Operation support device, operation support method, and operation support program

Abstract

To enable appropriate handling of system malfunctions.SOLUTION: An operation 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-related system operations so as to generate information regarding system operations related to work indicated by the text. The generation device 100 outputs the information regarding the system operations related to the work indicated by the text to the user.SELECTED DRAWING: Figure 2

Description

[Technical Field]

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

[0002] Organizations operate systems that are linked together to handle a variety of tasks, including accounting, inventory management, order management, quality control, production management, sales management, customer management, sales support, quotation management, human resources management, attendance management, and payroll calculations. When the above-mentioned systems are independent, data is exchanged between the systems, but this can sometimes cause problems due to poor data exchange between the systems.

[0003] For this reason, techniques for identifying problems occurring in the operation of multiple systems are sometimes used. For example, a conventional technique is known in which, when a failure notification email is received from a monitoring system, the function in which the failure occurred is identified from the failure notification email, information useful for identifying the cause is obtained from the corresponding failure log by keyword search, the received email and information related to the obtained log are associated and stored, and if a similar failure occurs at a later date, the past failure history is promptly notified to the system administrator (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2010-257066 Summary of the Invention [Problem to be solved by the invention]

[0005] However, with conventional technology, it can be difficult to respond appropriately to system malfunctions. For example, when multiple business systems are linked, it can be difficult to identify which system caused the malfunction and what the cause was. [Means for solving the problem]

[0006] Therefore, in order to solve the above-mentioned problems and achieve the objectives, the operation 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 the operation of a system related to a business, and generates information regarding the operation of the system related to the business indicated in the text, and an output unit that outputs the information regarding the operation of the system related to the business indicated in the text to the user. [Effects of the Invention]

[0007] The present invention has the effect of enabling appropriate responses to system malfunctions. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an overall picture of the processing of the operation support device according to this embodiment. [Figure 2] FIG. 2 is a diagram showing the configuration of the operation 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 system information according to this embodiment. [Figure 6] FIG. 6 is a table showing an example of defect information according to this embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of the operation support process according to this embodiment. [Figure 8] FIG. 8 is a diagram illustrating an example of the operation support process according to this embodiment. [Figure 9] FIG. 9 is a diagram illustrating an example of the operation support process according to this embodiment. [Figure 10]FIG. 10 is a diagram showing a flowchart of the operation support process according to this embodiment. [Figure 11] FIG. 11 is a diagram showing a flowchart of the operation support process according to this embodiment. [Figure 12] FIG. 12 is a diagram showing a flowchart of the operation support process according to this embodiment. [Figure 13] FIG. 13 is a diagram illustrating tsuzumi. [Figure 14] FIG. 14 is a diagram illustrating tsuzumi. [Figure 15] FIG. 15 is a diagram illustrating tsuzumi. [Figure 16] FIG. 16 is a diagram illustrating IOWN. [Figure 17] FIG. 17 is a diagram illustrating an example of a computer that executes the operation support process according to this embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] 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.

[0010] <Overview> Fig. 1 is a diagram illustrating an overall view of the processing of the operation support device 100 according to this embodiment. The operation support device 100 shown in Fig. 1 is an example of a computer that provides a technology for generating predetermined responses to inquiries from users regarding systems related to business operations operated in an organization, and outputting information related to the operation of the system, such as responses to users who have made inquiries.

[0011] In the following sections, "a system related to the business operations operated in an organization" may be simply referred to as "system." Furthermore, an "employee" is a person who belongs to a specific organization and performs the business assigned to that specific organization. Furthermore, a "user" is an employee who uses the operation support device 100 of this embodiment in the above-mentioned specific organization, an administrator who manages the operation support device 100, etc. Furthermore, "information related to the operation of the system" may be referred to as "system operation information."

[0012] (background) In order to manage various information within an organization, systems related to various operations such as accounting management, inventory management, order management, quality control, production management, sales management, customer management, sales support, quotation management, human resources management, attendance management, and payroll calculation may be linked and operated.

[0013] (Reference technologies and issues) However, there are cases where problems occur in the above-mentioned cooperation between multiple systems, etc. To address this, a reference technology has been known as a technique for identifying problems, in which the location and cause of the problem are identified based on a failure notification from a monitoring system, and the system administrator is promptly notified.

[0014] However, with the above-mentioned reference technologies, it may be difficult to respond appropriately to system malfunctions. For example, since the conventional technologies identify the malfunction that has occurred and notify the system administrator, when multiple systems related to multiple operations are linked, it may be difficult to identify which system the malfunction occurred in and what the cause was.

[0015] (Processing by the operation support device 100) Therefore, in order to solve the above-mentioned problems, the operation support device 100 according to this embodiment uses natural language text (hereinafter, may be simply referred to as "text information") related to business such as inquiries received from users such as system administrators and end users to cause a generative model to generate an answer corresponding to the inquiry, and outputs the generated answer to the user who made the inquiry. Now, returning to Fig. 1, the operation support process performed by the operation support device 100 will be described.

