongs based on the execution result of the clustering. The topic is identified by the topic ID output by the machine learning model M. The setting work support unit 203 supports the setting work by predicting the next setting operation (the setting that the user should specify next, that is, the recommended setting) based on the settings of the training applications belonging to the topic. For example, the next setting operation is predicted from the tendencies of applications similar to the application being set (applications belonging to the same topic as the application being set).

[0071] For example, the setting work support unit 203 refers to the topic database DB2 and acquires topic data of the topic to which the application being set by the user belongs. The setting work support unit 203 predicts the next specified field setting based on the topic data and the current field setting of the application being set by the user. The setting work support unit 203 predicts, based on the topic data, the field setting that is lacking in the current field setting of the application being set by the user as the field setting to be specified by the next setting operation.

[0072] For example, when the user has not yet specified a field type with a relatively high utilization rate indicated by the topic data, the setting work support unit 203 proposes the field type to the user. Even if the user has specified a field type with a relatively high utilization rate indicated by the topic data, if the field type is relatively less in the application being set, the setting work support unit 203 proposes the field type to the user. The setting work support unit 203 may calculate an evaluation value using a predetermined calculation formula based on the field type specified for the application being set and the utilization rate of each field type indicated by the topic data, and propose to the user the field type with a relatively high evaluation value.

[0073] In the example of FIG. 4, assume that it is shown that the utilization rate of the field type "numerical value" and the utilization rate of the field type "calculation" in the topic data of the topic to which the application being set by the user belongs are relatively higher than the utilization rates of other field types. In this case, when the user specifies two fields of the field type "numerical value" for the application being set, the setting work support unit 203 identifies, by the processing of the machine learning model M, that the application being set belongs to the above topic. The setting work support unit 203 identifies, based on the above topic data, that the utilization rate of the field type "calculation" that the user has not yet specified is high, and proposes to the user the field of the field type "calculation" as shown in the lower part of FIG. 4.

[0074] Note that the setting work support unit 203 may propose field settings other than the field type to the user. For example, when the tendency of other field settings such as field names is learned by the machine learning model M, the setting work support unit 203 may propose the other field settings to the user. When the tendency of other settings (for example, graph settings) other than the field settings is learned by the machine learning model M, the setting work support unit 203 may propose the other settings to the user.

[0075] In addition, in this embodiment, the case where the processing by the setting work support unit 203 is executed every time the user performs some setting operation is taken as an example. However, the setting work support unit 203 does not necessarily execute the processing every time a setting operation is performed. For example, the setting work support unit 203 may execute the processing every time the user performs a predetermined number of (for example, three) setting operations. The setting work support unit 203 may execute the processing when the user performs an operation for requesting support by the machine learning model M. When the machine learning model M cannot predict the settings to be proposed, the setting work support unit 203 may refrain from making a proposal to the user.

[0076] [3-3. Functions Implemented on the User Terminal] For example, the user terminal 30 includes a data storage unit 300, a display control unit 301, and an operation reception unit 302. The data storage unit 300 is realized by the storage unit 32. Each of the display control unit 301 and the operation reception unit 302 is realized by the control unit 31.

[0077] [Data Storage Unit] The data storage unit 300 stores data necessary for the settings of the application. For example, the data storage unit 300 stores a browser for displaying various screens of the setting work support system 1. For example, the data storage unit 300 stores a program dedicated to groupware.

[0078] [Display Control Unit] The display control unit 301 causes various screens in the setting work support system 1 to be displayed on the display unit 35. For example, based on the data received from the server 20, the display control unit 301 causes a screen such as the app screen SC1 or the setting screen SC2 to be displayed on the display unit 35.

[0079] [Operation reception unit] The operation reception unit 302 receives various operations in the setting work support system 1. For example, it receives operations on the app screen SC1 or the setting screen SC2. The data indicating the operation content received by the operation reception unit 302 is appropriately transmitted to the server 20.

[0080] [4. Processing executed by the setting work support system] FIG. 9 is a diagram showing an example of the processing executed by the setting work support system 1. The control units 21 and 31 execute the programs stored in the storage units 22 and 32 respectively, whereby the processing in FIG. 9 is executed. It is assumed that the learning of the machine learning model M has been completed when the processing in FIG. 9 is executed. The processing in FIG. 9 is an example of the processing of the setting work support method of the present embodiment.

[0081] As shown in FIG. 9, when the user performs an operation to create a new app, the user terminal 30 executes a process for displaying the setting screen SC2 between the user terminal 30 and the server 20 (S1). When the user performs some setting operation on the setting screen SC2, the user terminal 30 transmits setting operation data indicating the user's setting operation to the server 20 (S2). The server 20 receives the setting operation data from the user terminal 30 (S3). The server 20 identifies the user's setting operation based on the setting operation data (S4). The server 20 records data indicating the history of the user's setting operations in the storage unit 22. That is, the server 20 records data indicating what field settings were specified for the app being set in the storage unit 22.

