Work support system, work support method, and program

Abstract

To improve user convenience.SOLUTION: A work support system (1) provided herein is capable of supporting work of users with no-code or low-code. An extension content information acquisition unit (201) acquires extension content information regarding extension content of a work support function in the work support system (1) based on user input. A code generation unit (206) generates code for extension of the work support function based on the extension content information and AI. A provision unit (207) provides the code to a user.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present disclosure relates to a business support system, a business support method, and a program. [Background technology]

[0002] Conventionally, there are known technologies that can support user work with no-code or low-code. For example, Patent Document 1 describes an automatic code generation system that acquires text data from documents or conversations, extracts contexts by natural language analysis of the acquired text data, and generates one or more programs according to the extracted contexts by referring to a code database in which one or more codes are associated with each context and stored, a program grammar analysis database in which grammar books for programming languages ​​are recorded, and an automatic program generation knowledge database in which programs that have been made efficient for processing operations to be realized are associated.

[0003] For example, Patent Document 2 describes a website creation support device that uses text data in which a user describes the contents of a target website to be created in natural language as input to a large-scale language model, derives source code for the target website using the large-scale language model, uses the source code to present the user with a preview of the target website when displayed on a web browser, determines the URL of the target website in response to a user operation specifying the URL, and publishes the target website on the Internet by uploading the source code to a rental server that is associated with the URL and for which the user has an account. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2023-018851 [Patent Document 2] Patent No. 7378003 Summary of the Invention [Problem to be solved by the invention]

[0005] However, while the technology of Patent Document 1 can automatically generate code using a database such as a code database, it does not generate code for expanding the functionality of a business support system that can support users' business operations with no code or low code. Similarly, the technology of Patent Document 2 can automatically generate code using a large-scale language model, but it does not generate code for expanding the functionality of the business support system. For this reason, the conventional technology has not been able to improve the convenience of users who use the business support system.

[0006] One of the purposes of the present disclosure is to improve user convenience. [Means for solving the problem]

[0007] A business support system according to one aspect of the present disclosure is a business support system capable of supporting a user's business with no-code or low-code, and includes an extension content information acquisition unit that acquires extension content information regarding extension content of a business support function in the business support system based on input from the user, a code generation unit that generates code for extending the business support function based on the extension content information and AI, and a provision unit that provides the code to the user. [Effects of the Invention]

[0008] According to the present disclosure, it is possible to improve convenience for users. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 illustrates an example of a hardware configuration of a business support system. [Figure 2] FIG. 10 is a diagram illustrating an example of a business support screen displayed on a user terminal. [Figure 3] FIG. 10 is a diagram illustrating an example of a business support screen displayed on a user terminal. [Figure 4] FIG. 2 is a diagram illustrating an example of functions realized by the business support system. [Figure 5] FIG. 10 is a diagram illustrating an example of a template database. [Figure 6] FIG. 1 is a diagram illustrating an example of AI used in code generation. [Figure 7] FIG. 10 is a diagram illustrating an example of a business support database. [Figure 8] FIG. 2 is a diagram illustrating an example of processing executed in the business support system. [Figure 9] FIG. 10 is a diagram illustrating an example of functions realized by a modified example of a business support system. [Figure 10] FIG. 10 is a diagram illustrating an example of a process for modifying a code. [Figure 11] FIG. 11 is a diagram showing an example of a business support screen according to a third modified example. DETAILED DESCRIPTION OF THE INVENTION

[0010] [1. Hardware configuration] An example of an embodiment of a business support system, a business support method, and a program according to the present disclosure will be described. FIG. 1 is a diagram illustrating an example of the hardware configuration of the business support system. For example, the business support system 1 includes a voice conversion server 10, a code generation server 20, a business support server 30, and a user terminal 40. Each of the voice conversion server 10, the code generation server 20, the business support server 30, and the user terminal 40 is connected to a network N such as the Internet or a LAN. While FIG. 1 illustrates one of each of the voice conversion server 10, the code generation server 20, the business support server 30, and the user terminal 40, there may be multiple of at least one of these.

[0011] The voice conversion server 10 is a server computer that executes the voice conversion process described below. For example, the voice conversion server 10 includes a control unit 11, a storage unit 12, and a communication unit 13. The control unit 11 includes at least one processor. The storage unit 12 includes at least one of a volatile memory such as 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.

[0012] The code generation server 20 is a server computer that executes the code generation process described below. For example, the code generation 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 similar to those of the control unit 11, the storage unit 12, and the communication unit 13, respectively.

[0013] The business support server 30 is a server computer that executes business support processing described below. For example, the business support server 30 includes a control unit 31, a storage unit 32, and a communication unit 33. The hardware configurations of the control unit 31, the storage unit 32, and the communication unit 33 may be similar to those of the control unit 11, the storage unit 12, and the communication unit 13, respectively.

[0014] The user terminal 40 is a user's computer. For example, the user terminal 40 is a personal computer, a tablet terminal, a smartphone, or a wearable terminal. The user terminal 40 includes a control unit 41, a memory unit 42, a communication unit 43, an operation unit 44, a display unit 45, an audio input unit 46, and an audio output unit 47. The hardware configurations of the control unit 41, the memory unit 42, and the communication unit 43 may be similar to those of the control unit 11, the memory unit 12, and the communication unit 13, respectively. The operation unit 44 includes an input device such as a mouse or a touch panel. The display unit 45 includes an LCD or organic EL display. The audio input unit 46 includes at least one microphone. The audio output unit 47 includes at least one speaker.

[0015] The programs stored in the storage units 12, 22, 32, and 42 may be supplied via the network N. The hardware configurations of the voice conversion server 10, the code generation server 20, the business support server 30, and the user terminal 40 are not limited to the example shown in FIG. 1 . For example, at least one of the voice conversion server 10, the code generation server 20, the business support server 30, and the user terminal 40 may include at least one of a reading unit (e.g., a memory card slot) that reads a computer-readable information storage medium and an input / output unit (e.g., a USB terminal) for direct connection to an external device. The programs stored in the information storage medium may be supplied to at least one of the voice conversion server 10, the code generation server 20, the business support server 30, and the user terminal 40 via at least one of the reading unit and the input / output unit.

[0016] Furthermore, the business support system 1 only needs to include at least one computer. The computers included in the business support system 1 are not limited to the example of FIG. 1. For example, the business support system 1 may include only the code generation server 20 and the business support server 30. In this case, the voice conversion server 10 and the user terminal 40 exist outside the business support system 1. The business support system 1 may also include only the code generation server 20. In this case, the voice conversion server 10, the business support server 30, and the user terminal 40 exist outside the business support system 1. The business support system 1 may also include the code generation server 20 and other server computers.

[0017] [2. Overview of the business support system] In this embodiment, the business support system 1 can support the user's business with no-code or low-code. No-code means that the user does not input any code. In other words, no-code means that the user does not need to input any code to use the business support system 1. Low-code means that the user inputs only the minimum necessary code. In other words, the user only needs to input the minimum necessary code to use the business support system 1.

[0018] Code is an instruction for a computer. In other words, code is information that enables a computer to understand a user's instructions. The code may be any code used in the field of computer software. For example, the code may be programming language code, CSS (Cascading Style Sheets) code, database language code, markup language code, or other code. Programming languages ​​also include languages ​​known as scripting languages. The code in this embodiment may be any of the various types of code that those skilled in the computer software field would call code.

[0019] The business support system 1 being able to support the user's business with no code means that the business support system 1 can execute the business support process described below based on pre-prepared code without the user having to enter any code. The business support system 1 being able to support the user's business with low code means that if the user enters only the minimum necessary code, the business support system 1 can execute the business support process described below based on the minimum necessary code entered by the user and the pre-prepared code.

[0020] The meanings of the terms no-code and low-code may be those generally known. A person skilled in the field of computer software can understand the meanings of no-code and low-code based on the common general technical knowledge at the time of filing. No-code and low-code may have a well-known meaning that can be understood by a person skilled in the art based on the common general technical knowledge at the time of filing. For example, the minimum amount of code required for low-code may be an amount that can be understood by a person skilled in the art based on the common general technical knowledge at the time of filing. For example, the minimum amount of code required for low-code may be approximately 1 to 100 lines, or may be 101 lines or more.

[0021] For example, the business support system 1 has various business support functions for supporting a user's business. The business support functions are functions realized by a program developed for business support. The types of business support functions may be known. For example, the business support functions may be a database function for a user to store data in a database, a communication function for a user to communicate with other users, a schedule function for a user to manage a schedule, an email management function for a user to manage emails, or other functions.

[0022] In this embodiment, the business support system 1 provides a cloud-based groupware to the user as an example. The business support system 1 may also provide an on-premise groupware to the user. The business support system 1 may also provide a service to the user that supports business operations but is not classified as groupware. For example, an organization such as a company to which the user belongs contracts with the business support system 1. As a member of the organization, the user uses the business support functions of the business support system 1. When the user logs in to the business support system 1 from the browser of the user terminal 40, the user terminal 40 displays a business support screen on the display unit 45, which allows the user to use the business support functions. The business support screen may be displayed on a program dedicated to the business support system 1, rather than on a browser.

