Work support system, work support method, and program

Abstract

To improve convenience of a user.SOLUTION: A contribution information acquisition part (101) of a business support system (1) acquires contribution information related to contribution input by a user to the business support system (1) for supporting the business of the user. A registration information acquisition part (102) acquires registration information registered in the business support system (1) on the basis of the contribution information. The business support unit (103) performs business support by AI based on the registered information.SELECTED DRAWING: Figure 5

Description

[Technical Field]

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

[0002] Conventionally, business support systems that support user business operations have been known. For example, Patent Document 1 describes a technology that displays a help page related to a business support function on a terminal of a user who uses the business support function that supports business operations (for example, sales management operations, accounting operations, personnel and labor-related operations, or core business operations) in a company or the like. The user searches for information necessary for his or her own business operations from the help page. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-157668 Summary of the Invention [Problem to be solved by the invention]

[0004] However, with the technology of Patent Document 1, users have to operate their own terminals to open a help page and search for information necessary for their work, which is time-consuming for the users. For this reason, the technology of Patent Document 1 does not sufficiently improve user convenience.

[0005] One of the purposes of the present disclosure is to improve user convenience. [Means for solving the problem]

[0006] A business support system according to one aspect of the present disclosure includes a posting information acquisition unit that acquires posting information regarding posts entered by a user into a business support system that supports the user's business, a registration information acquisition unit that acquires registration information registered in the business support system based on the posting information, and a business support unit that provides business support using AI (Artificial Intelligence) based on the registration information. [Effects of the Invention]

[0007] According to the present disclosure, it is possible to improve convenience for users. [Brief explanation of the drawings]

[0008] [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 an application screen. [Figure 3] FIG. 10 is a diagram illustrating an example of an application screen. [Figure 4] FIG. 10 is a diagram illustrating an example of an application screen. [Figure 5] FIG. 2 is a diagram illustrating an example of functions realized by the business support system. [Figure 6] FIG. 2 is a diagram illustrating an example of a posted information database. [Figure 7] FIG. 10 is a diagram illustrating an example of a registration information database. [Figure 8] FIG. 1 is a diagram showing an example of the relationship between input to an AI and output from the AI. [Figure 9] FIG. 2 is a diagram illustrating an example of processing executed in the business support system. [Figure 10] FIG. 10 is a diagram illustrating an example of functions realized by a modified example of a business support system. [Figure 11] FIG. 10 is a diagram showing an example of relevance information changed in Modification 1. [Figure 12] FIG. 20 is a diagram showing an example of an application screen according to a seventh modification. [Figure 13] FIG. 20 is a diagram showing an example of an application screen according to Modification 8. DETAILED DESCRIPTION OF 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 a 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 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 memory unit 22, a communication unit 23, an operation unit 24, and a display unit 25. The hardware configurations of the control unit 21, the memory unit 22, and the communication unit 23 may be similar to those of the control unit 11, the memory 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] The programs stored in the storage units 12, 22 may be supplied via the network N. The hardware configurations 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 (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 server 10 and the user terminal 20 via at least one of the reading unit and the input / output unit.

[0013] 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 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 also include only the user terminal 20. In this case, the server 10 exists outside the business support system 1. The business support system 1 may also include other computers not shown in FIG. 1.

[0014] [2. Overview of the business support system] In this 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-premise groupware. The business support system 1 may also provide the user with a service that supports business, although it is not classified as groupware. The business support system 1 of this embodiment has, as one of the above functions, a communication tool that supports business. The communication tool is a tool that allows the user to communicate with other users regarding business matters.

[0015] In this embodiment, a comment function of an app, which is a type of database, is described as an example of a communication tool, but other types of communication tools may be used. The communication tool is not limited to the comment function of an app. For example, the communication tool may be a thread, a bulletin board not classified as a thread, a chat, a messaging app, an SNS, an SMS, or other tools.

[0016] For example, a user performs a task in cooperation with other users in an organization such as a company. The user communicates with other users related to the task using a communication tool provided by the task support system 1. For example, when the user logs in to the task support system 1 and selects an app, the user terminal 20 displays an app screen showing the contents of the records registered in the app on the display unit 25. In this embodiment, an example is given in which the app screen is displayed on a browser on the user terminal 20, but the app screen may also be displayed on an application for the task support system 1.

[0017] FIG. 2 is a diagram showing an example of an app screen. The example at the top of FIG. 2 shows an app screen SC of a customer management app for managing a user's customers. For example, the app screen SC includes a display area A showing comments registered in a record of the app. A comment is an example of a post. In the display area A, each of the multiple comments registered in the record is arranged in chronological order. A user can input a new comment into an input form F. When a user registers a new comment in the record, the new comment is displayed in the display area A.

[0018] In this embodiment, when a user registers a comment on a record of an app, AI (Artificial Intelligence) presents the user with information to support the user's work. AI is a program with artificial intelligence that supports the user's work. There are various definitions of AI, and the AI ​​in 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 in this embodiment may be machine learning defined by various known definitions. The machine learning may be supervised learning, semi-supervised learning, or unsupervised learning.

[0019] In this embodiment, a case where a large-scale language model corresponds to AI is taken as an example. Furthermore, a case where the AI ​​is managed by an external company different from the administrator of the business support system 1 (for example, a company that provides cloud-based groupware) is taken as an example. The business support system 1 uses the AI ​​managed by the external company via a network N. The AI ​​managed by the external company may be tuned for the business support system 1, but in this embodiment, a case where the AI ​​is a general-purpose AI that can be used by parties other than the business support system 1 is taken as an example.

[0020] For example, a general-purpose AI can generate general answers to resolve user questions, but cannot generate answers suitable for business support. While tuning the AI ​​for the business support system 1 is conceivable, preparing training data for tuning is extremely time-consuming. Therefore, in this embodiment, registration information registered in the business support system 1 is input to the AI, causing the AI ​​to generate answers suitable for business support.

[0021] For example, suppose that the employee list of the organization to which the user belongs is registered as registration information in the business support system 1. The employee list shows the names and affiliations of all employees, including the user. As shown in the upper part of FIG. 2, when posted information such as "By the way, which employee should I ask about how to apply for expense reimbursement for my business trip?" is acquired, the server 10 acquires the employee list as registration information appropriate for the posted information. As will be described in detail later, the registered information registered in the business support system 1 is associated with a vector indicating the meaning of the registered information, and the server 10 can acquire registration information corresponding to the user's posted information.

[0022] For example, the server 10 inputs the posted information and the employee list into the AI ​​and displays the response from the AI ​​on the application screen SC. For example, as shown in the lower part of FIG. 2, the application screen SC displays generated information such as "You should ask user U20 in the general affairs department about expense reimbursement," generated by the AI ​​("Excuse me for interrupting" in the example at the bottom of FIG. 2). The generated information is information generated by the AI. For example, the generated information may be a character string (text), an image, a table, a diagram, or other information. In this embodiment, the AI ​​generates generated information to support the user's work in response to the user's post, even if the user does not explicitly instruct the AI ​​to support the AI.

[0023] 3 and 4 are diagrams showing examples of application screens SC. The upper example of FIG. 3 shows an application screen SC of a project management application for managing user projects. For example, when posted information such as "I'm planning to give an overview of Product DDD at an upcoming seminar. Are there any easy-to-understand materials?" is registered in the project management application, the server 10 acquires the Product DDD catalog as registration information appropriate for the posted information. The server 10 inputs the posted information and registration information into the AI ​​and displays the response from the AI ​​on the application screen SC. As shown in the lower example of FIG. 3, the application screen SC displays generated information such as "Product DDD is a useful tool that improves customer teamwork..." that summarizes the Product DDD catalog by the AI.

