JP7023440B1 - Programming support device, programming support method, and programming support program - Google Patents

Abstract

The programming support device (1) is information on a source code input unit (60) in which a source code being created input to the programming software is input and a device in which a program corresponding to the first source code is used. A combination of the setting input unit (50) into which the first used device setting and the first used function setting, which is information on the function used by the device, are input, and the source code, the used device setting, and the used function setting. A inference device (30) that infers a template source code corresponding to combination information using a trained model that infers a template source code that is a source code template from information, and a source code input to the source code input unit. It is provided with a difference extraction device (40) that extracts the difference between the template source code and the template source code as a difference source code, and a source code output unit (70) that outputs the difference source code.

Description

The present disclosure relates to programming support devices, programming support methods, and programming support programs that support the creation of programs.

When a manufacturing device or the like is designed or developed, it is necessary to create the source code of the program to be incorporated in the manufacturing device. Since the source code creation time and modification time occupy a large part of the development man-hours of the entire manufacturing equipment, the development man-hours can be reduced by reducing the source code creation time and modification time, and the development of the manufacturing equipment can be reduced. Costs can also be reduced.

For example, the programming device of Patent Document 1 realizes efficiency of program creation work and maintenance work, and inputs a program algorithm, sequence, etc. when creating a program in order to eliminate human error. Automatically outputs a program or document.

Japanese Unexamined Patent Publication No. 9-73306

However, in the technique of Patent Document 1, when creating the source code of the program, it is necessary to input all the algorithms, sequences, etc. of all specifications, so that it is not possible to create the desired source code in a short time. Have difficulty.

The present disclosure has been made in view of the above, and an object of the present invention is to obtain a programming support device capable of easily creating a desired source code in a short time.

In order to solve the above-mentioned problems and achieve the object, the programming support device of the present disclosure includes a source code input unit in which a first source code, which is a source code in the process of being created, is input to the programming software. It includes a first device setting that is information on the device in which the program corresponding to the first source code is used, and a setting input unit in which the first function setting that is information on the function used by the device is input. .. Further, the programming support device of the present disclosure is a template source code which is a template of the first source code from the combination information which is a combination of the first source code, the first device used setting, and the first used function setting. It is provided with an inference device that infers the template source code corresponding to the combination information by using the trained model that infers. Further, the programming support device of the present disclosure includes a difference extraction device that extracts the difference between the first source code input to the source code input unit and the template source code inferred by the inference device as a difference source code, and a difference. It is equipped with a source code output unit that outputs source code.

The programming support device according to the present disclosure has an effect that a desired source code can be easily created in a short time.

The figure which shows the structure of the programming support apparatus which concerns on Embodiment 1. The figure which shows the structure of the learning apparatus which concerns on Embodiment 1. A flowchart showing a processing procedure of learning processing by the learning device according to the first embodiment. The figure which shows the structure of the inference apparatus which concerns on Embodiment 1. A flowchart showing a processing procedure of inference processing by the inference device according to the first embodiment. A flowchart showing a processing procedure of programming support processing by the programming support device according to the first embodiment. The figure which shows the hardware configuration example which realizes the programming support apparatus which concerns on Embodiment 1.

Hereinafter, the programming support device, the programming support method, and the programming support program according to the embodiment of the present disclosure will be described in detail with reference to the drawings.

Embodiment 1.
FIG. 1 is a diagram showing a configuration of a programming support device according to the first embodiment. The programming support device 1 is a computer that supports programming when a user executes programming using an engineering tool that is programming software.

The programming support device 1 utilizes AI (Artificial Intelligence) to provide information for complementing the source code input to the programming software from the source code, the device used setting, and the function setting used. ..

The device used setting is information on the device on which the program is used. The function setting used is information on the function used by the device in which the program is used. The device in which the program corresponding to the source code is used is, for example, a PLC (Programmable Logic Controller). In this case, the programming software used by the user is programming software for creating a program for PLC.