[0016] First, the operation support device 100 receives text information related to a task input by a user. Next, the operation support device 100 performs a conversion process for the text information ((1) in FIG. 1). Specifically, the operation support device 100 converts the received text information into a prompt used to input the text information into a generative model ((1-1) and (1-2) in FIG. 1).

[0017] The operation support device 100 executes a process for generating system operation information ((2) in FIG. 1). The operation 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 system operation information related to a business has been provided, and generates system operation information ((2-3) in FIG. 1) related to the business indicated in the text information.

[0018] The operation support device 100 outputs system operation information related to the business indicated in the text information to the user ((3) in FIG. 1). Specifically, the operation support device 100 outputs the system operation information generated by a predetermined generative model to a terminal device 200 operated by the user. The terminal device 200 can then display the system operation information, including system information and malfunction information, output by the operation support device 100 to the user ((3-1) in FIG. 1).

[0019] In this way, the operation support device 100 according to this embodiment can generate a response to an inquiry from a user, including information on the location, cause, and countermeasures of a malfunction in a system operated within an organization, and output the response to the user who made the inquiry. Therefore, the operation support device 100 has the effect of enabling an appropriate response to the malfunction in the system.

[0020] <Explanation of the Operation Support Device 100> Next, the configuration of the operation support device 100 according to this embodiment will be described. FIG. 2 is a diagram showing the configuration of the operation support device 100 according to this embodiment. As shown in FIG. 2, the operation support device 100 has a communication unit 110, a storage unit 120, and a control unit 130. Although not shown in FIG. 2, the operation support device 100 may also include an input unit such as a keyboard or a mouse for accepting inputs such as operations by an administrator or the like. The operation support 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 system operation information, etc. to the administrator or the like.

[0021] (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 system operation information.

[0022] 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.

[0023] (Storage unit 120) The storage unit 120 stores data and programs used for various processes by the control unit 130, as well as various data acquired through 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, a system information DB 123, and a defect information DB 124.

[0024] (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.

[0025] 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.

[0026] 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."

[0027] 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.

[0028] 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.

[0029] (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.

[0030] 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."

[0031] 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.

[0032] 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.

[0033] (System Information DB123) The system information DB 123 is a database that stores system information including information such as the configuration of a system operated in a target organization, a system flow, and a checklist. An example of the system information stored in the system information DB 123 will now be described using a table. Fig. 5 is a table showing an example of system information according to this embodiment.

[0034] 5, the system information DB 123 stores a system name, configuration information, system flow information, and a checklist in association with "No." This "No." identifies individual system information. For example, the system information DB 123 stores a system name "D," configuration information "E," system flow information "F," and checklist "G," all of which are identified by the number "1."

[0035] The system name "D" includes information that combines letters, numbers, symbols, etc. to identify the system being operated. The configuration information "E" is configuration information related to the system being operated, and includes, for example, information such as the combination of elements such as the platform, applications, databases, etc., such as the OS (Operating System) used in the system.

[0036] System flow information "F" includes information such as flowcharts that visualize the flow of data exchange and processing between a single system or multiple systems being operated. Also, checklist "G" is information such as a list of tasks and check items used to prevent system malfunctions or to identify the location and cause of malfunctions when they occur.

[0037] (Bug Information DB124) The defect information DB 124 is a database that stores information relating to defects in systems related to business operations operated in a target organization (hereinafter, this information may be referred to as "defect information"). An example of defect information stored in the defect information DB 124 will now be described using a table diagram. Fig. 6 is a table diagram showing an example of defect information according to this embodiment.

[0038] 6, the malfunction information DB 124 stores a system name, an occurrence location, a cause, and a countermeasure in association with a "No.", which is information for identifying individual malfunction information. For example, the malfunction information DB 124 stores a system name "D," an occurrence location "H," a cause "I," and a countermeasure "J," identified by a No. "1," as malfunction information.

[0039] The above-mentioned system name "D" is information for identifying the system, and includes information similar to the system name stored in the system information DB 123. That is, this means that the system information stored in the system information DB 123 corresponds to the malfunction information stored in the malfunction information DB 124. Furthermore, the above-mentioned system name item may include multiple pieces of information for identifying the system.

[0040] The location of occurrence "H" is information that identifies the location of the malfunction in the system being operated, and includes, for example, information on the location of the hardware failure, the location of the interruption in the communication of information, the location of the processing stoppage, etc. The cause "I" is information on the cause of the malfunction, and includes, for example, information on the hardware failure, the interruption in the communication of information, the processing stoppage, etc.

[0041] Countermeasure "J" is information on how to prevent malfunctions from occurring or how to resolve malfunctions that have occurred, and specifies methods for dealing with causes of malfunctions such as hardware failures, interruptions in information communication, and processing stoppages.

[0042] (control unit 130) Here, the explanation will be continued by returning to Fig. 2. The control unit 130 has an internal memory for temporarily storing programs that define various processing procedures and the like of the operation 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, an output unit 134, and a responding unit 135.