[0082] Server 20 executes clustering of the app being set by the user based on the field settings specified by the user in previous setting operations and the machine learning model M (S5). In S5, Server 20 executes clustering by generating data representing the field settings specified by the user in the same vector format as the training data and inputting it into the machine learning model M. Based on the execution result of the clustering in S5 and the topic database DB2, Server 20 determines whether the field settings (recommended field settings) specified by the next setting operation are predicted (S6). At the stage when the user has just started specifying field settings, the topic to which the app being set belongs may not be identified. In this case, the field settings are not predicted.

[0083] In S6, if it is determined that the field settings specified by the next setting operation are predicted (S6: Y), Server 20 executes a process for proposing the identified field settings to the user terminal 30 (S7). In S7, Server 20 transmits data indicating the field settings to be proposed to the user terminal 30. The user terminal 30 proposes the field settings to the user using a placeholder function or the like based on the data. In S6, if it is not determined that the field settings specified by the next setting operation are predicted (S6: N), the process of S7 is not executed. The user terminal 30 determines whether the user has performed an end operation to end the app settings (S8). The end operation may be any operation performed from the setting screen SC2 (for example, an operation in which the user selects the "Update" button).

[0084] In S8, if it is determined that the user has not performed an end operation (S8: N), the process returns to the process of S2. In this case, the application settings are continued. In S8, if it is determined that the user has performed an end operation (S8: Y), the user terminal 30 executes a process for saving the application settings in the application database DB3 between the user terminal 30 and the server 20 (S9), and this process ends. In S9, the user terminal 30 transmits final setting data indicating the final settings of the application to the server 20. The server 20 generates a new application ID and application setting data corresponding to the final setting data, and stores them in the application database DB3. When the process of S9 is completed, the application created by the user is used in the user's organization. The above process is completed without the user entering a code.

[0085] [5. Summary of Embodiment] The setting work support system 1 of the present embodiment can support the application setting work by the user based on the setting operation performed by the user and the machine learning model M in which the training data is learned. By the support of the setting work support system 1, the work load of the setting work by the user is reduced. For example, a user can obtain general information such as how to use an application in general from the help page of the application, but may not be able to obtain information corresponding to the application currently being set. In this regard, the setting work support system 1 can realize support according to each user by using the machine learning model M. The setting work support system 1 can also give a motivation to start using the application to a user who is considering using the application. For example, a user who has never used an application may not know what settings to specify and may hesitate to use the application. In this regard, with the support of the setting work support system 1, it becomes easier for the user to start using the application. As a result, the setting work support system 1 can promote the use of the application.

[0086] In addition, the setting work support system 1 supports the setting work based on the setting specified by the setting operation and the machine learning model M. Thereby, the setting work support system 1 can achieve more effective support by having the machine learning model M analyze the specific setting specified by the user.

[0087] In addition, the setting work support system 1 supports the setting work by proposing to the user the field setting specified by the next setting operation based on the field setting specified by the setting operation and the machine learning model M. The field setting is a particularly important setting of the application and is a complex setting that novice users are particularly likely to be troubled by. For this reason, users often get lost in the field setting, but the setting work support system 1 can achieve more effective support by having the machine learning model M analyze the field setting specified by the user.

[0088] In addition, the setting work support system 1 supports the setting work by proposing to the user the field type specified by the next setting operation based on the field type specified by the setting operation and the machine learning model M. For example, novice users are often troubled by specifying the field type, but the setting work support system 1 can achieve more effective support by having the machine learning model M analyze the field type currently specified by the user and proposing the next field type to the user.

[0089] In addition, the setting work support system 1 executes clustering of the application being set based on the setting specified by the setting operation and the machine learning model M, and supports the setting work based on the execution result of the clustering. Thereby, the setting work support system 1 can support the setting work based on the tendency of the training application similar to the application being set. For example, the user can continue the setting work of the application while referring to the settings of the training application similar to the application that the user is about to create.

[0090] [6. Variation example] Note that the present disclosure is not limited to the embodiments described above. It can be appropriately modified without departing from the spirit of the present disclosure.

[0091] FIG. 10 is a diagram showing an example of functions realized by the setting work support system 1 of the modification example. As shown in FIG. 10, in the modification example described hereinafter, the server 20 includes a user attribute data acquisition unit 204 and a past setting data acquisition unit 205. Each of the user attribute data acquisition unit 204 and the past setting data acquisition unit 205 is realized by the control unit 21.

[0092] [6-1. Modification Example 1] For example, in the embodiment, the field type was mainly described as an example of field setting, but the field setting may be other settings of the field. In Modification Example 1, a case where the field setting is a field layout that is the layout of the field will be taken as an example. The layout is the position of the field in the application. For example, the order of the fields in the application (the order of the columns), or the position of the form of the field on the lower application screen SC1 in FIG. 2 corresponds to the field layout.