[0024] The upper example of Figure 4 shows an application screen SC of an inquiry response application for managing responses to inquiries. For example, when posted information such as "What to do when error code 1125 occurs frequently... I wonder if similar inquiries have been received in the past" is registered in the inquiry response application, the server 10 acquires a collection of past inquiry cases as registered information appropriate to the posted information. The server 10 inputs the posted information and registered information into the AI ​​and displays the response from the AI ​​on the application screen SC. As shown in the lower example of Figure 4, the application screen SC displays generated information such as "Regarding the frequent occurrence of error code 1125, it appears that past inquiries were handled by deleting data GGG in folder FFF.", which is a predetermined response method extracted by the AI ​​from the inquiry case.

[0025] As described above, the business support system 1 acquires registration information to be input to the AI ​​based on the posting information indicating posts input by the user. The business support system 1 inputs the posting information and registration information into the AI ​​and presents the output information output from the AI ​​to the user, thereby supporting the user's business. As a result, the AI ​​generates generated information specific to the business support system 1 rather than a general answer, and the user can obtain generated information suitable for their own business, so the business support system 1 can improve user convenience. Details of the business support system 1 will be described below.

[0026] [3. Functions realized by the business support system] FIG. 5 is a diagram showing an example of functions realized by the business support system 1. As shown in FIG.

[0027] [3-1. Functions realized by the server] For example, the server 10 includes a data storage unit 100, a posted information acquisition unit 101, a registered information acquisition unit 102, and a business support unit 103. Each of the data storage units 100 is realized by a memory unit 12. Each of the posted information acquisition unit 101, the registered information acquisition unit 102, and the business support unit 103 is realized by a control unit 11.

[0028] [Data storage section] The data storage unit 100 stores data for supporting business operations. For example, the data storage unit 100 stores a posted information database DB1 and a registered information database DB2.

[0029] FIG. 6 is a diagram showing an example of the posted information database DB1. The posted information database DB1 is a database in which a plurality of pieces of posted information are stored. For example, the posted information database DB1 stores a posting ID, a posting user ID, location information, posted information, and posting date and time. Any information may be stored in the posted information database DB1. The information stored in the posted information database DB1 is not limited to the example of FIG. 6. For example, the posted information database DB1 may store the number of likes, views, and replies for a post, or other information.

[0030] The posting ID is an ID that can identify a post in the business support system 1. The posting user ID is the user ID of the user who input the post. The user ID is an ID that can identify a user in the business support system 1. When the generated information generated by AI corresponds to the posted information, an ID that can identify the AI ​​may be used as the posting user ID. The location information is information that can identify the location where the post was made. For example, the location information may be the ID of the app where the post was made, the ID of a record, the ID of a thread, the ID of a schedule managed by a schedule management tool with a comment function, the ID of an email managed by an email management tool with a comment function, or another ID.

[0031] Post information is information about posts entered by a user. In this embodiment, the post information indicates a character string (text) entered in a natural language. The post information may indicate information other than a character string. For example, the post information may indicate symbols not classified as characters, emojis, images, files, mention information, reaction information, or other information. The post date and time is the date and time when the post was made. The post indicated by the post information may also be called a comment or a message.

[0032] FIG. 7 is a diagram showing an example of the registration information database DB2. The registration information database DB2 is a database in which a plurality of pieces of registration information are stored. For example, the registration information database DB2 stores vector information and registration information. The information stored in the registration information database DB2 is not limited to the example of FIG. 7. For example, if the actual data of the registration information is stored in a location other than the registration information database DB2, the registration information database DB2 may store a link to the registration information. In addition, for example, the registration information database DB2 may store meta information, which will be described later. The registration information database DB2 may be prepared by a user or by an administrator of the business support system 1.

[0033] Vector information is information that indicates the meaning of registered information in a vector format. Vector information is sometimes called an embedded representation. The vectors indicated by the vector information are used to enable a computer to recognize the meaning of natural language. Vector information may have any number of dimensions and may be in various formats used in the natural language field. Vector information is used as an index used in searching registered information. The index of registered information may be information other than vector information. For example, the index of registered information may be information in which the meaning of words is expressed in a format other than vector format (e.g., an array, a matrix, a single number, or a combination of multiple numbers), keywords, sentences, or other information.

[0034] Registration information is information registered in the business support system 1. Registration information can also be referred to as information related to a user's business. Posted information is also a type of registration information. Registration information may be information other than posted information. For example, registration information may be a record registered in an app (e.g., specific values ​​of a field), a file uploaded to the business support system 1, information registered in a tool other than a communication tool (e.g., a schedule management tool, a task management tool, or a shared email management tool) (e.g., information indicating the specific contents of a schedule, information indicating the specific contents of a task, or information indicating the specific contents of a shared email), or other information.

[0035] For example, the vector information associated with the registered information may be prepared by an administrator of the business support system 1, or the server 10 may acquire the vector information by creating a summary of the registered information and vectorizing the meaning of the summary. The server 10 acquires vector information indicating the meaning of each registered information, and stores the vector information and the registered information in the registered information database DB2. Similarly, when information other than vector information is used as an index for the registered information, the server 10 may associate an index prepared by the administrator with the registered information and store it in the registered information database DB2, or may perform morphological analysis or the like on the registered information to extract keywords, and store them as an index in the registered information database DB2.

[0036] The data stored in the data storage unit 100 is not limited to the above examples. The data storage unit 100 may store data for supporting business operations. For example, the data storage unit 100 may store a default prompt input to the AI. In the case where the AI ​​is not managed by an external system but by the server 10, the data storage unit 100 may store actual data of the AI. The AI ​​includes a program that performs calculations of embedded expressions, etc., and parameters referenced by the program. The data storage unit 100 may store data (e.g., HTML data) for displaying an application screen SC. The data storage unit 100 may store actual data of the contents of application records.

[0037] [Posted Information Acquisition Department] The posted information acquisition unit 101 acquires posted information regarding posts entered by a user in the business support system 1 that supports the user's business. For example, when a user enters a new post using a communication tool such as a comment function of an app, the user terminal 20 transmits posted information indicating the new post to the server 10. The posted information acquisition unit 101 acquires the posted information from the user terminal 20. The posted information acquisition unit 101 stores the posted information in the posted information database DB1. The posted information acquisition unit 101 can acquire any posted information from the posted information database DB1 at any timing. For example, in a case where business support using AI is performed after the posted information is stored in the posted information database DB1, the posted information acquisition unit 101 may acquire, from the posted information database DB1, posted information of the user who made the post that is the target of business support.

[0038] For example, the posted information acquisition unit 101 issues a posting ID for a new post so that it does not overlap with other posting IDs. The posted information acquisition unit 101 associates with the new posting ID and stores in the posted information database DB1 the posting user ID, which is the user ID of the user who posted the post, location information such as the app ID of the app from which the post was made, the posted information, and the posting date and time. The user terminal 20 transmits the posting user ID and location information to the server 10 along with the posted information. The posted information acquisition unit 101 acquires the posting user ID and location information from the user terminal 20. The posted information acquisition unit 101 acquires the date and time when the posted information was acquired as the posting date and time.

[0039] [Registration Information Acquisition Department] The registration information acquisition unit 102 acquires registration information registered in the business support system 1 based on the posted information. In the present embodiment, an example is given in which the registration information acquisition unit 102 acquires registration information from the registration information database DB2. However, the registration information acquisition unit 102 may acquire registration information based on other methods. For example, the registration information acquisition unit 102 may acquire information that is not stored in the registration information database DB2 as the registration information. For example, the registration information acquisition unit 102 may acquire graphed information as the registration information, or may search for registration information by combining multiple search methods. For example, the registration information acquisition unit 102 may search the registration information database DB2 using the posted information as a query based on a known search engine (for example, a search engine provided by a company that operates a search portal site). The search engine outputs registration information corresponding to the posted information, which is the query, based on an index stored in the registration information database DB2. The registration information acquisition unit 102 acquires registration information found in the search by the search engine. The search engine outputs registration information having an index corresponding to the query.