[0043] (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.

[0044] (Generation unit 132) The generation unit 132 provides predetermined prior knowledge to the generative model to be used, such as system information including system configuration information, system flow information, and checklists for the system in the target organization, and malfunction information including malfunction locations, causes, and countermeasures. 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 system operation information. Note that the provision of the above-mentioned prior knowledge may be achieved by prompt engineering, adapter tuning, or the like, which will be described later.

[0045] Specifically, the generation unit 132 inputs a prompt including an instruction to generate malfunction information into a generation model that has been provided with system configuration information related to the business and system operation information related to the business, including malfunction information, and generates information regarding system malfunctions related to the business.

[0046] 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 information such as "system name," "configuration information," "system flow information," and "checklist" stored in the system information DB 123, and information such as "location of occurrence," "cause," and "countermeasure" stored in the malfunction information DB 124. Then, the generation unit 132 generates system operation information indicated in the text information input by the user.

[0047] In addition, the generation unit 132 inputs a prompt including an instruction to generate defect information to be introduced into a generation model to which configuration information of the system related to the business and system operation information related to the business including defect information have been provided, and generates defect information to be introduced.

[0048] For example, the generation unit 132 converts text information input by a user into a prompt. Next, the generation unit 132 inputs the converted prompt into a generation model that has been provided in advance with information such as "system name," "configuration information," "system flow information," and "checklist" stored in the system information DB 123. Then, the generation unit 132 generates system operation information including information about malfunctions predicted to occur in the future for a system, etc., that is being considered for introduction into a target organization and that is indicated in the text information input by the user.

[0049] As a specific example, the generation unit 132 generates defect information that includes at least one of a candidate location for the defect, a cause of the defect, a countermeasure for eliminating the cause of the defect, and a countermeasure for preventing the cause of the defect.

[0050] Specifically, the generation unit 132 generates malfunction information that includes the location of a malfunction in a specified data communication or file generation between systems, the cause of the malfunction, and countermeasures for the malfunction, as a malfunction related to the logical connection between systems.

[0051] For example, the processing of the generation unit 132 will be described taking as an example a case where a problem occurs in a function that performs file transfer or data communication based on an API (Application Programming Interface) between a plurality of systems.

[0052] If a logical malfunction occurs in the function that performs the above-mentioned data communication, the generation unit 132 generates information regarding the system malfunction to identify the logical cause, including information regarding the possible locations and causes of the malfunction, such as whether the target file has been generated and whether the target file contains an error.

[0053] On the other hand, the generation unit 132 generates fault information for faults related to the physical connection between systems, including the location of the connection failure between the systems or the abnormality in the operation of the systems, the cause of the fault, and countermeasures for the fault.

[0054] For example, if a physical malfunction occurs in the function that performs the above-mentioned data communication, the generation unit 132 generates information regarding the system malfunction to identify the physical cause, including information regarding the operating status of the target system (whether the system is stopped or not), and information regarding possible locations and causes of the malfunction, such as whether there is a malfunction in the lines that physically connect the systems.

[0055] The generation unit 132 can automatically generate system operation information using text information input by employees, etc. Specifically, the generation unit 132 converts text information related to the employee's work, which is input on a daily basis, into a prompt including an instruction to generate system operation information related to the work. Next, the generation unit 132 inputs the converted prompt into a generative model to which the system operation information related to the work has been provided, thereby generating system operation information related to the work. The generated system operation information is then stored in the memory unit 120 by the storage unit 133, which will be described later.

[0056] 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.

[0057] (storage section 133) The storage unit 133 stores the generated system operation information in the memory unit 120. Specifically, the storage unit 133 stores the system information generated by the generation unit 132 in the system information DB 123. The storage unit 133 also stores the malfunction information generated by the generation unit 132 in the malfunction information DB 124. 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 described later.

[0058] (output unit 134) The output unit 134 outputs to the user the system operation information for the organization indicated in the text information. For example, the output unit 134 outputs to the user information about the configuration of the system operated in the target organization generated by the generation unit 132, information about the malfunction including potential locations where the malfunction may occur, causes of the malfunction, countermeasures for eliminating the causes of the malfunction, and countermeasures for preventing the causes of the malfunction. Note that 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 described later.

[0059] (Response section 135) The response unit 135 generates response information by inputting a prompt including an instruction to generate response information corresponding to the inquiry content received from the user to the generation model provided with the system operation information related to the business generated by the generation unit 132. Then, the response unit 135 outputs the generated response information to the user who made the inquiry. Note that an example of processing by the response unit 135 will be described later with reference to FIG. 8.

[0060] (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 system operation information in response to text information input by the operation support device 100, based on a large-scale language model or the like in which a prompt is set to generate system operation information.

[0061] 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.

[0062] (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 operation support device 100, and receives and displays system operation information and the like from the operation support device 100.