[0093] For example, the user can perform a setting operation for specifying the field layout from the setting screen SC2. In the examples of FIGS. 3 and 4, the order of the fields in the application may be such that the field of the form in the upper left of the display area A21 is No. 1, and the order becomes later as it goes to the right and downward. The position of the form of the field on the application screen SC1 may be the same as the position of the form of the field in the display area A21. The setting operation for specifying the field layout may be any other operation. For example, an operation in which the user inputs a numerical value indicating the order of the fields, an operation in which the user exchanges the order of the fields from a list similar to the record list L10, or other operations may correspond to the setting operation of Modification Example 1.

[0094] The setting work support unit 203 of Modification Example 1 supports the setting work by proposing to the user the field layout specified by the next setting operation based on the field layout specified by the setting operation and the machine learning model M. The training data of Modification Example 1 is created based on the field layout of the training app. For example, the training data indicates the order of fields in the training app (e.g., whether it is in the order of numerical value, numerical value, calculation, etc.) or the form position of the fields (e.g., the form position of the fields of each field type of numerical value, numerical value, calculation).

[0095] For example, the learning unit 102 of Modification Example 1 performs learning of the machine learning model M based on the training data created based on the field layout of the training app. The learning unit 102 performs learning of the machine learning model M so that the training apps with similar field layouts belong to the same topic. The learning unit 102 generates a topic database DB2 in which topic data indicating the tendency of the field layout of the training app belonging to each topic is stored. For example, the topic data stored in the topic database DB2 of Modification Example 1 indicates the tendency of the field layout of the training app belonging to the topic. For example, the topic data of a certain topic indicates the order of the fields of the training app belonging to the topic or the arrangement of the forms of the fields of the training app belonging to the topic.

[0096] For example, the setting work support unit 203 identifies the topic to which the app being set belongs based on the field layout of the app being set and based on the machine learning model M. The setting work support unit 203 inputs data indicating the field layout of the app being set into the machine learning model M. The machine learning model M executes clustering based on the data and identifies the topic to which the app being set belongs. Although what the data used in the clustering indicates is different from the embodiment, the clustering process is the same as in the embodiment.

[0097] For example, the setting operation support unit 203 predicts the field layout specified by the following setting operation based on the topic data of the topic to which the app being set belongs. For example, in the example of the lower setting screen SC2 in FIG. 4, assume that the topic data indicates that there is a tendency for fields of field type "numerical value" to be arranged side by side in two columns horizontally, and further ahead, a field of field type "calculation" is arranged. In this case, when the user arranges two fields of field type "numerical value" side by side horizontally, the setting operation support unit 203 predicts that some field will be arranged ahead of them. The setting operation support unit 203 proposes to the user to arrange a field ahead of them.

[0098] Note that the setting operation support unit 203 may determine whether the field layout specified by the user for the app being set is different from the field layout indicated by the topic data of the topic to which the app being set belongs. When it is determined that these are different, the setting operation support unit 203 may propose to the user the field layout indicated by the topic data.

[0099] For example, in an app such as shown in FIGS. 2 to 4, assume that the user has specified, as the first three fields in the app being set, a field of field type "calculation", a field of field type "numerical value", and a field of field type "numerical value" in this order. In this case, assume that the topic data of the topic to which the app being set belongs indicates, as the order of the first three fields, a field of field type "numerical value", a field of field type "numerical value", and a field of field type "calculation" in this order. In this case, since the setting operation support unit 203 determines that these are different, it proposes to the user the order indicated by the topic data.

[0100] For example, the setting operation support unit 203 determines whether the position of the form of each field in the display area A21 of the app being set is different from the position of the form of each field indicated by the topic data of the topic to which the app being set belongs. When it is determined that these are different, if the difference (for example, the two-dimensional position difference of the form) is equal to or greater than the threshold value, the setting operation support unit 203 proposes to the user the position of the form of each field indicated by the topic data. When other elements are used as the field layout, the setting operation support unit 203 may propose the other elements to the user.

[0101] The setting operation support system 1 of Modification Example 1 supports the setting operation by proposing to the user the field layout specified by the next setting operation based on the field layout specified by the setting operation and the machine learning model M. For example, a user who is not familiar with creating apps may not fully understand what kind of field layout is appropriate and may be confused about specifying the field layout. The setting operation support system 1 can achieve more effective support by analyzing the field layout specified by the user with the machine learning model M and proposing the field layout to the user.

[0102] [6-2. Modification Example 2] For example, the setting operation support unit 203 may propose to the user a training app similar to the app being set. Similar to the embodiment, the training data created based on the training app is learned in the machine learning model M of Modification Example 2. The setting operation support unit 203 of Modification Example 2 supports the setting operation by proposing to the user a training app based on the setting specified by the setting operation and the machine learning model M. The training app to be proposed is a training app belonging to the same topic as the app being set.

