Business management system, business management method, and program

Abstract

To generate specified outputs suited to individual applications from a business overview indicating a basic business flow.SOLUTION: A business management system for managing a specified business is configured to: acquire a business overview of the specified business; and transmit question data to a large-scale language model based on the acquired business overview to acquire, as an answer, at least one of generating a name of the specified business, generating business details, generating a business department, and identifying a business manager; and generate a specified output based on the acquired answer.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a technique that is effective for managing a given task. [Background technology]

[0002] 2. Description of the Related Art Conventionally, systems that automatically support input of business operations are known. For example, Patent Document 1 discloses a system that automatically records the work hours of cargo handling and other operations in a daily report. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent 7180719 Summary of the Invention [Problem to be solved by the invention]

[0004] However, this is merely an automation of daily work reports. The inventors have noticed that when such work procedures are changed, there is a problem. That is, when a conventional work procedure is changed, all documents such as the work list and the work procedure manual must be revised, which is time-consuming. The inventors therefore came up with the idea of ​​automatically creating and updating documents such as task lists and task procedure manuals based on an outline of basic task procedures.

[0005] The present invention aims to provide a business management system, business management method, and program that are capable of generating specified outputs (creating a list of tasks, creating business procedure manuals, etc.) suited to individual purposes from a business overview that shows the basic business flow. [Means for solving the problem]

[0006] The present invention provides a business management system for managing a predetermined business, A business summary acquisition unit that acquires a business summary of the predetermined business; an answer acquisition unit that acquires, as an answer, at least one of generating a name of the predetermined business, generating business details, generating a business department, and identifying a business person by transmitting question data to a large-scale language model based on the acquired business summary; A generation unit that generates a predetermined output based on the obtained answer; The present invention provides a business management system comprising:

[0007] According to the present invention, content relating to a predetermined task is obtained as an answer from a large-scale language model based on a task summary of the predetermined task, and a predetermined output is generated based on this answer. As a result, it is possible to generate specific outputs suited to individual purposes from a business overview showing a basic business flow.

[0008] Although the present invention is in the category of a system, the same functions and effects can be obtained with a method and a program. Effect of the Invention

[0009] According to the present invention, it is possible to generate a predetermined output that matches an individual purpose from a business overview that shows a basic business flow. [Brief description of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram for explaining an overview of a business management system 1. [Diagram 2] FIG. 1 is a diagram illustrating a functional configuration of a business management system 1. [Diagram 3] FIG. 13 is a flowchart showing a generation process executed by a computer 10. [Figure 4] 1A and 1B are diagrams illustrating examples of question data and answer data. [Diagram 5] 1A and 1B are diagrams illustrating examples of question data and answer data. [Figure 6]1A and 1B are diagrams illustrating examples of question data and answer data. [Figure 7] 1A and 1B are diagrams illustrating examples of question data and answer data. [Figure 8] 1A and 1B are diagrams illustrating examples of question data and answer data. [Figure 9] 1A and 1B are diagrams illustrating examples of question data and answer data. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Hereinafter, a detailed description will be given of an embodiment of the present invention with reference to the accompanying drawings. In the following drawings, the same elements are designated by the same numbers or symbols throughout the description of the embodiment.

[0012] [Overview of Business Management System 1] 1 is a schematic diagram for explaining an overview of the business management system 1. Components of the business management system 1 will be explained based on FIG. The business management system 1 is a system for managing a predetermined business (business related to dispatching taxis, etc.) that is composed of a computer 10 having at least a server function. In this embodiment, in addition to the computer 10, the business management system 1 includes an information terminal 3 managed by a user 2 who uses the system, and a computer 4 that holds a large-scale language model. The computer 10 has a server function and may be realized, for example, by a single computer, or may be realized by a plurality of computers, such as a cloud computer. In this specification, a cloud computer may refer to either a scalable use of any computer to perform a specific function, or a computer that includes multiple functional modules to realize a system, the functions of which can be freely combined. The information terminals 3 are terminal devices managed by the users 2 of the system, and are, for example, terminal devices such as mobile phones, smartphones, tablet terminals, personal computers, laptop computers, etc. The number of information terminals 3 may be a number corresponding to the number of users 2, is not particularly limited, and can be designed as appropriate. The computer 4 is a computer that holds a large-scale language model, and like the computer 10, may be realized by, for example, a single computer, or may be realized by multiple computers like a cloud computer.