[0040] In this embodiment, vector information is used as an index, and therefore the registered information acquisition unit 102 acquires, from the registered information database DB2, registered information associated with vector information having a similar meaning to the posted information. For example, the registered information acquisition unit 102 inputs the posted information into a known program (e.g., a large-scale language model or an encoder used in natural language processing) that calculates vector information from an input character string, and acquires the vector information of the posted information calculated by the program. For example, the registered information acquisition unit 102 may acquire multiple pieces of registered information using a method similar to the information search method used in Retrieval-Augmented Generation (RAG), which is a mechanism for searching for information and generating answers using the search results.

[0041] For example, the registration information acquisition unit 102 acquires, from the registration information database DB2, registration information associated with vector information that is closest to the vector information of the posted information. The vector information being closest means that the distance in vector space is closest. The registration information acquisition unit 102 may acquire registration information associated with vector information that is second or later closest to the vector information of the posted information. For example, the registration information acquisition unit 102 may acquire up to a predetermined number of registration information in order of proximity to the vector information of the posted information. The registration information acquisition unit 102 may acquire registration information associated with vector information that is within a predetermined distance from the vector information of the posted information.

[0042] For example, as shown in FIG. 2, assume that posted information such as "By the way, which employee should I ask about how to apply for expense reimbursement for my business trip?" is acquired. In this case, the registered information acquisition unit 102 converts the posted information into vector information and identifies, from the registered information database DB2, vector information that is closest to the vector information of the posted information. Since the employee list stored in the registered information database DB2 is registered information related to employees, it is assumed that the vector information of the employee list is closest to the vector information of the posted information. In this case, the registered information acquisition unit 102 acquires the employee list from the registered information database DB2 as registered information.

[0043] For example, as shown in FIG. 3, assume that posted information such as "I'm planning to give an overview of Product DDD at an upcoming seminar, but are there any easy-to-understand materials?" is acquired. In this case, the registered information acquisition unit 102 converts the posted information into vector information and identifies, from the registered information database DB2, vector information that is closest to the vector information of the posted information. Since the catalog of Product DDD stored in the registered information database DB2 is information related to Product DDD, it is assumed that the vector information of the catalog of Product DDD is closest to the vector information of the posted information. In this case, the registered information acquisition unit 102 acquires the catalog from the registered information database DB2 as registered information.

[0044] For example, as shown in FIG. 4, assume that posted information such as "What to do when error code 1125 occurs frequently...I wonder if similar inquiries have been received in the past" is acquired. In this case, the registered information acquisition unit 102 converts the posted information into vector information and identifies, from the registered information database DB2, vector information that is closest to the vector information of the posted information. Since the inquiry cases stored in the registered information database DB2 are information related to inquiry cases received in the past, it is assumed that the vector information of the inquiry case is closest to the vector information of the posted information. In this case, the registered information acquisition unit 102 acquires the inquiry cases from the registered information database DB2 as registered information.

[0045] In addition, when an index other than vector information is associated with the registered information, the registered information acquisition unit 102 may execute a search based on a search engine, using the posted information as a query and referring to the index, and acquire the registered information hit by the search. The registered information acquisition unit 102 may acquire the registered information based on another program (for example, an AI trained to acquire registered information) instead of a search engine.

[0046] [Business Support Department] The business support unit 103 provides business support using AI based on the registration information. In this embodiment, a large-scale language model managed by an external company corresponds to the AI, so the business support unit 103 transmits posted information and registered information to an external system, which is the system of the external company. Upon receiving the posted information and registered information transmitted by the business support unit 103, the external system inputs the registered information into the AI. The business support unit 103 obtains output information of the AI ​​from the external system and presents the output information to the user, thereby providing business support to the user.

[0047] Presenting the output information means transmitting the output information to the user terminal 20. In the examples of FIGS. 2 to 4, the business support unit 103 presents the output information to the user by displaying the output information on the application screen SC. The business support unit 103 may also display the output information on a screen other than the application screen SC (for example, a thread screen, a schedule screen, or an email screen). For example, the business support unit 103 may present the output information to the user using other media such as email instead of the screen of the business support system 1.

[0048] In this embodiment, the AI ​​is exemplified as a GPT (Generative Pre-trained Transformer), but the AI ​​may be of other known types. The AI ​​is not limited to GPT. For example, the AI ​​may be a Transformer-based model other than GPT (e.g., BERT: Bidirectional Encoder Representations from Transformers), a large-scale language model other than a Transformer-based model, a machine learning model not classified as a large-scale language model (e.g., a neural network), or a program that does not use a machine learning technique.

[0049] The AI ​​calculates an embedded representation of information input to it (e.g., registered information) based on parameters adjusted through prior learning. The embedded representation is information that indicates the meaning of the input information. The embedded representation may be in any format. For example, the embedded representation may be a vector, an array, a matrix, a single number, or a combination of multiple numbers. The AI ​​generates and outputs generated information based on the embedded representation. The AI ​​may divide the registered information into units called tokens and calculate an embedded representation for each token. The AI ​​may output generated information based on the sequence of the embedded representations of the tokens, or may output generated information after predicting the next sentence as necessary.

[0050] FIG. 8 is a diagram showing an example of the relationship between input to an AI and output from the AI. The example in FIG. 8 illustrates a case in which the business support unit 103 provides business support to a user by inputting posted information and registered information to the AI ​​and presenting generated information generated by the AI ​​to the user. The business support unit 103 may input only registered information to the AI ​​without inputting posted information. In this embodiment, since the AI ​​is managed by an external system, the business support unit 103 inputs registered information, etc. to the AI ​​by transmitting the registered information, etc. to be input to the AI ​​to the external system.

[0051] For example, the business support unit 103 may input a default prompt to the AI. In the case of a general-purpose AI such as GPT, unless the task to be performed by the AI ​​is clearly specified, it may be difficult to sufficiently improve the accuracy of the generated information generated by the AI. Therefore, the business support unit 103 may input a default prompt to the AI, including a natural language indicating that generated information to support the user's business is to be output, such as "Please generate generated information that supports the business of the organization based on the posted information and registered information." The default prompt may include a natural language indicating what information is to be input to the AI. The default prompt may include tags for embedding the posted information and registered information in a natural language sentence.

[0052] FIG. 8 illustrates the relationship between input and output when posted information such as that shown in FIG. 2 is acquired. For example, assume that posted information such as "By the way, which employee should I ask about how to apply for expense reimbursement for a business trip?" is acquired, and an employee list is acquired as registered information. In this case, the business support unit 103 inputs the posted information and the employee list, which is an example of registered information, to the AI. In the example of FIG. 8, the business support unit 103 also inputs a default prompt to the AI. The AI ​​calculates these embedded expressions and outputs generated information such as "For information about expense reimbursement, you should ask user U20 in the general affairs department." as generated information corresponding to the embedded expressions. The business support unit 103 acquires the generated information output by the AI ​​and displays the generated information in display area A of the application screen SC, thereby providing business support using the AI.

