Work support device, work support method, and work support program

Abstract

To enable efficient management of work-related information.SOLUTION: A work support device 100 disclosed herein is configured to input a prompt based on a natural language text received from a user into a generative model provided with information regarding work support so as to generate information regarding work support indicated by the text. The work support device 100 outputs the information regarding the work support indicated by the text.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to a task assistance device, a task assistance method, and a task assistance program. [Background technology]

[0002] Employees belonging to an organization may be required to manage various information in the course of their work. For example, if a task has a deadline or a date for completion, employees may be required to manage the schedule for that task themselves and ensure that the task is carried out without any omissions. Employees may also be required to record the work they perform in a prescribed format, such as a daily report.

[0003] Conventional techniques for allowing employees to manage information as described above are known. For example, a conventional technique is known in which schedules for each employee or organization are input into a scheduler managed on the cloud and shared with the entire organization (see, for example, Non-Patent Document 1). Another conventional technique for efficiently recording business records such as daily reports involves acquiring input information for a first work record from schedule information that represents the content of a first schedule, and identifying work records related to the first work record based on the acquired input information by referring to a storage unit that stores work records for past schedules (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2024-027233 [Non-patent literature]

[0005] [Non-Patent Document 1] Google Calendar,<URL:https: / / workspace.google.com / intl / ja / lp / calendar / > ,<Searched on March 28, 2020> Summary of the Invention [Problem to be solved by the invention]

[0006] However, conventional technologies have issues with efficiently managing information related to work. For example, while conventional technologies can efficiently share schedules with employees themselves or the entire organization, they require time and effort, such as inputting schedules in advance, which can hinder efficient work. Furthermore, when managing information such as employees' daily reports and sales records, employees are required to input the information themselves, which can hinder efficient work. [Means for solving the problem]

[0007] Therefore, in order to solve the above-mentioned problems and achieve the objectives, the business assistance device of the present invention is characterized by having a generation unit that inputs a prompt based on natural language text received from a user to a generation model provided with information regarding business assistance, and generates information regarding business assistance indicated in the text, and an output unit that outputs the information regarding business assistance indicated in the text. [Effects of the Invention]

[0008] The present invention has the effect of enabling efficient management of information relating to business. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating an overall picture of the processing of the task support device according to this embodiment. [Figure 2] FIG. 2 is a diagram showing the configuration of the task assistance device according to this embodiment. [Figure 3] FIG. 3 is a table diagram showing an example of employee information according to this embodiment. [Figure 4] FIG. 4 is a table showing an example of text information according to this embodiment. [Figure 5] FIG. 5 is a table diagram showing an example of schedule information according to this embodiment. [Figure 6] FIG. 6 is a table diagram showing an example of a sales activity record according to this embodiment. [Figure 7] FIG. 7 is a diagram showing an example of the business support process according to this embodiment. [Figure 8] FIG. 8 is a diagram showing an example of the business support process according to this embodiment. [Figure 9] FIG. 9 is a flowchart showing the operation support process according to this embodiment. [Figure 10] FIG. 10 is a flowchart showing the operation support process according to this embodiment. [Figure 11] FIG. 11 is a diagram illustrating tsuzumi. [Figure 12] FIG. 12 is a diagram illustrating tsuzumi. [Figure 13] FIG. 13 is a diagram illustrating tsuzumi. [Figure 14] FIG. 14 is a diagram illustrating IOWN. [Figure 15] FIG. 15 is a diagram illustrating an example of a computer that executes the task support process according to this embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0010] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention (hereinafter referred to as "embodiments") will be described with reference to the drawings. Note that the embodiments are not limited to the following description.

[0011] <Overview> Fig. 1 is a diagram illustrating an overall view of the processing of a business support device 100 according to this embodiment. The business support device 100 shown in Fig. 1 is an example of a computer that provides technology to assist in inputting information related to business support, including information on a user's schedule and information on a record of sales activities, which are related to the business of a user belonging to a specific organization.

[0012] In the following sections, an "employee" is a person who belongs to a specific organization and performs tasks assigned to the specific organization. A "user" is an employee who uses the task support device 100 according to this embodiment in the specific organization, or an administrator who manages the task support device 100. In addition, "information related to task support" may be written as "task support information."

[0013] (background) Employees belonging to an organization may be required to manage the schedule of their work and ensure that work is carried out without any omissions, and to enter records of the work they have done in accordance with a prescribed format.

[0014] (Reference technologies and issues) Therefore, a reference technology is known in which employee schedules are input into a scheduler managed on the cloud and managed and visualized across the entire organization.Also, a reference technology is known in which past work records corresponding to input information are referenced and work records related to the input information are identified to assist in inputting work records.

[0015] However, in the above-mentioned reference technology, employees must input information about their own schedules and work, which may be a burden for the employees. Therefore, the above-mentioned reference technology has a problem in efficiently managing information about work.

[0016] (Processing by the business support device 100) Therefore, the business assistance device 100 according to this embodiment generates information about the user's schedule and sales information using text in a natural language related to the business input by the user (hereinafter, may be simply referred to as "text information") and outputs it to the user. Now, returning to FIG. 1, the business assistance process by the business assistance device 100 will be described.

[0017] First, the business assistance device 100 receives text information related to a business operation input by a user. Next, the business assistance device 100 performs a conversion process of the text information ((1) in FIG. 1). Specifically, the business assistance device 100 converts the received text information into a prompt to be input to a generative model ((1-1) and (1-2) in FIG. 1).

[0018] The business support device 100 inputs a prompt ((2-1) in FIG. 1) based on text information received from a user to the generation model 10 ((2-2) in FIG. 1) to which business support information has been provided, and generates ((2) in FIG. 1) the business support information ((2-3) in FIG. 1) shown in the text information.