[0023] 2 and 3 are diagrams showing an example of a business support screen displayed on the user terminal 40. In this embodiment, a case where a user uses a database function is taken as an example. For example, the user uses an app, which is a type of database. The user can store any data related to the user's business in the app. For example, the user can store not only data stored in the app's fields but also other data in the app. For example, the user can store comments to other users, files such as documents or images, or other data in the app. The app can also be said to have a complex business support function that not only has a database function but also a communication function, a file management function, and the like.

[0024] For example, when a user selects an app, the user terminal 40 displays a business support screen SC on the display unit 45, which shows a list L of records, which are units of data that make up the app, as shown in the upper part of FIG. 2. In the example in the upper part of FIG. 2, records of a minutes management app in which the user manages minutes are shown in list L. When the user selects a record in list L, the user terminal 40 displays details of the record on the business support screen SC. For example, the user can update the record from the business support screen SC.

[0025] In this embodiment, a user can create an app with no-code or low-code. For example, a user can create an app without entering code by performing simple configuration tasks such as field settings. A user can use a pre-prepared default app without performing configuration tasks. A user can expand the business support functions of an app by entering the minimum necessary code. In other words, a user can create a low-code app by expanding the business support functions of an app created with no-code. Expanding business support functions can also be called customizing the business support functions.

[0026] For example, a user may extend the functionality of an app by inputting a script to be executed in a browser on the user terminal 40. A script is code written in a scripting language. A user may extend the functionality of an app by inputting CSS (Cascading Style Sheets) code. The business support system 1 may also support other codes besides scripts and CSS. If a user tries to extend the functionality of an app by inputting such codes, the user needs to have some knowledge of codes. Even if the user has knowledge of codes, it is time-consuming to input the codes.

[0027] Therefore, the business support system 1 of this embodiment has a code generation function in which AI (Artificial Intelligence) generates code so that users can easily expand the functions of an app. The code generation function may be a default function of the business support system 1 (a function that all users can use from the beginning), but in this embodiment, it is a plug-in that users can add at their discretion. A user who wishes to use the code generation function adds the code generation function using a plug-in. A plug-in is a collection of programs and data for the code generation function. When a user adds a plug-in, the user can use the programs and data for the code generation function.

[0028] AI is a program with artificial intelligence that assists users in their work. There are various definitions of AI, and the AI ​​of this embodiment may be AI defined by various known definitions. The AI ​​may be AI called generative AI or conversational AI. For example, the AI ​​may be a large-scale language model, a machine learning model not classified as a large-scale language model, a program called a bot, or other programs. There are various definitions of machine learning, and the machine learning of this embodiment may be machine learning defined by various known definitions. The machine learning may be any of supervised learning, semi-supervised learning, and unsupervised learning.

[0029] In this embodiment, a case where a large-scale language model corresponds to an AI will be described as an example. Furthermore, as an example of code generated by an AI, a script (e.g., JAVASCRIPT (registered trademark)) executed in a browser of the user terminal 40 will be described. For example, a user may use text (characters) or voice to give instructions to the AI. In the example shown in the upper part of FIG. 2, the user selects icon I to start voice input and speaks the content of the function they want to expand in the app. When the voice input unit 46 detects the user's voice, the user terminal 40 executes a process to convert the user's voice into text with the voice conversion server 10. Once the user's voice is converted into text, the user terminal 40 displays the text in an input form F, as shown in the lower part of FIG. 2. If the text is incorrect, the user can correct the text by operating the operation unit 44. The user can also manually input text into the input form F without using voice input.

[0030] In the example at the bottom of Figure 2, the user gives an instruction such as "Create a function to color the record with the oldest meeting date green." For example, in order for the business support system 1 to expand the functionality of the app to meet the user's instruction, it needs to generate code that indicates the process of identifying the record with the oldest meeting date and the process of changing the color of that record. The business support system 1 causes the AI ​​to generate the code. For example, when the user selects button B, the code generation server 20 causes the AI ​​to generate code according to the user's instruction. As shown at the top of Figure 3, the business support screen SC enters a state waiting for code generation. The instruction entered by the user is displayed in display area A of the business support screen SC.

[0031] For example, when the code generation server 20 causes an AI to generate code, the business support server 30 deploys the code generated by the AI. If the code generated by the AI ​​is a script to be executed in the browser of the user terminal 40, the user terminal 40 receives the code from the business support server 30 and executes the code in the browser. If the AI ​​generates code that meets the user's wishes, the user terminal 40 can execute the code to color the record with the oldest meeting date green among the records displayed in the list L, as shown in the lower part of Figure 3. The response from the AI ​​is displayed in the display area A of the business support screen SC. When the user performs an operation to end the code generation, the code generated by the AI ​​is reflected in the app. If the user does not perform the operation, the code generated by the AI ​​is discarded.

[0032] As described above, when a user inputs an instruction to an AI to expand the business support function of an app, the business support system 1 causes the AI ​​to generate code for expanding the business support function. The business support system 1 realizes the function expansion according to the user's wishes based on the code generated by the AI. Since the user can expand the business support function of an app by inputting an instruction in natural language without inputting code, the business support system 1 can improve user convenience. Details of the business support system 1 will be explained below.

[0033] [3. Functions realized by the business support system] FIG. 4 is a diagram showing an example of functions realized by the business support system 1. As shown in FIG.

[0034] [3-1. Functions realized by the voice conversion server] For example, the voice conversion server 10 includes a data storage unit 100 and a voice conversion unit 101. The data storage unit 100 is realized by a storage unit 12. The voice conversion unit 101 is realized by a control unit 11. Note that if voice input is not performed, the business support system 1 does not need to include the voice conversion server 10.

[0035] [Data storage section] The data storage unit 100 stores data necessary for the speech conversion process. For example, the data storage unit 100 stores a speech conversion program that indicates the speech conversion process. The speech conversion process is at least one of a process of converting speech to text and a process of converting text to speech. In this embodiment, an example is given in which the speech conversion process includes both of these processes, but the speech conversion process may include only one of these processes. A speech conversion program for converting speech to text and a speech conversion program for converting text to speech may be separate programs. The speech conversion program may be a known program. For example, the speech conversion program may be a program using a pattern matching method that utilizes speech waveform patterns, a machine learning method, or other methods.

[0036] [Voice conversion section] The speech conversion unit 101 executes speech conversion processing based on a speech conversion program. For example, the speech conversion server 10 acquires input speech data indicating speech input by a user from a user terminal 40. The data format of the input speech data may be a known format. The speech conversion unit 101 converts the speech input by the user into text based on the speech data and the speech conversion program. The speech conversion unit 101 transmits input text data indicating the text of the speech input by the user to the user terminal 40. The speech conversion unit 101 may transmit the input text data to the code generation server 20, the business support server 30, or another computer.

[0037] For example, the speech conversion unit 101 acquires answer text data indicating the text of an answer from the AI ​​from the code generation server 20, the business support server 30, or another computer. The speech conversion unit 101 converts the text of the answer from the AI ​​into speech based on the answer text data and a speech conversion program. The speech conversion unit 101 transmits answer voice data indicating the speech of the text of the answer from the AI ​​to the user terminal 40. The user terminal 40 acquires the answer voice data from the speech conversion server 10. The user terminal 40 outputs the answer from the AI ​​as voice from the voice output unit 47 based on the answer voice data. The user terminal 40 may acquire the answer text data from the speech conversion server 10, the code generation server 20, the business support server 30, or another computer. The user terminal 40 may display the answer from the AI ​​in the display area A of the business support screen SC based on the answer text data.

[0038] [3-2. Functions realized by the code generation server] For example, the code generation server 20 includes a data storage unit 200, an extension content information acquisition unit 201, a function setting information acquisition unit 202, a template code acquisition unit 203, a specification information acquisition unit 204, a default prompt acquisition unit 205, a code generation unit 206, and a providing unit 207. The data storage unit 200 is realized by the memory unit 22. The extension content information acquisition unit 201, the function setting information acquisition unit 202, the template code acquisition unit 203, the specification information acquisition unit 204, the default prompt acquisition unit 205, the code generation unit 206, and the providing unit 207 are each realized by the control unit 21.

[0039] [Data storage section] The data storage unit 200 stores data necessary for the code generation process. For example, the data storage unit 200 stores a template database DB1.

[0040] FIG. 5 is a diagram showing an example of the template database DB1. For example, the template database DB1 stores indexes used in searching for template codes and template codes. The index is information referenced when searching for a template code. In this embodiment, an example is given in which vector information (embedded expression) indicating the meaning of text in natural language is used as the index. The vector information may be acquired by a known method (for example, Word2Vec or FastText). The vector information may be an embedded expression calculated based on the template code by an AI that generates code.

[0041] In this embodiment, an index associated with a template code is vector information of the extension content of the function extended by the template code (i.e., the content of the function realized by the process indicated by the template code). For example, a template code indicating a process to change the background color of a record stores vector information of text such as "This is the code to change the background color of the record" as an index. A template code indicating a process to change the font size of a record stores vector information of text such as "This is the code to change the font size of the record" as an index.

