Work support system, work support method, and program

Abstract

To improve the convenience for a user who uses a communication tool for supporting work.SOLUTION: A posted data acquisition unit (101) of a work support system (1) acquires posted data indicating a post that has been made on a communication tool that supports work. A mention determination unit (102) determines, based on the posted data, whether a mention has been made on an artificial intelligence (AI). A prompt data acquisition unit (103) acquires prompt data indicating a prompt provided in advance. An answer data generation unit (104) causes, when it is determined that the mention has been made, the AI to generate answer data indicating an answer to the post based on the posted data and the prompt data. An answer display unit (105) displays the answer on the communication tool based on the answer data.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 Art

[0002] Conventionally, technologies for assisting users' operations using AI (Artificial Intelligence) such as large language models have been studied. For example, Patent Document 1 describes an interactive chatbot that searches a collection of multiple sentences to be searched based on a character string input by a user on an interaction screen for chatting between the user and a chatbot, which is an example of AI, and acquires and presents to the user one or more sentences of search results that match the character string.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the technology of Patent Document 1, when a user tries to search a collection of sentences using a chatbot while communicating with another user using a communication tool for assisting operations, the user needs to open a dedicated interaction screen and chat with the chatbot separately from the communication tool. Therefore, the technology of Patent Document 1 cannot sufficiently improve the convenience for the user.

[0005] One object of the present disclosure is to enhance the convenience of the user in a communication tool for assisting operations.

Means for Solving the Problems

[0006] A business support system according to an aspect of the present disclosure includes a posting data acquisition unit that acquires posting data indicating a posting made in a communication tool for supporting business, a mention determination unit that determines whether or not a mention of AI (Artificial Intelligence) has been made based on the posting data, a prompt data acquisition unit that acquires prompt data indicating a pre-prepared prompt, an answer data generation unit that causes the AI to generate answer data indicating an answer to the posting based on the posting data and the prompt data when it is determined that the mention has been made, and an answer display unit that displays the answer on the communication tool based on the answer data.

Effect of the Invention

[0007] According to the present disclosure, the convenience of users in a communication tool for supporting business can be improved.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Mode for Carrying Out the Invention

[0009] [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 showing an example of the hardware configuration of a business support system. For example, the business support system 1 includes a server 10 and a user terminal 20. Each of the server 10 and the user terminal 20 is connected to a network N such as the Internet or a LAN.

[0010] The server 10 is a server computer. For example, the 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 a RAM and a non-volatile memory such as a flash memory. The communication unit 13 includes at least one of a communication interface for wired communication and a communication interface for wireless communication.

[0011] The user terminal 20 is a user's computer. For example, the user terminal 20 is a personal computer, a tablet terminal, a smartphone, or a wearable terminal. For example, the user terminal 20 includes a control unit 21, a storage unit 22, a communication unit 23, an operation unit 24, and a display unit 25. The hardware configurations of the control unit 21, the storage unit 22, and the communication unit 23 may be the same as those of the control unit 11, the storage unit 12, and the communication unit 13, respectively. The operation unit 24 is an input device such as a mouse or a touch panel. The display unit 25 is a liquid crystal or organic EL display.

[0012] Note that the programs stored in the storage units 12 and 22 may be supplied via the network N. The hardware configurations of each of the server 10 and the user terminal 20 are not limited to the example in FIG. 1. For example, at least one of the server 10 and the user terminal 20 may include at least one of a reading unit (for example, a memory card slot) that reads a computer-readable information storage medium and an input / output unit (for example, a USB terminal) for directly connecting to an external device. The program stored in the information storage medium may be supplied to at least one of the server 10 and the user terminal 20 via at least one of the reading unit and the input / output unit.

[0013] Also, the business support system 1 may include at least one computer. The computer included in the business support system 1 is not limited to the example in FIG. 1. For example, the business support system 1 may include only the server 10. In this case, the user terminal 20 exists outside the business support system 1. The business support system 1 may include the server 10 and another server computer.

[0014] [2. Overview of the Business Support System] In the present embodiment, the business support system 1 has various functions for supporting the user's business. For example, the business support system 1 may provide the user with cloud-based or on-premises groupware. The business support system 1 may provide the user with a service that is not classified as groupware but supports the business. The business support system 1 of the present embodiment has, as one of the above functions, a communication tool for supporting the business. The communication tool is a tool for the user to communicate with other users regarding the business.

[0015] In this embodiment, a thread is described as an example of a communication tool, but the communication tool may be of other types. The communication tool is not limited to a thread. For example, the communication tool may be a bulletin board, a chat, a comment function in the business support system 1, a message app, an SNS, an SMS, or other tools that are not classified into threads. When a kind of database called an app having a comment function is provided to a user, the comment function of the app may correspond to the communication tool.

[0016] For example, a user cooperates with other users of a team in an organization such as a company to perform work. The user uses the communication tool provided by the business support system 1 to communicate with other users of the same team regarding work. For example, when the user logs in to the business support system 1 and selects the communication tool, the user terminal 20 causes the display unit 25 to display a communication tool screen showing the communication tool. In this embodiment, the case where the communication tool screen is displayed on the browser of the user terminal 20 is taken as an example.

[0017] FIG. 2 is a diagram showing an example of the communication tool screen. As shown in FIG. 2, the user terminal 20 causes the communication tool screen SC to display the content of the thread selected by the user among the plurality of threads created in the business support system 1. For example, on the communication tool screen SC, the posts made to the thread are arranged in chronological order. The post is the content of the communication. The post can also be called a message or text. For example, the post is a character string, a file, a link, or a combination thereof. The user can make a new post to the thread or make a reply post to an existing post.

[0018] FIG. 3 is a diagram showing an example of a user making a new post. As shown in the upper part of FIG. 3, the user inputs a new post into the input form F10. In this embodiment, the user can mention other users. A mention is a notification to other users. For example, the user can mention other users by inputting information of other users (e.g., the name of other users) after a specific symbol (e.g., @). The mention will be displayed on the screen of the other user. The mechanism of the mention may be the same as a known mechanism. For example, an email indicating that the user has been mentioned may be sent to the other user who has been mentioned.

[0019] In this embodiment, the user can mention AI (Artificial Intelligence) in the same way as the mention to other users. AI is a program having artificial intelligence to support the user's work. Although there are various theories about the definition of AI, the AI in this embodiment may be an AI defined by various known definitions. The AI may be an AI called generative AI or interactive AI. For example, the AI may be a large language model, a machine learning model not classified as a large language model, a program called a bot, or other programs. Although there are also various theories about the definition of machine learning, the machine learning in this embodiment may be a machine learning defined by various known definitions. The machine learning may be any of supervised learning, semi-supervised learning, or unsupervised learning.