[0019] The business support device 100 outputs business support information indicated in the text information ((3) in FIG. 1). Specifically, the business support device 100 outputs business support information generated by a predetermined generative model to a terminal device 200 operated by a user. The terminal device 200 can display to the user the business support information output by the business support device 100, including information on employee work schedules (hereinafter, sometimes referred to as "schedule information") and information on user sales activity records (hereinafter, sometimes referred to as "sales activity records") ((3-1) in FIG. 1).

[0020] In this way, the business support device 100 according to this embodiment can generate schedule information and sales activity records using text information related to the user's business, whereas conventionally users had to input schedule information and sales activity records themselves. Therefore, the business support device 100 has the effect of enabling efficient management of information related to business.

[0021] <Description of the business support device 100> Next, the configuration of the business assistance device 100 according to this embodiment will be described. FIG. 2 is a diagram showing the configuration of the business assistance device 100 according to this embodiment. As shown in FIG. 2, the business assistance device 100 has a communication unit 110, a storage unit 120, and a control unit 130. Although not shown in FIG. 2, the business assistance device 100 may also include an input unit such as a keyboard or a mouse for receiving input such as operations by an administrator or the like. The business assistance device 100 may also include a display unit such as a display for displaying input text information, prompts to be set for the generative model, generated business assistance information, etc. to an administrator or the like.

[0022] (Communication unit 110) The communication unit 110 performs data communication related to the input of text information input via the terminal device 200 operated by the user. The communication unit 110 also performs data communication related to the output of generated information related to the operation of the system.

[0023] The communication unit 110 is realized by a NIC (Network Interface Card) or the like, and controls communication via an electric communication line such as a LAN (Local Area Network), the Internet, etc. The communication unit 110 is connected to the network by wire or wirelessly as necessary, and can transmit and receive information bidirectionally with the generative model 10, the terminal device 200, etc.

[0024] (Storage unit 120) The storage unit 120 stores data and programs used for various processes by the control unit 130, and various data acquired by the operation of the control unit 130. The storage unit 120 is realized by a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 2 , the storage unit 120 has an employee information DB 121, a text information DB 122, and a business support information DB 123.

[0025] (Employee Information DB121) Employee information DB121 is a database that stores employee information including identification information and attribute information of employees who belong to a predetermined organization. Specifically, employee information DB121 stores information such as employee identification information based on a combination of predetermined characters, numbers, symbols, etc. that identify employees, and organizational attribute information, which is attribute information of employees within the organization.

[0026] Here, an example of employee information stored in the employee information DB 121 will be described with reference to a table diagram. Fig. 3 is a table diagram showing an example of employee information according to this embodiment.

[0027] 3, employee information DB121 stores employee identification information and organization attribute information in association with "No.", which is information identifying individual employee information. For example, employee information DB121 stores employee identification information "A" and organization attribute information "B," which are identified by No. "1."

[0028] The above-mentioned employee identification information "A" may include information for identifying the employee, such as the employee's name, nickname, handle name, identification number, identification symbol, identification character string, etc.

[0029] Organizational attribute information "B" may include gender, seniority, department, position, job rank, career history, talent, skills, areas of expertise, qualifications, acquaintances, communication tendencies and preferences, communication data, personality, chat data, self-introduction data (self-promotion), career sheet, keywords, and other information used for matching offers.

[0030] (Text information DB122) The text information DB 122 is a database that stores text information, which is information on business-related conversations and utterances input by employees. An example of the text information stored in the text information DB 122 will now be described using a table. Fig. 4 is a table showing an example of text information according to this embodiment.

[0031] 4, the text information DB 122 stores employee identification information and text in association with "No.", which is information that identifies individual text information. For example, the text information DB 122 stores employee identification information "A" and text "C," which are identified by No. "1."

[0032] The above-mentioned employee identification information "A" is information that identifies an employee, and is the same information as the employee identification information stored in employee information DB 121. That is, this means that the employee information stored in employee information DB 121 and the text information stored in text information DB 122 correspond to each other.

[0033] Text "C" is information on dialogues and speeches based on natural language input via the terminal device 200 operated by an employee. Specifically, the text includes business-related text such as text about purchasing, text about systems used in business, text about business schedules, text about business and sales activities, text about employee skills and evaluations, and text including general business-related conversations between employees.

[0034] (Business support information DB123) The business support information DB 123 is a database that stores business information including information about employee business schedules (schedule information) and information about sales activity records (sales activity records). Here, examples of the schedule information and sales activity records stored in the business support information DB 123 will be described using the table diagrams shown in FIGS. 5 and 6.

[0035] First, an example of schedule information will be described with reference to FIG. 5. FIG. 5 is a table diagram showing an example of schedule information according to this embodiment. As shown in FIG. 5, the business support information DB 123 stores employee identification information, task name, task content, and deadline as schedule information, in association with "No.", which is information that identifies individual schedule information. For example, the business support information DB 123 stores employee identification information "A," task name "D," task content "E," and deadline "December 31, 2024," identified by No. "1," as schedule information.

[0036] The above-mentioned employee identification information is information for identifying an employee, and is the same information as the employee identification information stored in the employee information DB 121. That is, this means that the employee information stored in the employee information DB 121 and the schedule information stored in the business support information DB 123 correspond to each other.

[0037] The task name is information that combines letters, numbers, symbols, etc. to identify the name of the employee's task. The task content is information about the content of the employee's task, including, for example, the task content related to the task. The deadline is the deadline for carrying out or completing the task.

[0038] Next, an example of a sales record stored in the business support information DB 123 will be described using the table diagram shown in FIG. 6. FIG. 6 is a table diagram showing an example of a sales activity record according to this embodiment. As shown in FIG. 6, the business support information DB 123 stores employee identification information and sales records as sales activity records in association with "No.", which is information that identifies individual sales activity records. For example, the business support information DB 123 stores employee identification information "A" and sales record "F," identified by No. "1," as sales activity records.