[0042] The vector information may be any information used in searching for template codes. The vector information may not be the above-described information in which text has been vectorized, but may be information in which the template code itself has been vectorized. The index is not limited to vector information. The index may be any information that is referenced during a search. For example, the index may be information in a format other than a vector. For example, the index may be an array, a matrix, a single number, a combination of multiple numbers, or other information that indicates meaning in natural language. The index may be text that describes the template code, keywords related to the template code, a category to which the template code belongs, or other information.

[0043] The template code is a code prepared in advance. In this embodiment, an example is given in which the business operator operating the business support system 1 prepares the template code, but the template code may be prepared by any party. For example, a user may prepare the template code. The template code may be shared between users. The template code may also be prepared by another business operator cooperating with the business operator operating the business support system 1. The template code associated with a certain index is a code for realizing an extension of the function indicated by the index. The template code indicates the processing for the extension content of the function.

[0044] For example, if text vector information such as "This is the code to change the background color of the record" is stored as an index, the template code associated with the index indicates a process to change the background color of the record (a process to identify a specific HTML element and change the style of that element). The template code includes a style tag that sets the color of the page to a specified color and a function for calling the style tag. If text vector information such as "This is the code to change the font size of the record" is stored as an index, the template code associated with the index indicates a process to change the font size of the record (a process to identify a specific HTML element and change the size of that element). The template code includes a style tag that sets the font size of the page to a specified size and a function for calling the style tag.

[0045] The data stored in the data storage unit 200 is not limited to the above example. The data storage unit 200 can store any data. In this embodiment, an example is given in which the code generation server 20 uses an AI of an external service that cooperates with the business support system 1, so the data storage unit 200 does not store the AI ​​itself, but the data storage unit 200 may store the AI ​​itself. That is, in this embodiment, an example is given in which the actual data of the AI ​​is stored in the system of another service, but the data storage unit 200 may store the actual data of the AI.

[0046] FIG. 6 is a diagram showing an example of AI used in code generation. For example, the AI ​​includes a program that indicates a series of processes such as calculating an embedded representation, and parameters referenced by the program. The embedded representation is information that enables the AI ​​to understand the meaning of data. For example, the embedded representation is expressed as a multidimensional vector. The embedded representation is also sometimes called a feature that indicates the characteristics of the data. The embedded representation may be expressed in a format other than a multidimensional vector. The AI ​​may include other data other than the parameters (for example, data equivalent to a dictionary of terms). The other data is referenced by the program. The other data may be data separate from the AI. The AI ​​calculates an embedded representation of input data input to itself based on the parameters, and produces output according to the embedded representation. For example, the parameters are weights and biases.

[0047] The AI ​​programs and parameters may be publicly known programs and parameters. For example, the AI ​​programs and parameters may be programs and parameters used in large-scale language models such as GPT (Generative Pre-trained Transformer) or BERT (Bidirectional Encoder Representations from Transformers), programs and parameters used in machine learning models such as neural networks or GANs (Generative Adversarial Networks), programs and parameters used in generative AI or interactive AI that do not fall into these categories, or other programs and parameters. The AI ​​programs and parameters may be various programs and parameters that a person skilled in the computer software field would understand based on the common general technical knowledge at the time of filing.

[0048] In this embodiment, a large-scale language model (e.g., GPT) will be described as an example of AI, and therefore the AI ​​program refers to a process of analyzing input data input to the AI. AI parameters are parameters such as weights and biases that the AI ​​refers to in order to analyze the meaning of natural language. The AI ​​performs language analysis of the input data input to itself based on the parameters adjusted through learning, and outputs according to the results of the language analysis. For example, the AI ​​divides the natural language text represented by the input data into multiple tokens. The AI ​​calculates embedded expressions that indicate the meaning of each token based on the parameters. The AI ​​understands the meaning of natural language based on the order of the embedded expressions of each token. The AI ​​may make predictions according to the order of the embedded expressions of each token, as necessary. The AI ​​outputs output data according to the order of the embedded expressions.

[0049] In this embodiment, an example is given in which various codes have been learned by the AI. The AI ​​may only learn codes that the business support system 1 can handle (e.g., JAVASCRIPT (registered trademark)), but in this embodiment, it is assumed that other codes have also been learned. The AI ​​may be able to handle codes in various languages. For example, output data from the AI ​​may differ depending on the input data. If the input data is a question, the output data indicates an answer to the question. If the input data is an instruction to generate code, the output data includes the code. In this case, the output data may include not only the code but also an explanation of the code. The output data may include any type of information.

[0050] As shown in FIG. 6, in this embodiment, an example is given in which input data to an AI includes extended content information, function setting information, template code, specification information, and a default prompt. Details of this information included in the input data will be described later. The input data only needs to include at least extended content information. The input data is not limited to the example of this embodiment. For example, at least one of function setting information, template code, specification information, and default prompt does not need to be included in the input data. The output data from the AI ​​is code. The output data may include code and information other than code (for example, a response from the AI). The output data from the AI ​​may not be code, but may be intermediate code used to generate code that is ultimately provided to the user.

[0051] [Extended content information acquisition section] The extended content information acquisition unit 201 acquires extended content information relating to the extended content of the business support function in the business support system 1 based on the user's input. In this embodiment, an example is given in which the user inputs voice from the voice input unit 46, but the user may also input from the operation unit 44. For example, the user may input instructions to the AI ​​from the operation unit 44. The user may also input by selecting a part (for example, an image such as a button or a check box) as a user interface.

[0052] The extended content information is an instruction to the AI. The extended content information can also be referred to as the user's intention. The extended content information is sometimes called a prompt for the AI. Information included in the input data other than the extended content information can also be referred to as supplementary information input to the AI ​​along with the prompt. There are various definitions of the word "prompt," but if information input to the AI ​​corresponds to a prompt, then information other than the extended content information also corresponds to a prompt. The definition of the word "prompt" may be any of various known definitions. In this embodiment, since AI is used to expand the business support function, the extended content information indicates the content of the business support function that the user desires to expand (the content of customization that the user desires). The extended content information is written in natural language, but may also be information in which the meaning of the natural language is vectorized.

[0053] In this embodiment, an example is taken of a case where the text entered into input form F when the user selects button B corresponds to the extended content information. Therefore, the extended content information is text indicating the specific content that the user desires to extend in the business support function. When the user selects button B, the user terminal 40 transmits the extended content information, which is the text entered into input form F, to the code generation server 20. The extended content information acquisition unit 201 acquires the extended content information from the user terminal 40. The extended content information acquisition unit 201 may acquire only one piece of extended content information, or may acquire multiple pieces of extended content information.

[0054] The extended content information may not be text in a natural language, but may be the voice input by the user. In this case, the extended content information acquisition unit 201 may acquire the extended content information, which is voice, from the user terminal 40 and then request the voice conversion server 10 to convert the extended content information into text. The extended content information acquisition unit 201 acquires the extended content information converted into text from the voice conversion server 10. In this embodiment, since the AI ​​is a large-scale language model, the information converted into text is input to the AI. The extended content information acquisition unit 201 may acquire the extended content information indirectly via the voice conversion server 10, the business support server 30, or another computer, rather than acquiring the extended content information directly from the user terminal 40.

[0055] [Function setting information acquisition section] The function setting information acquisition unit 202 acquires function setting information related to the settings of the business support function. The function setting information indicates the settings of the business support function to be expanded. In the examples of Figures 2 and 3, the database function of the app selected by the user corresponds to the business support function to be expanded. The app selected by the user is the app displayed on the business support screen SC when the expansion content information is acquired (in the examples of Figures 2 and 3, "minutes management app"). Therefore, the function setting information indicates the settings of the app selected by the user. The function setting information acquisition unit 202 may acquire only one piece of function setting information, or may acquire multiple pieces of function setting information.

[0056] In this embodiment, the setting data of the application selected by the user is stored in a business support database DB2, which will be described later, and therefore the function setting information acquisition unit 202 acquires at least one item of the setting data stored in the business support database DB2 as the function setting information. The function setting information acquisition unit 202 may acquire all items of the setting data as the function setting information, but in this embodiment, the function setting information acquisition unit 202 acquires, from the setting data, the setting items of the field of the application selected by the user as the function setting information. The function setting information acquisition unit 202 does not acquire other items of the setting data, such as access right settings, as the function setting information.

[0057] For example, when a user selects button B with text entered in input form F on the business support screen SC, the function setting information acquisition unit 202 acquires the application ID of the application selected by the user from the user terminal 40. The application ID is assumed to be included in the display data (e.g., HTML data) of the business support screen SC. The application ID may be included as part of the URL (e.g., an argument included in the link of button B). The function setting information acquisition unit 202 may acquire the application ID of the application to be extended in some way. The function setting information acquisition unit 202 may acquire the application ID of the application selected by the user from the speech conversion server 10, the business support server 30, or another computer.

