Task management system, task management method, and program

Abstract

[Problem] To generate, from a task outline that indicates a basic workflow, a prescribed output that matches an individual use. [Solution] This task management system for managing a prescribed task acquires a task outline of the prescribed task and transmits question data to a large language model on the basis of the acquired task outline, so as to acquire, as an answer thereto, at least one of the generation of the name of the prescribed task, the generation of the details of the task, the generation of a department for the task, and the specification of a handler for the task and, on the basis of the acquired answer, generate a prescribed output.

Description

Business management system, business management method and program

[0001] The present invention relates to a technique that is effective for managing a predetermined business.

[0002] Conventionally, systems that automatically assist in inputting work have been known. For example, Patent Document 1 discloses a system that automatically records work hours for cargo handling and the like in a daily report.

[0003] Patent 7180719

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

[0005] The present invention aims to provide a business management system, business management method, and program that can generate specified outputs (creating a business list, creating a business procedure manual, etc.) that match individual purposes from a business overview that shows the basic business flow.

[0006] The present invention provides a business management system for managing specified tasks, comprising: a task summary acquisition unit that acquires a task summary of the specified task; an answer acquisition unit that sends question data to a large-scale language model based on the acquired task summary, and acquires at least one of the following as an answer: generation of the name of the specified task, generation of task details, generation of the task department, and identification of the task manager; and a generation unit that generates a specified output based on the acquired answer.

[0007] According to the present invention, content related 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 a predetermined output that matches individual applications from a task summary that shows the basic task flow.

[0008] Although the present invention is categorized as a system, the same effects and advantages can be obtained even when it is a method or a program.

[0009] According to the present invention, it is possible to generate predetermined outputs that match individual applications from a business overview that shows a basic business flow.

[0010] FIG. 1 is a diagram illustrating an overview of a business management system 1. FIG. 2 is a diagram illustrating the functional configuration of the business management system 1. FIG. 3 is a diagram illustrating a flowchart of a generation process executed by a computer 10. FIG. 4 is a diagram illustrating an example of question data and answer data. FIG. 5 is a diagram illustrating an example of question data and answer data. FIG. 6 is a diagram illustrating an example of question data and answer data. FIG. 7 is a diagram illustrating an example of question data and answer data.

[0011] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail 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 embodiments.

[0012] [Overview of the Service Management System 1] FIG. 1 is a schematic diagram illustrating an overview of the service management system 1. The components of the service management system 1 will be described based on FIG. 1. The service management system 1 is a system for managing a specific service (such as a service related to dispatching taxis) and is composed of a computer 10 having at least a server function. In this embodiment, the service management system 1 includes, in addition to the computer 10, an information terminal 3 managed by a user 2 who uses the system, and a computer 4 that stores a large-scale language model. The computer 10 has a server function and may be implemented, for example, by a single computer or by multiple computers, such as a cloud computer. In this specification, a cloud computer may refer to either a computer that uses any computer scalably to perform a specific function, or a computer that includes multiple functional modules to realize a system and uses the functions in any combination. The information terminal 3 is a terminal device managed by a user 2 of the system, such as a mobile phone, smartphone, tablet, personal computer, or laptop computer. The number of information terminals 3 may be any number corresponding to the number of users 2, and is not particularly limited and can be designed as appropriate. The computer 4 is a computer that stores 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] An outline of the processing steps when the business management system 1 manages a predetermined business will be described.

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

[0015] Based on the acquired business summary, computer 10 sends question data to the large-scale language model, thereby acquiring at least one of the following as an answer: generating a name of a specific business, generating business details, generating a business department, and identifying a business person in charge of the business (step S2). Computer 10 sends the acquired business summary and question to computer 4. Computer 4 utilizes the large-scale language model to generate an answer to the business summary and question. Computer 4 generates at least one of the following as an answer: generating a name of a specific business, generating business details, generating a business department, and identifying a business person in charge of the business. Computer 10 acquires this generated answer.

