Method for supporting system operation task by ai

Abstract

[Problem] The purpose of the present invention is to provide a method for supporting a system operation task by AI to improve operational efficiency. [Solution] A method for supporting system operation tasks by AI according to one aspect of the present invention is provided to a system for supporting system operation, the system including: a user terminal of a user who uses an application; a server terminal of a system operation service provider that handles application operation tasks; and an operator terminal of a person in charge of the operation tasks, the user terminal, the server terminal, and the operator terminal being connected via a network. The server terminal receives request information from the user terminal, refers to a natural language analysis model connected to the server terminal on the basis of the request information, searches knowledge data including an operation flow of the application, receives answer information generated by the natural language analysis model on the basis of the search result, and transmits the generated answer information to the user terminal.

Description

How AI can support system operations

[0001] The present invention relates to a method for supporting system operation work using AI.

[0002] Conventionally, when users of an application inquire about how to use the system or about problems they are having, the person in charge of system operations (operators) would refer to knowledge data, check the operational flow, and send the data to the application to complete the request.

[0003] However, as the number of requests increases, it becomes difficult to operate in this manner. As one method for improving the efficiency of help desk operations, for example, Patent Document 1 discloses a help desk system that determines FAQs based on user attributes in response to inquiries from users.

[0004] JP 2008-046852 A

[0005] However, particularly in system operation work, requests from users are becoming more complex, making it difficult to respond to requests simply by referring to FAQs, as in the technology disclosed in Patent Document 1.

[0006] Therefore, the present invention is a method for supporting system operation work using AI, and aims to achieve further improvements in work efficiency.

[0007] In one aspect of the present invention, there is provided a method for supporting system operation using AI, which is provided to a system that supports system operation, the system including a user terminal of a user who uses an application, a server terminal of a system operation company that performs operation work for the application, and an operator terminal of a person in charge of the operation work, wherein the user terminal, server terminal, and operator terminal are connected via a network, wherein the server terminal receives request information from the user terminal, references a natural language analysis model connected to the server terminal based on the request information, searches for knowledge data including the operation flow of the application, receives answer information generated by the natural language analysis model based on the search results, and transmits the generated answer information to the user terminal.

[0008] According to the present invention, a method for supporting system operation work using AI can further improve work efficiency.

[0009] FIG. 1 is a block configuration diagram showing a system for supporting system operation work using AI according to a first embodiment of the present invention. FIG. 2 is a functional block configuration diagram showing the server terminal 100 of FIG. 1. FIG. 3 is a functional block configuration diagram showing the user terminal 200 of FIG. 1. FIG. 4 is a diagram showing an example of user data stored in the server 100. FIG. 5 is a diagram showing an example of chatbot data stored in the server 100. FIG. 6 is a flowchart showing an example of a method for supporting system operation work using AI according to a first embodiment of the present invention. FIG. 7 is a flowchart showing another example of a method for supporting system operation work using AI according to a first embodiment of the present invention. FIG. 8 is an example of an application screen provided by the server terminal 100 according to the first embodiment of the present invention.

[0010] Hereinafter, embodiments of the present invention will be described with reference to the drawings. Note that the embodiments described below do not unduly limit the content of the present invention described in the claims. Furthermore, not all of the components shown in the embodiments are necessarily essential components of the present invention.

[0011] <Configuration> Figure 1 is a block diagram showing a system for supporting system operation work using AI according to a first embodiment of the present invention. This system 1 includes a server terminal 100, a user terminal 200 managed by the user, an operator terminal 300 for a person in charge of system operation, and the LLM 400. The server terminal 100 receives requests from users (e.g., employees of a specific company) using an application that implements an in-house workflow, via a user terminal or another terminal via an API (Application Programming Interface), regarding inquiries about how to use the application, how to use the workflow, and usage problems. The server terminal 100 analyzes the requests, generates responses to the requests using a large-scale language model (LLM, e.g., GPT) 400, and outputs the responses via a chatbot or the like. Furthermore, an application server 500 for the workflow-implemented application used by the user may be connected to each terminal constituting the system 1 via the API (Application Programming Interface). For the sake of convenience, each terminal is described as a single terminal, but the number of each terminal is not limited.