When the device in which the program is used is a PLC, an example of the device setting used is a unit name used by the PLC such as a CPU (Central Processing Unit) unit, a power supply unit, an input / output unit, an analog unit, and a communication unit. When the device in which the program is used is PLC, an example of the function setting to be used is a function name such as RS485 communication and pulse output.

The programming support device 1 of the first embodiment uses a trained model created by machine learning such as unsupervised learning, and uses a source code that complements the source code in the process of being created input to the programming software (difference described later). Source code) is extracted and presented to the user. The source code in the process of being created input to the programming software is the first source code.

The source code in the process of being created received by the programming support device 1 may be a source code in the process of being newly created or a source code in the process of being changed. In the first embodiment, a case where the source code in the process of being created received by the programming support device 1 is the source code in the process of being newly created will be described.

The programming support device 1 includes a source code input unit 60, a setting input unit 50, an inference device 30, a difference extraction device 40, and a source code output unit 70. Further, the programming support device 1 is connected to the display device 2.

The source code input unit 60 receives the source code (first source code) in the process of being created input to the programming software and outputs it to the inference device 30, the difference extraction device 40, and the source code output unit 70. Programming software is software that creates source code according to user operations. The programming software may execute programming in the programming support device 1, or may execute programming in another device (source code creation device) different from the programming support device 1. The source code creation device is a computer that creates source code according to the operation by the user. The source code in the process of being created input to the programming software is input to the setting input unit 50.

The setting input unit 50 receives the used function setting and the used device setting input by the user and outputs them to the inference device 30. The used function setting and the used device setting accepted by the setting input unit 50 are the used function setting and the used device setting corresponding to the source code received by the source code input unit 60.

The used function setting and the used device setting may be input to the setting input unit 50 from an external device. The used function setting in the first embodiment is the first used function setting, and the used device setting in the first embodiment is the first used device setting. That is, the used function setting corresponding to the source code being created input to the programming software is the first used function setting, and the used device setting corresponding to the existing source code is the first used device setting.

The inference device 30 is a source code input unit based on combination information which is a combination of the function setting and the equipment setting used from the setting input unit 50 and the source code sent from the source code input unit 60. Source code template sent from 60 Infer the source code. Specifically, the inference device 30 infers the program group number based on the combination information, and extracts the template source code corresponding to the program group number. The program group number is the number of the group to which the program corresponding to the source code belongs.

For example, the program created by the user includes a socket communication program, an RS485 communication program, a pulse output program, and the like. Further, the socket communication program includes a transmission program, a reception program, a retransmission program, and the like. Further, socket communication programs include bit data transmission, word data transmission, and multiple data transmission. The inference device 30 infers the program group number for the source code of the lowest layer program such as bit data transmission, word data transmission, and multiple data transmission.

Template source code is a template of source code. The template source code is the source code required when the function setting and the device setting used are used. The template source code is, for example, the source code of the central Vj of the cluster described later.

The inference device 30 estimates the program group number corresponding to the combination information by using the trained model that estimates the program group number from the combination information, and reads out the template source code corresponding to the program group number. As a result, the inference device 30 infers the template source code corresponding to the combination information using the trained model.

The difference extraction device 40 compares the template source code sent from the inference device 30 with the source code sent from the source code input unit 60, and uses these differences as the difference source code in the source code output unit 70. Output. The difference source code is source code that complements the source code of the program being created by the user. In other words, the difference source code is a source code that is not accepted by the source code input unit 60 among the source codes required when the function setting and the device setting used are used.

The source code output unit 70 outputs the source code sent from the source code input unit 60 and the difference source code sent from the difference extraction device 40 to a display device 2 such as a liquid crystal monitor. The source code output unit 70 causes the display device 2 to display the source code and the difference source code on the same screen.

In this way, the programming support device 1 infers the template source code from the source code of the program being created, the function setting used, and the device setting used, using the trained model created by machine learning. Then, the programming support device 1 extracts the difference source code based on the inferred template source code and displays it on the display device 2. As a result, the programming support device 1 presents to the user a difference source code that complements the source code of the program being created. By presenting the difference source code to the user, the programming support device 1 can shorten the time for the user to create the source code, and can prevent the source code from being overcorrected when the program is changed.