[0063] The type of the terminal device 200 is not particularly limited, and may be, for example, a smartphone, a tablet, a PDA (Personal Digital Assistant), a PC (Personal Computer), a notebook PC, or the like.

[0064] (Example of processing) An example of the operation support process by the operation support device 100 according to this embodiment will now be described with reference to Fig. 7 to Fig. 9. Fig. 7 to Fig. 9 are diagrams showing an example of the operation support process according to this embodiment.

[0065] Note that Fig. 7 shows an example of "generation and output processing of system operation information" as a first example, Fig. 8 shows an example of "response processing to inquiries" as a second example, and Fig. 9 shows an example of "generation and storage processing of system operation information" as a third example.

[0066] (First example) First, the first example of the "generation process and output process of system operation information" will be described. Fig. 7 shows an operation support device 100 that generates system operation information, a terminal device 200 operated by a user such as a system administrator, and a generation model 10 used by the operation support device 100.

[0067] First, the terminal device 200 receives text information from the user, such as "A problem named B has occurred in system A. Please investigate the cause." Then, the terminal device 200 transmits the text information received from the user to the operation support device 100 ((1-1) in FIG. 7).

[0068] The operation 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 operation support device 100 converts text information such as "A problem named B has occurred in system A. Please investigate the cause." into a prompt to be input to a generation model such as "For problem B that has occurred in system A, please generate the location of the problem, its cause, and a countermeasure."

[0069] The operation support device 100 executes a process for generating system operation information ((2) in FIG. 7). Specifically, the operation support device 100 inputs the converted prompt to the generation model 10, which has been provided with prior knowledge for generating system operation information ((2-1) in FIG. 7), and generates "system configuration," "location of failure," "cause of failure," "countermeasure," etc. as failure information ((2-2) in FIG. 7).

[0070] Here, the operation support device 100 stores the generated failure information such as "system configuration," "failure location," "failure cause," and "countermeasure" in the failure information DB 124 ((2-3) in FIG. 7).

[0071] The operation support device 100 also executes a process of outputting malfunction information to the user ((3) in FIG. 7). The operation support device 100 transmits malfunction information including "system configuration," "location of malfunction," "cause of malfunction," "countermeasure," etc. to the terminal device 200 operated by the user. Then, the terminal device 200 displays the received malfunction information to the user ((3-1) in FIG. 7).

[0072] As described above, the operation support device 100 can automatically generate system operation information (fault information) related to a target organization from text information input by a user. Therefore, the operation support device 100 can reduce the man-hours required for an administrator or the like to identify faults that have occurred or are predicted to occur in a system and to formulate countermeasures.

[0073] (Second example) Next, the second example of the "response process to an inquiry" will be described. Fig. 8 shows an operation support device 100 that generates system operation information, a terminal device 200 operated by a user such as an end user, and a generation model 10 used by the operation support device 100.

[0074] First, the terminal device 200 receives text information from the user, such as "I can't process XX in system A properly." Then, the terminal device 200 transmits the text information received from the user to the operation support device 100 ((1-1) in FIG. 8).

[0075] The operation support device 100 converts the text information ((1-1) in FIG. 8) received from the terminal device 200 into a prompt ((1-2) in FIG. 8). For example, the operation support device 100 converts text information such as "System A's XX cannot be processed properly" into a prompt to be input to a generation model such as "In order to identify the cause of the problem of System A's XX processing not being executed properly, please generate information (specific information) to identify countermeasures for problems that have occurred in the past."

[0076] The operation support device 100 executes a process for generating specific information ((2) in FIG. 8). Specifically, the operation support device 100 inputs the converted prompt to the generation model 10, which has been provided with prior knowledge for generating specific information ((2-1) in FIG. 8), and generates specific information for identifying the "countermeasures" stored in the defect information DB 124 ((2-2) in FIG. 8).

[0077] The operation support device 100 uses the generated identification information to execute an identification process and an output process (response process) of the identified information ((3) in FIG. 8). Specifically, the operation support device 100 identifies information stored in the malfunction information DB 124 that matches information such as "countermeasures" included in the generated identification information ((3-1) in FIG. 8). Next, the operation support device 100 acquires the information such as "countermeasures" identified by the identification process from the malfunction information DB 124 as response information ((3-2) in FIG. 8).

[0078] The operation support device 100 executes a response process to output response information to the user ((3-3) in FIG. 8). Specifically, the operation support device 100 transmits response information including the system name, countermeasures, etc. to the terminal device 200 operated by the user. Then, the terminal device 200 displays the received response information to the user ((3-4) in FIG. 8).

[0079] As described above, the operation support device 100 can automatically generate answers to user inquiries. Therefore, when an end user of a system encounters an unclear point or a problem while using the system, the operation support device 100 enables the end user to resolve the unclear point or problem without having to inquire with an administrator each time. Therefore, the operation support device 100 enables the end user to efficiently use the system.