[0053] For example, as shown in Figure 3, assume that posted information such as "I'm planning to give an overview of Product DDD at an upcoming seminar. Are there any easy-to-understand materials?" is acquired, and a catalog for Product DDD is acquired as registered information. In this case, the business support unit 103 inputs the posted information and the Product DDD catalog, which is an example of registered information, to the AI. The AI ​​calculates the embedded representations and outputs generated information such as "Product DDD is a useful tool for improving customer teamwork..." as generated information corresponding to the embedded representation. The business support unit 103 acquires the generated information output by the AI ​​and displays the generated information in display area A of the application screen SC, thereby providing business support using AI.

[0054] For example, as shown in FIG. 4, assume that posted information such as "What to do when error code 1125 occurs frequently... I wonder if similar inquiries have been received in the past" is acquired, and an example of the inquiry is acquired as registered information. In this case, the business support unit 103 inputs the posted information and the example of the inquiry, which is an example of registered information, to the AI. The AI ​​calculates these embedded expressions and outputs generated information according to the embedded expressions, such as "Regarding the frequent occurrence of error code 1125, it seems that in past inquiries, the response was to delete data GGG in folder FFF." The business support unit 103 acquires the generated information output by the AI ​​and displays the generated information in display area A of the application screen SC, thereby providing business support using the AI.

[0055] The business support unit 103 may present the generated information generated by the AI ​​to the user as is, or may present the generated information to the user after adding a fixed phrase such as "Excuse me for interrupting!" to the generated information as shown in FIGS. 2 to 4. The business support unit 103 may provide business support using AI every time a user posts, but posts that do not particularly require business support may also be input. For this reason, the business support unit 103 may determine whether or not to provide business support using AI based on the posted information.

[0056] For example, the business support unit 103 may read the syntax of the posted information, and if the post contains a question, determine to provide business support by AI, and if the post does not contain a question, determine not to provide business support by AI. The business support unit 103 may determine whether to provide business support by AI by using another AI that determines whether to provide business support by AI. The business support unit 103 may provide business support by AI only to users who have turned on the function of business support by AI. The business support unit 103 may provide business support by AI only when a post is made to a specific location such as a specific app or a specific thread. The business support unit 103 may provide business support by AI only when a user explicitly instructs business support by AI.

[0057] [3-2. Functions implemented on user devices] 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. The display control unit 201 and the operation reception unit 202 are each realized by the control unit 21.

[0058] [Data storage section] 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 an application dedicated to the business support system 1.

[0059] [Display control section] 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 application screen SC based on data received from the server 10.

[0060] [Operation reception section] The operation receiving unit 202 receives various operations in the business support system 1. For example, it receives operations on various screens such as the application screen SC. Data indicating the operation content received by the operation receiving unit 202 is transmitted to the server 10. When a user inputs a post, the operation receiving unit 202 transmits, to the server 10, post information indicating the post input by the user.

[0061] [4. Processing performed by the business support system] Fig. 9 is a diagram showing an example of processing executed in the business support system 1. The processing in Fig. 9 is executed by the control units 11 and 21 executing programs stored in the storage units 12 and 22, respectively. The processing in Fig. 9 is executed when a user logs in to the business support system 1 and then uses the comment function of the app to input a post.

[0062] As shown in FIG. 9 , when a user logs in to the business support system 1 and selects an arbitrary record of an arbitrary application, the user terminal 20 executes processing with the server 10 to display an application screen SC showing the contents of the selected record (S1). The user terminal 20 accepts input of a post into the input form F of the application screen SC (S2). When the user performs an operation to complete input of the post, the user terminal 20 generates posted information and transmits it to the server 10 (S3). The server 10 acquires the posted information from the user terminal 20 (S4). The server 10 issues a post ID and stores the posted information in the posted information database DB1 (S5). The server 10 executes processing with the user terminal 20 to update the application screen SC (S6). The processing of S6 causes the post entered by the user to be reflected in the display area A of the application screen SC.

[0063] The server 10 acquires registration information from the registration information database DB2 based on the posted information (S7). The server 10 transmits the posted information acquired in S4 and the registration information acquired in S7 to the external system, thereby inputting them to the AI ​​(S8). In S8, the server 10 may also transmit a default prompt to the external system. The server 10 acquires generated information corresponding to the posted information and the registration information from the AI ​​of the external system (S9). The server 10 stores the generated information of the AI ​​in the posted information database DB1 as posted information by the AI ​​(S10). The server 10 executes processing to update the application screen SC between the server 10 and the user terminal 20 (S11), and this processing ends. As a result of the processing of S11, the output information from the AI ​​is reflected as a new comment in the display area A of the application screen SC.

[0064] [5. Summary of embodiments] The business support system 1 of this embodiment acquires posted information regarding posts input by users to the business support system 1. The business support system 1 acquires registered information from a registered information database DB2 based on the posted information. The business support system 1 performs business support using AI based on the registered information. This allows the AI ​​to generate generated information specific to the business support system 1, rather than a general answer, using the registered information specific to the business support system 1. Since users can obtain generated information suitable for their own business, the business support system 1 can increase user convenience.

[0065] Furthermore, the business support system 1 provides business support to users by inputting posted information and registered information into the AI ​​and presenting generated information generated by the AI ​​to the user. This allows the business support system 1 to have the AI ​​generate generated information according to the posted information as well as the registered information, and therefore can present generated information that matches the specific content of the user's post to the user. As a result, the user can obtain generated information that matches the content of the business they are currently facing, thereby improving user convenience.

[0066] [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.

[0067] 10 is a diagram showing an example of functions realized in the modified business support system 1. As shown in FIG. 10, the modified example described below realizes a meta information acquisition unit 104, a feedback acquisition unit 105, a learning unit 106, an attribute information acquisition unit 107, and a location information acquisition unit 108. Each of the meta information acquisition unit 104, the feedback acquisition unit 105, the learning unit 106, the attribute information acquisition unit 107, and the location information acquisition unit 108 is realized by the control unit 11.

[0068] [6-1. Variation 1] For example, the registration information acquisition unit 102 may acquire only one piece of registration information, but in Modification 1, an example is given in which the registration information acquisition unit 102 acquires multiple pieces of registration information. A search engine that searches for registration information may calculate relevance information regarding the relevance between each of the multiple pieces of registration information and the posted information. The registration information acquisition unit 102 of Modification 1 acquires multiple pieces of registration information associated with relevance information regarding the relevance with the posted information.

[0069] Relevance refers to the degree to which registered information matches posted information. For example, relevance information may be a ranking according to the degree of relevance to posted information, or a score indicating the degree of relevance to posted information. The score may be a known score such as TF-IDF (Term Frequency-Inverse Document Frequency). The calculation method for relevance information may be the same as that used by known search engines. For example, relevance information may be expressed using numbers, characters, symbols, or a combination thereof.

[0070] The business support unit 103 of the first modification provides business support using an AI based on the relevance information for each of the multiple pieces of registered information. For example, the business support unit 103 inputs each of the multiple pieces of registered information and the relevance information associated with each of the multiple pieces of registered information to the AI. The AI ​​calculates an embedded expression based on this information and outputs generated information corresponding to the embedded expression. The business support unit 103 may input only registered information, among the multiple pieces of registered information, whose relevance indicated by the relevance information is relatively high to the AI. A relatively high relevance means that the ranking is at or above a predetermined rank, the score is in the top m places (m is an arbitrary natural number that is a threshold), or the score is at or above a threshold.

[0071] For example, the search engine calculates the relevance information based on an algorithm used in general-purpose searches, rather than an algorithm specific to the business support system 1. In this case, the relevance information calculated by the search engine may not be relevance information specific to the business support system 1. Therefore, in Modification 1, an example is given of a case where the relevance information calculated by the search engine is changed by meta information, which is information specific to the business support system 1.