[0020] In this embodiment, a case where a large language model corresponds to AI is taken as an example. For example, a user can mention AI by entering a character string (e.g., bot) indicating AI instead of information of another user after a specific symbol (e.g., @). When a mention to AI is made, the server 10 causes the AI to generate response data indicating a response to the user's post based on the post data indicating the user's post (in the example of the communication tool screen SC in the upper part of FIG. 3, the sentence "I will explain the popular programming language to the department head at the regular meeting next week. Please teach me the popular programming language.") and the prompt data indicating the prompt prepared in advance on the business support system 1 side.

[0021] For example, the server 10 transmits data for causing the communication tool screen SC to display the response indicated by the response data generated by the AI to the user terminal 20. As shown in the lower part of FIG. 3, the user terminal 20 displays the AI's response (in the example in the lower part of FIG. 3, the sentence "The popularity of programming languages is constantly changing, but as of 2023, several languages are attracting attention. For example, the following 5 languages are...") on the communication tool screen SC based on the data received from the server 10. In the AI's response, the user who made the post may be mentioned. In the example in the lower part of FIG. 3, the user is mentioned by the character string "@user U1" included in the AI's response.

[0022] As described above, when the user makes a post mentioning AI in the communication tool, the business support system 1 causes the AI to generate response data indicating a response according to the user's post. In the communication tool, the AI's response is displayed. As a result, the user does not need to go back and forth between the communication tool and other tools for causing the AI to generate a response, so the business support system 1 can improve the convenience of the user. Hereinafter, the details of the business support system 1 will be described.

[0023] [Functions Realized by the Business Support System] FIG. 4 is a diagram showing an example of functions implemented by the business support system 1.

[0024] [3-1. Functions Implemented by the Server] For example, the server 10 includes a data storage unit 100, a posting data acquisition unit 101, a mention determination unit 102, a prompt data acquisition unit 103, an answer data generation unit 104, and an answer display unit 105. Each of the data storage units 100 is realized by the storage unit 12. Each of the posting data acquisition unit 101, the mention determination unit 102, the prompt data acquisition unit 103, the answer data generation unit 104, and the answer display unit 105 is realized by the control unit 11.

[0025] [Data Storage Unit] The data storage unit 100 stores data necessary for business support. For example, the data storage unit 100 stores a user database DB1 in which various user data is stored, a communication tool database DB2 in which various data in the communication tool is stored, and prompt data PD indicating a pre-prepared prompt.

[0026] FIG. 5 is a diagram showing an example of the user database DB1. For example, the user database DB1 stores a user ID, a password, user name data indicating the user's name, and user attribute data. Any data may be stored in the user database DB1. The data stored in the user database DB1 is not limited to the example of FIG. 5. For example, organization data indicating the organization to which the user belongs may be stored in the user database DB1.

[0027] The user ID is an example of user identification data for the server 10 to identify the user. When the user ID is used for login, the user ID may also be called a user account. The user identification data may be other data such as an email address or a phone number. The password is used for authentication at login. The name indicated by the user name data is used for mention to the user. In the mention to the user, other data such as the user ID may be used. The user attribute data is data indicating the attributes of the user. Details of the user attribute data will be described in a modification example described later.

[0028] FIG. 6 is a diagram showing an example of the communication tool database DB2. For example, in the communication tool database DB2, a thread ID which is an ID for identifying a thread and post data indicating a post to the thread are stored. Any data may be stored in the communication tool database DB2. The data stored in the communication tool database DB2 is not limited to the example of FIG. 6. For example, the communication tool database DB2 may store the user ID of the user who made the post, the post date and time, the user or AI mentioned, and data on reactions to the post, etc.

[0029] For example, when a user creates a new thread, the server 10 issues a thread ID for the thread. When a new post is made to the thread, the post data acquisition unit 101 described later associates the post data indicating the new post with the issued thread ID and stores it in the communication tool database DB2. The post data may include not only the text indicating the content of the post but also other data such as files included in the post. In the present embodiment, the answer data indicating the answer from the AI is also stored in the communication tool database DB2 as a type of post data, but the answer data may be stored in another database.

[0030] FIG. 7 is a diagram showing an example of prompt data PD. The prompt data PD shows a default prompt prepared in advance. A prompt is an instruction (input) to the AI. A post indicated by the posted data is also a type of prompt. In the present embodiment, a case where an operator who manages the business support system 1 prepares the prompt data PD is taken as an example. The prompt data PD may be prepared by the user or may be prepared by an administrator in the organization to which the user belongs. In the example of the prompt data PD in FIG. 7, the post indicated by the posted data is inserted after "User:".

[0031] Note that the data stored in the data storage unit 100 is not limited to the above example. The data storage unit 100 can store arbitrary data. For example, the data storage unit 100 may store actual data of the AI. The actual data of the AI includes a program indicating processing such as calculation of embedded expressions and parameters referred to by the program. The actual data of the AI may include knowledge data indicating knowledge accumulated in the AI. Although it is assumed that learning of a large language model, which is an example of the AI, is completed, the parameters can be adjusted by relearning such as fine-tuning. The AI may be stored in a computer other than the server 10. In this case, the server 10 communicates with the other computer and uses the AI.

[0032] As in the present embodiment, when the AI is a large language model, the AI may be any large language model. For example, the AI may be a transformer-based model such as ChatGPT or BERT, or may be another model that is not transformer-based. The AI may be a machine learning model that is not classified as a large language model. For example, the AI may be a model such as an adversarial generation network, a neural network, or a support vector machine. The AI may be a program that is not classified as a machine learning model including a large language model. For example, the AI may be a rule-based AI or a program that analyzes a user's post by natural language processing such as morphological analysis.

[0033] For example, the data storage unit 100 may store programs and data of each function of the business support system 1. The data storage unit 100 may store data such as a program of a communication tool, data referred to by the program, and data for displaying the communication tool screen SC (e.g., HTML data). The data storage unit 100 may store data of other functions other than the communication tool (e.g., a schedule management function for managing a user's schedule, a file management function for managing a user's files, or a mail management function for managing shared mails).

[0034] [Post data acquisition unit] The post data acquisition unit 101 acquires post data indicating a post made in a communication tool for supporting business. For example, the post data acquisition unit 101 acquires post data from the user terminal 20. In the examples of the communication tools in FIGS. 2 and 3, the post data indicates a post input by the user in the input form F10. The post data indicates a character string input by the user. The post data may indicate other information other than the character string. For example, the post data may indicate an emoji, a file, an image, a video, a link, or other information specified by the user.