[0013] The following describes an overview of the processing steps performed when the business management system 1 manages a given business.

[0014] The computer 10 acquires a business summary of a predetermined business (step S1). The computer 10 acquires from the information terminal 3 a business overview of a predetermined business and questions related to the content of the business desired by the user 2.

[0015] The computer 10 sends question data to the large-scale language model based on the acquired business summary, and acquires at least one of the following answers: generating a name of a specified business, generating business details, generating a business department, and identifying a business person in charge (step S2). The computer 10 transmits the acquired business summary and question to the computer 4 . The computer 4 utilizes a large-scale language model to generate an answer to the business summary and the question. The computer 4 generates at least one of the following as an answer: generation of a name of a predetermined business, generation of business details, generation of a business department, and identification of a business person in charge. The computer 10 obtains this generated answer.

[0016] The computer 10 generates a predetermined output based on the obtained answer (step S3). Based on the obtained answers, the computer 10 generates a predetermined output corresponding to the question related to the content of the business desired by the user 2.

[0017] The above is an overview of the processing steps of the business management system 1. According to this work management system 1, it is possible to generate a predetermined output that matches an individual purpose from a work summary that shows a basic work flow.

[0018] [Device configuration] 2 is a block diagram showing the configuration of the business management system 1. The device configuration of the business management system 1 will be described with reference to FIG. The task management system 1 is a system for managing a specific task, and is composed of at least a computer 10. In this embodiment, in addition to the computer 10, the task management system 1 is composed of an information terminal 3 managed by a user 2 of the system, and a computer 4 that holds a large-scale language model. The business management system 1 is a system in which a computer 10 is connected to an information terminal 3 and a computer 4 so as to be capable of data communication via a network 8 such as a public line network. In addition to the computer 10, information terminal 3, and computer 4 described above, the business management system 1 may also include other terminals and devices (such as utilization systems that work in conjunction with this system to execute necessary processing), and the number, types, and functions thereof are not particularly limited and can be designed as appropriate. Furthermore, the large-scale language model may be held by the computer 10 instead of the computer 4. In this case, the task management system 1 is made up of the computer 10 and the information terminal 3.

[0019] The computer 10 has a server function and may be realized, for example, by a single computer, or may be realized by a plurality of computers, such as a cloud computer. The computer 10 has a control unit such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a RAM (Random Access Memory), and a ROM (Read Only Memory), and has, as a communication unit, a device for enabling communication with other terminals and devices, a business summary acquisition unit 11 for acquiring a business summary of a specified business, and an answer acquisition unit 12 for acquiring at least one of the following as an answer: generating the name of the specified business, generating business details, generating the business department, and identifying the person in charge of the business by sending question data to a large-scale language model based on the acquired business summary. The computer 10 includes a storage unit such as a hard disk, a semiconductor memory, a recording medium, a memory card, etc. The computer 10 holds various databases (hereinafter, the databases may be simply referred to as "DBs") in the storage unit. The computer 10 includes, as processing units, various devices for executing various processes, a generation unit 13 for generating a predetermined output based on the obtained answer, and the like.

[0020] In the computer 10, the control unit loads a predetermined program and cooperates with the communication unit to realize a business overview acquisition module, a response acquisition module, and a notification module. In addition, in the computer 10, the control unit reads a predetermined program and cooperates with the processing unit to realize a generating module and a specific module.

[0021] The information terminal 3 is a terminal device managed by the user 2, and is, for example, the terminal device described above. The information terminal 3 is equipped with a CPU, GPU, RAM, ROM, etc. as a terminal control unit, a device etc. for enabling communication with other terminals and devices etc. as a communication unit, and various devices etc. for receiving specified inputs, inputting and outputting various data and drawings etc. as an input / output unit.