[0039] The above-mentioned employee identification information is information for identifying an employee, and is the same information as the employee identification information stored in the employee information DB 121. That is, this means that the employee information stored in the employee information DB 121 and the sales activity records stored in the business support information DB 123 correspond to each other.

[0040] Sales records are records of sales activities conducted by employees. For example, sales records include information such as the date of the sales activity, the destination of the sales activity, the content of the sales activity such as proposed products and services, visitors, accompanying persons, the status of the sales activity such as orders received, lost orders, and continuation of the sales activity, and next actions.

[0041] (control unit 130) Now, returning to Fig. 2, the explanation will be continued. The control unit 130 has an internal memory for temporarily storing programs defining various processing procedures and the like of the business support device 100 and processing data, and is realized by electronic circuits such as a CPU (Central Processing Unit) and an MPU (Micro Processing Unit), and integrated circuits such as an ASIC (Application Specific Integrated Circuit) and an FPGA (Field Programmable Gate Array). As shown in Fig. 2, the control unit 130 has a receiving unit 131, a generating unit 132, a storage unit 133, and an output unit 134.

[0042] (Reception Department 131) The receiving unit 131 receives text information input by the user via the terminal device 200 via the communication unit 110 described above.

[0043] (Generation unit 132) The generation unit 132 provides predetermined prior knowledge, such as business information including schedule information related to employee work and sales activity records, to the generative model to be used. Then, the generation unit 132 inputs prompts based on text information received from the user to the generative model to which the predetermined prior knowledge has been provided, thereby generating a sales activity record. Note that the provision of the above-mentioned prior knowledge may be realized by prompt engineering, adapter tuning, or the like, which will be described later.

[0044] The generating unit 132 inputs a prompt including an instruction to generate the schedule information to the generative model to which task support information including the schedule information has been provided, and generates the schedule information.

[0045] For example, the generation unit 132 converts text information input by the user into a prompt. Next, the generation unit 132 inputs the converted prompt into a generation model that has been provided in advance with schedule information such as "task name," "task content," and "deadline" stored in the business support information DB 123. Then, the generation unit 132 generates business support information such as schedule information indicated in the text information input by the user.

[0046] Specifically, the generation unit 132 generates schedule information including at least one of the target task indicated in the text, the time required for the target task estimated based on information about the past task history, the start date of the target task, the end date of the target task, and the status of the target task. Note that the schedule information includes information about the planned start date of the task, information about the deadline for the task, and information about uncompleted tasks.

[0047] For example, the generation unit 132 generates information for identifying a task, such as "Task name: A," and information about the task status, such as "Task status: not started," from an utterance such as "Task A will be performed on March 1st every year," which is included in text input by the user. Next, the generation unit 132 calculates an estimated required time for "Task name: A" based on past task history, etc. Then, the generation unit 132 generates information about the scheduled start of the task, including "Task name: A," "Required time: XX hours," "Start date of the task (scheduled start date): March 1st every year," and "Task status: not started." Note that, for the scheduled start date of the task, in addition to the date and time indicated in the utterance, the generation unit 132 can generate information about the scheduled start of the task, which sets the date and time when the task will start as the date and time obtained by adding or subtracting a predetermined number of days from the date and time indicated in the utterance.

[0048] For example, the generation unit 132 generates information about a task, such as "Task name: B," and information about the task status, such as "Task status: start status unknown," from an utterance such as "Task B must be completed by March 1st" included in text input by the user. Next, the generation unit 132 calculates an estimated required time for "Task name: B" based on past task history, etc. Then, the generation unit 132 generates information about the task deadline, including "Task name: B," "Required time: XX," "Task end date (task completion deadline): March 1st," and "Task status: start status unknown." Note that, in addition to the date and time indicated in the utterance, the generation unit 132 can generate information about the task deadline, where the task completion deadline is a date and time obtained by adding or subtracting a predetermined number of days from the date and time indicated in the utterance.

[0049] Furthermore, the generation unit 132 generates information about incomplete tasks among the tasks being handled by the employee. For example, based on an utterance such as "Task B must be completed by March 1st," the generation unit 132 generates information about the task, such as "Task Name: B," and information about the task status, such as "Task Status: Incomplete." Next, the generation unit 132 calculates the estimated time required to complete the task based on past performance records of "Task B" and similar tasks. The generation unit 132 then generates information about the incomplete task, including information such as "Task Name: B," "Required Time: XX hours," "End Date of Task (Deadline for Task Completion): March 1st," and "Task Status: Incomplete."

[0050] The generation unit 132 inputs a prompt including an instruction to generate a sales activity record to the generation model to which business support information including the sales activity record has been provided, and generates the sales activity record.

[0051] For example, the generation unit 132 converts text information input by the user into a prompt. Next, the generation unit 132 inputs the converted prompt into a generation model that is provided in advance with a sales activity record such as a "sales record" stored in the business support information DB 123. Then, the generation unit 132 generates business support information such as a sales activity record indicated in the text information input by the user.

[0052] As a specific example, the generating unit 132 generates at least one of the following as the sales activity record: sales activity date, sales activity destination, sales activity content, employee, sales activity status, and next action. The generated information is then output by the output unit 134, which will be described later.

[0053] The generation unit 132 can automatically generate business support information using text information input by employees, etc. Specifically, the generation unit 132 converts text information related to the employee's business, which is input on a daily basis by employees, etc., into a prompt including an instruction to generate the business support information. Next, the generation unit 132 inputs the converted prompt into the generative model to which the business support information was provided, thereby generating the business support information. The generated business support information is then stored in the memory unit 120 by the storage unit 133, which will be described later.

[0054] The generation unit 132 can use at least one of a large-scale language model having general-purpose knowledge and tsuzumi as a generative model. Furthermore, the generation unit 132 can use a generative model that communicates via a communication network related to IOWN (Innovative Optical and Wireless Network). Details of tsuzumi and IOWN will be explained later in the section on modified examples.