[0058] For example, the function setting information acquisition unit 202 requests function setting information from the business support server 30 based on the application ID of the application selected by the user. The request includes the application ID. Upon receiving the request, the business support server 30 refers to the business support database DB2 and acquires setting data associated with the application ID. The business support server 30 acquires at least a portion of the setting data (for example, field setting items) as function setting information. The business support server 30 transmits the function setting information to the code generation server 20. The function setting information acquisition unit 202 acquires the function setting information from the business support server 30.

[0059] In the examples of Figures 2 and 3, the minutes management app selected by the user has seven fields: "Record Number," "Meeting Date," "Meeting Time," "Attendees," "Task," "Decisions," and "Next Steps." The function setting information acquisition unit 202 acquires function setting information including the field codes, field names, field types, and order of these seven fields, or a combination thereof. If other setting items exist as setting items for the fields, the function setting information acquisition unit 202 may acquire function setting information including the other setting items.

[0060] The function setting information may indicate settings corresponding to the business support function to be expanded. The function setting information is not limited to the example of this embodiment. For example, the function setting information may indicate settings other than the fields of the app. The function setting information may indicate the app name, notes for an administrator who manages the app, the layout of a form for users to input data, the display format of the list L, the format of a graph displayed based on data stored in the app, the app icon, other app designs, notification settings, access right settings, or other settings.

[0061] Furthermore, when the user extends a database function other than the application, the function setting information acquisition unit 202 may acquire function setting information indicating the settings of the other database function. When the user extends the communication function, the function setting information acquired may indicate the settings of the communication function (for example, settings for transcribing information such as thread names and thread comments, or the layout of threads).

[0062] For example, when a user extends the schedule function, the function setting information acquired indicates the settings of the schedule function (for example, the settings of users who will use the schedule function, the settings of facilities such as conference rooms to be reserved using the schedule function, or the layout of the schedule function screen). When a user extends the email management function, the function setting information acquired indicates the settings of the email management function (for example, the folder names for emails, the settings for sorting emails into folders, or the layout of the email function screen). It is assumed that this function setting information is stored in the business support database DB2.

[0063] [Template code acquisition section] The template code acquisition unit 203 acquires template codes related to business support functions that are prepared in advance. In this embodiment, the template codes are stored in the template database DB1, and therefore the template code acquisition unit 203 acquires the template codes from the template database DB1. The template code acquisition unit 203 may acquire the template codes from a database other than the template database DB1, a computer other than the code generation server 20, or an external information storage medium. The template code acquisition unit 203 may acquire only one template code, or may acquire multiple template codes.

[0064] In this embodiment, the template code acquisition unit 203 acquires a template code by searching a template database DB1, which stores multiple template codes, based on the extension content information. For example, the template code acquisition unit 203 uses the extension content information as a query to search the template database DB1. The template code acquisition unit 203 acquires template codes that are found in the search from among the template codes stored in the template database DB1. The search algorithm may be the same as an algorithm used in known search engines, etc.

[0065] For example, the template code acquisition unit 203 acquires vector information of the natural language text indicated by the extended content information. The vectorization of the natural language text may be performed by a known method (for example, Word2Vec or FastText). The template code acquisition unit 203 acquires a template code associated with vector information that is close in distance to the vector information of the natural language text indicated by the extended content information, from the vector information stored as an index in the template database DB1.

[0066] For example, the template code acquisition unit 203 may acquire a template code associated with vector information having the shortest distance to the vector information of the natural language text indicated by the extension content information. The template code acquisition unit 203 may acquire a template code associated with vector information whose distance from the vector information of the natural language text indicated by the extension content information is less than a threshold. The template code acquisition unit 203 may acquire a predetermined number of template codes in descending order of distance to the vector information of the natural language text indicated by the extension content information. By using the vector information as an index, the template code acquisition unit 203 can acquire a template code that meets the user's intention even if it does not match as a keyword, thereby enabling more flexible searches.

[0067] The method by which the template code acquisition unit 203 acquires a template code is not limited to the above example. The template code acquisition unit 203 may acquire a template code prepared in advance. For example, the template code acquisition unit 203 may acquire a template code by performing a search based on an index other than vector information (for example, a keyword). The template code acquisition unit 203 may acquire a template code prepared in advance without performing a search. For example, the template code acquisition unit 203 may acquire all of the template codes prepared in advance, or may acquire a randomly selected template code. The template code acquisition unit 203 may acquire a template code selected by the user from a plurality of template codes.

[0068] [Specification Information Acquisition Section] The specification information acquisition unit 204 acquires specification information regarding the specifications required for the code. The specifications required for the code are specifications established by the business operator that operates the business support system 1. The specifications required for the code can also be referred to as guidelines that define requirements for the code. For example, the specifications required for the code may be specifications for the API of the business support system 1, specifications specified in coding guidelines, specifications specified in security guidelines, specifications for character codes usable in the business support system 1, specifications for variables usable in the business support system 1, specifications for ID or class attributes, specifications for the description format of URLs, or other specifications. These specifications are assumed to be written in natural language, but the specifications written in natural language may also be vectorized.

[0069] The specification information may be information indicating the details of the specification. For example, the specification information may include text indicating the specifications required for the code. In other words, the specification information is information describing the details of the specification in natural language. The specification information may be in any format. For example, the specification information may be a text file, a rich text file, a document file, an HTML file, or other formats. The specification information may include other elements such as tables or figures in addition to text. In this embodiment, the data storage unit 200 stores the specification information. For example, the specification information acquisition unit 204 refers to the data storage unit 200 to acquire the specification information. The specification information acquisition unit 204 may acquire the specification information from a computer other than the code generation server 20 or from an external information storage medium. The specification information acquisition unit 204 may acquire only one piece of specification information or multiple pieces of specification information.

[0070] Note that specification information specific to each business support function may be prepared for that business support function. For example, specification information for the application, specification information for database functions other than the application, specification information for the communication function, specification information for the schedule function, and specification information for the email management function may be prepared separately from each other. The specification information acquisition unit 204 may acquire specification information for the business support function to be expanded from among the multiple business support functions.

[0071] [Default prompt acquisition section] The default prompt acquisition unit 205 acquires a default prompt related to code generation, which is a default prompt prepared in advance. In this embodiment, an example is given in which the default prompt is prepared by the business operator that operates the business support system 1, but the default prompt may be prepared by any party. For example, the user may prepare the default prompt, or another user in the organization to which the user belongs may prepare the default prompt. The default prompt may also be shared between users. The default prompt may also be prepared by another business operator that cooperates with the business operator that operates the business support system 1.

[0072] In this embodiment, the case where the data storage unit 200 stores a default prompt will be taken as an example. For example, the default prompt acquisition unit 205 refers to the data storage unit 200 and acquires the default prompt. The default prompt acquisition unit 205 may acquire the default prompt from a computer other than the code generation server 20 or from an external information storage medium. The default prompt acquisition unit 205 may acquire only one default prompt, or may acquire multiple default prompts. The default prompt acquisition unit 205 may acquire a default prompt from the multiple default prompts that corresponds to the extended content information.

[0073] For example, an AI may be able to generate code in various languages. On the other hand, the business support system 1 may only support a specific language (e.g., JAVASCRIPT (registered trademark)). In this case, the user may not specify the specific language. For this reason, a default prompt may be provided, which contains text indicating that the AI ​​will generate code in a specific language. This default prompt allows the AI ​​to identify the language in which code should be generated.

[0074] For example, the default prompt may be text indicating the role that the AI ​​should play, such as "You are an AI that helps users create code." Such a default prompt allows the AI ​​to identify the role that it should play. Another example of a default prompt may be text indicating that the AI ​​will provide some kind of response to the user along with the code, such as "Please explain the code you generated." Such a default prompt allows the AI ​​to identify that it should generate an answer to the user (e.g., an explanation of the code) along with the code.

[0075] For example, the default prompt may be text indicating what each of the extension content information, function setting information, template code, and specification information is. The default prompt may be text such as, "This information is extension content information indicating the extension content desired by the user. Please generate code that meets the user's wishes based on this information." Such a default prompt allows the AI ​​to identify that the extension content information indicates the user's wishes. Similarly, for each of the function setting information, template code, and specification information, the default prompt may be text indicating details of this information. Such a default prompt allows the AI ​​to identify how to use each of the function setting information, template code, and specification information.

[0076] [Code generation part] The code generation unit 206 executes a code generation process. The code generation process is a process for generating code. The code generation unit 206 generates code for extending the business support function based on the extension content information and the AI. For example, the code generation unit 206 inputs input data including the extension content information to the AI. In this embodiment, since the AI ​​is stored in an external system, the code generation unit 206 transmits the input data to the external system. When the AI ​​is stored in the data storage unit 200, the code generation unit 206 simply inputs the input data to the AI ​​stored in the data storage unit 200.