The trained model used by the programming support device 1 is created by a learning process by a learning device described later. Further, the programming support device 1 includes an inference device 30, and the inference device 30 infers the program group number using the trained model. Here, the learning process of the program group number by the learning device and the inference process of the program group number by the inference device 30 will be described.

<Learning phase>
FIG. 2 is a diagram showing a configuration of a learning device according to the first embodiment. The learning device 10 includes a data acquisition unit 11, a model generation unit 12, and a template source code generation unit 13. The model generation unit 12 is connected to the trained model storage unit 21, and the template source code generation unit 13 is connected to the template source code storage unit 22.

The data acquisition unit 11 acquires the source code, the function setting used, and the equipment setting used as learning data, and outputs the data to the model generation unit 12.

The model generation unit 12 learns the program group number based on the learning data created based on the combination (combination information) of the source code, the function setting used, and the device used setting output from the data acquisition unit 11. .. In other words, the model generation unit 12 learns the program group number corresponding to the source code by classifying the source code into the program group to which the program corresponding to the source code belongs based on the learning data. That is, the model generation unit 12 generates a trained model that infers the program group number from the source code, the function setting used, and the device setting used. The learning data is data in which the source code, the function setting used, and the device setting used are associated with each other.

As the learning algorithm, the model generation unit 12 can use known algorithms such as supervised learning, unsupervised learning, and reinforcement learning. As an example, a case where the model generation unit 12 applies the K averaging method (clustering), which is learning without supervision, will be described. Unsupervised learning refers to a method of learning features in the learning data by giving learning data that does not include a result (label) to a learning device such as the learning device 10.

The model generation unit 12 learns the program group number by so-called unsupervised learning according to the grouping method by the K-means method, for example. The K-means clustering method is a non-hierarchical clustering algorithm, and is a method of classifying a given number of clusters into k using the average of clusters.

Specifically, the K-means method is processed in the following flow. First, the model generation unit 12 randomly allocates clusters for each data xi (source code). Next, the model generation unit 12 calculates the center Vj of each cluster based on the allocated data. Next, the model generation unit 12 obtains the distance between each xi and each Vj, and reassigns the xi to the cluster of the nearest central Vj. Then, when the allocation of all xi clusters does not change in the above processing, or when the amount of change falls below a predetermined threshold value, the model generation unit 12 determines that the clusters have converged and clusters. Ends the processing of.

The model generation unit 12 of the first embodiment is programmed by so-called unsupervised learning according to the learning data created based on the combination of the source code, the function setting used, and the equipment setting used acquired by the data acquisition unit 11. Learn the group number.

The model generation unit 12 generates a trained model by executing the above learning, and outputs the generated trained model to the trained model storage unit 21. Each time the model generation unit 12 generates a trained model, the model generation unit 12 updates the trained model stored in the trained model storage unit 21 with the latest trained model.

The template source code generation unit 13 generates the template source code based on the combination of all the program group numbers output from the model generation unit 12 and the source code at the center of the cluster classified into each program group number. .. The template source code generation unit 13 sets, for example, the source code at the center of the cluster classified by the program group number in the template source code. The template source code generation unit 13 generates a template source code for each program group number.

The template source code generation unit 13 outputs the template source code associated with the program group number to the template source code storage unit 22. Each time the template source code generation unit 13 generates the template source code, the template source code stored in the template source code storage unit 22 is updated with the latest template source code. That is, the template source code generation unit 13 stores the latest template source code in the template source code storage unit 22 for each program group number.

The trained model storage unit 21 stores the trained model output from the model generation unit 12. The template source code storage unit 22 stores the correspondence between the template source code output from the template source code generation unit 13 and the program group number.