[0055] (storage section 133) The storage unit 133 stores the business support information generated by the generation unit 132 in the memory unit 120. Specifically, the storage unit 133 stores at least one of schedule information and sales activity records in the memory unit 120. An example of the storage process by the storage unit 133 will be described in detail in the section describing an example of the process below.

[0056] (output unit 134) The output unit 134 outputs the business support information for the organization indicated in the text information. Specifically, the output unit 134 outputs the reminder information generated by the generation unit 132 using the schedule information.

[0057] For example, the output unit 134 outputs reminder information that combines one or more of information on the scheduled start date of work, information on the deadline for work, and information on uncompleted work, which are generated by the generation unit 132. Also, for example, the output unit 134 outputs information on a daily sales report that combines one or more of information on the date of sales activity, the destination of sales activity, the content of sales activity, employees, the status of sales activity, and next actions, which are generated by the generation unit 132.

[0058] An example of the output process by the output unit 134 will be described in detail in the section describing an example of the process below.

[0059] (Generative Model 10) The generation model 10 is a generation model such as a large-scale language model, and generates output information in response to a generation instruction in an input natural language. Specifically, the generation model 10 generates business support information in response to text information input by the business support device 100, based on a large-scale language model or the like in which a prompt is set to generate system operation information.

[0060] The generative model 10 according to this embodiment may be realized by an information processing device such as a server. The generative model 10 can generate an answer in response to a prompt based on prior knowledge that has been provided, input, learned, added, etc.

[0061] (Terminal device 200) The terminal device 200 is an information processing terminal device operated by a user. Specifically, the terminal device 200 receives text information from the user, transmits the received text information to the business support device 100, and receives and displays business support information from the business support device 100.

[0062] (Example of processing) An example of the task assistance process by the task assistance device 100 according to this embodiment will now be described with reference to Fig. 7 and Fig. 8. Fig. 7 and Fig. 8 are diagrams showing an example of the task assistance process according to this embodiment.

[0063] 7 shows an example of "schedule information generation and output processing" as a first example, and FIG. 8 shows an example of "sales activity record generation and output processing" as a second example.

[0064] (First example) The first example of "schedule information generation processing and output processing" will be described. Fig. 7 shows a business support device 100 that generates schedule information, a terminal device 200 operated by a user, and a generation model 10 used by the business support device 100.

[0065] First, the terminal device 200 receives text information from the user, such as "Task A will be performed on March 1st every year." Then, the terminal device 200 transmits the text information received from the user to the task support device 100 ((1-1) in FIG. 7).

[0066] The business support device 100 converts text information ((1-1) in FIG. 7) received from the terminal device 200 into a prompt ((1-2) in FIG. 7). For example, the business support device 100 converts text information such as "Task A will be performed on March 1st every year" into a prompt to be input to a generation model such as "Please generate schedule information for task A to be performed by a user on March 1st every year."

[0067] The task support device 100 executes a process for generating schedule information ((2) in FIG. 7). Specifically, the task support device 100 inputs the converted prompt to the generation model 10, which has been provided with prior knowledge for generating schedule information ((2-1) in FIG. 7), and generates schedule information such as "task name," "task content," and "deadline" ((2-2) in FIG. 7).

[0068] Here, the business support device 100 stores the generated schedule information such as "task name," "task content," and "deadline" in the business support information DB 123 ((3) in FIG. 7). Specifically, the business support device 100 associates employee identification information "A" ((3-1) in FIG. 7), task name "D" ((3-2) in FIG. 7), task content "E" ((3-3) in FIG. 7), and deadline "March 1st every year" ((3-4) in FIG. 7) with each other, and stores them in the business support information DB 123.

[0069] The business support device 100 executes a process of outputting schedule information to a user when a predetermined deadline arrives ((4) in FIG. 7). The business support device 100 transmits schedule information including "task name," "task content," "deadline," etc. to the terminal device 200 operated by the user. Then, the terminal device 200 displays the received schedule information to the user ((4-1) in FIG. 7).

[0070] (Second example) The second example, “Sales Activity Record Generation Process and Output Process,” will now be described. Fig. 8 shows a business support device 100 that generates a sales activity record, a terminal device 200 operated by a user, and a generation model 10 used by the business support device 100.

[0071] First, the terminal device 200 receives text information from the user, such as "On March 1st, I visited company A and conducted sales activities such as XX," or "As a result, I received an order for a new project." Then, the terminal device 200 transmits the text information received from the user to the business support device 100 ((1-1) in FIG. 8).

[0072] The business support device 100 converts text information ((1-1) in FIG. 8) received from the terminal device 200 into a prompt ((1-2) in FIG. 8). For example, the business support device 100 converts text information such as "On April 1st, we visited Company A and performed sales activity (XX)" and "As a result, we received an order for a new project" into a prompt to be input to a generation model such as "The user should generate a sales activity record including information that on April 1st, Company A performed sales activity (XX), and as a result, we received an order for a new project."

[0073] The business support device 100 executes a process for generating a sales activity record ((2) in FIG. 8). Specifically, the business support device 100 inputs the converted prompt to the generation model 10, which has been provided with prior knowledge for generating a sales activity record ((2-1) in FIG. 8), and generates a "sales record" or the like as a sales activity record ((2-2) in FIG. 8).

[0074] For example, the business support device 100 generates a sales record including information such as the date of the sales activity (April 1st), the destination of the sales activity (Company A), the content of the sales activity (XX), the visitor (employee), the accompanying person (none), the status of the sales activity (order received), and the next action (follow-up on the received order).

[0075] Here, the business support device 100 stores the generated sales activity records such as "sales record" in the business support information DB 123 ((3) in FIG. 8). Specifically, the business support device 100 associates the employee identification information "A" ((3-1) in FIG. 8) with the sales record "F" ((3-2) in FIG. 7) and stores them in the business support information DB 123.