[0012] The server terminal 100, the user terminal 200, the operator terminal 300, and the LLM 400 are connected to each other via a network NW1. The network NW is configured by the Internet, an intranet, a wireless LAN (Local Area Network), a WAN (Wide Area Network), or the like.

[0013] The server terminal 100, LLM 400, and application server 500 may be, for example, general-purpose computers such as workstations or personal computers, or may be configured using cloud computing, a cluster or multicomputer consisting of multiple computers, a virtual machine constructed virtually using software, or a quantum computer.

[0014] The user terminal 200 and the operator terminal 300 are, for example, information processing devices such as personal computers and tablet terminals, but may also be configured as smartphones, mobile phones, PDAs, etc.

[0015] In this embodiment, the system 1 is described as comprising a server terminal 100, a user terminal 200, an operator terminal 300, an LLM 400 and an application server 500, and a configuration in which users of each terminal use their respective terminals to perform operations on the server terminal 100; however, the server terminal 100 may be configured as a standalone unit, and the server terminal itself may have the function of allowing each user to perform operations directly.

[0016] Fig. 2 is a functional block diagram of the server terminal 100 of Fig. 1. The server terminal 100 includes a communication unit 110, a storage unit 120, and a control unit 130.

[0017] The communication unit 110 is a communication interface for communicating with the user terminal 200, the operator terminal 300, the LLM 400, and the application server 500 via the network NW1, and communication is performed according to a communication protocol such as TCP / IP (Transmission Control Protocol / Internet Protocol).

[0018] The storage unit 120 stores input data, programs for executing various control processes and functions in the control unit 130, and is composed of RAM (Random Access Memory), ROM (Read Only Memory), etc. The storage unit 120 also has a user data storage unit 121 that stores various data related to users, and a chatbot data storage unit 122 that stores information necessary for operating the chatbot. Note that a database (not shown) storing various data may be constructed outside the storage unit 120 or the server terminal 100.

[0019] The control unit 130 controls the overall operation of the server terminal 100 by executing a program stored in the storage unit 120, and is composed of a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), etc. Functions of the control unit 130 include an information receiving unit 131 that receives information from each user terminal, and an information processing unit 132 that processes the information. The information receiving unit 131 and the information processing unit 132 are activated by a program stored in the storage unit 120 and executed by the server terminal 100, which is a computer (electronic calculator).

[0020] The information receiving unit 131 receives information from the user terminal 200 via the communication unit 110. For example, request information including an inquiry (question, conversation, etc.) about how to use an application is received from the user terminal 200 via a chat interface displayed on the user terminal 200.

[0021] The information processing unit 132 performs predetermined information processing, such as analyzing request information received from the user terminal 200 and generating a response to the request information. Note that the server terminal 100 can also perform predetermined processing in cooperation with an external API server (LLM 300) connected via an API.

[0022] The control unit 130 may also have a screen generation unit (not shown) that generates screen information to be displayed via the user interface of the user terminal 200 upon request. For example, the control unit 130 generates a user interface by using image and text data (not shown) stored in the storage unit 120 as material and arranging various images and text in predetermined areas of the user interface based on predetermined layout rules. Processing related to the image generation unit may also be executed by a GPU (Graphics Processing Unit).

[0023] Fig. 3 is a functional block diagram showing the user terminal 200 of Fig. 1. The user terminal 200 includes a communication unit 210, a display operation unit 220, a storage unit 230, and a control unit 240.

[0024] The communication unit 210 is a communication interface for communicating with the server terminal 100 via the network NW, and communication is performed according to a communication protocol such as TCP / IP.

[0025] The display operation unit 220 is a user interface used for allowing a user to input instructions, analyzing the input data in accordance with the input data such as text, audio, and images from the control unit 240, and displaying the text, audio, and images as output, and is configured with a display, keyboard, and mouse when the user terminal 200 is configured as a personal computer, and is configured with a touch panel, etc. when the user terminal 200 is configured as a smartphone or tablet terminal. This display operation unit 220 is started up by a control program stored in the storage unit 230 and executed by the user terminal 200, which is a computer (electronic calculator).