Next, the learning process by the learning device 10 will be described with reference to FIG. FIG. 3 is a flowchart showing a processing procedure of learning processing by the learning device according to the first embodiment.

The data acquisition unit 11 acquires learning data (step S10). Specifically, the data acquisition unit 11 acquires the source code, the function used setting, and the device used device setting. For example, the source code, the function setting, and the device setting used are input to the data acquisition unit 11 from the programming software that creates the source code. The source code acquired by the data acquisition unit 11 is, for example, the source code as a finished product created so far.

Although the data acquisition unit 11 is supposed to acquire the source code, the function setting used, and the device setting used at the same time here, they may be acquired at different timings. That is, the source code, the function setting used, and the device used setting may be input to the data acquisition unit 11 in association with each other, and the data acquisition unit 11 inputs the data of the source code, the function setting used, and the device setting used, respectively. It may be acquired at different timings.

The model generation unit 12 executes the learning process (step S20). Specifically, the model generation unit 12 programs by so-called unsupervised learning according to the learning data created based on the combination of the source code, the function setting used, and the device setting used acquired by the data acquisition unit 11. Train the group number and generate a trained model. The trained model storage unit 21 stores the trained model generated by the model generation unit 12 (step S30).

The template source code generation unit 13 generates the template source code based on the combination of all the program group numbers output from the model generation unit 12 and the source code at the center of the cluster classified into each program group number. .. The template source code storage unit 22 stores the template source code output from the template source code generation unit 13. This is the learning phase.

<Utilization phase>
FIG. 4 is a diagram showing a configuration of an inference device according to the first embodiment. The inference device 30 includes a data acquisition unit 31, an inference unit 32, and a template source code acquisition unit 33.

The data acquisition unit 31 acquires the source code, the function setting used, and the device setting used. The source code is input to the data acquisition unit 31 from the source code input unit 60, and the function setting and the equipment setting to be used are input from the setting input unit 50.

The inference unit 32 infers the program group number using the trained model stored in the trained model storage unit 21. That is, the inference unit 32 inputs the data (data for inference) acquired by the data acquisition unit 31 into the trained model, and infers the program group number. Specifically, the inference unit 32 inputs the source code, the used function setting, and the used device setting acquired by the data acquisition unit 31 into the trained model, so that the source code, the used function setting, and the used device setting can be obtained. Infer which cluster it belongs to. The inference unit 32 outputs the inference result data as a program group number to the template source code acquisition unit 33.

The template source code acquisition unit 33 acquires the template source code from the template source code storage unit 22 using the program group number inferred by the inference unit 32, and outputs the template source code to the difference extraction device 40. That is, the template source code acquisition unit 33 reads the template source code associated with the program group number from the template source code storage unit 22.

In the first embodiment, the case where the inference unit 32 infers the program group number using the learned model learned by the model generation unit 12 of the learning device 10 has been described, but the inference unit 32 has another learning. A trained model created by the device may be acquired and the program group number may be inferred based on the trained model.

In this way, the inference device 30 outputs the template source code acquired using the program group number obtained based on the source code, the function setting used, and the device setting used to the difference extraction device 40.

Next, the inference processing of the template source code by the inference device 30 will be described with reference to FIG. FIG. 5 is a flowchart showing a processing procedure of inference processing by the inference device according to the first embodiment.

The data acquisition unit 31 acquires data for inferring the template source code (step S110). Specifically, the data acquisition unit 31 acquires the source code, the function used setting, and the device used device setting. The source code acquired by the data acquisition unit 31 is the source code corresponding to the program being created by the user.

The inference unit 32 infers the program group number using the trained model stored in the trained model storage unit 21. That is, the inference unit 32 inputs the data acquired by the data acquisition unit 31 into the trained model (step S120), and infers the program group number by the trained model. The inference unit 32 outputs the inference result data as a program group number (step S130).

The template source code acquisition unit 33 acquires the template source code from the template source code storage unit 22 using the program group number inferred by the inference unit 32, and outputs the template source code to the difference extraction device 40 (step S140). .. This is the inference phase.