[0076] The business support device 100 outputs the sales activity record based on an output instruction from a user or a data output instruction from another server, etc. For example, the business support device 100 executes a process of outputting the sales activity record to the user ((4) in FIG. 8).

[0077] The business support device 100 transmits a sales activity record, including "sales activity date," "sales activity destination," "sales activity content" such as proposed products and proposed services, "visitors," "accompanying persons," "sales activity status" such as orders received, lost orders, and continuation of sales activities, "next action," etc., to the terminal device 200 operated by the user. Then, the terminal device 200 displays the received sales activity record to the user ((4-1) in FIG. 8).

[0078] (Procedure for business support processing) Next, the procedure of the task assistance process realized by the task assistance device 100 according to this embodiment will be described with reference to Fig. 9 and Fig. 10. Fig. 9 and Fig. 10 are diagrams showing a flowchart of the task assistance process according to this embodiment.

[0079] 9 shows an example of a processing procedure for "schedule information generation processing and output processing." Also, FIG. 10 shows an example of a processing procedure for "sales activity record generation processing and output processing."

[0080] First, an example of a processing procedure for "schedule information generation processing and output processing" will be described with reference to Fig. 9. The generation unit 132 provides prior knowledge to the generative model (S101). Specifically, the generation unit 132 inputs, to the generative model to be used, a prompt including an instruction to store schedule information such as "task name," "task content," and "deadline" stored in the task support information DB 123. Through the above-described processing, the generation unit 132 causes the generative model to generate schedule information.

[0081] Here, if the user does not perform an operation such as an instruction to start the generation process, the business support device 100 waits for the process (No in S102). On the other hand, if the user performs an operation such as an instruction to start the generation process (Yes in S102), the business support device 100 starts the process of S103.

[0082] The accepting unit 131 accepts text information from a user (S103). Next, the generating unit 132 converts the input text information into a prompt (S104). Next, the generating unit 132 inputs the converted prompt into a generative model to generate schedule information (S105). Next, the storing unit 133 stores the generated schedule information in the memory unit 120 (S106).

[0083] If the due date for the schedule has not arrived (No in S107), the business support device 100 waits for processing. On the other hand, if the due date for the schedule has arrived (Yes in S107), the output unit 134 outputs the schedule information (S108). Then, the business support device 100 ends the processing.

[0084] Next, an example of the processing procedure for the "sales activity record generation processing and output processing" will be described with reference to FIG. 10. The generation unit 132 provides prior knowledge to the generative model (S201). Specifically, the generation unit 132 inputs, to the generative model to be used, a prompt including an instruction to store a sales activity record such as "sales record" stored in the business support information DB 123. Through the above-described processing, the generation unit 132 causes the generative model to generate a sales activity record.

[0085] Here, if the user does not perform an operation such as an instruction to start the generation process, the business support device 100 waits for the process (No in S202). On the other hand, if the user performs an operation such as an instruction to start the generation process (Yes in S202), the business support device 100 starts the process of S203.

[0086] The accepting unit 131 accepts text information from a user (S203). Next, the generating unit 132 converts the input text information into a prompt (S204). Next, the generating unit 132 inputs the converted prompt into a generative model to generate a sales activity record (S205). Next, the storage unit 133 stores the generated sales activity record in the memory unit 120 (S206).

[0087] Here, if there is no instruction to output the stored sales activity record (No in S207), the business support device 100 waits for processing. On the other hand, if there is an instruction to output the stored sales activity record (Yes in S207), the output unit 134 outputs the schedule information (S208). Then, the business support device 100 ends the processing.

[0088] (effect) Next, we will explain the effects of the task assistance device 100 according to this embodiment. Conventionally, employees have to input information about their own schedules and tasks themselves, which places a burden on employees, and there are problems with efficient management of task information.

[0089] Therefore, the generation unit 132 of the task assistance device 100 according to this embodiment inputs a prompt based on the text information received from the user to the generation model to which the task assistance information has been provided, and generates the task assistance information indicated in the text information. Then, the output unit 134 of the task assistance device 100 outputs the task assistance information indicated in the text information.

[0090] By the above-described processing, the business support device 100 according to this embodiment can generate business support information including information such as the user's schedule information and sales activity records, using text information, etc., of business-related exchanges between the user and other employees during work, etc. As a result, the business support device 100 according to this embodiment has the effect of enabling efficient management of information related to work by automatically generating business support information, whereas in the past, the user had to input schedules and sales activity records into a system, etc.

[0091] Furthermore, the task assistance device 100 according to this embodiment achieves predetermined effects by executing the processes described below.

[0092] In the past, users themselves had to input schedule information such as work plans and deadlines into the target system. Therefore, the generation unit 132 generates schedule information by inputting a prompt including an instruction to generate schedule information to a generation model to which work support information including schedule information has been provided.

[0093] As described above, the business assistance device 100 can automatically generate schedule information related to a user based on text information such as utterances input by the user. Therefore, the business assistance device 100 eliminates the need for the user to manually input schedule information. Therefore, the business assistance device 100 enables efficient management of business assistance information, thereby improving the business efficiency of the user.

[0094] In the past, users had to manually input records of their sales activities into the target system. Therefore, the generation unit 132 generates schedule information including at least one of the target task indicated in the text, the estimated time required for the target task based on information about the past task history, the start date of the target task, the end date of the target task, and the status of the target task. The output unit 134 then outputs reminder information generated using the schedule information generated by the generation unit 132.

[0095] As described above, the task assistance device 100 can generate schedule information, such as information about the scheduled start date of a task for the user, information about the deadline for the task, and information about uncompleted tasks, based on text information such as utterances input by the user, and can remind the user of the task. Therefore, the task assistance device 100 eliminates the need for the user to input schedule information, and improves the user's task efficiency by reminding the user of appropriate tasks.