[0035] For example, when a user makes a new post in a certain thread, the user terminal 20 transmits the thread ID of the thread in which the new post was made and the post data indicating the new post to the server 10. The post data acquisition unit 101 acquires the thread ID and the post data from the user terminal 20. The post data acquisition unit 101 stores the thread ID and the post data acquired from the user terminal 20 in the communication tool database DB2 in association with each other. The post data acquisition unit 101 can acquire the post data stored in the communication tool database DB2 at an arbitrary timing.

[0036] [Mention determination unit] The mention determination unit 102 determines whether a mention of the AI has been made based on the posted data. In the present embodiment, the mention determination unit 102 determines whether a mention of the AI has been made in the same way as a mention of a user who uses a communication tool based on the posted data. The method of mention may be a known method. In the present embodiment, a case where a mention is made when a character string indicating the user's name is input after a specific symbol (for example, @) is given as an example. The mention may be a method in which other symbols are used, or a method in which an image such as a button is used without inputting a symbol in particular.

[0037] For example, the mention determination unit 102 determines whether a specific character string (for example, bot) indicating a mention of the AI is input after a specific symbol in the post indicated by the posted data. If the mention determination unit 102 determines that no specific character string is input after the specific symbol, it does not determine that a mention of the AI has been made. When the mention determination unit 102 determines that a specific character string is input after the specific symbol, it determines that a mention of the AI has been made.

[0038] Note that the mention determination unit 102 may make a determination according to the method of mention defined in the communication tool. For example, when a mention of the AI is made by selecting a specific image or text displayed on the communication tool screen SC, the mention determination unit 102 may determine whether a mention of the AI has been made by determining whether the specific image or text has been selected. The mention determination unit 102 may determine whether a mention of the AI has been made by determining whether information of a specific format indicating a mention of the AI is included in the posted data.

[0039] [Prompt data acquisition unit] The prompt data acquisition unit 103 acquires prompt data PD. In the present embodiment, since the prompt data PD is stored in the data storage unit 100, the prompt data acquisition unit 103 acquires the prompt data PD from the data storage unit 100. The prompt data PD may be stored in a computer other than the server 10 or an external information storage medium. In this case, the prompt data acquisition unit 103 acquires the prompt data PD from the other computer or the external information storage medium.

[0040] The prompt data PD may indicate a default prompt or may indicate arbitrary content. For example, the prompt data PD may indicate the name of the organization to which the user belongs, the type of data such as plugins available to the AI, the content of the task to be executed by the AI, the format of the answer data, or a combination thereof. The prompt data PD may be not only a character string indicating a default prompt but also a character string (in the example of FIG. 7, "User:") indicating the insertion position of the post indicated by the post data.

[0041] Note that prompt data PD may be prepared for each thread. In this case, in the data storage unit 100, the thread ID and the prompt data PD are stored in association with each other. The prompt data acquisition unit 103 acquires the prompt data PD associated with the thread ID of the thread in which the post indicated by the post data was made. The prompt data PD may be prepared for each user or organization instead of each thread. In this case, in the data storage unit 100, the user ID or organization ID and the prompt data PD are stored in association with each other. The prompt data acquisition unit 103 acquires the prompt data PD associated with the user ID or organization ID of the user who made the post indicated by the post data.

[0042] [Answer data generation unit] When it is determined that a mention has been made, the response data generation unit 104 causes an AI to generate response data indicating a response to the post based on the post data and the prompt data PD. The response data generation unit 104 inputs each of the post data and the prompt data PD into the AI. The response data generation unit 104 may insert the post indicated by the post data into the prompt indicated by the prompt data PD and then input the prompt into the AI. The response data generation unit 104 acquires the response data output from the AI.

[0043] Note that the processing of the AI after the input to the AI is performed may be known processing. As in this embodiment, when the AI is a large language model, the AI divides the input to itself into tokens based on the learned parameters and calculates the embedding representation of each token based on the learned parameters. A token is a part of the input to the AI. A token includes at least one character. The AI outputs response data indicating a response according to the order of the embedding representations while predicting the next token as necessary based on the order of the embedding representations of the tokens. These series of processes are executed by a program included in the actual data of the AI. These series of processes may be known processes adopted in interactive AIs and the like.

[0044] For example, when the AI is a machine learning model not classified as a large language model, the AI may calculate the embedding representation without particularly dividing the tokens and output response data indicating a response according to the embedding representation. When the AI is a program that is not a machine learning model, the AI may determine whether the input to itself conforms to a predetermined rule without calculating the embedding representation and output response data indicating a response according to the execution result of the determination. These series of processes are also executed by a program included in the actual data of the AI.

[0045] Note that the response data only needs to show the response from the AI and can be in any format. For example, the response data may show the text of the response from the AI. If the AI generates an image as a response, the response data may show the image generated by the AI. If the AI obtains a file managed by the business support system 1 as a response, the response data may show the said file. The response data may show a combination of two or more of text, images, and files.

[0046] Also, the AI can process any task based on the user's post. In the example of FIG. 3, the task corresponds to the AI providing information to the user. The task may be any task that can be processed by a known AI. For example, the task may be searching for information stored in the database managed by the business support system 1, searching for information managed by an Internet encyclopedia, machine translation, summary creation, text generation, image generation, post review, or other tasks. Even if the user does not specifically specify a task, the AI may determine the task to be processed by itself.

[0047] [Response Display Section] Based on the response data, the response display section 105 causes the response to be displayed on the communication tool. Causing the response display section 105 to display the response on the communication tool means that the response display section 105 executes the process for displaying the response on the communication tool screen SC. In this embodiment, since the response display section 105 is realized by the server 10, the response display section 105 causes the AI's response to be displayed on the communication tool by sending display data for displaying the response in the communication tool to the user terminal 20. The display data may be the same as the response data or may be separate data generated from the response data.

[0048] The display data may be in any format. It may be data necessary for displaying any information on the communication tool screen SC. For example, when the communication tool screen SC is displayed on a browser, the display data may be data in a markup language such as HTML. When the communication tool screen SC is displayed by an application dedicated to the business support system 1, the display data may be data necessary for displaying any information in the application (for example, image data or text data). In the example of FIG. 3, the answer display unit 105 displays an answer from the AI as a reply to the user's post. The user's post is also displayed on the communication tool screen SC by the processing of the server 10.

[0049] [Functions realized on the user terminal] For example, the user terminal 20 includes a data storage unit 200, a display control unit 201, and an operation reception unit 202. The data storage unit 200 is realized by the storage unit 22. Each of the display control unit 201 and the operation reception unit 202 is realized by the control unit 21.