[0103] FIG. 11 is a diagram showing an example of the setting screen SC2 of Modification 2. For example, in the same manner as in the embodiment, the setting work support unit 203 identifies the topic to which the app being set belongs. The setting work support unit 203 selects any one of a plurality of training apps belonging to the topic. The setting work support unit 203 may randomly select any one of the plurality of training apps, or may select a representative training app in the topic (for example, a training app designated by the creator of the machine learning model M). As shown in FIG. 11, the setting work support unit 203 causes the user terminal 30 to display a button B22 for displaying the settings of the training app on the setting screen SC2.

[0104] For example, when the user selects the button B22, the setting work support unit 203 causes the user terminal 30 to display a setting screen SC2 showing the settings of the training app. In the example of FIG. 11, the setting work support unit 203 refers to the app database DB3 and acquires the app setting data of the training app "site manager app" similar to the app being set. The setting work support unit 203 displays all or part of the acquired app setting data on the setting screen SC2. The user continues the setting work of the app being set with reference to the settings of the training app. The user replaces the settings of the app being set with the settings of the training app displayed on the setting screen SC2 as needed. The user may copy the training app and create a new app instead of the app being set.

[0105] The setting work support system 1 of Modification 2 supports the setting work by proposing a training app to the user based on the setting specified by the setting operation and the machine learning model M. Thereby, since the user can perform the setting work with reference to the training app, the setting work support system 1 can improve the convenience of the user.

[0106] [6-3. Modification 3] For example, the machine learning model M may learn training data indicating the settings specified by the training setting operations and the order in which the training setting operations were performed. The training data of Modification 3 indicates not only the number of field types as described in the embodiment, but also the order of the setting operations when the settings of the training application are made. For example, the order of the setting operations is also shown in the training data, such as the first setting operation indicating a field of the field type "numerical value", the second setting operation indicating a field of the field type "numerical value", and the third setting operation indicating a field of the field type "calculation". The training data may indicate the order in which setting operations such as deletion of fields are performed.

[0107] For example, even if two fields of the field type "numerical value" are specified and one field of the field type "calculation" is specified, the next setting operation may differ depending on the order in which they are specified. For example, when specified in the order of numerical value, numerical value, calculation, it is often the case that a numerical value is specified next, but when specified in the order of numerical value, calculation, numerical value, it may often be the case that a calculation is specified next. Thus, not only the simple number of field types but also the tendency of the order in which the field types are specified may be learned by the machine learning model M. The machine learning model M performs clustering considering not only the number of field types but also the order of the setting operations as one of the features. For this reason, even if the number of field types is the same, training applications with different orders of setting operations may belong to different topics.

[0108] The setting work support unit 203 of Modification Example 3 supports the setting work based on the setting specified by the setting operation, the order in which the setting operation was performed, and the machine learning model M. For example, the setting work support unit 203 inputs into the machine learning model M not only the setting indicated by the setting operation performed by the user for the app being set, but also the data indicating the order in which the setting operation was performed. The machine learning model M performs clustering considering the order as one of the features. The setting work support unit 203 proposes to the user the field type that the user will specify next based on the execution result of the clustering by the machine learning model. Although the point that the order is considered in the clustering is different from the embodiment, the processing after the clustering is executed (the processing for proposing the field type) is the same as in the embodiment.

[0109] The setting work support system 1 of Modification Example 3 supports the setting work based on the setting specified by the setting operation, the order in which the setting operation was performed, and the machine learning model M. Thereby, when what should be proposed to the user differs depending on the order of the setting operations, the setting work support system 1 can achieve more effective support. For example, even when two fields of the field type "numerical value" are specified and one field of the field type "calculation" is specified, the setting work support system 1 makes different proposals to the user for the field type to be proposed depending on whether it was specified in the order of numerical value, numerical value, calculation and whether it was specified in the order of numerical value, calculation, numerical value, so that an appropriate proposal can be made to the user.

[0110] [6-4. Modification Example 4] For example, the machine learning model M is not limited to a model that performs clustering as described in the embodiments. In Modification 4, other examples of the machine learning model M will be described. The machine learning model M in Modification 4 is an interactive model. An interactive model is a model that generates a response according to the text when a user inputs text in natural language. The text input by the user includes content related to the settings of the application. For example, the user inputs text such as the purpose of the application or the desired general application settings. The interactive model can also be called a chat model.

[0111] FIG. 12 is a diagram showing an example of the processing executed by the setting work support system 1 in Modification 4. As shown in FIG. 12, for example, when the user inputs text such as "Please create an attendance management application.", the machine learning model M divides the text into tokens and calculates an embedding representation. The machine learning model M generates a response "Would it be okay to create a time card application?" according to the embedding representation.