[0072] The business support system 1 of the first modification example includes a meta information acquisition unit 104. The meta information acquisition unit 104 acquires meta information associated with each of a plurality of pieces of registered information. The meta information is incidental information associated with the registered information. The meta information can also be considered an attribute of the registered information. For example, if the registered information is other posted information (e.g., posted information entered by another user) different from the posted information acquired by the posted information acquisition unit 101, the meta information may be the number of likes, views, replies, posting user ID, posting time, or other information of the other posted information. The meta information may be information indicating the importance of the registered information. For example, registered information with a large number of likes, views, or replies is attracting attention from more users and is therefore highly important information. Registered information posted by a user with a specific posting user ID, such as an executive of an organization, is highly important information.

[0073] The meta information may be any information corresponding to the registration information. The meta information is not limited to the number of likes described above. For example, if the registration information is a document such as an employee directory, a catalog, or an inquiry example, the meta information may be the update date and time or version of the document. This meta information is stored in the registration information database DB2. The meta information acquisition unit 104 acquires, from the registration information database DB2, meta information associated with each of the multiple pieces of registration information acquired by the registration information acquisition unit 102. The meta information may be stored in a database other than the registration information database DB2. In this case, the meta information acquisition unit 104 may acquire, from the other database, meta information associated with each of the multiple pieces of registration information acquired by the registration information acquisition unit 102.

[0074] The business support unit 103 of the first modification example changes the relevance information of each of the plurality of registered information based on the meta information of each of the plurality of registered information, and inputs the changed relevance information of each of the plurality of registered information to the AI. For example, the business support unit 103 changes the relevance information based on the meta information of each of the plurality of registered information so that the relevance indicated by the relevance information of registered information that is relatively important in the business support system 1 becomes higher. The importance is estimated based on the content of the meta information. For example, a large number of likes, views, replies, or other numerical values ​​corresponds to high importance. For example, if the posting user ID is a specific user ID (e.g., the user ID of an executive of an organization), this corresponds to high importance.

[0075] For example, suppose that each of the multiple pieces of registered information is posted information different from the posted information acquired by the posted information acquisition unit 101. Furthermore, consider a case where the number of likes corresponds to the meta information. In this case, the business support unit 103 changes the relevance information of each of the multiple pieces of registered information according to the number of likes indicated in the meta information of the registered information. The business support unit 103 changes the relevance information so that the relevance indicated by the relevance information of registered information with a relatively large number of likes becomes higher.

[0076] FIG. 11 is a diagram showing an example of relevance information changed in Modification Example 1. For example, when the relevance information indicates a ranking, the business support unit 103 rearranges the ranking based on the number of likes for each of the multiple registered information. That is, the business support unit 103 reranks each of the multiple registered information based on the number of likes for each of the multiple registered information. The business support unit 103 may simply rerank in order of the number of likes, or may change the ranking so that only registered information with a number of likes equal to or greater than a threshold is ranked higher than its current ranking. As another example, the business support unit 103 may change the ranking so that only registered information with a number of likes less than a threshold is ranked lower than its current ranking.

[0077] 11, the registered information acquisition unit 102 acquires registered information A associated with relevance information indicating a first ranking, registered information B associated with relevance information indicating a second ranking, registered information C associated with relevance information indicating a third ranking, registered information D associated with relevance information indicating a fourth ranking, registered information E associated with relevance information indicating a fifth ranking, and registered information F associated with relevance information indicating a sixth ranking. These rankings are calculated by the search engine.

[0078] For example, the meta information acquisition unit 104 acquires the number of likes for each of the registered information A to F as meta information. If the number of likes for the registered information B and D is greater than the number of likes for the registered information A, C, E, and F, the business support unit 103 changes the ranking of the registered information B and D, which have a relatively large number of likes, so that they are ranked higher than the ranking calculated by the search engine. In other words, the business support unit 103 changes the ranking of the registered information B and D, which have a relatively small number of likes, so that they are ranked lower than the ranking calculated by the search engine.

[0079] For example, the business support unit 103 supports the user's business by inputting the posted information, the registered information A to F, the rankings of each of the registered information A to F after the change, and a default prompt into the AI, and presenting the generated information output from the AI ​​to the user. As the default prompt, a prompt to generate the generated information based on the rankings, such as "Please generate the generated information taking into consideration the rankings of each of the multiple registered information," may be used. The business support unit 103 may input only the registered information that has a relatively high ranking after the change among the registered information A to F (for example, only the top three registered information B, D, and A) to the AI.

[0080] The business support unit 103 may determine the final ranking based solely on the number of likes for each of the registered information A to F. However, in this case, the final ranking will be in descending order of the number of likes, and the calculation results of the search engine will not be reflected. For this reason, the business support unit 103 may determine the final ranking by comprehensively considering the ranking calculated by the search engine and the number of likes for each of the registered information A to F. For example, the business support unit 103 may determine the final ranking so that fluctuations in the ranking based on the number of likes remain within a predetermined rank (for example, so that the ranking calculated by the search engine will not rise higher than third place no matter how many likes there are).

[0081] For example, when the relevance information indicates a score, the business support unit 103 changes the score based on the number of likes for each of the multiple registered information. The business support unit 103 may increase or decrease the score depending on the number of likes, or may change only the score of registered information with a number of likes equal to or greater than a threshold so as to be higher than the current score. As another example, the business support unit 103 may change only the score of registered information with a number of likes less than a threshold so as to be lower than the current score. The business support unit 103 may input data to the AI ​​based on the changed relevance information. For example, the business support unit 103 may input the changed relevance information to the AI, or may input only registered information with a relatively high relevance indicated by the changed relevance information to the AI.

[0082] Note that even when the meta information is information other than the number of likes, the business support unit 103 may change the relevance information for each of the plurality of registered information based on the meta information for each of the plurality of registered information. For example, when the meta information is the number of views or the number of replies, the business support unit 103 may change the relevance information so that the ranking of registered information with a relatively high number of views or replies is increased above the current ranking or the score of the registered information is increased above the current score. When the meta information is a posting user ID, the business support unit 103 may change the relevance information so that the ranking of registered information of a specific posting user ID is increased above the current ranking or the score of the registered information is increased above the current score.

[0083] The business support system 1 of the first modification acquires a plurality of pieces of registered information associated with relevance information regarding the relevance to posted information. The business support system 1 acquires meta information associated with each of the plurality of pieces of registered information. The business support system 1 changes the relevance information for each of the plurality of pieces of registered information based on the meta information for each of the plurality of pieces of registered information, and provides input to the AI ​​based on the changed relevance information for each of the plurality of pieces of registered information. This allows the business support system 1 to provide input to the AI ​​based on relevance information suitable for the business support system 1, thereby improving the accuracy of business support.

[0084] [6-2. Variation 2] For example, as described in the embodiment, the business support unit 103 may input registration information to the AI. In this case, the AI ​​may calculate a score related to the likelihood of the generated information. The score indicates the accuracy of the generated information. The score may also be called likelihood, certainty, or probability. The score calculation method may be the same as a known method. For example, the AI ​​may calculate the score of the generated information based on a known calculation method such as an n-gram model, a hidden Markov model, a transformer model, or a probabilistic language model. The score is expressed as a number, a character, a symbol, or a combination thereof. In the second modification, the score is a number. The higher the number, the more likely the generated information is. The score in the second modification is calculated by the AI, and therefore differs from the score of the example of relevance information in the first modification.

[0085] The business support unit 103 of the second modification acquires generated information generated by an AI and a score related to the likelihood of the generated information. The business support unit 103 provides business support to the user by presenting the generated information to the user based on the score. For example, the business support unit 103 determines whether the score is equal to or greater than a threshold. If the business support unit 103 determines that the score is less than the threshold, it does not present the generated information to the user (does not provide business support to the user), and if it determines that the score is equal to or greater than the threshold, it presents the generated information to the user (provides business support to the user).