[0050] [Data storage unit] The data storage unit 200 stores data for business support. For example, the data storage unit 200 stores a browser for displaying various screens of the business support system 1. For example, the data storage unit 200 stores a program dedicated to the business support system 1.

[0051] [Display control unit] The display control unit 201 causes the display unit 25 to display various screens in the business support system 1. For example, the display control unit 201 causes the display unit 25 to display various screens such as the communication tool screen SC based on the data received from the server 10.

[0052] [Operation reception unit] The operation reception unit 202 receives various operations in the business support system 1. For example, it receives operations on various screens such as the communication tool screen SC. The data indicating the operation content received by the operation reception unit 202 is appropriately transmitted to the server 10.

[0053] [4. Processes Executed in the Business Support System] FIG. 8 is a diagram showing an example of a process executed in the business support system 1. The control units 11 and 21 execute the programs stored in the storage units 12 and 22, respectively, whereby the process of FIG. 8 is executed. The process of FIG. 8 is executed when the user selects an arbitrary thread in the communication tool after logging in to the business support system 1.

[0054] The server 10 executes a process for displaying a communication tool screen SC indicating the thread selected by the user between the user terminal 20 based on the communication tool database DB2 (S1). In S1, the server 10 generates display data (for example, HTML data) of the communication tool screen SC based on the existing post data of the thread and transmits it to the user terminal 20. The user terminal 20 displays the communication tool screen SC as shown in FIG. 2 on the display unit 25 based on the display data. It is assumed that the display data also shows the thread ID of the thread to be displayed.

[0055] The user terminal 20 receives an input of a post to the input form F10 (S2). In S2, the user can make a post including the character string "@bot" for a mention to the AI, or can also make a post that does not particularly include the character string. When the user performs an operation for transmitting the post, the user terminal 20 transmits the thread ID of the currently displayed thread and the post data indicating the post input by the user to the server 10 (S3). The server 10 acquires the thread ID and the post data from the user terminal 20 (S4).

[0056] Server 10 determines whether a mention of the AI has been made based on the posted data (S5). In S5, Server 10 determines whether the character string "@bot" for mentioning the AI is shown in the posted data. In S5, if it is determined that no mention of the AI has been made (S5: N), Server 10 associates the thread ID and the posted data and stores them in the communication tool database DB2 (S6), and this process ends. In this case, the generation of response data by the AI is not performed. The process in S6 is the same as the process at the time of posting in a known thread. When a mention of another user is made, Server 10 executes a process for the mention of another user.

[0057] In S5, if it is determined that a mention of the AI has been made (S5: Y), Server 10 acquires the pre-stored prompt data PD (S7). Server 10 causes the AI to generate response data based on the posted data and the prompt data PD (S8). In S8, Server 10 inserts the posted string of the post indicated by the posted data at the predetermined position indicated by the prompt data PD, and then inputs to the AI. The AI executes processes including token splitting and calculation of embedding expressions, and outputs response data. Server 10 acquires the response data output from the AI.

[0058] Server 10 stores the thread ID and the posted data in the communication tool database DB2 in association with each other (S9). In S9, server 10 stores the posted data of the post input by the user and the answer data generated by the AI in the communication tool database DB2. Based on the answer data, server 10 executes a process for displaying an answer on the communication tool with the user terminal 20 (S10), and this process ends. In S10, server 10 generates display data for the communication tool screen SC showing the post input by the user and the answer from the AI and transmits it to the user terminal 20. The user terminal 20 displays the post input by the user and the answer from the AI on the communication tool screen SC based on the display data.

[0059] [Summary of Embodiment] The business support system 1 of the present embodiment determines whether or not a mention of the AI is made based on the posted data. When it is determined that a mention of the AI is made, the business support system 1 causes the AI to generate answer data based on the posted data and the prompt data PD. The business support system 1 outputs an answer on the communication tool based on the answer data. As a result, the user does not need to go back and forth between the communication tool and other tools for generating an answer for the AI, so the business support system 1 can improve the convenience of the user who uses the communication tool. For example, since the user can communicate with other users on the communication tool and ask questions about the AI on the communication tool, the business support system 1 can improve the business efficiency of the user.

[0060] In addition, the business support system 1 determines whether a mention of AI has been made in the same way as a mention to a user who uses a communication tool, based on the posted data. As a result, the user can mention the AI in the same way as when making a mention to another user, so the business support system 1 can effectively improve the convenience for the user.

[0061] [6. Modification Example] Note that the present disclosure is not limited to the embodiments described above. The present disclosure can be appropriately changed without departing from the gist of the present disclosure.

[0062] FIG. 9 is a diagram showing an example of functions realized by the business support system 1 of the modification example. As shown in FIG. 9, in the modification example described below, a location data acquisition unit 106, a business data acquisition unit 107, another posted data acquisition unit 108, a user attribute data acquisition unit 109, a task identification unit 110, and an AI identification unit 111 are realized. Each of the location data acquisition unit 106, the business data acquisition unit 107, the other posted data acquisition unit 108, the user attribute data acquisition unit 109, the task identification unit 110, and the AI identification unit 111 is realized by the control unit 11.

[0063] [6-1. Modification Example 1] For example, a user can make a post at any location in the communication tool. The location in the communication tool can also be a group that manages a plurality of posts collectively. If the communication tool is a thread, the thread in which the post was made among the plurality of threads created in the communication tool corresponds to the location. If the communication tool is a chat, the chat room in which the post was made among the chat rooms created in the communication tool corresponds to the location. Similarly, for other communication tools, a group that manages a plurality of posts collectively may correspond to the location. Since the content to be answered by the AI may change depending on the location where the post was made, the AI may generate answer data in consideration of the location where the post was made.

[0064] The business support system 1 of Modification Example 1 includes a location data acquisition unit 106. The location data acquisition unit 106 acquires location data indicating the location where a post is made using a communication tool. For example, the location data acquisition unit 106 acquires location data from the user terminal 20. When a user inputs a post at a certain location, the user terminal 20 transmits the location data indicating the location together with the post data. The location data may be included in a part of the post data. When the communication tool is a thread, the location data is the thread ID. When the server 10 can identify the thread by the name of the thread, the location data may indicate the name of the thread. The location data may indicate an individual tree within the thread rather than the thread. In this case, the tree corresponds to the location.

[0065] Note that the location data may be data indicating a location corresponding to the communication tool. For example, when the communication tool is a chat, the location data may be an ID for identifying a chat room. Similarly for other communication tools, the location data may be data that enables the server 10 to identify the location where the post is made. The location data acquisition unit 106 may acquire this location data from the user terminal 20. When the location data indicating the location where the user is browsing is recorded in the data storage unit 100, the location data acquisition unit 106 may acquire the location data from the data storage unit 100.