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

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

[0018] [Device Configuration] FIG. 2 is a block diagram showing the configuration of the task management system 1. The device configuration of the task management system 1 will be described with reference to FIG. 2. The task management system 1 is a system for managing a specific task and is configured with at least a computer 10. In this embodiment, the task management system 1 is configured with, in addition to the computer 10, an information terminal 3 managed by a user 2 of the system, and a computer 4 that stores a large-scale language model. The task management system 1 is a system in which the computer 10 is connected to the information terminal 3 and the computer 4 via a network 8, such as a public line network, for data communication. In addition to the computer 10, information terminal 3, and computer 4, the task management system 1 may also include other terminals and devices (such as user systems that cooperate with the system and execute necessary processing), and the number, type, and functions of these devices are not particularly limited and can be designed as appropriate. Furthermore, the large-scale language model may be stored in the computer 10 rather than the computer 4. In this case, the task management system 1 would be configured with 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 by multiple computers, such as a cloud computer. The computer 10 includes, as a control unit, a central processing unit (CPU), a graphics processing unit (GPU), a random access memory (RAM), a read-only memory (ROM), etc., and, 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 predetermined business, and an answer acquisition unit 12 for 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 by sending question data to a large-scale language model based on the acquired business summary. The computer 10 includes, as a memory unit, a data storage unit such as a hard disk, semiconductor memory, recording medium, memory card, etc. The computer 10 stores various databases (hereinafter, the databases may be simply referred to as "DBs") in a storage unit. The computer 10 includes, as processing units, various devices that execute various processes, a generation unit 13 that generates predetermined outputs based on the acquired answers, and the like.

[0020] In the computer 10, the control unit reads a predetermined program, thereby realizing a business overview acquisition module, a response acquisition module, and a notification module in cooperation with the communication unit. Also, in the computer 10, the control unit reads a predetermined program, thereby realizing a generation module and a specification module in cooperation with the processing unit.

[0021] The information terminal 3 is a terminal device managed by the user 2, such as the terminal device described above. The information terminal 3 includes a CPU, GPU, RAM, ROM, etc. as a terminal control unit, a device that enables communication with other terminals and devices, etc. as a communication unit, and various devices that receive predetermined inputs, input and output various data and drawings, etc. as an input / output unit.

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

[0023] Below, we will explain each process executed by the business management system 1 together with the processes executed by each of the above-mentioned modules. In this specification, each module may execute its processing content as its own function, or may execute it via a specified application.

[0024] [Generation Process Executed by Computer 10] The generation process executed by the computer 10 will be described with reference to Fig. 3. This figure is a flowchart of the generation process executed by the computer 10. This generation process shows details of a business summary acquisition process (step S1) that acquires a business summary of a predetermined business, an answer acquisition process (step S2) 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 sending question data to a large-scale language model based on the acquired business summary, and a generation process (step S3) that generates a predetermined output based on the acquired answer.

[0025] The business summary acquisition module acquires a business summary of a predetermined business (step S10). The predetermined business is, for example, a business related to dispatching taxis (such as dispatching business or sales management business). The business summary is, for example, related to an outline of the actual work performed in the predetermined business (for dispatching business, unlocking the office, setting up the dispatch system, starting the dispatch reception process, maintaining the household shrine, cleaning, checking equipment, etc.). The information terminal 3 accepts input from the user 2 of the business summary of the predetermined business, as well as questions related to the content of the business desired by the user 2 (such as the name of the predetermined business, business details, the name of the business department, and the name of the person in charge of the business). The information terminal 3 accepts these in a sentence format. Note that the information terminal 3 is not limited to a sentence format and may accept other formats (such as bullet points, words, and phrases). For example, the information terminal 3 accepts an input such as, "The dispatcher in the dispatch room will unlock the office, power on the PC that starts the dispatch system, start the reception process, maintain the Shinto altar, clean, check the equipment, etc. Please shorten this to a task name of 10 characters or less." Here, the task summary is "The dispatcher in the dispatch room will unlock the office, power on the PC that starts the dispatch system, start the reception process, maintain the Shinto altar, clean, check the equipment, etc. Please shorten this to a task name of 10 characters or less." The question related to the content of the task desired by the user 2 is "Please shorten this 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 in audio format using its own microphone, etc. In this embodiment, the input is assumed to be accepted in text format. The information terminal 3 transmits the accepted task summary and question to the computer 10. The task summary acquisition module receives these and acquires the task summary of the specified task.

[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 as question data to the computer 4. The computer 4 receives this question data. The computer 4 generates an answer to this question data using the large-scale language model based on the received question data. Here, the computer 4 analyzes the business summary and the content of the question, and generates an answer to this question by referring to the large-scale language model based on the analysis results. In the above example, the computer 4 generates as an answer "vehicle dispatch preparation work" as the name of a work of 10 characters or less that matches all business summaries.