[0112] For example, when a user inputs text such as "Thank you.", the machine learning model M generates data of a DSL (Domain Specific Language), which is a type of programming language or markup language for specific applications, based on the trends of the training time card applications. In Modification Example 4, the DSL generated by the machine learning model M is data in a format that can be input to the application creation program P for creating an application. The application creation program P creates an application based on the DSL. For example, the application creation program P includes code for a process of generating application setting data from the DSL data generated by the machine learning model M. Assume that the application creation program P is stored in the data storage unit 200. The server 20 executes the code indicated by the application creation program P, and the application creation program P realizes no-code or low-code application creation. When the computer storing the machine learning model M and the computer storing the application creation program P are separate, the application creation program P may be a part of the API. In creating an application, other programs other than the application creation program P may be used.

[0113] For example, when the application creation program P creates a temporary application, the machine learning model M obtains processing result data indicating the processing result of the application creation program P from the application creation program P. The processing result data may be in any format, for example, data of a markup language such as json. For example, the processing result data obtains data indicating the settings of the temporary application created by the application creation program P. The processing result data may indicate the types of data required for the application (for example, employee master data). Based on the processing result data, the machine learning model M generates a response to the user, "An application has been created. Employee master data is required." When the user inputs text such as "There should be an employee application.", the machine learning model M generates DSL data for causing the application creation program P to search for the employee application specified by the user.

[0114] For example, when the app creation program P searches for an app based on the DSL data, it generates processing result data indicating the app search results. Suppose the machine learning model M shows in the processing result data that three apps were found in the search. Then, the machine learning model M displays a message such as "Three candidates were found." and prompts the user to select one of the three apps. When the user enters text such as "Please use the second one.", the machine learning model M generates DSL data indicating that the master data of employees is to be associated with the second app. The app creation program P acquires the master data of employees from the second app based on the DSL data and updates the app setting data of the app being configured. The machine learning model M acquires processing result data indicating the update result of the app setting data from the app creation program P. Based on the processing result data, the machine learning model M displays a response to the user, "The app has been updated." In Modification Example 4, the user can complete the app configuration through such interaction.

[0115] In Modification Example 4, an example is given where the machine learning model M is a so-called large language model. For example, the machine learning model M may be a large language model such as GPT (Generative Pre-trained Transformer), BERT (Bidirectional Encoder Representations from Transformers), PaLM (Pathways Language Model), or LLaMA (Large Language Model Meta AI). The machine learning model M may also be other models not classified as large language models (for example, neural networks or sequence-to-sequence models). For example, the parameters of the machine learning model M may be matrices referred to during the calculation of embedded representations, positional encodings referred to in the encoding of token positions, or other parameters.

[0116] For example, the program of the machine learning model M includes an encoder that calculates an embedded representation, a decoder that creates data for output according to tasks such as schedule adjustment, an output layer that performs a final output based on the data, and processing of other intermediate layers. When the machine learning model M is a large language model, the machine learning model M also includes a program that represents the process of dividing the input data into a plurality of tokens. The program of the machine learning model M may be a known program. When the machine learning model M is a large language model, the machine learning model M also includes a program that represents the process of dividing the input data into a plurality of tokens.

[0117] In Modification Example 4, a case where a pre-trained large language model corresponds to the machine learning model M is taken as an example. For example, the learning unit 102 may re-learn the machine learning model M based on the training data. Re-learning is the adjustment of the parameters of the pre-trained machine learning model M. For example, re-learning is fine-tuning, transfer learning, or distillation. The learning unit 102 may perform learning of the machine learning model M (the machine learning model M with initial parameter values) that has not been pre-trained instead of re-learning the machine learning model M.

[0118] The training data of Modification Example 4 includes an input part input to the machine learning model M during learning and an output part that is the correct answer during learning. For example, the input part of the training data is the text input by the training user. The output part of the training data is the DSL data that is the correct answer when the text is input. The learning unit 102 adjusts the parameters of the machine learning model M so that the DSL data indicated by the output part of the training data is output when the text indicated by the input part of the training data is input.

[0119] For example, the input part of the training data may be the processing result data for training generated by the app creation program P. The output part of the training data may be the text that is the correct answer to the response to the user. When the processing result data indicated by the input part of the training data is input, the learning unit 102 adjusts the parameters of the machine learning model M so that the text indicated by the output part of the training data is output.

[0120] The setting operation of Modification Example 4 is an operation in which the user inputs a prompt to the machine learning model M for app settings. The prompt is the user's instruction to the machine learning model M. As shown in FIG. 12, in the case of the interactive machine learning model M, the prompt is basically input in text, but the prompt may also include symbols or the like indicating some instruction other than text. The setting work support unit 203 supports the setting work by obtaining input data in a format that can be input to the app creation program P for creating an app based on the prompt input by the setting operation and the machine learning model M. In the example of FIG. 12, the data generated by DSL corresponds to the input data.