[0022] The computer 4 is a computer that holds a large-scale language model, and may be realized, for example, by a single computer, or may be realized by multiple computers such as a cloud computer. The computer 4 includes a CPU, GPU, RAM, ROM, etc. as a control unit, a device for enabling communication with other terminals, devices, etc., and a device for outputting generated answers, etc. as a communication unit, and a data storage unit, etc. as a memory unit. The computer 4 holds a large-scale language model in the memory unit. The computer 4 includes various devices for executing various processes, and a device for generating answers to question data by utilizing the large-scale language model, etc. as a processing unit.

[0023] Hereinafter, each process executed by the business management system 1 will be described together with the process executed by each of the above-mentioned modules. In this specification, each module may execute its processing contents as its own function, or may execute its processing contents via a predetermined application.

[0024] [Generation process performed by computer 10] The generation process executed by the computer 10 will be described with reference to Fig. 3. This figure is a diagram showing a flowchart of the generation process executed by the computer 10. This generation process shows details of a process outline acquisition process (step S1) for acquiring a process outline of a predetermined task, a process for acquiring an answer (step S2) for acquiring at least one of the following as an answer: generation of a name of the predetermined task, generation of task details, generation of a task department, and identification of a task manager by transmitting question data to a large-scale language model based on the acquired process outline, and a process for generating a predetermined output based on the acquired answer (step S3).

[0025] The business overview acquisition module acquires a business overview of a predetermined business (step S10). The predetermined business is, for example, business related to dispatching taxis (dispatch business, sales management business, etc.). The job summary relates to, for example, an overview of the work actually performed in a given job (in the case of vehicle dispatch work, unlocking the office, starting up the vehicle dispatch system, processing the start of vehicle dispatch reception, managing the Shinto altar, cleaning, checking equipment, etc.). The information terminal 3 receives from the user 2 an input of a question related to the content of the business desired by the user 2 (the name of the business, details of the business, the name of the business department, the name of the person in charge of the business, etc.) together with a business overview of the predetermined business. The information terminal 3 receives these in a text format. Note that the information terminal 3 is not limited to the text format and may receive in other formats (bullet points, words, phrases, etc.). The information terminal 3 accepts an input such as "The dispatcher in the dispatch room will open the office door, turn on the power of the PC that starts the dispatch system, and prepare for the reception start process, the Shinto altar management, cleaning, equipment check, etc. Please shorten to a task name of 10 characters or less." Here, the task summary is "The dispatcher in the dispatch room will open the office door, turn on the power of the PC that starts the dispatch system, and prepare for the reception start process, the Shinto altar management, cleaning, equipment check, etc.", and the question related to the content of the task desired by the user 2 is "Please shorten to a task name of 10 characters or less." The information terminal 3 may accept this input in text format using a virtual keyboard displayed on its display unit, or may accept the input in voice format using a microphone or the like that the information terminal 3 has. In this embodiment, the input is assumed to be accepted in text format. The information terminal 3 transmits the accepted business summary and question to the computer 10. The business overview acquisition module receives these and acquires the business overview of the specified business.

[0026] The answer acquisition module transmits question data to the large-scale language model based on the acquired business summary (step S11). The answer acquisition module transmits the acquired business summary and question to the computer 4 as question data. The computer 4 receives this question data. The computer 4 utilizes a large-scale language model based on the received question data to generate an answer to this question data. Here, the computer 4 analyzes the business summary and the content of the question, and generates an answer to the question based on the analysis result by referring to the large-scale language model. In the above example, the computer 4 generates, as a response, "vehicle dispatch preparation work" as a work name of 10 characters or less that matches all of the work summaries.

[0027] The answer acquisition module acquires content related to a predetermined business as an answer based on the question data (step S12). The content related to the predetermined business is at least one of generating a name of the predetermined business, generating business details, generating a business department, and identifying a business person in charge. The computer 4 transmits the generated answer to the computer 10 as answer data. The answer acquisition module receives this answer data and acquires the content related to the predetermined business as an answer based on the question data.

[0028] The question data transmitted by the answer acquisition module and the answer data received by the answer acquisition module will be described with reference to FIGS.