[0026] The storage unit 230 stores input data, programs for executing various control processes and functions in the control unit 240, and is composed of RAM, ROM, etc. The storage unit 230 also temporarily stores the contents of communication with the server terminal 100.

[0027] The control unit 240 controls the overall operation of the user terminal 200 by executing the programs stored in the storage unit 230, and is composed of a CPU, GPU, etc. The operator terminal 300 can also have the same configuration as the user terminal 200, so a description thereof will be omitted.

[0028] FIG. 4 is a diagram showing an example of user data stored in the server 100. As shown in FIG.

[0029] The user data 1000 shown in Figure 4 stores various data related to a user. For convenience of explanation, Figure 4 shows an example of one user (e.g., a user unit) (a user identified by user ID "10001"), but information on multiple users can be stored. The various data related to a user can include, but are not limited to, basic information about the user (e.g., company ID, employee ID, name, company (corporation) name, department, job title, date of birth (age), address, contact information (email address, phone number), name of application used, authentication information for using the application (login ID, password), etc.) and conversation information (e.g., conversation history via a chat interface, etc.).

[0030] FIG. 5 is a diagram showing an example of chatbot data stored in the server 100.

[0031] The chatbot data 2000 stores various data related to the operation of the chatbot. Examples of the various data related to the operation of the chatbot include, but are not limited to, prompt data (conditional statements for controlling answer sentences generated by a language model), request information (questions, conversations, etc.) and answer sentences, conversation history data (natural language and / or data and datasets that vectorize natural language), knowledge data (knowledge related to system operation (how to use an application, how to use a workflow, information for troubleshooting, etc.), and information related to the operation flow for performing system operation. A feature of this embodiment is that knowledge data for generating appropriate answer sentences to questions is recorded for each user (business) and / or for each dataset, and prompts for controlling the answer sentences generated by the language model are also recorded. Here, the knowledge data can be generated and updated based on usage manual data such as FAQs for the application and conversation history with the user.

[0032] <Processing Flow> The processing flow of a method for generating a response sentence by a chatbot in response to request information including an inquiry (question sentence, conversation sentence) from a user, executed by the system 1 of this embodiment, will be described with reference to the figures from Fig. 6 onwards. Fig. 6 is a flowchart showing a basic flow as an example of a method for supporting system operation work using AI according to the first embodiment of the present invention.

[0033] First, in step S101, a user who uses an application in the company inputs request information (question, conversation, etc.) regarding how to use the system via a web browser on the user terminal 200 or a chat interface implemented in the application, etc. The information receiving unit 131 of the control unit 130 of the server terminal 100 receives the request information input by the user (e.g., "Please assign a paid account to Zoom (registered trademark) (a specific application)") from the user terminal 200 via the communication unit 110. The information processing unit 132 of the control unit 130 stores the received request information in the user data storage unit 121 and / or chatbot data storage unit 122 of the storage unit 120 as user data 1000 and / or chatbot data 2000.

[0034] Next, in the process of step S102, the information processing unit 132 searches for similar vector data by referring to the knowledge data stored in the chatbot data storage unit 122 (or an external database) of the memory unit 120 based on the vectorized vector data of the request information via the LLM 400. For example, knowledge data for the above request example may include knowledge such as "Zoom (registered trademark) (a specific application) cannot be assigned to temporary employees. Please confirm with your supervisor before applying."

[0035] Next, in step S103, the information processing unit 132 acquires the answer sentence generated by the LLM 400 based on the data corresponding to the approximate value extracted as the knowledge search result.

[0036] Next, in step S104, the information processing unit 132, while referring to the operation flow information, sends the generated reply sentence in a predetermined procedure to the application server 500 used by the user, and then sends it to the user terminal 200 via the application. The information processing unit 132 stores the generated reply sentence in the user data storage unit 121 and / or chatbot data storage unit 122 of the memory unit 120 as user data 1000 and / or chatbot data 2000.