[0080] (Third example) Next, a third example of "system operation information generation processing and storage processing" will be described with reference to Fig. 9. The third example is an example of processing in which system operation information is generated based on text information input by a user, as in the first example, and stored in storage unit 120, even when no instructions are given by the user or the like.

[0081] FIG. 9 shows an operation support device 100 that generates system operation information, a terminal device 200 operated by an employee, and a generation model 10 used by the operation support device 100.

[0082] First, the terminal device 200 receives text information such as "A problem named B has occurred in system A" as a business conversation between an employee. Then, the terminal device 200 transmits the text information received from the user to the operation support device 100 ((1-1) in FIG. 9).

[0083] As in the first example, the operation support device 100 converts the text information ((1-1) in FIG. 9) received from the terminal device 200 into a prompt ((1-2) in FIG. 9). Then, as in the first example, the operation support device 100 generates system operation information ((2) in FIG. 9).

[0084] The operation support device 100 stores the generated system operation information in the malfunction information DB 124 ((3) in FIG. 9). Specifically, the operation support device 100 associates the system name "D" ((3-1) in FIG. 9), the occurrence location "H" ((3-2) in FIG. 9), the cause "I" ((3-3) in FIG. 9), and the countermeasure "J" ((3-4) in FIG. 9) with each other, and stores them in the malfunction information DB 124.

[0085] For example, if a logical cause of a problem such as "a file for system collaboration has not been generated" occurs, the operation support device 100 identifies an event such as "a file has not been generated by system A." Then, the operation support device 100 stores the location of the problem, "system A," and the cause, "a file for system collaboration has not been generated," in the problem information DB 124.

[0086] Furthermore, if the logical cause is "a file for system cooperation has been generated, but the file contains an error," the operation support device 100 identifies an event such as "error B is contained in the file generated by system A." Then, the operation support device 100 stores the occurrence location "system A" and the cause "error B is contained in the file generated by system A" in the problem information DB 124.

[0087] On the other hand, if the physical cause is "the system has stopped," the operation support device 100 identifies an event such as "System A has stopped due to thermal runaway of equipment." Then, the operation support device 100 stores the location of the occurrence, "System A," and the cause, "stopped due to thermal runaway of equipment," in the malfunction information DB 124.

[0088] Furthermore, if the physical cause is "the line between the systems is physically disconnected," the operation support device 100 identifies an event such as "the line between system A and system C is disconnected."Then, the operation support device 100 stores the location of the occurrence, "the line between system A and system C," and the cause, "line disconnection," in the malfunction information DB 124.

[0089] As described above, the operation support device 100 can automatically generate system operation information included in text information input by a user, even without a user instruction, etc. The operation support device 100 can then accumulate the automatically generated system operation information to improve the generation of information related to system operation, and recommend to the user countermeasures for malfunctions and information on predicted malfunctions related to a system that is scheduled for new introduction.

[0090] (Operational support processing procedure) Next, the procedure of the operation support process realized by the operation support device 100 according to this embodiment will be described with reference to Fig. 10 to Fig. 12. Fig. 10 to Fig. 12 are diagrams showing flowcharts of the operation support process according to this embodiment.

[0091] Fig. 10 shows an example of a processing procedure for "generation and output processing of system operation information." Fig. 11 shows an example of a processing procedure for "response processing to inquiries." Fig. 12 shows an example of a processing procedure for "generation and storage processing of system operation information."

[0092] First, an example of a processing procedure for "system operation information generation processing and output processing" will be described with reference to FIG. 10. The generation unit 132 provides prior knowledge to the generative model (S101). Specifically, the generation unit 132 inputs, to the generative model, system operation information such as "system name," "configuration information," "system flow information," and "checklist" stored in the system information DB 123, and system operation information such as "location of occurrence," "cause," and "countermeasure" stored in the defect information DB 124, along with a prompt including an instruction to store the system operation information. Through the above-described processing, the generation unit 132 causes the generative model to generate system operation information for the target organization.

[0093] Here, if the user does not perform an operation such as an instruction to start the generation process, the operation 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 operation support device 100 starts the process of S103.

[0094] The receiving unit 131 receives text information from the 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 generation model to generate system operation information (S105). Next, the output unit 134 outputs the generated system operation information to the user (S106). Then, the operation assistance device 100 ends the processing.

[0095] Next, an example of a processing procedure for "response processing to inquiry" will be described with reference to FIG. 11. 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, system operation information such as "system name," "configuration information," "system flow information," and "checklist" stored in the system information DB 123, and "location of occurrence," "cause," and "countermeasure" stored in the defect information DB 124, as well as a prompt including an instruction to store the system operation information. Through the above-described processing, the generation unit 132 causes the generative model to generate system operation information for the target organization.

[0096] If the user does not issue an instruction to start the generation process, the operation support device 100 waits for the process (No in S202). On the other hand, if the user issues an instruction to start the generation process (Yes in S202), the operation support device 100 starts the process of S203.