[0066] The response data generation unit 104 of Modification Example 1 causes the AI to generate response data based further on the location data. For example, the response data generation unit 104 inputs the location data as a prompt to the AI. The AI calculates an embedded representation based not only on the post data and the prompt data PD but also on the location data. The AI outputs response data indicating a response corresponding to the embedded representation. The response data generation unit 104 acquires the response data output from the AI. The process in which the response display unit 105 outputs a response based on the response data may be the same as in the embodiment.

[0067] Note that the method by which the response data generation unit 104 obtains response data based on location data is not limited to the above example. The response data generation unit 104 may cause the AI to generate response data by using the location data in some form. For example, when prompt data PD corresponding to the location data is prepared, the response data generation unit 104 may obtain the prompt data PD associated with the location data and cause the AI to generate response data based on the posted data and the prompt data PD. As another example, for instance, when there are a plurality of AIs and an AI corresponding to the location data is prepared, the response data generation unit 104 may select the AI associated with the location data and cause the AI to generate response data based on the posted data and the prompt data PD.

[0068] The business support system 1 of Modification Example 1 further causes the AI to generate response data based on the location data. As a result, the business support system 1 can output a response according to the location where the post was made. The business support system 1 makes it easier to output the response desired by the user. For example, even within the same organization, the appropriate content may differ between the response to a post in the development department's thread and the response to a post in the sales department's thread. Even for the same post, the response in the development department may preferably include content related to development. The response in the sales department may also preferably include content related to sales. Since the AI of Modification Example 1 can generate response data corresponding to these departments, the accuracy of the response from the AI is improved.

[0069] [6-2. Modification Example 2] For example, business data related to the user's business is registered in the business support system 1. The business data is data for business support. For example, the business data may be a file uploaded by the user, a database registered in the business support system 1, a value of a field in the database, or other data. These business data may be considered by the AI. The data storage unit 100 of Modification Example 2 stores the business data. For example, the data storage unit 100 stores business data related to the business in the organization to which the user belongs for each organization.

[0070] The business support system 1 of Modification Example 2 includes a business data acquisition unit 107. The business data acquisition unit 107 acquires business data related to the business of the user who made the post. For example, when a user posts to a certain thread, the business data acquisition unit 107 acquires the file registered in the thread as business data. When a user posts using the comment function of an app, the business data acquisition unit 107 acquires the data of the fields of the app as business data. When a user posts to a specific record of an app, the business data acquisition unit 107 acquires the data of the record as business data. Since these business data are stored in the data storage unit 100 in advance, the business data acquisition unit 107 may acquire the business data by referring to the data storage unit 100.

[0071] The answer data generation unit 104 of Modification Example 2 causes the AI to generate answer data based further on the business data. For example, the answer data generation unit 104 inputs the business data as a prompt to the AI. The AI calculates the embedded representation based not only on the post data and the prompt data PD but also on the business data. The AI outputs answer data indicating an answer according to the embedded representation. The answer data generation unit 104 acquires the answer data output from the AI. The process in which the answer display unit 105 outputs an answer based on the answer data may be the same as in the embodiment.

[0072] Note that the method by which the response data generation unit 104 obtains response data based on the business data is not limited to the above example. The response data generation unit 104 may use the business data in some form to cause the AI to generate response data. For example, when prompt data PD corresponding to the business data is prepared, the response data generation unit 104 may obtain the prompt data PD associated with the business data and cause the AI to generate response data based on the posted data and the prompt data PD. As another example, when there are multiple AIs and an AI corresponding to the business data is prepared, the response data generation unit 104 may select the AI associated with the business data and cause the AI to generate response data based on the posted data and the prompt data PD.

[0073] The business support system 1 of Modification Example 2 causes the AI to generate response data based further on the business data. Thereby, the business support system 1 can output a response corresponding to the user's business. The business support system 1 makes it easier to output the response desired by the user. For example, when the AI generates response data in consideration of the content of the file registered in the thread, the AI can generate response data corresponding to the content related to the business up to the post made by the user. When the AI generates response data in consideration of the data registered in the records of the application, the AI can generate response data corresponding to the content of the record posted by the user using the comment function of the application. As a result, the business support system 1 can display on the communication tool screen SC a response closely related to the business related to the post made by the user.

[0074] [6-3. Modification Example 3] For example, in a communication tool, there may be not only the post made by the user but also other existing posts. Taking a thread as an example as in the embodiment, in the thread where the user made a post, there may be other existing posts. Similarly, in other communication tools such as chat, when the user makes a post, there may already be other existing posts that have been posted. Since other posts may include content related to the post made by the user (for example, a business topic related to the post made by the user), the AI may generate response data considering other posts as well.

[0075] The business support system 1 of Modification 3 includes an other post data acquisition unit 108. The other post data acquisition unit 108 acquires other post data indicating other posts different from the post. The other posts are existing posts. For example, when the user replies to some post, the post being replied to corresponds to the other post. When the user makes a post in a certain thread, the existing posts posted in the thread correspond to the other posts. The other post data is stored in the communication tool database DB2.

[0076] For example, the other post data acquisition unit 108 refers to the communication tool database DB2 and acquires other post data. Similarly, when other communication tools such as chat are adopted, the other post data acquisition unit 108 acquires other post data indicating existing other posts. The other post data acquisition unit 108 may acquire other post data for the entire past period, or may acquire other post data for a recent predetermined period (for example, one week). The other post data acquisition unit 108 may acquire other post data at the same location where the user made the post.

[0077] The response data generation unit 104 of Modification Example 3 causes the AI to generate response data based on additional submitted data. For example, the response data generation unit 104 inputs the additional submitted data as a prompt for the AI. The AI calculates the embedded representation based not only on the submitted data and the prompt data PD but also on the additional submitted data. The AI outputs response data indicating a response corresponding to the embedded representation. The response data generation unit 104 acquires the response data output from the AI. The process in which the response display unit 105 outputs a response based on the response data may be the same as in the embodiment.

[0078] Note that the method by which the response data generation unit 104 acquires response data based on additional submitted data is not limited to the above example. The response data generation unit 104 may cause the AI to generate response data by using the additional submitted data in some way. For example, if prompt data PD corresponding to the additional submitted data is prepared, the response data generation unit 104 may acquire the prompt data PD associated with the additional submitted data and cause the AI to generate response data based on the submitted data and the prompt data PD. For another example, if there are a plurality of AIs and an AI corresponding to the additional submitted data is prepared, the response data generation unit 104 may select the AI associated with the additional submitted data and cause the AI to generate response data based on the submitted data and the prompt data PD.