[0121] For example, the machine learning model M divides the prompt input by the user in the setting operation into a plurality of tokens. The machine learning model M calculates the embedding vector of each of the plurality of tokens based on the learned parameters. The machine learning model M generates input data after predicting the next word as necessary based on the calculated embedding vector. The input data indicates information for settings according to the prompt input by the user. Depending on the prompt input by the user, the machine learning model M may not generate input data.

[0122] The setting work support unit 203 of Modification Example 4 inputs the output data output from the machine learning model M as input data into the database creation program P. The setting work support unit 203 supports the setting work by causing the database creation program P to output processing result data indicating the processing result of the database creation program P. For example, the database creation program P executes processing for app settings based on the input data input to itself. The database creation program P generates and outputs processing result data based on its own code. The setting work support unit 203 supports the setting work by presenting a response according to a prompt to the user based on the processing result data obtained from the app creation program P and the machine learning model M. In the example of FIG. 12, the processing result by the app creation program P is shown by the processing result data in json format.

[0123] For example, the setting work support unit 203 inputs the processing result data to the machine learning model M. The machine learning model M calculates an embedding vector after dividing it into tokens as necessary based on the processing result data. The machine learning model M generates response data according to the embedding vector. The setting work support unit 203 causes the user terminal 30 to display the response by the machine learning model M by transmitting the data to the user terminal 30. Note that the setting work support unit 203 may support the setting work by directly displaying the content of the processing result data on the user terminal 30 instead of causing the machine learning model M to generate a response based on the processing result data. In this case, the user can check the content of the processing result data in json format.

[0124] The setting work support unit 203 of Modification Example 4 may determine whether the output data output from the machine learning model M is in a format that can be input into the application creation program P. In the case of FIG. 12, the setting work support unit 203 determines whether the output data output from the machine learning model M is in the DSL format. In this case, when it is determined that the output data is in the said format, the setting work support unit 203 supports the setting work by acquiring the output data as input data. When it is determined that the output data is not in the said format, the setting work support unit 203 supports the setting work by presenting a response according to the prompt to the user based on the output data.

[0125] In the example of FIG. 12, in the prompt initially input by the user, output data in the DSL format was not output, so no input data was input into the application creation program P, and a response to the user was displayed. As shown in FIG. 12, through repeated interaction between the user and the machine learning model M, the setting of the application is completed. Note that the interaction until the completion of the application setting may be once. In this case, the setting of the application is completed without the interaction being repeated. When the user performs an operation to end the setting of the application, the setting of the application may be completed.

[0126] The setting work support system 1 of Modification Example 4 supports the setting work by acquiring input data in a format that can be input into the application creation program P based on the prompt input by the setting operation and the machine learning model M. Thereby, the setting work support system 1 can complete the setting of the application without having the user specify the application setting itself. For example, the user only needs to input a rough outline of the desired application as a prompt, so the setting work support system 1 can achieve more effective support.

[0127] In addition, the setting work support system 1 inputs the output data output from the machine learning model M as input data into the database creation program P, and outputs the processing result data indicating the processing result of the database creation program P to the database creation program P, thereby supporting the setting work. By using the machine learning model M to output the processing result data to the database creation program P, the setting work support system 1 eliminates the need for the user to directly specify the settings for outputting the processing result data to the database creation program P, so that the convenience of the user can be effectively improved. As a result, the setting work support system 1 can improve the accuracy of the application.

[0128] In addition, when it is determined that the output data output from the machine learning model M is in a predetermined format, the setting work support system 1 supports the setting work by acquiring the output data as input data. When it is determined that the output data is not in a predetermined format, the setting work support system 1 supports the setting work by presenting a response according to the prompt to the user based on the output data. Thereby, even if the desired setting is not achieved in the first interaction, the setting work support system 1 can correct the setting by repeating the interaction. As a result, the setting work support system 1 can improve the accuracy of the application. For example, even if the machine learning model M fails to output the output data in the format required for the application settings, the setting work support system 1 can continue the interaction with the user. While the interaction with the user continues, the setting work support system 1 can output the output data in a predetermined format.

[0129] [6-5. Variant 5] For example, the content to be proposed to the user may vary depending on the organization or department to which the user belongs. In the example of FIG. 4, even if the user arranges two fields of the field type "numerical value", the field types that the setting work support system 1 should next propose may differ between the case where the user belongs to the manufacturing industry and the case where the user belongs to the service industry. For example, the field types that the setting work support system 1 should next propose may differ between the case where the user belongs to the sales department and the case where the user belongs to the development department. Therefore, the setting work may be supported in consideration of some attributes of the user.

[0130] The setting work support system 1 of Modification 5 includes a user attribute data acquisition unit 204. The user attribute data acquisition unit 204 acquires user attribute data indicating the attributes of the user. Assume that the user attribute data is stored in the database storage unit 201. The attributes of the user may be information that can classify the user from any perspective. For example, in addition to the industry type or department of the organization described above, the attributes may be the user's age group, gender, years of service, job title, hobbies, or other attributes. The attributes of the user may be specified by the user himself / herself, or may be specified by an administrator in the user's organization.