Next, the operation of the programming support device 1 according to the first embodiment will be described with reference to FIG. FIG. 6 is a flowchart showing a processing procedure of programming support processing by the programming support device according to the first embodiment.

The programming support device 1 acquires data for inferring the template source code (step S210). Specifically, the setting input unit 50 acquires the used function setting and the used device setting, and the source code input unit 60 acquires the source code. The source code acquired by the source code input unit 60 is the source code corresponding to the program being created by the user.

The setting input unit 50 inputs the acquired function settings and equipment settings to the inference device 30, and the source code input unit 60 inputs the acquired source code to the inference device 30 (step S220). Further, the source code input unit 60 inputs the acquired source code to the difference extraction device 40 and the source code output unit 70.

The inference device 30 infers the program group number by inputting the source code, the function setting, and the equipment setting used into the trained model, and acquires the template source code using the program group number. The inference device 30 acquires the template source code by extracting the template source code corresponding to the program group number from the template source code storage unit 22. The inference device 30 outputs the acquired template source code (step S230). As a result, the inference device 30 inputs the template source code to the difference extraction device 40 (step S240).

The difference extraction device 40 calculates the difference source code by comparing the source code sent from the source code input unit 60 with the template source code sent from the inference device 30. The difference extraction device 40 outputs the calculated difference source code to the source code output unit 70 (step S250).

The source code output unit 70 outputs the source code sent from the source code input unit 60 and the difference source code sent from the difference extraction device 40 to the display device 2. The display device 2 displays the difference source code that complements the source code of the program being created by the user (step S260).

The difference source code displayed by the display device 2 is a source code that the user has not input when creating the program. That is, the difference source code displayed by the display device 2 is an algorithm, a sequence, or the like that has not been input by the user among the algorithms and sequences of all the specifications necessary for creating the program.

In this way, the programming support device 1 extracts the difference between the acquired source code and the template source code, and proposes the difference source code, which is the source code that complements the source code of the program being created, in the display device 2. Can be displayed on the screen of.

If the user inputs the source code halfway at the time of creating or modifying the source code of the program, the display device 2 displays the subsequent source code or the difference source code for complementing the correction omission part. As a result, the programming support device 1 can shorten the time for creating the source code and prevent omission of correction of the source code when the program is changed.

In the first embodiment, the case where unsupervised learning is applied to the learning algorithms used by the model generation unit 12 and the inference unit 32 has been described, but the learning algorithm is not limited to unsupervised learning. As for the learning algorithm, it is also possible to apply reinforcement learning, supervised learning, semi-supervised learning, or the like, in addition to unsupervised learning.

Further, as the learning algorithm used in the learning device 10, deep learning, which learns the extraction of the feature amount itself, can be used, and other known methods may be used.

When the model generation unit 12 realizes unsupervised learning in the first embodiment, not only the non-hierarchical clustering by the K-means method as described above but also other known methods capable of clustering are applied. May be done. For example, the model generation unit 12 may apply hierarchical clustering such as the shortest distance method.

In the first embodiment, the learning device 10, the inference device 30, the trained model storage unit 21, and the template source code storage unit 22 are connected to the programming support device 1 via, for example, the programming support device 1. It may be a device separate from the device. Further, the learning device 10, the inference device 30, the learned model storage unit 21, and the template source code storage unit 22 may be built in the programming support device 1. Further, the learning device 10, the inference device 30, the learned model storage unit 21, and the template source code storage unit 22 may exist on the cloud server.

Further, the model generation unit 12 may learn the program group number according to the learning data created for the plurality of programming software. The model generation unit 12 may acquire learning data from a plurality of programming software used in the same area, or may acquire learning data from a plurality of programming software that operate independently in different areas. You may use to learn the program group number. It is also possible to add or remove programming software that collects learning data from the target on the way. Further, the learning device 10 that has learned the program group number for a certain programming software may be applied to another programming software, and the program group number may be relearned and updated for the other programming software. Further, the model generation unit 12 may acquire learning data from a device other than the programming software, for example, a source code storage device that stores the source code.