[0029] FIG. 4 is a diagram showing an example of question data and answer data regarding the generation of a business name. The question data 20 shows, "The dispatcher in the dispatch room will unlock the office, power on the PC that runs the dispatch system and start the reception process, manage the Shinto altar, clean, check the equipment, etc. Please shorten this to a job name of 10 characters or less." Here, the job summary is "The dispatcher in the dispatch room will unlock the office, power on the PC that runs the dispatch system and start the reception process, manage the Shinto altar, clean, check the equipment, etc.", and the question requested by user 2 is "Please shorten this to a job name of 10 characters or less." At this time, it is clear that user 2 wants the name of the job. The answer generated to this business summary and question is shown in the answer data 21. Here, the answer is "vehicle dispatch preparation business." In other words, the content shown in this answer data 21 indicates the name of the business desired by the user 2.

[0030] FIG. 5 is a diagram showing an example of question data and answer data relating to the generation of business details. The question data 30 shows, "The dispatcher in the dispatch room unlocks the office, turns on the dispatch system PC, starts the reception process on the dispatch system PC, manages the Shinto altar, cleans, and checks the equipment. Please provide detailed information." Here, the job summary is "The dispatcher in the dispatch room unlocks the office, turns on the dispatch system PC, starts the reception process on the dispatch system PC, manages the Shinto altar, cleans, and checks the equipment.", and the question requested by user 2 is "Please provide detailed information." At this point, it is clear that user 2 wants the job details. The answer generated for this business overview and question is shown in the answer data 31. Here, the answer is "This sentence shows how a person working in the dispatch office of a taxi company performs a series of tasks to start dispatching business. Specifically, he / she first unlocks the office, turns on the dispatch system PC to start reception, and prepares the PC to operate the dispatch system. Then, he / she manages the Shinto altar, cleans the room, checks the equipment, and finishes tidying up. These tasks are essential for smooth dispatching of taxis, and are indispensable for smooth business operations." In other words, the contents shown in the answer data 31 show the details of the business desired by the user 2.

[0031] FIG. 6 is a diagram showing an example of question data and answer data regarding the creation of a business department. As question data 40, "The name of the department listed in Department: The dispatcher in the dispatch room prepares to start the taxi dispatching business (preparing the dispatch system, etc.) is..." is shown. Here, the business summary is "The dispatcher in the dispatch room prepares to start the taxi dispatching business (preparing the dispatch system, etc.)." and the question requested by user 2 is "The name of the department listed in Department: The dispatcher in the dispatch room prepares to start the taxi dispatching business (preparing the dispatch system, etc.)." At this time, it is clear that user 2 is requesting a business department. The answer generated for this business summary and question is shown in answer data 41. Here, the answer is "The department name "Dispatch Office" is listed." In other words, the content shown in this answer data 41 indicates the business department desired by user 2.

[0032] FIG. 7 is a diagram showing an example of question data and answer data relating to identifying a person in charge of a business. The question data 50 shows "The dispatcher in the dispatch room prepares to start a taxi dispatch operation (preparing the dispatch system, etc.). The subject of is." Here, it can be seen that the business summary is "The dispatcher in the dispatch room prepares to start a taxi dispatch operation (preparing the dispatch system, etc.)," ​​and the question desired by user 2 is "The subject of is." The answer generated for this task summary and question is shown in answer data 51. Here, the answer is "The subject of this sentence is 'the dispatcher'. The predicate part shows what the dispatcher in the dispatch room does." In other words, the content shown in this answer data 51 shows the task person desired by user 2.

[0033] FIG. 8 is a diagram showing an example of question data and answer data relating to identifying a business procedure. The question data 60 shows, "Please list the tasks of the dispatcher in the dispatch room unlocking the office, turning on the dispatch system PC, starting reception on the dispatch system PC, managing the Shinto altar, cleaning, and checking the equipment." Here, the task summary is "The dispatcher in the dispatch room unlocking the office, turning on the dispatch system PC, starting reception on the dispatch system PC, managing the Shinto altar, cleaning, and checking the equipment.", and the question requested by user 2 is, "Please list the tasks." At this time, it is clear that user 2 is requesting a task procedure. The answer generated for this task summary and question is shown in answer data 61. Here, the answer is "Below is a list of tasks performed by the dispatcher in the dispatch room, extracted from the given sentence: Unlock the office Turn on the dispatch system PC Perform reception start processing on the dispatch system PC Maintain the Shinto altar Clean the room Check the equipment As can be seen from the above, the dispatcher in the dispatch room performs various preparatory tasks before starting the taxi dispatching task." In other words, the content shown in this answer data 61 indicates the task procedure desired by user 2.