[0079] The business support system 1 of Modification Example 3 causes the AI to generate response data based on additional posted data. As a result, the business support system 1 can output responses corresponding not only to the posts made by the user but also to other posts in the communication tool. The business support system 1 makes it easier to output the responses desired by the user. For example, the additional posted data may show the background leading up to the post made by the user. By generating response data based on the additional posted data, the AI can generate response data corresponding to the background leading up to the post made by the user, thereby improving the accuracy of the responses from the AI. For example, even if the background leading up to the post made by the user is not shown, the AI can generate response data corresponding to the background up to that point.

[0080] [6-4. Modification Example 4] For example, the additional posted data acquisition unit 108 of Modification Example 3 may acquire additional posted data of other posts in the same tree as the post indicated by the posted data acquired by the posted data acquisition unit 101 among a plurality of other posts made in the communication tool. A tree is a collection of posts when replies are continuously made starting from a certain post. A tree is a collection of the starting post and the posts of the replies made based on that post. A tree can also be said to be a collection of posts indicating the same topic.

[0081] Note that the tree ID for identifying the tree is assumed to be stored in the communication tool database DB2. For example, when the user makes a new post without quoting other posts, the server 10 generates a new tree ID and stores it in the communication tool database DB2. When a reply is made to the post, the server 10 associates the tree ID with the posted data of the reply post. As a result, the original post and the reply post belong to the same tree. Other communication tools such as chats may also support a similar tree structure.

[0082] For example, when a user posts to a certain tree, the other post data acquisition unit 108 acquires the tree ID of the tree to which the user posted. The other post data acquisition unit 108 acquires other post data associated with the tree ID from among the other post data stored in the communication tool database DB2. Assuming that the user posts to a certain tree of a certain thread, the other post data acquisition unit 108 acquires other post data of other posts belonging to the said tree. The other post data acquisition unit 108 does not acquire other post data of other posts belonging to other trees of the said thread. Although the other post data used by the answer data generation unit 104 for acquiring answer data is different from Modification Example 3 in that it is other post data of other posts in the same tree as the post, the method itself for generating answer data based on other post data may be the same as that of Modification Example 3.

[0083] The business support system 1 of Modification Example 4 acquires other post data of other posts in the same tree as the post from among a plurality of other posts made using the communication tool. As a result, the business support system 1 can acquire answer data in consideration of the topic leading up to the post. The business support system 1 makes it easier to output the answer desired by the user. For example, in a thread where a large number of posts have been made, there may be other posts that have nothing to do with the post made by the user. On the other hand, since other posts in the same tree as the post made by the user are likely to be related to the post made by the user, the AI can generate an answer that is closely related to the post made by the user.

[0084] [6-5. Modification Example 5] For example, the answers desired by users may vary depending on the attributes of the users. The attributes of a user are the classification of the user. The attributes of a user may be the type of work the user is in charge of. For example, the attributes of a user may be the industry of the organization the user belongs to, the department of the user in the organization, the user's job title, demographic information such as the user's gender or age, or other information. For example, even if they are in the same organization, the answers desired by users belonging to the development department and users belonging to the sales department may differ from each other. Another example is that the answers desired by user employees and users without a job title may also differ. Therefore, the AI may generate answer data considering the attributes of the users.

[0085] The business support system 1 of Modification 5 includes a user attribute data acquisition unit 109. The user attribute data acquisition unit 109 acquires user attribute data indicating the attributes of the user who made the post. In Modification 5, since the user attribute data is stored in the user database DB1, the user attribute data acquisition unit 109 acquires the user attribute data from the user database DB1. The user attribute data may indicate any attribute including the examples described above. The user may specify the attribute indicated by their own user attribute data. The administrator of the organization to which the user belongs may specify the attributes of the user. The user attribute data may be stored in another computer or an external information storage medium other than the server 10. The user attribute data acquisition unit 109 may acquire the user attribute data from another computer or an external information storage medium.

[0086] The answer data generation unit 104 of Modification 5 generates answer data based on the user attribute data as well. For example, the answer data generation unit 104 inputs the user attribute data as a prompt for the AI. The AI calculates the embedding representation based not only on the post data and the prompt data PD but also on the user attribute data. The AI outputs answer data indicating an answer corresponding to the embedding representation. The answer data generation unit 104 acquires the answer data output from the AI. The process of the answer display unit 105 outputting an answer based on the answer data may be the same as in the embodiment.

[0087] Note that the method by which the response data generation unit 104 obtains response data based on user attribute data is not limited to the above example. The response data generation unit 104 may use the user attribute data in some form to cause the AI to generate response data. For example, when prompt data PD corresponding to the user attribute data is prepared, the response data generation unit 104 may obtain the prompt data PD associated with the user attribute data and cause the AI to generate response data based on the posted data and the prompt data PD. As another example, for instance, when there are a plurality of AIs and an AI corresponding to the user attribute data is prepared, the response data generation unit 104 may select the AI associated with the user attribute data and cause the AI to generate response data based on the posted data and the prompt data PD.

[0088] The business support system 1 of Modification Example 5 further generates response data based on the user attribute data. As a result, the business support system 1 can output not only the posts made by the user but also responses according to the attributes of the user who made the posts. The business support system 1 makes it easier to output the responses desired by the user. For example, when the user attribute data indicates the department of the user, the AI can generate response data according to the content of the work handled by the department of the user who made the post. When the user attribute data indicates the position of the user, the AI can generate response data according to the position of the user who made the post.

[0089] [6-6. Modification Example 6] For example, the AI may generate answer data by referring not only to the knowledge stored in itself but also to the databases managed by the business support system 1. The data storage unit 100 of Modification Example 6 stores various databases in which the business data described in Modification Example 3 is stored. For example, the databases store business data indicating in-house regulations, business data indicating in-house dictionaries, business data indicating schedules, business data indicating e-mails, business data indicating various information related to customers, or other business data. These databases are referred to and updated by functions other than the communication tool among the functions of the business support system 1.

[0090] The answer data generation unit 104 of Modification Example 6 generates answer data when the AI refers to at least one of the plurality of databases managed by the business support system 1. For example, the answer data generation unit 104 inputs the posted data and the prompt data PD to the AI. The AI calculates the embedded representation based on the input, and selects at least one of the plurality of databases based on the embedded representation. The AI outputs answer data including the business data stored in the selected database. The answer data shows all or part of the content indicated by the business data. The AI may modify the content of the business data and generate answer data showing the modified content. The process of the answer display unit 105 outputting an answer based on the answer data may be the same as in the embodiment.