[0077] For example, the AI ​​calculates the embedding of input data based on parameters adjusted through prior learning. In this embodiment, a large-scale language model, such as GPT, corresponds to the AI. Therefore, the AI ​​divides the input data into tokens based on the parameters and calculates the embedding of each token. If necessary, the AI ​​predicts the next step based on the order of the embedded representations of the tokens. The AI ​​outputs code as output data based on the order. For example, the AI ​​may generate code based on a well-known function called a code interpreter, which generates code from the learning results of various languages. The AI ​​may output output data that includes not only the code but also the text of a response to the user. The code generation unit 206 generates code according to the extension content information by acquiring the code included in the output data output by the AI.

[0078] For example, the extension content information is obtained based on user input, and therefore indicates the extension content of the business support function desired by the user. In the examples of Figures 2 and 3, the extension content information indicates specific content, such as turning the oldest meeting date record green. AI can understand such extension content information through language analysis and generate code for extending the business support function to be extended. While the AI ​​generating code for functional extension of the no-code or low-code business support system 1 is a novel configuration at the time of filing, the technology itself for generating code based on prompts may be publicly known at the time of filing. Therefore, a person skilled in the art can understand the process of generating code by the AI ​​of this embodiment to the extent that it can be implemented based on the description of this embodiment and the common general technical knowledge at the time of filing.

[0079] In this embodiment, the code generation unit 206 generates code further based on the function setting information. For example, the code generation unit 206 inputs input data including extension content information and function setting information to the AI. The AI ​​calculates an embedded expression based on not only the extension content information but also the function setting information. The embedded expression reflects not only the extension content information but also the settings indicated by the function setting information. The AI ​​outputs output data including a code corresponding to the calculated embedded expression. The code generation unit 206 generates code corresponding to the function setting information by obtaining the code included in the output data output by the AI.

[0080] For example, if the function setting information indicates the setting items of a field in an app selected by a user, the AI ​​identifies which field to process based on the embedded expression corresponding to the setting items of the field indicated by the function setting information. The AI ​​generates code indicating the processing for the identified field. In the examples of Figures 2 and 3, the AI ​​identifies that processing is required for the meeting date field from the embedded expression corresponding to the extended content information. The AI ​​identifies that the app selected by the user has a meeting date field from the embedded expression corresponding to the function setting information, and determines that processing should be performed for that field. Based on these identification results, the AI ​​generates output data including code indicating the processing for the meeting date field.

[0081] In this embodiment, the code generation unit 206 generates code further based on the template code. For example, the code generation unit 206 inputs input data including extension content information and the template code to the AI. The AI ​​calculates an embedded expression based on not only the extension content information but also the template code. The embedded expression reflects not only the extension content information but also the settings indicated by the template code. The AI ​​outputs output data including code corresponding to the calculated embedded expression. The code generation unit 206 generates code corresponding to the template code by obtaining the code included in the output data output by the AI.

[0082] For example, when a template code corresponding to the extended content information is acquired, the code generation unit 206 roughly determines what kind of code should be generated based on the embedded expression corresponding to the template code corresponding to the extended content information. The AI ​​generates code corresponding to the extended content information based on the roughly determined code. In the examples of FIGS. 2 and 3, a template code indicating a process for changing the background color of a record is acquired. Based on the template code, the AI ​​roughly determines what kind of code is required to change the background color of the record, and generates output data including a code for changing the background color of the record with the oldest meeting date.

[0083] In this embodiment, the code generation unit 206 generates code further based on the specification information. For example, the code generation unit 206 inputs input data including the extended content information and the specification information to the AI. The AI ​​calculates an embedded expression based on not only the extended content information but also the specification information. The embedded expression reflects not only the extended content information but also the settings indicated by the specification information. The AI ​​outputs output data including a code corresponding to the calculated embedded expression. The code generation unit 206 generates code corresponding to the specification information by obtaining the code included in the output data output by the AI.

[0084] For example, if the specification information indicates the API specifications of the business support system 1, the code generation unit 206 determines what specifications of code to generate based on the embedded expression corresponding to the API specifications according to the specification information. The AI ​​generates code corresponding to the specification information based on the roughly determined specifications. In the examples of Figures 2 and 3, the business support function to be extended is an app, so the specification information indicates the API specifications of the app. The AI ​​determines the API specifications of the app based on the specification information and generates output data including code that satisfies the specifications.

[0085] In this embodiment, the code generation unit 206 generates code further based on the default prompt. For example, the code generation unit 206 inputs input data including extended content information and the default prompt to the AI. The AI ​​calculates an embedded expression based on not only the extended content information but also the default prompt. The embedded expression reflects not only the extended content information but also the settings indicated by the default prompt. The AI ​​outputs output data including a code corresponding to the calculated embedded expression. The code generation unit 206 generates code corresponding to the default prompt by obtaining the code included in the output data output by the AI.

[0086] For example, if the language of the code that the AI ​​should generate is indicated in the default prompt, the code generation unit 206 determines in which language the AI ​​should generate code based on the embedded expression corresponding to the default prompt. The AI ​​generates code in that language. In the examples of FIGS. 2 and 3, the code needs to be generated in a language that is executed on the browser of the user terminal 40, so the default prompt indicates that language. The AI ​​determines the language of the code that it should generate based on the default prompt and generates output data including code in that language.

[0087] The code generation unit 206 may generate a code based on input data including other information. For example, the code generation unit 206 may generate a code based on input data including not only function setting information of an app selected by the user but also data stored in the app's record. The code generation unit 206 may generate a code based on input data including user information about the user himself / herself. The user information may be a user profile, an organization to which the user belongs, or other information.

[0088] [Provider] The providing unit 207 provides the code to the user. Providing the code by the providing unit 207 means that the providing unit 207 transmits data indicating the code itself or data indicating the execution result of the code to the user terminal 40. The providing unit 207 may transmit this data directly to the user terminal 40, or may transmit this data indirectly via another computer such as the business support server 30. In this embodiment, since the code is executed on the browser of the user terminal 40, the providing unit 207 transmits data indicating the code itself (for example, HTML data including the code) to the user terminal 40 as an example.

[0089] In this embodiment, the code generated by the code generation unit 206 is deployed by the business support server 30 and then transmitted to the user terminal 40. Deploying is the deployment of the code to the business support function to be extended. In the examples of FIGS. 2 and 3, deploying is the deployment of the code to the application selected by the user. For example, the providing unit 207 requests the business support server 30 to deploy the code generated by the code generation unit 206. Upon receiving the deployment request, the business support server 30 deploys the code requested by the code generation server 20. For example, the business support server 30 performs deployment by embedding the code in display data (e.g., HTML data) of the business support screen SC. The code may be embedded at any position in the display data.

[0090] For example, the providing unit 207 provides the code to the user by executing a process for displaying a screen showing the code deployment results on the user terminal 40 of the user. The business support screen SC at the bottom of FIG. 3 is an example of a screen showing the code deployment results. Therefore, the description of the business support screen SC at the bottom of FIG. 3 can be replaced with a screen showing the code deployment results. The screen showing the code deployment results may be any screen for the business support function to be expanded. The deployment method itself may be a known method. For example, the business support server 30 may execute the code and send only data showing the execution results to the user terminal 40.

[0091] In the present embodiment, the case where the providing unit 207 requests the business support server 30 to deploy code is taken as an example; however, the providing unit 207 may request a computer other than the business support server 30 to deploy code. For example, if the user terminal 40 has a deployment function, the providing unit 207 may provide the code to the user by requesting the user terminal 40 to deploy the code. The providing unit 207 may deploy the code itself and provide the code to the user by causing the user terminal 40 to display a business support screen SC indicating the code deployment result. The providing unit 207 may provide the code to the user by simply transmitting data indicating the code to the user terminal 40 without particularly executing the deployment.

[0092] For example, once the user confirms that the functionality has been expanded in line with their wishes, they perform an operation to terminate code generation. In this case, the business support server 30 associates the code with the user and stores it in the data storage unit 300. From the next time onwards, the user can use the code stored in the data storage unit 300. For example, if the user again invokes an app for which a code was generated by AI, the display data of the business support screen SC of the app will include the code. The user can also modify or delete the code stored in the data storage unit 300.

[0093] [3-3. Functions realized by the business support server] For example, the business support server 30 includes a data storage unit 300 and a business support unit 301. The data storage unit 300 is realized by the storage unit 32. The business support unit 301 is realized by the control unit 31.

[0094] [Data storage section] The data storage unit 300 stores data necessary for business support processing. For example, the data storage unit 300 stores a business support database DB2 that stores various data of the business support system 1. In this embodiment, a situation in which a user extends the functions of an application is taken as an example, and therefore a case in which various data of the application is stored in the business support database DB2 is taken as an example.

[0095] 7 is a diagram showing an example of the business support database DB2. For example, the business support database DB2 stores an application ID, an application name, application setting data, and record data. The data stored in the business support database DB2 is not limited to the example shown in FIG. 7. For example, the business support database DB2 may store data other than applications (for example, data on threads through which users communicate with each other, schedule data, or email data).