[0086] The business support system 1 of the second modification inputs registration information to an AI and acquires generated information generated by the AI ​​and a score related to the likelihood of the generated information. The business support system 1 provides business support to the user by presenting the generated information to the user based on the score. This allows the business support system 1 to provide appropriate business support according to the score of the generated information. For example, the business support system 1 can prevent generated information with a low score from being presented to the user. By presenting generated information with a high score to the user, the business support system 1 can present more accurate generated information to the user. From the user's perspective, being presented with low-accuracy generated information every time the user posts something can be cumbersome, but the business support system 1 prevents the user from feeling this cumbersome and can provide more appropriate business support.

[0087] [6-3. Variation 3] For example, the business support system 1 may be configured to accept feedback from the user regarding business support provided by AI. The feedback may be provided by a selection indicating that the generated information is good, a selection indicating that the generated information is not good, input of a score indicating an evaluation of the generated information generated by AI, input of a natural language string indicating specific feedback content from the user, or other operation. For another example, if the generated information presented to the user includes a link, whether or not the user selected the link may correspond to feedback. If a new post by the user after the generated information is presented includes content related to the generated information, it is possible that the user used the generated information as a reference, and therefore the new post may correspond to feedback. Variation 3 illustrates an example in which feedback from the user is learned by AI.

[0088] The business support system 1 of the third modification includes a feedback acquisition unit 105 and a learning unit 106. The feedback acquisition unit 105 acquires feedback from the user regarding business support by AI. For example, when a feedback icon is displayed near the AI-generated information displayed on the application screen SC, the feedback acquisition unit 105 acquires feedback from the user based on an operation on the icon. When an icon indicating that the generated information is good is selected, the feedback acquisition unit 105 acquires feedback indicating that the generated information is good. When an icon indicating that the generated information is poor is selected, the feedback acquisition unit 105 acquires feedback indicating that the generated information is poor.

[0089] For example, when a user interface part that accepts input of a score for feedback is displayed near the AI ​​generation information displayed on the application screen SC, the feedback acquisition unit 105 acquires the score entered by the user based on an operation on the part as feedback.When an input form that accepts input of a character string in a natural language for feedback is displayed near the AI ​​generation information displayed on the application screen SC, the feedback acquisition unit 105 acquires the character string entered into the input form as feedback.

[0090] The learning unit 106 causes the AI ​​to learn the feedback. The learning method for causing the AI ​​to learn the feedback from the user may be the same as a known learning method. For example, the learning unit 106 may cause the AI ​​to learn the feedback by having the AI ​​learn the feedback from the user as a reward in reinforcement learning. In this case, the learning unit 106 causes the AI ​​to learn the feedback by fine-tuning the parameters of the AI ​​based on the feedback from the user and the reinforcement learning algorithm.

[0091] For example, the learning unit 106 may treat user feedback as training data based on a learning method called supervised learning, thereby causing the AI ​​to learn the feedback. As described in the embodiment, when the AI ​​is managed by an external system, the learning unit 106 may transmit user feedback to the external system, causing the AI ​​to learn the feedback. In this case, the process of adjusting the AI ​​parameters is performed by the external system. When the business support system 1 manages the AI, the learning unit 106 itself may adjust the AI ​​parameters based on the feedback.

[0092] The business support system 1 of the third modification acquires feedback from the user regarding business support provided by the AI. The business support system 1 causes the AI ​​to learn the feedback. This allows the business support system 1 to improve the accuracy of the AI ​​through feedback from the user. The business support system 1 can provide highly accurate business support, thereby effectively improving user convenience.

[0093] [6-4. Variation 4] For example, the information that the business support unit 103 refers to for business support using AI is not limited to the posted information and registered information described in the embodiment. Modification 4 takes as an example a case where attribute information about a user is referenced. Attribute information is information about the attributes of a user. Attributes can also be considered as classifications of users. For example, attribute information may be the user's organization, industry, department, position, team, role, years of service, or other profile. Attribute information may also be demographic information such as the user's gender or age.

[0094] The business support system 1 of the fourth modification includes an attribute information acquisition unit 107. The attribute information acquisition unit 107 acquires attribute information related to a user. The data storage unit 100 of the fourth modification stores a user database in which various information about a user is stored. For example, the user database associates a user ID with attribute information. The attribute information acquisition unit 107 acquires the attribute information of the user from the user database. In the example of the application screen SC of FIGS. 2 to 4, when a user inputs a post in the input form F, the attribute information acquisition unit 107 acquires attribute information associated with the user ID of the user.

[0095] The method for identifying the user ID may be the same as the method adopted in known online services. For example, the attribute information acquisition unit 107 may identify which user is accessing the server 10 based on a session ID that can identify a session between the server 10 and the user terminal 20, and acquire attribute information associated with the user ID of the user. The user attribute information may be stored in a database other than the user database, a computer other than the server 10, or an information storage medium. In this case, the attribute information acquisition unit 107 may acquire the attribute information from the other database, the other computer, or the information storage medium.

[0096] The business support unit 103 of the fourth modification provides business support using AI based on attribute information. For example, the business support unit 103 inputs not only the posted information, registered information, and default prompt, but also attribute information to the AI. The default prompt may contain an instruction in natural language to generate generated information based on the attribute information, such as "Please generate generated information based on the user's attribute information." The AI ​​calculates an embedded expression based on not only the posted information, registered information, and default prompt, but also the attribute information, and outputs the generated information based on the embedded expression. The business support unit 103 obtains the generated information output from the AI ​​and provides business support using AI by presenting the generated information to the user.

[0097] For example, suppose the attribute information is the user's job title. Furthermore, suppose the default prompt includes an instruction such as, "Generate generated information according to the user's job title." In this case, the AI ​​outputs generated information according to the user's job title. For example, if the user is an executive, he or she may be familiar with information about the entire organization, but may not have detailed knowledge of the specifications of individual products. Therefore, the AI ​​may generate generated information that includes detailed specifications of the target product rather than information about the entire organization. If the user is a new employee, he or she may not have knowledge of both information about the entire organization and the detailed specifications of individual products. Therefore, the AI ​​may generate generated information that includes an overview of both.

[0098] The business support system 1 of the fourth modification acquires attribute information about a user. The business support system 1 provides business support using AI based on the attribute information. This allows the business support system 1 to provide business support according to the user's attribute information, thereby further improving user convenience. For example, since the AI ​​may vary the content of the generated information depending on attribute information such as the user's job title, the business support system 1 can present generated information appropriate for the user.

[0099] [6-5. Variation 5] For example, the content of appropriate business support may change depending on the location where the user posted. The location here does not refer to the real-world location where the user is, but to the location on the business support system 1 where the user uploaded the posted information. For example, the app where the user posted, the thread where the user posted, the schedule where the user posted, or the email where the user posted corresponds to the location where the user posted. Variation 5 takes as an example a case where business support is provided depending on the location where the user posted.

[0100] The business support system 1 of the fifth modification includes a location information acquisition unit 108. The location information acquisition unit 108 acquires location information related to a location where a post was made in the business support system 1. In the fifth modification, an example is given in which the location information is stored in the posted information database DB1. Therefore, the location information acquisition unit 108 acquires the location information from the posted information database DB1. The location information may be stored in a database other than the posted information database DB1, a computer other than the server 10, or an information storage medium. In this case, the location information acquisition unit 108 may acquire the location information from the other database, the other computer, or the information storage medium.