[0097] The receiving unit 131 receives text information from the user (S203). Next, the generating unit 132 converts the input text information into a prompt (S204). Next, the responding unit 135 inputs the converted prompt into a generation model to generate specific information for generating response information (S205). Next, the responding unit 135 acquires response information using the generated specific information (S206). Next, the responding unit 135 outputs response information corresponding to the user's inquiry to the user (S207). Then, the operation assistance device 100 ends the processing.

[0098] Next, an example of the processing procedure for "system operation information generation processing and storage processing" will be described with reference to Fig. 12. Similar to the processing described with reference to Fig. 10, the generation unit 132 provides prior knowledge to the generative model (S301). Next, the reception unit 131 receives text information from the user (S302). Next, the generation unit 132 converts the text information into a prompt (S303). Next, the generation unit 132 inputs the converted prompt into the generative model to generate system operation information (S304).

[0099] The storage unit 133 stores the generated system operation information in the system information DB 123 and the malfunction information DB 124 (storage unit 120) (S305). Then, the operation support device 100 ends the process.

[0100] (effect) Next, the effects of the operation support device 100 according to this embodiment will be described. Conventionally, when a failure such as a system malfunction occurs, a technique is known that identifies the malfunction and notifies a system administrator. However, with the above technique, when multiple systems related to multiple operations are linked, it may be difficult to identify in which system the malfunction occurred and what the cause was.

[0101] Therefore, the generation unit 132 of the operation support 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 system operation information relating to the business is provided, thereby generating the system operation information relating to the business indicated in the text information. Then, the output unit 134 of the operation support device 100 outputs the system operation information relating to the business indicated in the text information to the user.

[0102] By the above-described processing, the operation support device 100 according to this embodiment can generate system operation information including system information and malfunction information by using text information about system malfunctions, usage, etc., contained in text information, etc., in which the user has exchanged work-related information with other employees during work, etc. As a result, the operation support device 100 according to this embodiment has the effect of enabling appropriate responses to system malfunctions by automatically generating system operation information, whereas in the past, users had to identify malfunctions, etc. and plan countermeasures themselves.

[0103] Furthermore, the operation assistance device 100 according to this embodiment achieves the respective predetermined effects by executing the processes described below.

[0104] Conventionally, users themselves have had to identify system malfunctions, etc., and plan countermeasures, etc. Therefore, the generation unit 132 inputs a prompt including an instruction to generate malfunction information to a generation model to which configuration information of a system related to a business and system operation information related to the business, including malfunction information, are provided, and generates information about system malfunctions related to the business.

[0105] As described above, the operation support device 100 can automatically generate system-related malfunction information and countermeasures based on text information such as utterances input by the user. Therefore, the operation support device 100 has the effect of enabling the user to efficiently and effectively deal with a system malfunction even when the malfunction occurs.

[0106] Conventionally, when a new system or the like is introduced, the user himself / herself has to identify anticipated system defects, etc., and plan countermeasures, etc. Therefore, the generation unit 132 inputs a prompt including an instruction to generate defect information to be introduced to a generation model to which configuration information of the system related to the business and system operation information related to the business including defect information are provided, and generates defect information to be introduced.

[0107] Specifically, the generation unit 132 generates malfunction information including at least one of a candidate location of a malfunction, a cause of the malfunction, a countermeasure for eliminating the cause of the malfunction, and a countermeasure for preventing the cause of the malfunction. For example, the generation unit 132 generates malfunction information including, as a malfunction related to a logical connection between systems, a location of a malfunction in a predetermined data communication between systems or a malfunction in file generation between systems, a cause of the malfunction, and a countermeasure for the malfunction. Also, for example, the generation unit 132 generates malfunction information including, as a malfunction related to a physical connection between systems, a location of a connection failure between systems or a system operation abnormality between systems, a cause of the malfunction, and a countermeasure for the malfunction.

[0108] As described above, the operational support device 100 automatically generates information on anticipated defects and countermeasures for a new system to be introduced based on text information such as speech input by the user, thereby enabling the user to efficiently and effectively identify defects that are predicted to occur and plan countermeasures for those defects, even when a new system is introduced.

[0109] Conventionally, when a problem occurs in a system that an end user or the like uses and the end user or the like finds it difficult to resolve the problem by themselves, the end user or the like has to make an inquiry to the administrator or the like of the system. Therefore, the response unit 135 generates response information by inputting a prompt including an instruction to generate response information corresponding to the content of the inquiry received from the user to the generation model provided with system operation information related to the business generated by the generation unit 132. Then, the response unit 135 outputs the generated response information to the user who made the inquiry.

[0110] Through the above-described processing, the operation support device 100 can generate response information for malfunctions, unclear points, etc. in response to inquiries from users. Therefore, the operation support device 100 enables end users who lack understanding or knowledge about the system to resolve unclear points or malfunctions about the system without having to inquire of an administrator, etc.