[0096] The generation unit 132 generates a sales activity record by inputting a prompt including an instruction to generate a sales activity record to a generative model provided with business support information including the sales activity record. As a specific example, the generation unit 132 generates at least one of the following as the sales activity record: a sales activity implementation date, a sales activity destination, a sales activity content, an employee, a sales activity status, and a next action. Then, the output unit 134 outputs information related to the daily sales report generated by the generation unit 132, which combines one or more of the sales activity implementation date, the sales activity destination, the sales activity content, the employee, the sales activity status, and the next action.

[0097] As described above, the business support device 100 can automatically generate a sales activity record for a user based on text information such as utterances input by the user. Therefore, the business support device 100 eliminates the need for the user to manually input the sales activity record. Therefore, the business support device 100 enables efficient management of business support information, thereby improving the business efficiency of the user.

[0098] The generation unit 132 converts text information related to the employee's work into a prompt including an instruction to generate work support information. Next, the generation unit 132 inputs the converted prompt into the generative model to which the work support information was provided, thereby generating the work support information. The storage unit 133 stores the work support information generated by the generation unit 132 in the memory unit 120.

[0099] Through the above-described process, even when there is no instruction for generation processing from a user or the like, the business support device 100 can generate business support information using text information related to conversations between employees and store the information in the storage unit 120. That is, the business support device 100 can automatically generate and store business support information using text information such as daily business conversations. As a result, the business support device 100 can improve the accuracy of the generation processing of business support information instructed by a user by using the stored business support information, thereby achieving the effect of enabling efficient management of business information.

[0100] <Modification> The following describes modified examples realized by the task assistance device 100 according to this embodiment.

[0101] (Data, etc.) The text information, prompts, task support information, names of the functional parts of the task support device 100, steps, processes, names of steps or processes, etc. used in the description of the above embodiment are merely examples and can be changed as desired.

[0102] For example, the employee information DB121 stores employee identification information and organization attribute information in association with "No.", which is information identifying individual employee information, but is not limited to this. Furthermore, the text information DB122 stores employee identification information and text information in association with "No.", which is information identifying individual text information, but is not limited to this. Furthermore, the business support information DB123 stores employee identification information, task name, task content, deadline, and schedule information in association with "No.", which is information identifying individual schedule information. Furthermore, the business support information DB123 stores employee identification information and sales records as sales activity records in association with "No.", which is information identifying individual sales activity records, but is not limited to this.

[0103] (Combination of processing examples, etc.) The first to third examples according to the present embodiment described above are merely examples, and the present invention is not limited to the described contents.

[0104] (An example of a generative model) The business support device 100 according to this embodiment can use a large-scale language model such as ChatGPT (registered trademark) (see, for example, Reference 1) or a large-scale language model such as tsuzumi (registered trademark) (see, for example, Reference 2) as a generative model.

[0105] (Reference 1):ChatGPT(OpenAI),<URL:https: / / openai.com / chatgpt> ,<Searched on March 29, 2020> (Reference 2): NTT's large-scale language model "tsuzumi",<URL:https: / / www.rd.ntt / research / LLM_tsuzumi.html> ,<Searched on March 29, 2020>

[0106] From now on, tsuzumi will be described as an example of a generative model used by the task assistance device 100 according to this embodiment. Figures 11 to 13 are diagrams for explaining tsuzumi.

[0107] First, the concept of tsuzumi will be explained using Figure 11. tsuzumi is a small, energy-efficient large-scale language model that achieves the same level of accuracy as ChatGPT, a single large-scale language model that consumes a lot of power.

[0108] Tsuzumi is a large-scale language model that is compact by focusing on a high-quality corpus and supporting only English and Japanese, rather than on the amount of training data. Furthermore, for domain specialization, Tsuzumi can be fine-tuned and can integrate with external data by combining search and generative AI (Artificial Intelligence).

[0109] As mentioned above, tsuzumi is a compact generative model, making it possible to create and operate multiple large-scale language models with specific specialized fields and diverse personalities. Furthermore, by linking small, large-scale language models for each specialized field (e.g., "medical care," "retail," "construction," "local government," "technology," "travel," "culture," "religion," "art," "education," "finance," "legal affairs," and "banking") based on a predefined network, tsuzumi achieves the formation of generative models with higher performance, efficiency, fault tolerance, and democratization than conventional single, huge, large-scale language models.

[0110] Furthermore, tsuzumi allows flexible tuning such as the fine tuning mentioned above. Specifically, tsuzumi allows tuning by "prompt engineering" as shown in Figure 12, "full fine tuning," and "adapter tuning."

[0111] For example, "prompt engineering" shown in Figure 12 (1) is a tuning method that uses prompts with added information about a specific field when setting prompts for the base model. In tuning using prompt engineering, the base model itself is not changed and only the prompts that are set are changed, so the learning cost can be reduced compared to other methods.

[0112] For example, "full fine-tuning" shown in Figure 12 (2) is a tuning method in which the base model is additionally trained or retrained using training data related to a specific field. In full fine-tuning, a tuning model specialized for a target field can be constructed by training the base model using training data for the target field. Therefore, full fine-tuning can improve the accuracy of inference and generation compared to other methods.

[0113] For example, "adapter tuning" shown in Figure 12 (3) is a tuning method that adds a submodule related to a specific field to the base model. Adapter tuning can improve the accuracy of inference and generation by fine-tuning the base model using a submodule related to the target field. Furthermore, because adapter tuning does not require retraining the base model, it can improve accuracy while reducing training costs compared to full fine tuning.

[0114] Furthermore, tsuzumi can construct a model based on a “multi-adapter.” Here, a multi-adapter will be explained using FIG.

[0115] As explained using (3) in Figure 12, tsuzumi allows fine-tuning of the model by adding adapters (sub-modules) to the base model. tsuzumi can also add a combination of one or more adapters to the base model.