Here, the hardware configuration of the programming support device 1 will be described. FIG. 7 is a diagram showing an example of a hardware configuration that realizes the programming support device according to the first embodiment.

The programming support device 1 can be realized by the processor 100, the memory 200, the input device 300, and the output device 400. An example of the processor 100 is a CPU (central processing unit, processing unit, arithmetic unit, microprocessor, microprocessor, also referred to as DSP (Digital Signal Processor)) or system LSI (Large Scale Integration). Examples of the memory 200 are RAM (Random Access Memory) and ROM (Read Only Memory).

The programming support device 1 is realized by the processor 100 reading and executing a computer-executable programming support program for executing the operation of the programming support device 1 stored in the memory 200. It can be said that the programming support program, which is a program for executing the operation of the programming support device 1, causes the computer to execute the procedure or method of the programming support device 1.

The programming support program executed by the programming support device 1 has a modular configuration including an inference device 30 and a difference extraction device 40, which are loaded on the main storage device and generated on the main storage device. Will be done.

The input device 300 receives the source code, the function setting, and the device setting used from the user or an external device and sends them to the memory 200. That is, the input device 300 executes the processing of the setting input unit 50 and the source code input unit 60.

The memory 200 stores source code, used function settings, used device settings, and the like. The source code, the function setting used, and the device setting used are sent to the processor 100. Further, the memory 200 is used as a temporary memory when the processor 100 executes various processes. The output device 400 outputs the difference source code to the display device 2. That is, the output device 400 executes the processing of the source code output unit 70.

The programming assistance program may be provided as a computer program product in an installable or executable file, stored in a computer-readable storage medium. Further, the programming support program may be provided to the programming support device 1 via a network such as the Internet. It should be noted that some of the functions of the programming support device 1 may be realized by dedicated hardware such as a dedicated circuit, and some may be realized by software or firmware.

Further, the inference device 30 and the difference extraction device 40 may be realized by different hardware configurations. In this case, the inference device 30 infers the template source code by using an inference program which is a program for inferring the template source code. Further, the difference extraction device 40 generates a difference source code by using a difference extraction program which is a program for extracting the difference between the source code and the template source code. The learning device 10 also has the same hardware configuration as the programming support device 1.

As described above, in the first embodiment, the learning device 10 creates a trained model by learning the template source code corresponding to the source code, the function setting used, and the device setting used. Further, the inference device 30 infers the template source code by inputting the source code, the function setting used, and the device setting used into the trained model.

Then, the programming support device 1 displays the difference between the source code input by the user and the template source code on the display device 2 as a difference source code. As a result, the user can easily input the source code in a short time without missing the source code. Therefore, the programming support device 1 makes it possible for the user to easily create a desired source code in a short time.

Embodiment 2.
Next, the second embodiment will be described with reference to FIG. In the second embodiment, the source code of the program being changed is input to the source code input unit 60 of the programming support device 1. Then, the difference extraction device 40 of the programming support device 1 extracts the difference between the source code acquired by the source code input unit 60 and the template source code inferred by the inference device 30. As a result, the programming support device 1 can display the proposal of the difference source code that complements the source code of the program being changed on the screen of the display device 2.

When the source code of the program is changed, it is generally necessary to modify a plurality of parts. In this case, the programming support device 1 extracts a plurality of differences from the template source code as the difference source code. .. In this case as well, the programming support device 1 can prevent omission of correction of the source code by displaying the difference source code that complements the source code of the program.

An existing source code may be input to the source code input unit 60 of the programming support device 1. In this case as well, the difference extraction device 40 extracts the difference between the source code acquired by the source code input unit 60 and the template source code inferred by the inference device 30. Then, the source code output unit 70 displays the proposal of the difference source code that complements the existing source code on the screen of the display device 2. The existing source code is the second source code. Further, the used function setting corresponding to the existing source code is the second used function setting, and the used device setting corresponding to the existing source code is the second used device setting.