[0027] The answer acquisition module acquires content related to the 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. Computer 4 transmits the generated answer as answer data to computer 10. The answer acquisition module receives this answer data and acquires 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 illustrating an example of question data and answer data related to the generation of a task name. The question data 20 shows, "The dispatcher in the dispatching room will unlock the office, power on the PC running the dispatch system and start the reception process, maintain the Shinto altar, clean, check the equipment, etc. Please shorten this to a task name of 10 characters or less." Here, the task summary is, "The dispatcher in the dispatching room will unlock the office, power on the PC running the dispatch system and start the reception process, maintain the Shinto altar, clean, check the equipment, etc. Please shorten this to a task name of 10 characters or less." It can be seen that user 2 is requesting a task name. The task summary and the answer generated for the question are shown in answer data 21. Here, the answer is "Dispatch preparation task." In other words, the content shown in answer data 21 indicates the name of the task desired by user 2.

[0030] FIG. 5 is a diagram showing an example of question data and answer data related to the generation of task 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 a detailed description." Here, the task 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." The question requested by user 2 is, "Please provide a detailed description." It can be seen that user 2 is requesting task details. The task summary and the answer generated for the question are shown in answer data 31. Here, the answer is, "This sentence describes the sequence of tasks performed by a staff member working in the dispatch office of a taxi company to begin dispatch operations. Specifically, the staff member first unlocks the office, turns on the dispatch system PC to begin reception, and prepares the PC to operate the dispatch system. The staff member then maintains the household altar, cleans the room, checks the equipment, and completes tidying up. These tasks are essential for the smooth running of taxi dispatch operations and are essential for smooth business operations." In other words, the content shown in this answer data 31 indicates the details of the operations desired by User 2.

[0031] FIG. 6 is a diagram illustrating an example of question data and answer data related to the generation of a business department. The question data 40 shows the name of the department listed in "Department: The dispatcher in the dispatch room prepares for the start of taxi dispatch operations (preparing the dispatch system, etc.)." Here, the business summary is "Department: The dispatcher in the dispatch room prepares for the start of taxi dispatch operations (preparing the dispatch system, etc.).", and the question desired by user 2 is "The name of the department listed in "." At this point, 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 name of the department listed is 'Dispatch Room.'" 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 the identification of a service provider. The question data 50 shows, "The dispatcher in the dispatch room prepares to start the taxi dispatch service (preparing the dispatch system, etc.). The subject of is." Here, it can be seen that the service summary is, "The dispatcher in the dispatch room prepares to start the taxi dispatch service (preparing the dispatch system, etc.)." and the question desired by user 2 is, "The subject of is." The answer generated for this service summary and the question is shown in answer data 51. Here, the answer is, "The subject of this sentence is 'dispatcher.' The predicate part indicates what the dispatcher in the dispatch room will do." In other words, the content shown in this answer data 51 indicates the service provider desired by user 2.

[0033] FIG. 8 is a diagram showing an example of question data and answer data relating to the identification of a business procedure. The question data 60 shows, "Please list the following tasks: The dispatcher in the dispatch room unlocks the office, turns on the dispatch system PC, starts reception on the dispatch system PC, manages the household shrine, cleans, and checks the equipment." Here, the business summary is, "The dispatcher in the dispatch room unlocks the office, turns on the dispatch system PC, starts reception on the dispatch system PC, manages the household shrine, cleans, and checks the equipment." The question requested by user 2 is, "Please list the following tasks." At this point, it is clear that user 2 is requesting a business procedure. The business summary and the answer generated in response to the question are 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 operation." In other words, the content shown in this answer data 61 indicates the work procedure desired by user 2.

[0034] FIG. 9 is a diagram showing an example of question data and answer data related 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 processing from the menu, enter customer 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 below." Here, the business summary is, "Enter your login ID and password to log in to the vehicle dispatch system. Select sales input processing from the menu, enter customer information, sales date information, product details, product unit price information, and product quantity information, and calculate and register total sales amount information." The question requested by user 2 is, "Extract the information below." It can be seen that user 2 is requesting INPUT information. The business summary and the answer generated for the question are shown in answer data 71. Here, the response is "Processing content: Sales input processing Input information: Customer 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 dispatch system Select sales input processing Input customer 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 response data 71 indicates the INPUT information desired by user 2.