[0101] The business support unit 103 of the fifth modification example performs business support using AI based on location information. For example, the business support unit 103 inputs not only the posted information, registered information, and default prompt, but also location information to the AI. The default prompt may contain an instruction in natural language to generate generated information based on the location information, such as "Please generate generated information based on the user's location information." The AI ​​calculates an embedded expression based on not only the posted information, registered information, and default prompt, but also the location information, and outputs the generated information based on the embedded expression. The business support unit 103 obtains the generated information output from the AI ​​and presents the generated information to the user, thereby performing business support using AI.

[0102] For example, suppose the location information indicates the app in which the user posted. Furthermore, suppose the default prompt includes an instruction such as, "Generate generated information according to the app in which the user posted." In this case, the AI ​​outputs generated information according to the app in which the user posted. For example, if the user posts to a customer management app, generated information including content related to the customer may be appropriate. Therefore, the AI ​​may generate generated information including content related to the customer. If the user posts to an expense reimbursement app, generated information including content related to the expense reimbursement may be appropriate. Therefore, the AI ​​may generate generated information including content related to the expense reimbursement.

[0103] The business support system 1 of the fifth modification acquires location information about the location where a post was made in the business support system 1. The business support system 1 provides business support using AI based on the location information. This allows the business support system 1 to provide business support according to the location where the user made the post, thereby further improving user convenience. For example, the AI ​​may vary the content of the generated information depending on the location where the user made the post, so the business support system 1 can present generated information appropriate for the user.

[0104] [6-6. Variation 6] For example, in Variation 1, an example was given of a case where meta information is used to change relevance information. Meta information may be used for purposes other than changing relevance information. Variation 6 describes an example of another use of meta information. The business support system 1 of Variation 6 includes a meta information acquisition unit 104. The meta information acquisition unit 104 is as described in Variation 1. In Variation 6, the meta information acquisition unit 104 may be a function included in the registration information acquisition unit 102.

[0105] The registration information acquisition unit 102 of the sixth modification acquires registration information based on meta information. For example, the registration information acquisition unit 102 may acquire registration information based not only on vector information but also on meta information. If the meta information is the number of likes, the registration information acquisition unit 102 preferentially acquires registration information for which the number of likes indicated by the meta information is relatively large. The registration information acquisition unit 102 may calculate an appropriateness score indicating the appropriateness of the registration information based on the vector information and the meta information, and acquire the registration information based on the appropriateness score.

[0106] For example, the formula for calculating the suitability score may be determined so that the shorter the distance in the vector space described in the embodiment and the greater the number of likes, the higher the suitability score. The formula for calculating the suitability score is assumed to be stored in the data storage unit 100. The same applies when the number of views or the number of replies is used as meta information other than the number of likes. The registered information acquisition unit 102 acquires registered information with a relatively high suitability score. For example, the registered information acquisition unit 102 may acquire registered information with the highest suitability score. The registered information acquisition unit 102 may acquire a predetermined number of registered information with the highest suitability score (for example, the top five registered information). The registered information acquisition unit 102 may acquire registered information with a suitability score equal to or greater than a threshold.

[0107] For example, if the meta information is a posting user ID, the registration information acquisition unit 102 preferentially acquires registration information in which the posting user ID indicated by the meta information is a specific user ID (e.g., the user ID of an executive). A formula for calculating the suitability score may be defined so that the suitability score is high when the distance in the vector space described in the embodiment is short and the meta information indicates a specific user ID. The registration information acquisition unit 102 acquires registration information with a relatively high suitability score. The flow of business support after the registration information acquisition unit 102 acquires the registration information may be the same as in the embodiment or modified examples 1 to 5.

[0108] The business support system 1 of the sixth modification acquires meta information associated with the registration information. The business support system 1 acquires the registration information further based on the meta information. This allows the business support system 1 to provide business support based on the registration information corresponding to the meta information, thereby enabling more appropriate business support. The business support system 1 can improve user convenience. For example, the business support system 1 can provide business support based on highly important registration information with a relatively high number of likes. The business support system 1 can provide business support based on registration information posted by executives of an organization.

[0109] [6-7. Variation 7] For example, as explained somewhat in the embodiment, the registration information database DB2 may store schedule information relating to the schedules of other users different from the user as registration information. The schedule information is information indicating details of the schedule. For example, the schedule information may indicate the date and time of the schedule, the title, the location, the participants, notes, the reserved facilities, or other information. The schedule information may be similar to information employed in known schedule management tools. In the seventh modification, it is assumed that information capable of identifying which schedule information belongs to which user is stored in the registration information database DB2.

[0110] FIG. 12 is a diagram showing an example of an application screen SC according to the seventh modification. The registration information acquisition unit 102 according to the seventh modification acquires schedule information as registration information. For example, the registration information acquisition unit 102 identifies other users designated by a user based on the user's posted information. In the example at the top of FIG. 12, the character string included in the user's post includes the name of the other user (e.g., "user U20"). The data storage unit 100 according to the seventh modification stores a user database in which information such as the names of various users who use the business support system 1 is stored. The registration information acquisition unit 102 identifies the names of the other users included in the post by comparing the character string indicated in the posted information with the names stored in the user database. The registration information acquisition unit 102 acquires schedule information of the identified other users from the registration information database DB2. The other users may be identified by other information such as a user ID instead of by name.

[0111] The business support unit 103 of Modification 7 provides business support using AI based on schedule information. In Modification 7, the AI ​​is not a so-called generative AI, which uses a large-scale language model as an example, but is a program that supports a user's business through information processing. Actual data of the AI ​​is stored in the data storage unit 100. For example, the business support unit 103 provides business support by displaying the contents of the schedule information acquired by the registration information acquisition unit 102 on the application screen SC through processing of a program equivalent to the AI. In the example at the bottom of FIG. 12 , the business support unit 103 displays the contents of the schedule information (for example, the dates and times when other users have plans indicated by the posted information) on the application screen SC as a post indicating a response from the AI. The business support unit 103 may also display the free time of other users identified based on the schedule information on the application screen SC as a post indicating a response from the AI.

[0112] Note that in Variation 7, the AI ​​may also be a so-called generation AI. In this case, the business support unit 103 inputs not only the posted information, registered information, and default prompt, but also schedule information to the AI. The default prompt may contain an instruction in natural language to generate generation information according to the schedule information, such as "Please generate generation information according to the user's schedule information." The AI ​​calculates an embedded expression based on not only the posted information, registered information, and default prompt, but also the schedule information, and outputs the generation information according to the embedded expression. The business support unit 103 may obtain the generation information output from the AI ​​and present the generation information to the user, thereby providing business support using the AI.

[0113] In the registration information database DB2 of the seventh modification, schedule information relating to the schedules of other users different from the user is stored as registration information. The business support system 1 acquires the schedule information as registration information. The business support system 1 provides business support using AI based on the schedule information. This allows the business support system 1 to provide business support according to the schedule information, thereby further improving user convenience.

[0114] [6-8. Variation 8] For example, in Variation 7, a user may make a post by mentioning another user. A mention is a designation of another user to whom the user wants to notify about a post. For example, a user can mention another user by entering a specific symbol (e.g., @) followed by the other user's information (e.g., the other user's name). The mention is displayed on the screen of the other user. The mechanism for mentioning may be similar to a known mechanism. For example, an email indicating that the mentioned user has been mentioned may be sent to the mentioned user.

[0115] FIG. 13 is a diagram showing an example of an application screen SC of Modification Example 8. As shown in the upper part of FIG. 13, the posted information acquisition unit 101 acquires posted information in which another user is mentioned. In the example in the upper part of FIG. 13, a user mentions another user by inputting a specific symbol (e.g., @) followed by the name of the other user (e.g., the character string "User U3"). The posted information includes the specific symbol followed by the name of the other user. The other user can know that they have been mentioned by a notification function on the business support system 1, email, or the like.