[0111] The generation unit 132 converts text information related to the employee's work into a prompt including an instruction to generate system operation information related to the work. Next, the generation unit 132 inputs the converted prompt into the generative model to which the system operation information related to the work has been provided, thereby generating system operation information related to the work. The storage unit 133 then stores the generated system operation information in the memory unit 120.

[0112] Through the above-described processing, even when there is no instruction for generation processing from a user or the like, the operation support device 100 can generate system operation information using text information related to conversations between employees and store the information in the storage unit 120. That is, the operation support device 100 can automatically generate and store system operation information using text information related to the system contained in daily business conversations and the like. As a result, the operation support device 100 can use the stored system operation information to improve the accuracy of the generation processing of system operation information instructed by a user and the accuracy of generating response information to a user, thereby achieving the effect of enabling appropriate responses to system malfunctions.

[0113] <Modification> The following describes modified examples realized by the operation assistance device 100 according to this embodiment.

[0114] (Data, etc.) The text information, prompts, system operation information, names of functional parts of the operation 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.

[0115] For example, the employee information DB 121 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. The text information DB 122 stores employee identification information and text information in association with "No.", which is information identifying individual text information, but is not limited to this. The system information DB 123 stores system names, configuration information, system flow information, and checklists in association with "No.", which is information identifying individual system information. The malfunction information DB 124 stores system names, locations of occurrences, causes, and countermeasures in association with "No.", which is information identifying individual malfunction information, but is not limited to this.

[0116] (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.

[0117] (An example of a generative model) The operation support device 100 of this embodiment can use large-scale language models such as ChatGPT (registered trademark) (see, for example, Reference 1) or large-scale language models such as tsuzumi (registered trademark) (see, for example, Reference 2) as generation models.

[0118] (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>

[0119] From here, tsuzumi will be described as an example of a generative model used by the operation support device 100 according to this embodiment. Figures 13 to 15 are diagrams for explaining tsuzumi.

[0120] First, the concept of tsuzumi will be explained using Figure 13. tsuzumi is a small, energy-efficient large-scale language model that achieves the same level of accuracy as ChatGPT, a huge single large-scale language model that consumes a lot of power.

[0121] 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).

[0122] 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, such as "medical care," "retail," "construction," "local government," "technology," "travel," "culture," "religion," "art," "education," "finance," "legal affairs," and "banking" based on a specified network, tsuzumi achieves the formation of generative models that are high-performance, efficient, fault-tolerant, and highly democratic compared to conventional single, huge, large-scale language models.

[0123] Furthermore, tsuzumi allows flexible tuning such as the fine tuning mentioned above. Specifically, tsuzumi allows tuning by "prompt engineering" as shown in Figure 14, "full fine tuning," and "adapter tuning."

[0124] For example, "prompt engineering" shown in (1) of Figure 14 is a tuning method that uses prompts with information about a specific field added 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.

[0125] For example, "full fine-tuning" shown in Figure 14 (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.

[0126] For example, "adapter tuning" shown in Figure 14 (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.

[0127] Furthermore, tsuzumi can build a model based on a “multi-adapter.” Here, the multi-adapter will be explained using FIG.

[0128] As explained using (3) in Figure 14, 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.

[0129] For example, as shown in Fig. 15, 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.

[0130] 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.

[0131] 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.

[0132] In other words, tsuzumi can be used as an appropriate generation model for executing specific processing, such as operational support processing by the operational support device 100 of this embodiment, corresponding to the use, purpose, and target field of the processing.

[0133] (IOWN technology) The generative model used by the operation assistance device 100 according to the present embodiment described above may be realized using technology related to the Innovative Optical and Wireless Network (IOWN) technology.

[0134] Here, we will explain the IOWN technology. Figure 16 is a diagram explaining IOWN. As shown in Figure 16, the IOWN technology consists of three main technology fields: "All-Photonics Network (APN)," "Digital Twin Computing (DTC)," and "Cognitive Foundation (CF (Cognitive Foundation (registered trademark))."

[0135] (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."

[0136] (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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] (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.

[0141] Furthermore, as shown in FIG. 16, the IOWN technology provides high-value-added services by linking the above-mentioned APN, DTC, and network services provided by operators.

[0142] For example, as shown in (1) of Figure 16, 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 16, 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 a business operator at high speed and with low latency in services such as information analysis. Also, as shown in (3) of Figure 16, 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.

[0143] The operation support device 100 according to this embodiment can efficiently realize operation support processing based on a generative model such as tsuzumi, which is configured based on the IOWN technology that transmits data at high speed and with low latency as described above.

[0144] For example, the operation support device 100 can generate system operation information with higher accuracy than conventional methods based on tsuzumi, which is learned using text information related to one's own organization or other organizations that is collected in large quantities at high speed and with low latency via a network constructed based on IOWN.

[0145] (Regarding business-related natural language text) In the present embodiment, it has been described that the operation support device 100 uses "text in a natural language related to business." The "text in a natural language related to business" does not mean including only text related to business, but also broadly includes, for example, natural language conversations between employees, such as daily conversations and business-related meeting details.