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

[0036] Returning to FIG. 3 , the rest of the generation process will be explained. The generation module generates a predetermined output (step S13). The predetermined output is at least one of creating a task list, creating a workflow, and creating a business procedure. Furthermore, this predetermined output corresponds to the content of the predetermined task desired by user 2 in the response described above. For example, if user 2 desires to generate a task name, generate task details, generate a task department, identify task personnel, and identify a business procedure, the predetermined output is at least one of creating a task list, creating a workflow, and creating a business procedure. Furthermore, if user 2 desires to identify INPUT information, the predetermined output is at least one of creating an IN-OUT information list and creating a business management DB. Furthermore, if user 2 desires to identify calculation logic, the predetermined output is at least one of creating a calculation logic list and creating a program. An example will be explained in which the generation module creates a task list, creating a workflow, and creating a business procedure. The generation module modifies part or all of an existing task list, workflow, or procedure in accordance with the content desired by user 2. Alternatively, the generation module generates a new task list, workflow, or procedure in accordance with the content desired by user 2. For example, the generation module modifies part or all of the content of an online manual that describes a task list, workflow, or procedure in accordance with the content desired by user 2. Alternatively, the generation module generates a new online manual that describes a task list, workflow, or procedure in accordance with the content desired by user 2. The generation module extracts predetermined keywords (predetermined character strings, character strings related to a task overview, character strings related to a task procedure, character strings related to a business department, etc.) included in the response, and, based on the extracted character strings and a predetermined form, modifies the existing online manual or generates a new online manual.The identification module identifies users 2 who will be affected by the changed or new online manuals (i.e., who have had changes or additions made to their online manuals related to their work) based on the work content previously set for each user 2. The identification module also identifies the systems used to notify the identified users 2. These systems include, for example, systems that send emails and messages, systems that make phone calls, and systems that post to SNS (Social Networking Services). The notification module notifies the identified users 2 that changes or additions have been made to the online manual. For example, the notification module sends an email to the information terminal 3 managed by the user 2, containing a string indicating that the online manual has been changed or added, and with the changed or added online manual attached, to notify the user 2 that the online manual has been changed or added. Note that the notification module may also notify the user 2 of changes or additions to the online manual using methods other than those mentioned above. An example will be described in which the generation module generates an IN-OUT information list and a work management DB. The generation module modifies part or all of the existing IN-OUT information list according to the content desired by user 2. Alternatively, the generation module generates a new IN-OUT information list according to 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 modified or new IN-OUT information list. An example will be described in which the generation module generates a calculation logic list and a program. The generation module modifies part or all of the existing calculation logic list according to the content desired by user 2. Alternatively, the generation module generates a new calculation logic list according to the content desired by user 2. A program using calculation logic is generated based on the modified or new calculation logic list.

[0037] This completes the generation process.

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

[0039] The above-described 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 pre-recorded on a recording device (recording medium) and provided to the computer from the recording device 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-described 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 provides a business management system for managing a specified business, comprising: a business summary acquisition unit that acquires a business summary of the specified business; an answer acquisition unit that acquires, 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 person by sending question data to a large-scale language model based on the acquired business summary; and a generation unit that generates a specified output based on the acquired answer.

[0042] A second aspect disclosed in this embodiment provides the business management system according to the first aspect, wherein the generation unit generates the predetermined output based on predetermined keywords included in the acquired answer.

[0043] A third aspect disclosed in this embodiment provides the business management system according to the first aspect, wherein the predetermined output is at least one of the creation of a business list, the creation of a business flow, and the creation of a business procedure.

[0044] REFERENCE SIGNS LIST 1 Business management system 2 User 3 Information terminal 4 Computer 8 Network 10 Computer 11 Business overview acquisition unit 12 Answer acquisition unit 13 Generation unit 20, 30, 40, 50, 60, 70 Question data 21, 31, 41, 51, 61, 71 Answer data

Claims

1. A business management system for managing specified business tasks, comprising: a business summary acquisition unit that acquires a business summary of the specified business task; an answer acquisition unit that acquires at least one of the following answers by sending question data to a large-scale language model based on the acquired business summary: generating a name of the specified business task, generating business details, generating a business department, and identifying a person in charge of the business task; and a generation unit that generates a specified output based on the acquired answer.

2. The business management system according to claim 1, wherein the generation unit generates the predetermined output based on predetermined keywords contained in the acquired answer.

3. The business management system according to claim 1, wherein the predetermined output is at least one of the creation of a business list, the creation of a business flow, and the creation of business procedures.

4. A task management method executed by a computer for managing a specified task, comprising: a step of acquiring a task summary of the specified task; a step of sending question data to a large-scale language model based on the acquired task summary to acquire at least one of the following answers: generating a name of the specified task, generating task details, generating a task department, and identifying a task manager; and a step of generating a specified output based on the acquired answer.

5. A computer-readable program for causing a computer for managing a specified task to execute the steps of: acquiring a task summary of the specified task; sending question data to a large-scale language model based on the acquired task summary to acquire at least one of the following answers: generating a name of the specified task, generating task details, generating a task department, and identifying a task manager; and generating a specified output based on the acquired answer.

Images