[0131] The setting work support unit 203 of Modification 5 supports the setting work based on the setting operation, the machine learning model M, and the user attribute data. In Modification 5, assume that the training data includes the user attribute data of the training user. For example, the training data includes not only the settings of the training application but also the user attribute data of the training user who created the training application. The machine learning model M performs clustering by regarding not only the settings of the training application but also the user attribute data of the training user who created the training application as one of the features. The setting work support unit 203 supports the setting work based on the execution result of the clustering in which the user attribute data is also regarded as one of the features. Although the point that the user's attributes are considered in the clustering is different from the embodiment, the processing after the clustering is executed (the processing for proposing the field type) is the same as in the embodiment.

[0132] The setting work support system 1 of Modification Example 5 supports the setting work based on the setting operation, the machine learning model M, and the user attribute data. Thereby, since the setting work support system 1 can make a proposal according to the attributes of the user, the setting work by the user can be effectively supported.

[0133] [6-6. Modification Example 6] For example, if the user has made some app settings in the past, the content to be proposed to the user may be different based on the user's past tendencies. For example, assume that the user has placed two fields of the field type "numeric". If the user then has a tendency to place another field of the field type "numeric" instead of a field of the field type "calculation", it may be better to propose a field of the field type "numeric". Therefore, the setting work may be supported in consideration of the tendencies of the settings made by the user in the past.

[0134] The setting work support system 1 of Modification Example 6 includes a past setting data acquisition unit 205. The past setting data acquisition unit 205 acquires past setting data indicating past settings that are the settings made by the user in past setting operations. Assume that the user attribute data is stored in the database storage unit 201. For example, when the user performs a setting operation for some app, the server 20 records the past setting data corresponding to the setting indicated by the setting operation in the database storage unit 201 in association with the user ID of the user.

[0135] The setting work support unit 203 of Modification Example 6 supports the setting work based on the setting operation, the machine learning model M, and the past setting data. In Modification Example 6, it is assumed that the past setting data of the training user is included in the training data. For example, the training data includes not only the settings of the training application but also the past setting data indicating the settings made by the training user who created the training application in the past. The machine learning model M executes clustering by regarding not only the settings of the training application but also the past setting data of the training user who created the training application as one of the features. The setting work support unit 203 supports the setting work based on the execution result of the clustering that regards the past setting data as one of the features. Although the point that the past tendency of the user is considered in the clustering is different from the embodiment, the processing after the clustering is executed (the processing for proposing the field type) is the same as that in the embodiment.

[0136] The setting work support system 1 of Modification Example 6 supports the setting work based on the setting operation, the machine learning model M, and the past setting data. Thereby, since the setting work support system 1 can make a proposal according to the past tendency of the user, it can effectively support the setting work by the user.

[0137] [6-7. Other Modification Examples] For example, two or more of Modification Examples 1 to 6 may be combined.

[0138] For example, when the setting work support system 1 supports a user who performs the setting work of a groupware application, the setting work support system 1 may support a user who performs the setting work of a database other than the application. The setting work support system 1 may support a user who performs the setting work of a database that does not have a communication function or the like. The setting work support system 1 may support a user who performs the setting work of a database of a business support system that is not classified as groupware. The setting work support system 1 may support a user who performs the setting work of a database that has no relation to the business support system. For example, when the setting work support system 1 supports a user who performs the setting work of a new application, the setting work support system 1 may support a user who performs the setting work for changing the settings of an existing application. Also in this case, the setting work support system 1 may support the setting work by the user based on the settings of the existing application, the setting operations performed by the user for the setting change, and the machine learning model M.

[0139] For example, in the embodiment, the machine learning model M that performs application clustering is taken as an example, but the machine learning model M may execute processes other than clustering. For example, the input part of the training data may indicate some settings of the training application. The output part of the training data may indicate the settings (correct settings) specified next to the settings indicated by the input part. When an input part indicating some settings of the training application is input, the learning unit 102 performs learning of the machine learning model M so that the settings indicated by the output part corresponding to the input part are output. The setting work support unit 203 inputs the settings specified by the user in the application being set to the learned machine learning model M. The machine learning model M calculates the embedding representation of the setting based on the parameters adjusted by learning, and outputs the settings according to the embedding representation. The setting work support unit 203 may propose the settings output from the machine learning model M to the user. These series of processes may be implemented by a mechanism in which the machine learning model M used in natural language processing predicts the next word.

[0140] For example, the functions described as being implemented by the server 20 may be implemented by the user terminal 30. In this case, the functions may be implemented by a browser script or an application installed on the user terminal 30. For example, each function may be shared among a plurality of computers or may be implemented by one computer.