As described above, according to the second embodiment, the programming support device 1 causes the display device 2 to display the difference between the source code being changed or the existing source code and the template source code as the difference source code. Therefore, the programming support device 1 can propose to the user a difference source code that is in the process of being changed or that complements the existing source code.

The configuration shown in the above embodiments is an example, and can be combined with another known technique, can be combined with each other, and does not deviate from the gist. It is also possible to omit or change a part of the configuration.

1 Programming support device, 2 Display device, 10 Learning device, 11, 31 Data acquisition unit, 12 Model generation unit, 13 Template source code generation unit, 21 Learned model storage unit, 22 Template source code storage unit, 30 Inference device, 32 Inference unit, 33 Template source code acquisition unit, 40 Difference extraction device, 50 Setting input unit, 60 Source code input unit, 70 Source code output unit, 100 processor, 200 memory, 300 input device, 400 output device.

Claims (8)

The source code input section where the first source code, which is the source code in the process of being created, input to the programming software is input, and
A setting input unit for inputting a first used device setting which is information on a device in which a program corresponding to the first source code is used, and a first used function setting which is information on a function used by the device. ,
A trained model that infers a template source code that is a template of the first source code from the combination information that is a combination of the first source code, the first used device setting, and the first used function setting. With an inference device that infers the template source code corresponding to the combination information,
A difference extraction device that extracts the difference between the first source code input to the source code input unit and the template source code inferred by the inference device as a difference source code.
The source code output unit that outputs the difference source code and
To prepare
A programming support device characterized by that. The inference device is
The data acquisition unit that acquires the combination information and
An inference unit that infers the template source code corresponding to the combination information using the trained model.
Have,
The programming support device according to claim 1. The source code output unit outputs the first source code together with the difference source code.
The programming support device according to claim 1 or 2. The inference device infers the program group number, which is the number of the group to which the program corresponding to the first source code belongs, from the combination information using the trained model, and the inference device corresponds to the program group number. Inferring the difference source code by extracting the difference source code,
The programming support device according to any one of claims 1 to 3, wherein the programming support device is characterized by the above. A second source code, which is an existing source code created, is input to the source code input unit, and the second source code corresponding to the second source code is set to the setting input unit, and the second source code is set. When the second function setting corresponding to the source code of 2 is input,
The inference device infers the template source code corresponding to the combination of the second source code, the second used device setting, and the second used function setting by using the trained model.
The programming support device according to any one of claims 1 to 4, characterized in that. The first source code is a source code in the process of being newly created or changed.
The programming support device according to any one of claims 1 to 3, wherein the programming support device is characterized by the above. A source code input step in which the programming support device that supports programming accepts the first source code, which is the source code in the process of being created, input to the programming software.
The programming support device accepts a first used device setting which is information on a device in which a program corresponding to the first source code is used, and a first used function setting which is information on a function used by the device. Setting input step and
The template source code, which is a template of the first source code, from the combination information in which the programming support device is a combination of the first source code, the first used device setting, and the first used function setting. An inference step that infers the template source code corresponding to the combination information using a trained model that infers
A difference extraction step of extracting the difference between the first source code received by the programming support device and the inferred template source code as a difference source code.
The source code output step in which the programming support device outputs the difference source code, and
including,
A programming support method characterized by that. A source code input step that accepts the first source code, which is the source code in the process of being created, input to the programming software.
A setting input step for accepting a first used device setting which is information on a device in which a program corresponding to the first source code is used, and a first used function setting which is information on a function used by the device.
A trained model that infers a template source code that is a template of the first source code from the combination information that is a combination of the first source code, the first used device setting, and the first used function setting. Inference step to infer the template source code corresponding to the combination information using
A difference extraction step for extracting the difference between the received first source code and the inferred template source code as a difference source code.
The source code output step that outputs the difference source code, and
A programming support program characterized by having a computer execute.

Images