[0034] FIG. 9 is a diagram showing an example of question data and answer data relating to the identification of INPUT information. The question data 70 shows, "Enter your login ID and password to log in to the vehicle dispatch system. Select sales input process from the menu, enter business partner information, sales date information, product details, product unit price information, and product quantity information, and calculate and register total sales amount information. Extract the information of." Here, the business overview is, "Enter your login ID and password to log in to the vehicle dispatch system. Select sales input process from the menu, enter business partner information, sales date information, product details, product unit price information, and product quantity information, and calculate and register total sales amount information." and the question desired by user 2 is, "Extract the information of." At this time, it is clear that user 2 is requesting INPUT information. The answer generated for this business overview and question is shown in answer data 71. Here, the answer is "Processing content: Sales input processing Input information: Business partner information: Sales date information: Product details information: Product unit price information: Product quantity information: Output information: Total sales amount information Procedure: Log in to the vehicle dispatch system Select sales input processing Input business partner information, sales date information, product details information, product unit price information, and product quantity information Calculate total sales amount information Register total sales amount information." In other words, the content shown in this answer data 71 indicates the INPUT information desired by user 2.

[0035] As shown above, the question data includes details related to a business overview and a specific business desired by the user 2, and the answer data includes answers generated in response to these. It goes without saying that the contents of the predetermined business are not limited to the above-mentioned examples, and may be other than those. In addition, it goes without saying that the contents of the question data and the answer data are not limited to the above-mentioned examples, and may be other than those. Furthermore, the answer data does not necessarily have to be the same answer to the same question data, and a different answer may be generated by computer 4 each time question data is transmitted, or the answer may always be the same.

[0036] Returning to FIG. 3, the rest of the generation process will be described. The generating module generates a predetermined output (step S13). The predetermined output is at least one of creating a list of tasks, creating a workflow, and creating a workflow procedure. This predetermined output corresponds to the content of the predetermined task desired by user 2 in the above-mentioned response. For example, if user 2 desires to generate a task name, generate task details, generate a task department, identify a task manager, and identify a workflow procedure, the predetermined output is at least one of creating a list of tasks, creating a workflow, and creating a workflow procedure. If user 2 desires to identify INPUT information, the predetermined output is at least one of generating an IN-OUT information list and generating a task management DB. In addition, if user 2 desires to identify calculation logic, the predetermined output is at least one of generating a calculation logic list and generating a program. An example will be described in which the generation module creates a list of tasks, a business flow, and a business procedure. The generation module changes a part or all of the existing task list, task flow, and task procedure in accordance with the content desired by the user 2. Alternatively, the generation module generates a new task list, task flow, and task procedure in accordance with the content desired by the user 2. For example, the generation module changes a part or all of the content in an online manual in which the task list, task flow, and task procedure are described in accordance with the content desired by the user 2. Alternatively, the generation module generates a new online manual in which the task list, task flow, and task procedure are described in accordance with the content desired by the user 2. The generation module extracts a predetermined keyword (a preset character string, a character string related to a task overview, a character string related to a task procedure, a character string related to a task department, etc.) included in the answer, and matches the extracted character string to the form based on the extraction result and a preset form, thereby changing the existing online manual or generating a new online manual. The identification module identifies users 2 who will be affected by the changed or new online manuals (those online manuals related to their own work have been changed or added) based on the work content previously set for each user 2. The identification module also identifies the systems used that are necessary for notifying the identified users 2. Examples of such systems are systems that send emails and messages, systems that make phone calls, and systems that post on SNS (Social Networking Service). The notification module notifies the identified user 2 that a change or addition has been made to the online manual. The notification module, for example, sends an email to the information terminal 3 managed by this user 2, with a character string indicating that the online manual has been changed or added and with the changed or added online manual attached, to notify this user 2 that a change or addition has been made to the online manual. Note that the notification module may notify the user 2 that a change or addition has been made to the online manual by a method other than those mentioned above. An example in which the generation module generates an IN-OUT information list and a business management DB will be described. The generation module changes a part or all of the existing IN-OUT information list in accordance with the content desired by user 2. Alternatively, the generation module generates a new IN-OUT information list in accordance with the content desired by user 2. The generation module updates or adds to the business management DB that manages the IN-OUT information based on the changed or new IN-OUT information list. An example in which the generation module generates a list of calculation logic and generates a program will be described. The generation module changes a part or all of the existing calculation logic list in accordance with the content desired by the user 2. Alternatively, the generation module generates a new calculation logic list in accordance with the content desired by the user 2. Based on the changed or new calculation logic list, a program using calculation logic is generated.