[0096] The app ID is an ID that can identify an app. The app name is the name of the app, and the app setting data indicates the app settings specified by the user using no-code or low-code. For example, the app setting data may be the aforementioned field settings, graph settings, list L display settings, access rights settings, or other settings. Code generated by AI may be saved as part of the app setting data. The record data is data stored in a record. When a user creates a new app, data such as the app ID of the new app is stored in the business support database DB2. When a user updates an app, the data for that app in the business support database DB2 is updated.

[0097] The data stored in the data storage unit 300 is not limited to the above examples. The data storage unit 300 may store any data necessary for supporting business operations. For example, the data storage unit 300 may store data necessary for displaying the business support screen SC (e.g., HTML data or image data), or data necessary for deploying code (e.g., a deployment program).

[0098] [Business Support Department] The business support unit 301 executes business support processing to support a user's business. The business support processing is processing for providing a business support function to a user. For example, the business support processing is processing for displaying a business support screen SC on the user terminal 40. In this embodiment, since the function of the app is extended by the code generated by the code generation server 20, the business support processing may be processing for deploying the code generated by the AI ​​and displaying the result on the business support screen SC. Details of the processing for displaying the business support screen SC and the processing for deploying the code generated by the AI ​​are as described above.

[0099] [3-4. Functions implemented on user devices] For example, the user terminal 40 includes a data storage unit 400, a display control unit 401, and an operation reception unit 402. The data storage unit 400 is realized by the storage unit 42. The display control unit 401 and the operation reception unit 402 are each realized by the control unit 41.

[0100] [Data storage section] The data storage unit 400 stores data for business support. For example, the data storage unit 400 stores a browser for displaying various screens of the business support system 1. For example, the data storage unit 400 stores an application dedicated to the business support system 1. The data storage unit 400 stores display data for the business support screen SC.

[0101] [Display control section] The display control unit 401 causes the display unit 45 to display various screens in the business support system 1. For example, the display control unit 401 causes the display unit 45 to display a business support screen SC based on data received from the speech conversion server 10, the code generation server 20, or the business support server 30.

[0102] [Operation reception section] The operation reception unit 402 receives various operations in the business support system 1. For example, the operation reception unit 402 receives operations on the business support screen SC. Data indicating the operation content received by the operation reception unit 402 is transmitted to the voice conversion server 10, the code generation server 20, or the business support server 30 as appropriate.

[0103] [4. Processing performed by the business support system] FIG. 8 is a diagram showing an example of processing executed in the business support system 1. The processing of FIG. 8 is executed by the control units 11, 21, 31, and 41 executing programs stored in the storage units 12, 22, 32, and 42, respectively. Each processing of FIG. 8 is an example of processing included in a business support method. FIG. 8 shows an example of processing when a business support function of an app is extended. Note that in FIG. 8, the user terminal 40 may communicate indirectly with the speech conversion server 10 and the code generation server 20 via the business support server 30, rather than directly with each of them.

[0104] 8, the user terminal 40 executes processing with the business support server 30 to display a business support screen SC of an application selected by the user (S1). In S1, the business support server 30 generates display data for the business support screen SC of the application selected by the user based on the business support database DB2 and transmits the generated display data to the user terminal 40. Upon receiving the display data for the business support screen SC, the user terminal 40 displays the business support screen SC on the display unit 45. Thereafter, the user extends the business support functions of the application according to the flow shown in FIGS. 2 and 3.

[0105] When the user terminal 40 receives a voice input from the user via the voice input unit 46, it transmits input voice data indicating the voice input by the user to the voice conversion server 10 (S2). The voice conversion server 10 acquires the input voice data from the user terminal 40 (S3). The voice conversion server 10 executes a voice conversion process based on the voice conversion program and the input voice data (S4). The voice conversion server 10 transmits input text data indicating the text of the voice input by the user (S5). The user terminal 40 acquires the input text data from the voice conversion server 10 (S6).

[0106] When the user selects button B, the user terminal 40 transmits extension content information to the code generation server 20 (S7). In S7, the user terminal 40 requests the code generation server 20 to generate code. In S7, the application ID of the application to be extended is also transmitted. The code generation server 20 acquires the extension content information from the user terminal 40 (S8). The code generation server 20 executes processing to acquire function setting information with the business support server 30 (S9). In S9, the code generation server 20 transmits the application ID of the application to be extended to the business support server 30. The business support server 30 acquires function setting information required for code generation based on the application setting data associated with the application ID in the business support database DB2. The business support server 30 transmits the function setting information to the code generation server 20. The code generation server 20 acquires the function setting information from the business support server 30.

[0107] The code generation server 20 acquires template code based on the template database DB1 (S10). In S10, the code generation server 20 searches the template database DB1 based on the extension content information. The code generation server 20 acquires the template code found in the search. The code generation server 20 acquires specification information stored in the storage unit 22 (S11). The code generation server 20 acquires a default prompt stored in the storage unit 22 (S12). The code generation server 20 generates code based on input data including the information acquired in S8 to S12 and the AI ​​(S13). In S13, the code generation server 20 transmits the input data to an external system that manages the AI. The code generation server 20 acquires output data including the code generated by the AI ​​from the external system.

[0108] The code generation server 20 executes processing between the business support server 30 and the user terminal 40 to provide the code to the user (S14), and this processing ends. In S14, the code generation server 20 requests the business support server 30 to deploy the code generated in S13. The business support server 30 deploys the code and generates display data for the business support screen SC. The business support server 30 transmits the display data for the business support screen SC to the user terminal 40. Upon receiving the display data for the business support screen SC, the user terminal 40 executes the code included in the display data to display the business support screen SC on the display unit 45. If a voice output of the answer from the AI ​​is required, the voice conversion server 10 acquires data indicating the AI's answer from the code generation server 20 and executes processing to convert text to voice. The converted voice is output on the user terminal 40.

[0109] [5. Summary of embodiments] The business support system 1 of this embodiment can support a user's business with no-code or low-code. The business support system 1 acquires extension content information based on user input. The business support system 1 generates code for expanding the business support function based on the extension content information and AI. The business support system 1 provides the code to the user. This allows the user to expand the business support function by simply inputting information so that the business support system 1 can acquire the extension content information without having to enter code, thereby improving user convenience. For example, a user of the no-code or low-code business support system 1 may have little or no knowledge of code. The user can easily expand the business support function through the code generation process of the business support system 1 without acquiring knowledge of code. Even users with knowledge of code can avoid the hassle of entering code, so the business support system 1 can improve convenience for users with knowledge of code. For example, non-AI code generation tools may only provide limited functions to users and cannot meet the diverse needs of users. By utilizing AI, the business support system 1 can respond to a variety of user requests. The business support system 1 can generate code that can be customized to meet specific user requests.

[0110] The business support system 1 also acquires function setting information. The business support system 1 generates code based on the function setting information. This allows the business support system 1 to generate code according to not only the user's input but also the settings of the business support function to be extended. The business support system 1 generates code specific to the business support function the user is trying to extend, making it easier to generate code that meets the user's wishes. For example, in the examples of Figures 2 and 3, the business support system 1 can generate code according to the settings of fields, etc. of the app the user is trying to extend, making it easier to generate code that meets the user's wishes.

[0111] The business support system 1 also acquires a template code. The business support system 1 generates code based on the template code. This allows the business support system 1 to generate code that does not deviate from a predetermined format. For example, if the business support system 1 uses a general-purpose AI to generate code, there is a possibility that the system will generate code for a purpose other than business support. Since the AI ​​generates code based on the template code prepared in the business support system 1, it becomes easier to generate code for business support. In other words, the AI ​​can generate code according to the extended content information by referring to the template code. The business support system 1 becomes easier to generate code that meets the user's wishes.

[0112] Furthermore, the business support system 1 acquires the template code by searching a template database DB1 that stores multiple template codes based on the extended content information. This makes it easier for the business support system 1 to generate code that meets the user's wishes based on the template code corresponding to the extended content information. For example, the business support system 1 can search for a template code that meets the user's wishes and generate code based on the template code, making it easier to generate code that meets the user's wishes.

[0113] The business support system 1 also acquires specification information. The business support system 1 generates code further based on the specification information. This allows the business support system 1 to generate code that meets specifications specific to the business support system 1. For example, a general-purpose AI may generate general code regardless of the specifications specific to the business support system 1. The specification information allows the AI ​​to understand the specifications specific to the business support system 1, making it easier for the business support system 1 to generate code that meets the user's wishes. For example, the business support system 1 can generate code that meets security specifications, thereby reducing security risks.

[0114] The business support system 1 also acquires a default prompt. The business support system 1 generates a code further based on the default prompt. This allows the business support system 1 to generate a code after completing any missing items in the user's input with the default prompt. For example, even if the user does not input the language in which the AI ​​should generate a code, the business support system 1 can generate a code in that language by defining a specific language as the default prompt.

[0115] Furthermore, the business support system 1 provides the code to the user by executing a process for displaying a business support screen SC showing the code deployment results on the user terminal 40. This allows the business support system 1 to allow the user to check the code execution results, thereby improving user convenience. The business support system 1 can execute the process from code generation to deployment in a single flow, thereby accelerating the flow.