[0037] FIG. 7 is a diagram illustrating another example of a method for supporting system operation work using AI.

[0038] First, in step S201, a user who uses an application in the company inputs request information (question, conversation, etc.) regarding how to use the system via a web browser on the user terminal 200 or a chat interface implemented in the application, etc. The information receiving unit 131 of the control unit 130 of the server terminal 100 receives the request information input by the user (e.g., "Please assign a paid account to Zoom (registered trademark) (a specific application)") from the user terminal 200 via the communication unit 110. The information processing unit 132 of the control unit 130 stores the received request information in the user data storage unit 121 and / or chatbot data storage unit 122 of the storage unit 120 as user data 1000 and / or chatbot data 2000.

[0039] Next, in the process of step S202, the information processing unit 132 refers to the knowledge data stored in the chatbot data storage unit 122 (or an external database) of the memory unit 120 based on the vector data obtained by vectorizing the request information via the LLM 400, and searches for similar vector data. For example, knowledge data for the above request example may include knowledge such as "Zoom (registered trademark) (a specific application) cannot be assigned to temporary employees. Please confirm with your supervisor before applying."

[0040] If knowledge data is detected as a result of the search in step S202, the information processing unit 132 acquires a response sentence generated by the LLM 400 based on data corresponding to the approximate value extracted as the knowledge search result in step S204. On the other hand, if knowledge data is not detected as a result of the search in step S202 (or if the match rate of the detected approximate value is below a certain threshold), the information processing unit 132 issues a ticket, sends request information, and notifies the system operation staff in step S205 to the system operation staff's operator terminal 300, prompting them to confirm the request. The system operation staff then responds to the request information. At this time, the information processing unit 132 can also send a procedure manual based on the operation flow to the system operation staff terminal 200. An example of the procedure manual is information describing procedures such as, "1. Log in to Zoom (registered trademark) with an administrator account. 2. Add the requester's address from https: / / zoom.us / account / user# / . 3. Specify a licensed user." At this time, if the server terminal 100 and the application server 500 are linked via an API, the requester's address is registered in the target application (in this example, Zoom (registered trademark)) by approving the registration of the requester on the application provided by the server terminal 100, and a series of flows is completed, as shown in Fig. 8. When a response to the user's request information is sent via the chatbot, or via the operator or the application, the user is notified that the response has been completed, and a series of flows is completed.

[0041] As described above, with this embodiment, it is possible to improve business efficiency by introducing AI into request information from users, which previously was handled manually by system operation personnel, and by referring to knowledge data and operational flows regarding how to use applications and workflows, it is possible to not only improve efficiency but also achieve more accurate responses.

[0042] Although the embodiments of the present invention have been described above, they can be embodied in various other forms, and various omissions, substitutions, and modifications can be made. These embodiments, modifications, and omissions, substitutions, and modifications are included in the technical scope of the claims and their equivalents.

[0043] 1 System 100 Server terminal, 110 Communication unit, 120 Storage unit, 130 Control unit, 200 User terminal, 300 Operator terminal, 400 LLM, 500 Application server, NW1 Network

Claims

1. An AI-based method for assisting system operation provided to a system for assisting system operation, including a user terminal of a user who uses an application, a server terminal of a system operation provider who performs the operation work of the application, and an operator terminal of the person in charge of the operation work, wherein the user terminal, the server terminal, and the operator terminal are connected by a network. The method includes: the server terminal receiving request information from the user terminal, referring to a natural language analysis model connected to the server terminal based on the request information, searching for knowledge data including the operation flow of the application, receiving response information generated by the natural language analysis model based on the search result, and transmitting the generated response information to the user terminal.

2. The method according to claim 1, wherein the response information is transmitted to the user terminal via the application.

3. The method according to claim 1, wherein when no knowledge data is detected as the search result, a notification is sent to the operator terminal to generate response information.

4. The method according to claim 3, wherein the response information received from the operator terminal is transmitted to the user terminal via the application.

5. The method according to claim 3, wherein the server terminal stores the knowledge data in a storage unit.

Images