[0091] The business support system 1 of Modification Example 6 generates answer data by having AI refer to at least one of the plurality of databases managed by the business support system 1. As a result, the business support system 1 can output answer data related to the user's business. For example, when the user posts a question related to the company's regulations, the AI can generate answer data by referring to the database of the company's regulations, and the AI can generate answer data corresponding to the user's post. Which database the AI should refer to in the case of any post is specified by the embedded expression calculated by the AI. The AI can generate appropriate answer data based on the database corresponding to the content of the post.

[0092] [6-7. Modification Example 7] For example, in addition to a mention to the AI, the user may specify a task for the AI to execute. In Modification Example 7, the mention to the AI is assumed to be made by inputting "@bot" as in the embodiment. The task for the AI to execute is specified by the user inputting a character string indicating the task after a specific symbol (for example, #) different from the mention to the AI.

[0093] The business support system 1 of Modification Example 7 includes a task identification unit 110. The task identification unit 110 identifies the task specified by the user who made the post. For example, the task identification unit 110 acquires task data indicating the task specified by the user. The task data indicates the character string of the task specified by the user. In Modification Example 7, since the character string indicating the content of the task is input after the specific symbol "#", the task data indicates the specific symbol "#" and the character string. For example, if the task is for the AI to machine-translate the post into English, the task data indicates "#Translate into English". If the task is for the AI to create a summary of the posts in the thread, the task data indicates "#Create summary".

[0094] For example, the user specifies a task of machine translating the user's post into English by inputting a character string such as "[[Translation into English]]". When the user makes a post after specifying the task, the user terminal 20 transmits the post data to the server 10. The post data acquisition unit 101 of the server 10 acquires the post data in the same manner as in the embodiment. The data indicating the task may be data separate from the post data.

[0095] For example, the task identification unit 110 determines whether a specific symbol "[[#]]" for specifying a task is included in the post indicated by the post data. If the task identification unit 110 determines that the specific symbol "[[#]]" is not included in the post, it does not identify the task. In this case, generation of answer data by AI is performed in the same manner as in the embodiment. When the task identification unit 110 determines that the specific symbol "[[#]]" is included in the post, it identifies the character string "[[Translation into English]]" after the specific symbol "[[#]]" as the task.

[0096] Note that tasks that can be specified by the user may be predetermined. In this case, the task identification unit 110 may determine whether the specific symbol "[[#]]" and a character string defined as a task that can be specified by the user are included in the post, and acquire task data based on the result of the determination. For the specification of the task, symbols other than "[[#]]" may be used. The specific symbol for specifying the task may be any symbol different from the symbol for mention. The specific symbol for specifying the task may be the same symbol (for example, [[@]]) as the symbol for mention. In this case, if the character string after the symbol is not the user's name, the task identification unit 110 may regard the character string as indicating a task and acquire the task data.

[0097] Also, specific symbols do not have to be used for task specification. In this case, when a post including "@bot" indicating a mention to the AI is made, the task specifying unit 110 may perform language analysis on the text of the post to specify the task, and acquire task data indicating the task. For example, when tasks that can be specified by the user are predetermined, the task specifying unit 110 may determine whether a character string indicating a predetermined task is included in the text of the post, and acquire task data based on the result of the determination. The task specifying unit 110 may acquire task data based on an AI for task determination prepared separately from the AI that generates the response data. Additionally, for example, information (e.g., an image or text) for task specification may be displayed on the communication tool screen SC. The user may specify a task by selecting at least one of the plurality of pieces of information.

[0098] The response data generation unit 104 of Modification 7 causes the AI to generate response data based further on the task data. For example, the response data generation unit 104 inputs the task data as a prompt to the AI. The AI calculates the embedded representation based not only on the post data and the prompt data PD but also on the task data. The AI outputs response data indicating a response according to the embedded representation. The response data generation unit 104 acquires the response data output from the AI. The process in which the response display unit 105 outputs a response based on the response data may be the same as in the embodiment.

[0099] Note that the method by which the response data generation unit 104 obtains response data based on the task data is not limited to the above example. The response data generation unit 104 may use the task data in some form to cause the AI to generate response data. For example, when prompt data PD corresponding to the task data is prepared, the response data generation unit 104 may obtain the prompt data PD associated with the task data and cause the AI to generate response data based on the posted data and the prompt data PD. As another example, when there are multiple AIs and an AI corresponding to the task data is prepared, the response data generation unit 104 may select the AI associated with the task data and cause the AI to generate response data based on the posted data and the prompt data PD.

[0100] The business support system 1 of Modification Example 7 causes the AI to generate response data based on the task specified by the user. Thereby, the business support system 1 can output not only the post made by the user but also a response corresponding to the task specified by the user who made the post. The business support system 1 makes it easier to output the response desired by the user. For example, by the user specifying the task they want the AI to perform themselves, the business support system 1 can cause the AI to execute the task desired by the user and generate response data, thereby increasing the accuracy of the response from the AI.

[0101] [6-8. Modification Example 8] For example, the business support system 1 may have multiple AIs prepared. Each AI has learned training data specialized for a specific task. For example, each AI may have undergone retraining such as fine-tuning based on training data specialized for a specific task. In Modification Example 8, assume that three AIs are prepared: AI1 specialized for machine translation, AI2 specialized for summary creation, and AI3 specialized for research. The number of AIs may be any number. For example, there may be two AIs, or four or more AIs.

[0102] For example, AI1 has learned training data including training sentences described in a specific language (e.g., Japanese) and the sentences translated into another language different from the said language (e.g., English). AI2 has learned training data including training sentences and summaries of the said sentences. AI3 has learned training data such as data from Internet encyclopedias or data from encyclopedias created by the organization to which the user belongs. It is assumed that the learned AI1 to AI3 are stored in the data storage unit 100.

[0103] For example, the user may specify not only a mention to an AI but also an AI for which answer data is to be generated. In Modification 8, it is assumed that, similar to the embodiment, the user makes a mention to an AI by inputting a character string indicating the mention to the AI after a specific symbol "@". However, the said character string indicates any one of a plurality of AIs. When the user specifies AI1, the said character string becomes "bot1". When the user specifies AI2, the said character string becomes "bot2". When the user specifies AI3, the said character string becomes "bot3". It is assumed that correspondence data indicating which character string corresponds to which AI is stored in advance in the data storage unit 100.