[0116] [6. Modifications] The present disclosure is not limited to the above-described embodiments, and may be modified as appropriate without departing from the spirit of the present disclosure.

[0117] Fig. 9 is a diagram showing an example of functions realized in the modified business support system 1. As shown in Fig. 11, the modified example described below realizes a correction content information acquisition unit 208, a correction portion code generation unit 209, a code correction unit 210, a completion content information acquisition unit 211, a display screen information acquisition unit 212, and a user attribute information acquisition unit 213. Each of the correction content information acquisition unit 208, the correction portion code generation unit 209, the code correction unit 210, the completion content information acquisition unit 211, the display screen information acquisition unit 212, and the user attribute information acquisition unit 213 is realized by the control unit 21.

[0118] [6-1. Variation 1] For example, there may be multiple extensions that the business support function needs to expand. In this case, the user may be able to specify the extension information to the AI ​​one after another. In Variation 1, as shown in Figures 2 and 3, an example is given in which, after a function that marks the oldest record as green is added to the app, a function that marks the newest record as red and a function that duplicates records that include a specific user as an attendee are added. The user will have to enter information three times in total.

[0119] The extended content information acquisition unit 201 of the first modification acquires extended content information each time the user makes a new input. For example, in the state of the business support screen SC shown at the bottom of FIG. 3, the user makes a voice input to color the record with the most recent conference date red. The AI ​​generates code for coloring the record with the most recent conference date red based on the extended content information corresponding to the user's voice input. Then, the user makes a voice input to duplicate a record with a specific user as attendees. The AI ​​generates code for duplicating a record with a specific user as attendees based on the extended content information corresponding to the user's voice input. In this way, the extended content information acquisition unit 201 acquires extended function information each time the user makes successive inputs.

[0120] The code generation unit 206 of Modification 1 generates a code further based on the history of extension content information. The history of extension content information is extension content information acquired based on past inputs. The history includes at least one item of extension content information. The history of extension content information is stored in the data storage unit 200. The code generation unit 206 acquires the history of extension content information stored in the data storage unit 200 and generates a code. The code generation unit 206 may acquire the history of extension content information from another computer such as the user terminal 40. Since there is no history of extension content information at the time of the user's first input, the code generation unit 206 generates a code based on the extension content information at the time of the first input. This process is as described in the embodiment. From the user's second input onwards, the code generation unit 206 generates a code further based on the history of extension content information.

[0121] For example, the code generation unit 206 inputs input data including new extension content information and the history of the extension content information to the AI. The AI ​​calculates an embedded expression based on not only the new extension content information but also the history of the extension content information. The embedded expression reflects not only the new extension content information but also the history of the extension content information. The AI ​​outputs output data including a code corresponding to the calculated embedded expression. The code generation unit 206 generates a code corresponding to the history by obtaining the code included in the output data output by the AI.

[0122] For example, at the time of the user's second input, the code generation unit 206 inputs to the AI ​​input data including new extension content information corresponding to the second input and extension content information at the time of the first input, which is a history of extension content information. At the time of the user's third input, the code generation unit 206 inputs to the AI ​​input data including new extension content information corresponding to the third input and extension content information at the time of each of the first and second inputs, which is a history of extension content information. Similarly, at the time of the user's fourth input and thereafter, the code generation unit 206 inputs to the AI ​​input data including new extension content information and a history of extension content information corresponding to the inputs up to that point. The code generation unit 206 acquires a code included in the output data from the AI.

[0123] The business support system 1 of the first modification acquires extended content information every time the user makes a new input. The business support system 1 generates a code further based on the history of the extended content information. This allows the business support system 1 to generate a code that takes into account not only the latest input made by the user but also past input made by the user, thereby improving user convenience. For example, when a user repeatedly inputs information, the user may omit information that was previously input. By utilizing the history of the extended content information, the business support system 1 can identify the information omitted by the user from the previous context and generate a code.

[0124] [6-2. Variation 2] For example, AI may not be able to generate code that meets the user's wishes in one try. For this reason, the user may be able to instruct the AI ​​to modify the code it has generated. In the examples of Figures 2 and 3, the user may instruct the AI ​​to modify the code from the business support screen SC at the bottom of Figure 3. In Variation 2, an example is given in which the user instructs the AI ​​to modify the code by voice input, but the user may instruct the AI ​​to modify the code by any other input method. For example, the user may instruct the AI ​​to modify the code by text input.

[0125] The user may explicitly instruct the business support system 1 to modify the code by voice input, text input, or other operation (for example, selecting the "Modify" button). The business support system 1 can specify that the generated code should be modified rather than new code should be generated based on the user's explicit instruction. The AI ​​may also infer that the code should be modified even without the business support user giving an explicit instruction. The AI ​​may specify that the generated code should be modified rather than new code should be generated based on the input data. The AI ​​can make such a specification using the embedded representation of the input data.

[0126] FIG. 10 is a diagram showing an example of a process for correcting code. The business support system 1 of the second modification includes a correction content information acquisition unit 208 and a corrected portion code generation unit 209. The correction content information acquisition unit 208 acquires correction content information regarding the correction content of the code based on a user's input. The correction content information is an instruction indicated by the user's input when correcting the code. The correction content information can also be said to be the user's intention when correcting. The correction content information is sometimes called a prompt for the AI. As shown in FIG. 10, when correcting, input data including the correction content information is input to the AI.

[0127] In the second modification, an example is taken of a case where the text entered into input form F when the user selects button B when correcting code corresponds to the correction content information. Therefore, the correction content information is text indicating the specific content of the code correction the user wishes to make. When the user selects button B, the user terminal 40 transmits the correction content information, which is the text entered into input form F, to the code generation server 20. The correction content information acquisition unit 208 acquires the correction content information from the user terminal 40. The correction content information acquisition unit 208 may acquire only one piece of correction content information, or may acquire multiple pieces of correction content information.

[0128] The correction content information may not be text in a natural language, but may be the voice input by the user. In this case, the correction content information acquisition unit 208 may acquire the correction content information in the form of voice from the user terminal 40, and then request the voice conversion server 10 to convert the correction content information into text. The correction content information acquisition unit 208 acquires the correction content information converted into text from the voice conversion server 10. The correction content information acquisition unit 208 may not acquire the correction content information directly from the user terminal 40, but may acquire the correction content information indirectly via the voice conversion server 10, the business support server 30, or another computer.

[0129] The modified portion code generation unit 209 generates modified portion code, which is code after modifying a portion of the code before modification that is modified according to the modification content, based on the modification content information and AI. The portion modified according to the modification content is a portion of the code before modification. The amount of the modified portion varies depending on the modification content. For example, the modified portion may be only one line or two or more lines. The modified portion may not be a sequence of lines. For example, out of 20 lines of code, the modified portions may be the third and tenth lines. The portion to be modified is determined by AI.

[0130] For example, the AI ​​outputs, along with the code of the corrected portion, correction portion information that can identify the corrected portion in the code before correction. The correction portion information can also be referred to as the position of the corrected portion in the code before correction. For example, the correction portion information indicates the line number of the corrected portion. A default prompt during correction may be provided, such as, "Please correct only the portion of the code before correction that needs to be corrected. Please output the corrected code for that portion and the identification information for that portion." This default prompt allows the AI ​​to more accurately understand that it is necessary to output the code of the corrected portion and the identification information for the corrected portion.

[0131] For example, the correction portion code generation unit 209 inputs input data including the code before correction and correction content information to the AI. In the example of Figure 10, the correction portion code generation unit 209 inputs input data further including a default prompt to the AI. The AI ​​calculates an embedded expression based on not only the correction content information but also the code before correction. The embedded expression reflects not only the correction content information but also the code before correction. The AI ​​outputs output data including the correction portion code and correction portion identification information corresponding to the calculated embedded expression. The code generation unit 206 acquires the correction portion code and correction portion identification information included in the output data output by the AI. In the example of Figure 10, only the part of line 20 of the code before correction is output from the AI ​​as the correction portion code. The correction portion identification information indicates that it is line 20.

[0132] The code correction unit 210 of the second modification corrects the code by replacing the correction portion of the code before correction with the correction portion code. The replacement can also be referred to as overwriting or changing. In the example of FIG. 10, line 20 of the code before correction is replaced with the correction portion code. For example, the code correction unit 210 replaces the correction portion of the code before correction indicated by the correction portion identification information with the correction portion code. The user may also specify the correction portion. For example, the user may input, "Please correct the code on line 20." In this case, the correction content information includes the correction portion identification information. The AI ​​does not need to output the correction portion identification information. Even if the AI ​​does not output the correction portion identification information, the code correction unit 210 can simply replace the correction portion input by the user with the correction portion code.

[0133] The business support system 1 of the second modification acquires correction content information based on a user's input. The business support system 1 generates a correction portion code based on the correction content information and an AI. The business support system 1 corrects the code by replacing the portion of the code to be corrected according to the correction content with the correction portion code. This enables the business support system 1 to streamline the user's work of correcting code, thereby improving user convenience during correction. For example, when an AI regenerates the entire code, there is a possibility that the generated code will show processing that is completely different from that before the correction. However, by replacing only the portion of the code before the correction with the correction portion code, the business support system 1 can prevent this from becoming a processing that is completely different from that before the correction, thereby improving the accuracy of the correction.