[0146] (Regarding identified factors and events) In the present embodiment, an example of the causes and events of a malfunction identified by the operation support device 100 has been described, but the present invention is not limited to the above example. In other words, any malfunction or event that falls within the categories of the above-mentioned "logical causes and events" and "physical causes and events" is included in the category of malfunctions and causes targeted by the operation support device 100 according to the present embodiment.

[0147] (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.

[0148] <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.

[0149] 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.

[0150] <Program> In one embodiment, the various devices constituting the operation assistance device 100 can be implemented by installing an operation assistance program as package software or online software on a desired computer. For example, by executing the operation assistance program on an information processing device, the various devices constituting the operation assistance 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).

[0151] 17 is a diagram showing an example of a computer that executes the operation 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.

[0152] 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.

[0153] The hard disk drive 1090 stores, for example, an OS (Operating System) 1091, application programs 1092, program modules 1093, and program data 1094. That is, programs that define the processes of the various devices that make up the operation support device 100 are implemented as program modules 1093 in which computer-executable code is written. The program modules 1093 are stored, for example, in the hard disk drive 1090. For example, program modules 1093 for executing processes similar to those of the functional configurations of the various devices that make up the operation support device 100 are stored in the hard disk drive 1090. The hard disk drive 1090 may be replaced with an SSD (Solid State Drive).

[0154] 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.

[0155] 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.

[0156] <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]

[0157] 10 Generative Model 100 Operational support equipment 110 Communications Department 120 Storage section 121 Employee Information DB 122 Text Information DB 123 System Information DB 124 Bug Information DB 130 Control Unit 131 Reception 132 Generation part 133 Storage area 134 Output section 135 Response 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 about the operation of a system related to a business, and generates information about the operation of a system related to the business indicated in the text; an output unit that outputs information regarding the operation of a system related to the business indicated in the text to the user; An operation assistance device comprising:

2. The generation unit generating information about the system malfunction related to the business by inputting the prompt including an instruction to generate information about the system malfunction related to the business to a generation model provided with configuration information about a system related to the business and information about the operation of the system related to the business including information about a malfunction of the system related to the business; 2. The operation assistance device according to claim 1.

3. The generation unit inputting the prompt including an instruction to generate information regarding the malfunction of the system related to the business to be introduced into a generation model provided with configuration information of the system related to the business and information regarding the operation of the system related to the business including information regarding malfunctions of the system related to the business, thereby generating information regarding the malfunction of the system related to the business to be introduced; 2. The operation assistance device according to claim 1.

4. The generation unit generating information about the malfunction in the system related to the business, the information including at least one of a potential location of the malfunction, a cause of the malfunction, a countermeasure for eliminating the cause of the malfunction, and a countermeasure for preventing the cause of the malfunction; 4. The operation assistance device according to claim 2 or 3.

5. The generation unit generating information on a malfunction of a system related to the business, including the location of a malfunction in a predetermined data communication or file generation between the systems, the cause of the malfunction, and a countermeasure for the malfunction, as a malfunction related to a logical connection between the systems; 5. The operation assistance device according to claim 4.

6. The generation unit generating information on system malfunctions related to the business, including, as malfunctions related to physical connections between systems, locations of connection failures between the systems or abnormalities in system operation, causes of the malfunctions, and countermeasures for the malfunctions; 5. The operation assistance device according to claim 4.

7. generating response information by inputting a prompt including an instruction to generate response information corresponding to the inquiry content received from the user to a generative model provided with information about the operation of the system related to the business, the generative model being generated by the generation unit; The system further includes a response unit that outputs generated response information to the user who has made the inquiry.

4. The operation assistance device according to claim 1, wherein the operation assistance device is a device for operating a computer.

8. The generation unit converting natural language text related to the employee's work into prompts containing instructions for generating information related to the operation of the system; inputting the converted prompt into a generative model provided with information on the operation of a business-related system to generate information on the operation of the business-related system; The system further includes a storage unit that stores the generated information on the operation of the system related to the business in a storage unit.

4. The operation assistance device according to claim 1, wherein the operation assistance device is a device for operating a computer.

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

4. The operation assistance device according to claim 1, wherein the operation assistance device is a device for operating a computer.

10. The generation unit Using the generative model to communicate over a communication network related to an Innovative Optical and Wireless Network (IOWN), 10. The operation assistance device according to claim 9.

11. An operation assistance method to be executed by an operation 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 about the operation of a system related to a business, and generating information about the operation of a system related to the business indicated in the text; an output step of outputting information regarding the operation of a system related to the business indicated in the text to the user; An operation assistance method comprising:

12. a generation step of inputting a prompt based on a natural language text received from a user to a generation model provided with information about the operation of a system related to a business, and generating information about the operation of a system related to the business indicated in the text; an output step of outputting information regarding the operation of a system related to the business indicated in the text to the user; An operational support program that causes a computer to execute the above.

Images