[0104] The business support system 1 of Modification 8 includes an AI identification unit 111. The AI identification unit 111 identifies the AI specified by the user who made the post among a plurality of AIs. The AI identification unit 111 analyzes the post data based on the correspondence data to identify the AI specified by the user. For example, when it is determined that a mention to an AI has been made, the AI identification unit 111 refers to the last numerical value of the mention character string to identify the AI specified by the user. If the mention character string is "@bot1", the AI identification unit 111 identifies AI1. If the mention character string is "@bot2", the AI identification unit 111 identifies AI2. If the mention character string is "@bot3", the AI identification unit 111 identifies AI3.

[0105] Note that for the designation of the AI, a specific symbol different from the mention may be used. In this case, the user may designate the AI by inputting information indicating the AI to process the task after another symbol (for example, %) separately from "@bot" indicating the mention to the AI. For example, information (for example, an image or text) for the designation of the AI may be displayed on the communication tool screen SC. The user may designate the AI by selecting at least one of the plurality of pieces of such information. The user may designate a plurality of AIs.

[0106] The response data generation unit 104 of Modification 8 causes the AI designated by the user among the plurality of AIs to generate response data. For example, when AI1 is specified by the AI identification unit 111, the response data generation unit 104 causes AI1 among AI1 to AI3 to generate response data. When AI2 is specified by the AI identification unit 111, the response data generation unit 104 causes AI2 among AI1 to AI3 to generate response data. When AI3 is specified by the AI identification unit 111, the response data generation unit 104 causes AI3 among AI1 to AI3 to generate response data. Although it is different from the embodiment in that any one of the plurality of AIs generates response data, the process in which the AI generates response data may be the same as that in the embodiment. The process in which the response display unit 105 outputs a response based on the response data may also be the same as that in the embodiment.

[0107] The business support system 1 of Modification 8 causes the AI designated by the user among the plurality of AIs to generate response data. Thereby, the business support system 1 can cause the AI designated by the user to generate response data in addition to the post made by the user. The business support system 1 makes it easier to output the response desired by the user. For example, when the user designates by himself / herself the AI that he / she wants to process the task from among the plurality of AIs, the business support system 1 can cause the desired AI to process the task and generate response data for the AI, so that the accuracy of the response from the AI is improved.

[0108] [6-9. Other Modifications] For example, two or more of Modifications 1 to 8 may be combined. The answer data generation unit 104 may cause the AI to generate answer data based only on the posted data without relying on the prompt data PD. In this case, the business support system 1 does not include the prompt data acquisition unit 103. Even a business support system 1 that does not include the prompt data acquisition unit 103 allows the user to cause the AI to generate answer data from a communication tool such as a thread, thus solving the problem of enhancing user convenience. Therefore, a business support system 1 that does not include the prompt data acquisition unit 103 is also included in the scope of the present disclosure.

[0109] For example, the functions described as being implemented by the server 10 may be implemented by the user terminal 20. In this case, the function may be implemented by a browser script or an application installed on the user terminal 20. For example, each function may be shared by a plurality of computers or may be implemented by one computer.

Description of Reference Numerals

[0110] 1 Business support system, 10 Server, 11, 21 Control unit, 12, 22 Storage unit, 13, 23 Communication unit, 20 User terminal, 24 Operation unit, 25 Display unit, N Network, PD Prompt data, SC Communication tool screen, DB1 User database, DB2 Communication tool database, F10 Input form, 100 Data storage unit, 101 Posted data acquisition unit, 102 Mention determination unit, 103 Prompt data acquisition unit, 104 Answer data generation unit, 105 Answer display unit, 106 Location data acquisition unit, 107 Business data acquisition unit, 108 Other posted data acquisition unit, 109 User attribute data acquisition unit, 110 Task identification unit, 111 Identification unit, 200 Data storage unit, 201 Display control unit, 202 Operation reception unit.

Claims

1. A posting data acquisition unit that acquires posting data indicating a posting made by a communication tool for supporting business; A mention determination unit that determines whether or not a mention of AI (Artificial Intelligence) has been made based on the posting data; A prompt data acquisition unit that acquires prompt data indicating a pre-prepared prompt; When it is determined that the mention has been made, an answer data generation unit that causes the AI to generate answer data indicating an answer to the posting based on the posting data and the prompt data; An answer display unit that causes the communication tool to display the answer based on the answer data; A business support system including the above.

2. The business support system further includes a location data acquisition unit that acquires location data indicating a location where the posting was made by the communication tool, The answer data generation unit causes the AI to generate the answer data based further on the location data. The business support system according to claim 1.

3. The business support system further includes a business data acquisition unit that acquires business data related to the business of the user who made the posting, The answer data generation unit causes the AI to generate the answer data based further on the business data. The business support system according to claim 1 or 2.

4. The business support system further includes another posting data acquisition unit that acquires other posting data indicating another posting different from the posting, The answer data generation unit causes the AI to generate the answer data based further on the other posting data. The business support system according to claim 1 or 2.

5. The other posting data acquisition unit acquires the other posting data of the other postings in the same tree as the posting among the plurality of the other postings made by the communication tool. The business support system according to claim 4.

6. The business support system further includes a user attribute data acquisition unit that acquires user attribute data indicating an attribute of the user who made the posting, The answer data generation unit generates the answer data based further on the user attribute data. The business support system according to claim 1 or 2.

7. The response data generation unit generates the response data by having the AI refer to at least one of a plurality of databases managed by the business support system. The business support system according to claim 1 or 2.

8. The mention determination unit determines whether a mention has been made to the AI in the same manner as a mention to a user who uses the communication tool, based on the posted data. The business support system according to claim 1 or 2.

9. The business support system further includes a task identification unit that identifies a task specified by the user who made the post. The response data generation unit causes the AI to generate the response data based further on the task. The business support system according to claim 1 or 2.

10. The business support system further includes an AI identification unit that identifies the AI specified by the user who made the post among a plurality of the AIs. The response data generation unit causes the AI specified by the user among the plurality of AIs to generate the response data. The business support system according to claim 1 or 2.

11. Obtain posted data indicating a post made in a communication tool for supporting business. Based on the posted data, determine whether a mention has been made to an AI (Artificial Intelligence). Obtain prompt data indicating a pre-prepared prompt. When it is determined that the mention has been made, cause the AI to generate response data indicating a response to the post based on the posted data and the prompt data. Based on the response data, display the response in the communication tool. Business support method.

12. A posted data acquisition unit that acquires posted data indicating a post made in a communication tool for supporting business. A mention determination unit that determines whether a mention has been made to an AI (Artificial Intelligence) based on the posted data. A prompt data acquisition unit that acquires prompt data indicating a pre-prepared prompt. A response data generation unit that causes the AI to generate response data indicating a response to the post based on the posted data and the prompt data when it is determined that the mention has been made. An answer display unit that displays the answer on the communication tool based on the answer data. A program for causing a computer to function as such.

Images