Explanation of Reference Numerals

[0141] 1 Setting Work Support System, 10 Learning Terminal, 11, 21, 31 Control Unit, 12, 22, 32 Storage Unit, 13, 23, 33 Communication Unit, 20 Server, 30 User Terminal, 14, 34 Operation Unit, 15, 35 Display Unit, M Machine Learning Model, N Network, P App Creation Program, 100, 200 Machine Learning Model Storage Unit, 101, 201 Database Storage Unit, 102 Learning Unit, 202 Setting Operation Identification Unit, 203 Setting Work Support Unit, 204 User Attribute Data Acquisition Unit, 205 Past Setting Data Acquisition Unit, 300 Data Storage Unit, 301 Display Control Unit, 302 Operation Reception Unit, A20, A21 Display Area, B22 Button, DB1 Training Database, DB2 Topic Database, DB3 App Database, L10 Record List, SC1 App Screen, SC2 Setting Screen.

Claims

1. A setting operation identification unit that identifies a setting operation performed by a user for setting a database created using no-code or low-code; A machine learning model storage unit that stores a machine learning model in which training data created based on the setting for training has been learned; A setting operation support unit that supports the user in setting the database based on the setting operation and the machine learning model; A configuration support system including:

2. the setting operation is an operation by the user to specify the setting, The setting operation support unit supports the setting operation based on the setting specified by the setting operation and the machine learning model. The setting operation support system according to claim 1 .

3. the settings are field settings that are settings of a field in the database, The machine learning model is trained with the training data created based on the field setting for training, The setting operation support unit supports the setting operation by suggesting to the user the field setting to be specified by the next setting operation based on the field setting specified by the setting operation and the machine learning model. The setting operation support system according to claim 2 .

4. the field setting is a field type that is a type of the field; The setting operation support unit supports the setting operation by suggesting to the user the field type to be specified by the next setting operation based on the field type specified by the setting operation and the machine learning model. The setting operation support system according to claim 3 .

5. the field configuration is a field layout that is a layout of the field; The setting operation support unit supports the setting operation by proposing to the user the field layout to be specified by the next setting operation based on the field layout specified by the setting operation and the machine learning model.

5. The setting operation support system according to claim 3 or 4.

6. The machine learning model is trained with the training data created based on the training database, The setting operation support unit supports the setting operation by suggesting the training database to the user based on the setting specified by the setting operation and the machine learning model.

5. The setting operation support system according to claim 2.

7. The machine learning model is trained with the training data created based on the training database, the setting operation support unit executes clustering of the database being set based on the setting specified by the setting operation and the machine learning model, and supports the setting operation based on a result of the clustering execution.

5. The setting operation support system according to claim 2.

8. The machine learning model learns the training data indicating the settings specified by the setting operation for training and the order in which the setting operation for training was performed, The setting operation support unit supports the setting operation based on the settings specified by the setting operation, an order in which the setting operation was performed, and the machine learning model.

5. The setting operation support system according to claim 2.

9. The machine learning model is an interactive model, the setting operation is an operation in which the user inputs a prompt to the machine learning model for the setting; The setting operation support unit supports the setting operation by acquiring input data in a format that can be input to a database creation program that creates the database, based on the prompt input by the setting operation and the machine learning model. The setting operation support system according to claim 1 .

10. The setting work support unit supports the setting work by inputting output data output from the machine learning model as the input data to the database creation program and causing the database creation program to output processing result data indicating a processing result of the database creation program. The setting operation support system according to claim 9.

11. The setting operation support unit includes: Determining whether output data output from the machine learning model is in the format; When it is determined that the output data is in the format, the setting operation is supported by acquiring the output data as the input data; if the output data is not determined to be in the format, a response to the prompt is presented to the user based on the output data, thereby assisting the user in the setting operation; The setting is completed by repeating the dialogue between the user and the machine learning model.

11. The setting operation support system according to claim 9 or 10.

12. The setting work support system further includes a user attribute data acquisition unit that acquires user attribute data indicating attributes of the user, The setting operation support unit supports the setting operation based on the setting operation, the machine learning model, and the user attribute data.

5. The setting operation support system according to claim 1.

13. The setting operation support system further includes a past setting data acquisition unit that acquires past setting data indicating past settings that are the settings performed by the user in the past setting operation, The setting operation support unit supports the setting operation based on the setting operation, the machine learning model, and the past setting data.

5. The setting operation support system according to claim 1.

14. Identifying configuration operations performed by a user to configure a database created using no-code or low-code; Supporting the user in setting up the database based on the setting operation and a machine learning model that has been trained using training data created based on the setting for training. How to support the setup process.

15. A setting operation identification unit that identifies a setting operation performed by a user for setting a database created using no-code or low-code; a setting operation support unit that supports the user in setting up the database based on the setting operation and a machine learning model that has been trained using training data created based on the setting for training; A program that makes a computer function as a

Images