[0037] This completes the generation process.

[0038] Although each of the above processes is described as a separate process, the computer 10 can be configured to execute a combination of some or all of the above processes. Also, the computer 10 can be configured to execute each process at a timing other than the timing described.

[0039] The above-mentioned means and functions are realized by a computer (including a CPU, an information processing device, and various terminals) reading and executing a predetermined program. The program may be provided, for example, from a computer via a network (Software as a Service (SaaS)) or as a cloud service. The program may also be provided in a form recorded on a computer-readable recording medium. In this case, the computer reads the program from the recording medium, transfers it to an internal or external recording device, records it, and executes it. The program may also be recorded in advance on a recording device (recording medium) and provided from the recording device to the computer via a communication line.

[0040] Although the embodiments of the present invention have been described above, the present invention is not limited to the above-mentioned embodiments. Furthermore, the effects described in the embodiments of the present invention are merely a list of the most preferable effects resulting from the present invention, and the effects of the present invention are not limited to those described in the embodiments of the present invention.

[0041] A first aspect disclosed in this embodiment is a task management system for managing a predetermined task, A business summary acquisition unit that acquires a business summary of the predetermined business; an answer acquisition unit that acquires, as an answer, at least one of generating a name of the predetermined business, generating business details, generating a business department, and identifying a business person by transmitting question data to a large-scale language model based on the acquired business summary; A generation unit that generates a predetermined output based on the obtained answer; The present invention provides a business management system comprising:

[0042] In a second aspect of the present embodiment, the generation unit generates the predetermined output based on a predetermined keyword included in the acquired answer. According to a first aspect, there is provided a business management system.

[0043] A third aspect disclosed in this embodiment is such that the predetermined output is at least one of creating a list of tasks, creating a business flow, and creating a business procedure. According to a first aspect, there is provided a business management system. [Explanation of symbols]

[0044] 1 Business Management System 2 User 3. Information terminal 4. Computer 8 Network 10. Computers 11 Business summary acquisition department 12 Answer acquisition part 13 Generation part 20,30,40,50,60,70 Question data 21,31,41,51,61,71 Response data

Claims

1. A business management system for managing a predetermined business, A business summary acquisition unit that acquires a business summary of the predetermined business; an answer acquisition unit that acquires, as an answer, at least one of generating a name of the predetermined business, generating business details, generating a business department, and identifying a business person by transmitting question data to a large-scale language model based on the acquired business summary; A generation unit that generates a predetermined output based on the obtained answer; A business management system equipped with:

2. The generation unit generates the predetermined output based on a predetermined keyword included in the acquired answer. The business management system according to claim 1 .

3. The predetermined output is at least one of creating a list of tasks, creating a workflow, and creating a procedure for the tasks. The business management system according to claim 1 .

4. 1. A computer-implemented task management method for managing a predetermined task, comprising: acquiring a business summary of the predetermined business; a step of transmitting question data to a large-scale language model based on the acquired business summary, thereby acquiring at least one of a name of the predetermined business, a business detail, a business department, and a business person in charge as an answer; generating a predetermined output based on the obtained answers; A business management method comprising:

5. A computer for managing a specific task acquiring a business summary of the predetermined business; a step of transmitting question data to a large-scale language model based on the acquired business summary, thereby acquiring, as an answer, at least one of generating a name of the predetermined business, generating business details, generating a business department, and identifying a business person in charge; generating a predetermined output based on the obtained answers; A computer readable program for executing the program.

Images