[0116] For example, as shown in Fig. 13, tsuzumi fine-tunes the foundation model using an adapter specialized for organization A, an adapter specialized for organization B, and an adapter specialized for organization C. As a result, even when data with different characteristics, such as data from organization A, organization B, and organization C, is input, tsuzumi can accurately perform inference and generation processing based on the model fine-tuned by the adapters specialized for each organization.

[0117] For example, organization A could be the "research laboratory," organization B could be the "sales department," and organization C could be the "entire company." In other words, even if the characteristics and granularity of the organizations differ, tsuzumi can make fine adjustments using an adapter appropriate for the organization.

[0118] As mentioned above, tsuzumi is small and energy-efficient, and by combining small, large-scale language models specialized for specific fields, and by implementing flexible tuning, it is possible to achieve both accuracy and cost when performing inference and generation processing compared to conventional huge, large-scale language models.

[0119] In other words, tsuzumi can be used as an appropriate generation model for executing specific processing, such as business support processing by the business support device 100 of this embodiment, corresponding to the use, purpose, and target field of the processing.

[0120] (IOWN technology) The generative model used by the task assistance device 100 according to the present embodiment described above may be realized using a technology related to the Innovative Optical and Wireless Network (IOWN) technology.

[0121] Here, we will explain the IOWN technology. Figure 14 is a diagram explaining IOWN. As shown in Figure 14, the IOWN technology consists of three main technology fields: "All-Photonics Network (APN)," "Digital Twin Computing (DTC)," and "Cognitive Foundation (CF) (registered trademark)."

[0122] (All Photonics Network) The APN related to IOWN technology is a technology that enables the construction of high-speed networks by processing all network transfer functions in the optical domain. Specifically, the APN related to IOWN technology is a technology that realizes low-power, high-quality, large-capacity, and low-latency communications based on optical-based (photonics-based) technologies such as "photonics-electronic convergence technology," "large-capacity optical transmission system and device technology," "optical Ising machine," and "optical lattice clock network."

[0123] (Digital Twin Computing) DTC, which is related to IOWN technology, is a technology that maps individual objects in the real world onto a virtual space using the vast amount of data collected by devices connected to the APN described above.

[0124] Conventional digital twin frameworks are used by mapping individual objects, such as automobiles and robots, into a virtual space, performing analysis and predictions on them, and then mapping the results of the analysis and predictions back onto the real world.

[0125] On the other hand, DTC related to IOWN technology expands on the conventional concept of digital twins, freely combining digital twins of various industries, objects, and people to perform calculations, thereby reproducing with high accuracy the combination of multiple objects, such as people and automobiles in a city. Furthermore, DTC related to IOWN technology enables not only the expression of a person's external appearance, but also the digital expression of their internal state, such as consciousness and thoughts, by combining technologies that enable "speech recognition," "speech synthesis," "understanding of emotions and intentions," etc. to collect information and build a digital twin environment.

[0126] In this way, DTC related to IOWN technology is a technology that enables the creation of digital twins that do not exist in the real world by combining multiple entities that are single in the real world and replicating them as digital twins in a virtual space, or by exchanging or merging some of the components between multiple digital twins.

[0127] (Cognitive Foundation) CF related to IOWN technology is a technology that centrally performs the deployment, configuration, linkage, management, and operation of ICT (Information and Communication Technology) resources at different layers, from the cloud to edge computers, network services, user equipment, etc. Specifically, CF related to IOWN technology treats various targets as a group of virtualized ICT resources, and optimally integrates multiple resources at different layers using multi-orchestration functions as a hub.

[0128] Furthermore, as shown in FIG. 14, the IOWN technology provides high-value-added services by linking the above-mentioned APN, DTC, and network services provided by operators.

[0129] For example, as shown in (1) of Figure 14, IOWN technology provides a technology for transmitting information collected via APN to other terminal devices at high speed and with low latency. Also, as shown in (2) of Figure 14, IOWN technology provides a technology for collecting large amounts of information from terminal devices and outputting information such as analysis results from the service provided by the operator at high speed and with low latency in services such as information analysis. Also, as shown in (3) of Figure 14, IOWN technology provides a technology for transmitting large amounts of information at high speed and with low latency, using information obtained from surveillance cameras, automobile sensors, etc. to build a digital twin environment, make future predictions, and output the prediction results to the user.

[0130] The business assistance device 100 according to this embodiment can efficiently realize business assistance processing based on the generative model of Tsuzumi or the like configured based on the IOWN technology that transmits data at high speed and with low latency as described above.

[0131] For example, the business support device 100 can generate business support information with higher accuracy than conventional methods based on tsuzumi, which is learned using text information related to its own organization or other organizations that is collected in large quantities at high speed and with low latency via a network built based on IOWN.

[0132] (Regarding business-related natural language text) In the present embodiment, it has been described that the task assistance device 100 uses "text in a natural language related to a task." The "text in a natural language related to a task" does not mean including only text related to a task, but also broadly includes, for example, daily conversations, business-related meeting details, and other natural language conversations between employees.

[0133] (Flowcharts, etc.) The steps in the flowcharts may be interchanged as long as there is no contradiction, and some steps may not be performed. In addition, conjunctions such as "next," "continue," "further," "at this time," and "on this occasion" used in the explanation of the flowcharts do not limit the order or timing of the execution of the processes in the flowcharts.

[0134] <Hardware configuration> The components of each device shown in the figure are conceptual functional units and do not necessarily have to be physically configured as shown. In other words, the specific form of distribution and integration of each device is not limited to that shown, and all or part of each device can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc. Furthermore, all or any part of the processing functions performed by each device can be realized by a CPU and a program analyzed and executed by the CPU, or can be realized as hardware using wired logic.

[0135] Furthermore, among the processes described in this embodiment, all or part of the processes described as being performed automatically can also be performed manually using known methods. In addition, the information including the processing procedures, control procedures, specific names, various data, and parameters shown in the drawings can be changed as desired unless otherwise specified.