[0116] The registration information acquisition unit 102 of the eighth modification acquires, as registration information, schedule information of other users mentioned in posted information. For example, the registration information acquisition unit 102 identifies the name of the other user entered after a specific symbol in the posted information. The registration information acquisition unit 102 acquires the schedule information of the identified other users from the registration information database DB2. When multiple other users are mentioned in a single piece of posted information, the registration information acquisition unit 102 acquires the schedule information of each of the multiple other users.

[0117] The business support unit 103 of Modification 8 provides business support using an AI based on schedule information of another user mentioned in the posted information. In Modification 8, as in Modification 7, the AI ​​is not a so-called generating AI, but a program that supports a user's business through information processing. For example, the business support unit 103 provides business support by displaying the contents of the schedule information acquired by the registration information acquisition unit 102 on the application screen SC through processing of a program equivalent to the AI. In the example at the bottom of FIG. 13 , the business support unit 103 displays the contents of the schedule information (e.g., the date and time when another user mentioned in the posted information has an appointment) on the application screen SC as a post indicating a response from the AI. The business support unit 103 may also display the free time of another user identified based on the schedule information on the application screen SC as a post indicating a response from the AI. Note that in Modification 8, as in Modification 7, the AI ​​may be a so-called generating AI.

[0118] The business support system 1 of Variation 8 acquires posted information in which another user is mentioned. The business support system 1 acquires schedule information of the other user mentioned in the posted information as registration information. The business support system 1 provides business support using AI based on the schedule information of the other user mentioned in the posted information. This allows the business support system 1 to provide business support according to the schedule information of the mentioned other user, thereby further improving user convenience. For example, the user can easily know the schedule of the person who mentioned the person without having to display the schedule screen of the person. For example, the user can easily know whether the person is available to reply immediately.

[0119] [6-9. Variation 9] For example, a user can input posted information in any language. The registered information may be in the same language as the posted information, or in a language different from the language of the posted information. An example is given in which the registered information acquisition unit 102 of Variation 9 acquires registered information written in a language different from the language of the posted information. The vector information stored in the registered information database DB2 may be common regardless of language, or vector information may be prepared for each language. The language of the posted information may be identified by any method; for example, the user may specify the language themselves, or the language of the posted information may be identified by natural language processing.

[0120] The business support unit 103 of the ninth modification provides business support using an AI based on registered information written in a language different from the language of the posted information. For example, the business support unit 103 inputs the posted information written in a first language and the registered information written in a second language different from the first language to the AI. Since users often wish to view generated information in the same first language as their own posts, a default prompt in which an instruction such as "Please generate generated information in the same first language as the user's posted information" is written in a natural language may be input to the AI.

[0121] For example, the AI ​​calculates an embedded expression based on posted information in a first language, registered information in a second language, and a default prompt, and outputs generated information corresponding to the embedded expression. The business support unit 103 may obtain the generated information output from the AI ​​and present the generated information to a user, thereby providing business support using the AI. The business support unit 103 may machine-translate posted information in the first language into the second language and input the translated information to the AI. The business support unit 103 may machine-translate registered information in the second language into the first language and input the translated information to the AI.

[0122] The business support system 1 of the ninth modification acquires registered information written in a language different from the language of the posted information. The business support system 1 provides business support using AI based on the registered information written in the different language. This allows the business support system 1 to provide business support in various languages, thereby improving user convenience.

[0123] [6-10. Other variations] For example, two or more of the modifications 1 to 9 may be combined.

[0124] For example, the functions described as being realized by the server 10 may be realized by the user terminal 20. In this case, the functions may be realized by a browser script or an application installed on the user terminal 20. For example, each function may be shared among multiple computers or may be realized by a single computer. [Explanation of symbols]

[0125] 1 Business support system, 10 Server, 11,21 Control unit, 12,22 Memory unit, 13,23 Communication unit, 20 User terminal, 24 Operation unit, 25 Display unit, A Display area, F Input form, N Network, SC App screen, 100 Data storage unit, 101 Post information acquisition unit, 102 Registration information acquisition unit, 103 Business support unit, 104 Meta information acquisition unit, 105 Feedback acquisition unit, 106 Learning unit, 107 Attribute information acquisition unit, 108 Location information acquisition unit, 200 Data storage unit, 201 Display control unit, 202 Operation reception unit, DB1 Post information database, DB2 Registration information database.

Claims

1. a posting information acquisition unit that acquires posting information regarding a posting input by a user to a business support system that supports the user's business; a registration information acquisition unit that acquires registration information registered in the business support system based on the posted information; A business support unit that provides business support using AI (Artificial Intelligence) based on the registered information; Business support system including.

2. The business support unit inputs the posted information and the registered information into the AI ​​and presents generated information generated by the AI ​​to the user, thereby providing the business support to the user. The business support system according to claim 1 .

3. the registration information acquisition unit acquires a plurality of pieces of registration information associated with relevance information regarding a relevance to the posted information; the business support system further includes a meta information acquisition unit that acquires meta information associated with each of the plurality of pieces of registered information; The business support unit changes the relevance information for each of the plurality of pieces of registered information based on the meta information for each of the plurality of pieces of registered information, and performs input to the AI ​​based on the changed relevance information for each of the plurality of pieces of registered information. The business support system according to claim 2 .

4. The business support department inputting the registration information into the AI; Obtaining generated information generated by the AI ​​and a score regarding the likelihood of the generated information; providing the business support to the user by presenting the generated information to the user based on the score; The business support system according to any one of claims 1 to 3.

5. The business support system includes: a feedback acquisition unit that acquires feedback from the user regarding the business support provided by the AI; A learning unit that causes the AI ​​to learn the feedback; 4. The business support system according to claim 1, further comprising:

6. the business support system further includes an attribute information acquisition unit that acquires attribute information about the user; The business support unit performs the business support using the AI ​​further based on the attribute information. The business support system according to any one of claims 1 to 3.

7. the business support system further includes a location information acquisition unit that acquires location information regarding a location where the post was made in the business support system; The business support unit performs the business support using the AI ​​further based on the location information. The business support system according to any one of claims 1 to 3.

8. the business support system further includes a meta information acquisition unit that acquires meta information associated with the registration information, the registration information acquisition unit acquires the registration information based on the meta information. The business support system according to any one of claims 1 to 3.

9. the registration information acquisition unit acquires, as the registration information, schedule information relating to a schedule of another user different from the user; The business support unit performs the business support using the AI ​​based on the schedule information. The business support system according to any one of claims 1 to 3.

10. the posted information acquisition unit acquires the posted information in which the other user is mentioned, the registration information acquisition unit acquires, as the registration information, the schedule information of the other user mentioned in the posted information; The registration information acquisition unit performs the business support using the AI ​​based on the schedule information of the other user mentioned in the posted information. The business support system according to claim 9.

11. the registration information acquisition unit acquires the registration information written in a language different from the language of the posted information; The business support unit performs the business support using the AI ​​based on the registration information written in the different languages. The business support system according to any one of claims 1 to 3.

12. a post information acquisition step of acquiring post information regarding a post input by a user to a business support system that supports the user's business; a registration information acquisition step of acquiring registration information registered in the business support system based on the posted information; A business support step of providing business support using AI (Artificial Intelligence) based on the registered information; Business support methods including:

13. a posting information acquisition unit that acquires posting information regarding a posting input by a user to a business support system that supports the user's business; a registration information acquisition unit that acquires registration information registered in the business support system based on the posted information; a business support department that provides business support using AI (Artificial Intelligence) based on the registered information; A program that allows a computer to function as a

Images