[0134] [6-3. Variation 3] For example, user input alone may not contain enough information to generate code. For example, if a user inputs something like "Create a function to change the record with the oldest meeting date," the user does not explicitly state what they want to change in the record. Recent advances in AI have made it known that AI can estimate and complete missing information when user input is insufficient. For example, large-scale language models, such as GPT, can sometimes estimate missing information by predicting the rest of the user's input. In the above example, the AI ​​may be able to complete the information to change the color. Such AI can generate code by estimating and completing the missing information, even if the user input is insufficient. On the other hand, AI may also perform inappropriate completion that does not meet the user's wishes. For this reason, when AI completes information, a message to that effect may be displayed on the business support screen SC.

[0135] The business support system 1 of the third modification includes a supplementary content information acquisition unit 211. When the AI ​​generates code by supplementing missing parts in the extended content information, the supplementary content information acquisition unit 211 acquires supplementary content information regarding the content supplemented by the AI. The supplementary content is information that is missing in the user's input. The supplementary content can also be said to be content that the AI ​​has estimated as the user's desire, even though the user did not explicitly input it. The AI ​​supplements the user's input by predicting the continuation of the natural language input by the user. The supplementary content can also be said to be the result of a prediction by the AI.

[0136] For example, as a default prompt in Modification Example 3, a prompt such as "If the user's input is insufficient, please complete the information yourself. Please output so that it is clear which information has been completed" may be provided. The AI ​​can output the completion content information using such a default prompt. The completion content information acquisition unit 211 acquires the completion content information output from the AI. The completion content information is expressed in text as an example, but may also be in audio or other formats.

[0137] FIG. 11 is a diagram showing an example of the business support screen SC of Modification Example 3. The providing unit 207 further provides the user with the supplemented content based on the supplemented content information. In the example of FIG. 11, since the AI ​​has supplemented the color, the providing unit 207 provides the supplemented content to the user by displaying the business support screen SC with a message indicating this in the display area A. In the example of FIG. 11, a message such as "We assume you wish to change the color. If not, please enter the correction details" corresponds to the stored content.

[0138] For example, the providing unit 207 transmits the completion content information to the business support server 30 and requests it to display the completion content. Upon receiving the request, the business support server 30 generates display data for the business support screen SC so that the completion content indicated by the completion content information is displayed on the business support screen SC. The business support server 30 transmits display data for the business support screen SC indicating the completion content to the user terminal 40. The user terminal 40 displays the business support screen SC as shown in FIG. 11 on the display unit 45 based on the display data. If the AI's completion content is as intended, the user ends code generation. If the AI's completion content is not as intended, the user corrects the code or starts code generation again from the beginning.

[0139] The business support system 1 of the third modification acquires the supplemented content information when the AI ​​supplements the missing part in the extended content information and generates code. The business support system 1 further provides the supplemented content to the user based on the supplemented content information. This allows the user to know the supplemented content supplemented by the AI, so the business support system 1 can improve user convenience. For example, if the supplemented content supplemented by the AI ​​is incorrect, that part needs to be corrected, so the user can easily understand which part to focus on and check.

[0140] [6-4. Variation 4] For example, the business support system 1 may further include a display screen information acquisition unit 212 that acquires display screen information related to a screen displayed on the user terminal 40 when a user input is made. The display screen information is information that can identify the screen currently displayed on the user terminal 40. The display screen information may be in any format, such as the URL of the currently displayed screen, an ID assigned to the currently displayed screen, a screenshot of the currently displayed screen, or other information. For example, the display screen information may be included in a request such as an HTTP request sent from the user terminal 40. The URL of the business support screen SC or a part of it may be used as the display screen information.

[0141] The code generation unit 206 of Variation 4 may generate code further based on display screen information. For example, the code generation unit 206 may input input data including display screen information to the AI. The AI ​​calculates an embedded expression based on not only the extended content information but also the display screen information. The embedded expression reflects not only the extended content information but also the characteristics of the display screen information. The AI ​​outputs output data including a code corresponding to the calculated embedded expression. The code generation unit 206 generates a code corresponding to the display screen information by obtaining the code included in the output data output by the AI.

[0142] Note that the display screen information may not be used by the code generation unit 206, but may be used by another function. For example, the specification information acquisition unit 204 may acquire the specification information described in the embodiment based on the display screen information. In the examples of FIGS. 2 and 3, the display screen information may indicate an application ID that can identify an application. The specification information acquisition unit 204 may acquire the specification information of the application indicated by the application ID based on the application ID indicated by the display screen information. The processing after the specification information acquisition unit 204 acquires the specification information is as described in the embodiment.

[0143] The business support system 1 of the fourth modification generates a code further based on the display screen information. This allows the business support system 1 to generate a code corresponding to the business support screen SC displayed on the user terminal 40. For example, the business support system 1 can generate a code specific to an app displayed on the business support screen SC. The business support system 1 can generate a code specific to the specifications of an app currently displayed on the business support screen SC. The business support system 1 can generate a code specific to a screenshot of the business support screen SC.

[0144] [6-5. Variation 5] For example, the business support system 1 may further include a user attribute information acquisition unit 213 that acquires user attribute information related to user attributes. The user attribute information is information that allows users to be classified. For example, the user attribute information may be the user's organization, organization size, department, job title, industry, profile, year of joining the company, age, gender, or other information. The user attribute information may also be information called demographic information.

[0145] In the fifth modification, an example is taken in which the data storage unit 300 of the business support server 30 stores a user database in which user attribute information is stored. The user attribute information acquisition unit 213 acquires the user attribute information from the user database. The user attribute information acquisition unit 213 may acquire the user attribute information from a database other than the user database, a computer other than the business support server 30 (for example, the code generation server 20), or an external information storage medium. A user may be able to edit his or her own user attribute information.

[0146] The code generation unit 206 of variant example 5 generates code further based on user attribute information. For example, the code generation unit 206 inputs input data including user attribute information to the AI. The AI ​​calculates an embedded expression based on not only the extended content information but also the user attribute information. The embedded expression reflects not only the extended content information but also the characteristics of the user attribute information. The AI ​​outputs output data including a code corresponding to the calculated embedded expression. The code generation unit 206 generates a code corresponding to the user attribute information by obtaining the code included in the output data output by the AI.

[0147] The business support system 1 of the fifth modification generates a code further based on user attribute information. This allows the business support system 1 to generate a code according to the user's attributes. For example, if a code suitable for supporting the business of a user who belongs to a large company is different from a code suitable for supporting the business of a user who belongs to a small or medium-sized company, the business support system 1 can generate a code according to the size of the organization to which the user belongs. If a code suitable for supporting the business of a user who works in the food and beverage industry is different from a code suitable for supporting the business of a user who works in the apparel industry, the business support system 1 can generate a code according to the industry in which the user works.

[0148] [6-6. Other Modifications] For example, two or more of the modifications 1 to 5 may be combined.

[0149] For example, a function described as being realized by the voice conversion server 10 may be realized by the code generation server 20, the business support server 30, or the user terminal 40. A function described as being realized by the code generation server 20 may be realized by the voice conversion server 10, the business support server 30, or the user terminal 40. A function described as being realized by the business support server 30 may be realized by the voice conversion server 10, the code generation server 20, or the user terminal 40. A function described as being realized by the user terminal 40 may be realized by the voice conversion server 10, the code generation server 20, or the business support server 30. Each function may be shared by multiple computers or may be realized by a single computer. [Explanation of symbols]

[0150] 1 Business support system, 10 Voice conversion server, 11, 21, 31, 41 Control unit, 12, 22, 32, 42 Memory unit, 13, 23, 33, 43 Communication unit, 20 Code generation server, 30 Business support server, 40 User terminal, 44 Operation unit, 45 Display unit, 46 Voice input unit, 47 Voice output unit, 100 Data storage unit, 101 Voice conversion unit, 200 Data storage unit, 201 Extended content information acquisition unit, 202 Function setting information acquisition unit, 203 Template code acquisition unit, 204 Specification information acquisition unit, 205 Default prompt acquisition unit, 206 Code generation unit, 207 Provision unit, 208 Correction content information acquisition unit, 209 Correction part code generation unit, 210 Code correction unit, 211 Complement content information acquisition unit, 212 Display screen information acquisition unit, 213 User attribute information acquisition unit, 300 Data storage unit, 301 business support unit, 400 data storage unit, 401 display control unit, 402 operation reception unit, A display area, B button, F input form, I icon, L list, N network, SC business support screen, DB1 template database, DB2 business support database.

Claims

[Claim 1] A business support system that can support user business operations with no-code or low-code, an extension information acquisition unit that acquires extension information related to extension contents of the business support function in the business support system based on the input from the user; a code generation unit that generates a code for extending the business support function based on the extension content information and AI; a providing unit that provides the code to the user; Business support system including.

Images