[0136] <Program> In one embodiment, the various devices constituting the business support device 100 can be implemented by installing a business support program as package software or online software on a desired computer. For example, by executing the business support program on an information processing device, the various devices constituting the business support device 100 can function. The information processing device referred to here includes desktop and notebook personal computers. In addition, the information processing device also includes mobile communication terminals such as smartphones and mobile phones, and slate terminals such as PDAs (Personal Digital Assistants).

[0137] 15 is a diagram showing an example of a computer that executes the task support processing according to this embodiment. The computer 1000 includes, for example, a memory 1010 and a CPU 1020. The computer 1000 also includes a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. These components are connected by a bus 1080.

[0138] The memory 1010 includes a ROM (Read Only Memory) 1011 and a RAM 1012. The ROM 1011 stores, for example, a boot program such as a BIOS (Basic Input Output System). The hard disk drive interface 1030 is connected to a hard disk drive 1090. The disk drive interface 1040 is connected to a disk drive 1100. A removable storage medium such as a magnetic disk or optical disk is inserted into the disk drive 1100. The serial port interface 1050 is connected to, for example, a mouse 1110 and a keyboard 1120. The video adapter 1060 is connected to, for example, a display 1130.

[0139] The hard disk drive 1090 stores, for example, an OS (Operating System) 1091, an application program 1092, a program module 1093, and program data 1094. That is, a program that defines each process of the various devices that constitute the task support device 100 is implemented as a program module 1093 in which computer-executable code is written. The program module 1093 is stored, for example, in the hard disk drive 1090. For example, a program module 1093 for executing the same process as the functional configuration of the various devices that constitute the task support device 100 is stored in the hard disk drive 1090. Note that the hard disk drive 1090 may be replaced with an SSD (Solid State Drive).

[0140] Furthermore, setting data used in the processing of the above-described embodiment is stored as program data 1094, for example, in the memory 1010 or the hard disk drive 1090. Then, the CPU 1020 reads the program module 1093 or the program data 1094 stored in the memory 1010 or the hard disk drive 1090 into the RAM 1012 as necessary, and executes the processing of the above-described embodiment.

[0141] The program module 1093 and program data 1094 are not limited to being stored in the hard disk drive 1090, but may also be stored in, for example, a removable storage medium and read by the CPU 1020 via the disk drive 1100 or the like. Alternatively, the program module 1093 and program data 1094 may be stored in another computer connected via a network (such as a LAN or a WAN (Wide Area Network)). The program module 1093 and program data 1094 may then be read by the CPU 1020 from the other computer via the network interface 1070.

[0142] <Other> Although the present embodiment has been described above, the present embodiment is not limited by the descriptions and drawings that form part of the disclosure. In other words, other embodiments, examples, operational techniques, etc. that are made by those skilled in the art based on the present embodiment are all included in the scope of the present embodiment. [Explanation of symbols]

[0143] 10 Generative Model 100 Business support equipment 110 Communications Department 120 Storage section 121 Employee Information DB 122 Text Information DB 123 Business support information DB 130 Control Unit 131 Reception 132 Generation part 133 Storage area 134 Output section 200 Terminal Device

Claims

1. a generation unit that inputs a prompt based on a natural language text received from a user to a generation model provided with information on business support, and generates information on business support indicated in the text; an output unit that outputs information regarding business support indicated in the text; A task assistance device comprising:

2. The generation unit inputting the prompt including an instruction for generating information about the employee's work schedule to a generative model to which information about support for the work, including information about the employee's work schedule, is provided, thereby generating information about the employee's work schedule; 2. The task assisting device according to claim 1.

3. The generation unit generating information regarding the employee's work schedule, the information including at least one of the target work indicated in the text, the time required for the target work estimated based on information regarding past work history, the start date of the target work, the end date of the target work, and the status of the target work; The output unit outputting reminder information generated using information on the employee's work schedule generated by the generation unit; 3. The task assisting device according to claim 2.

4. The generation unit inputting the prompt including an instruction to generate information about a record of sales activities to a generative model to which information about support for the business including information about a record of sales activities has been provided, thereby generating information about the record of sales activities; 2. The task assisting device according to claim 1.

5. The generation unit generating at least one of the following information regarding the sales activity record: a sales activity implementation date, a sales activity destination, a sales activity content, an employee, a sales activity status, and a next action; The output unit outputting information about the daily sales report generated by the generating unit, the daily sales report being a combination of one or more of the sales activity implementation date, the sales activity destination, the content of the sales activity, the employee, the sales activity status, and the next action; 5. The task assisting device according to claim 4.

6. The generation unit converting natural language text related to the employee's work into prompts containing instructions for generating information to assist with the work; inputting the converted prompt into a generative model to which information related to business support has been provided, thereby generating information related to business support; 2. The task assisting device according to claim 1.

7. The system further includes a storage unit that stores the generated information on the business support in a storage unit.

7. The task support device according to claim 1, wherein the task support device is a task support device.

8. The generation unit As the generative model, at least one of a large-scale language model having general knowledge and Tsuzumi is used.

7. The task support device according to claim 1, wherein the task support device is a task support device.

9. The generation unit Using the generative model to communicate over a communication network related to an Innovative Optical and Wireless Network (IOWN), 9. The task support device according to claim 8.

10. A task assistance method executed by a task assistance device, a generation step of inputting a prompt based on a natural language text received from a user to a generation model provided with information on business support, and generating information on business support indicated in the text; an output step of outputting information relating to business support indicated in the text; A work assistance method comprising:

11. a generation step of inputting a prompt based on a natural language text received from a user to a generation model provided with information on business support, and generating information on business support indicated in the text; an output step of outputting information relating to business support indicated in the text; A business support program that causes a computer to execute the above.

Images