Method for supporting system operation task by ai

Abstract

To provide a method for supporting a system operation task by AI to improve operational efficiency.SOLUTION: A system includes: 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 are connected via a network. A method for supporting system operation tasks by AI includes: receiving, by the server terminal, request information from the user terminal; referring to a natural language analysis model connected to the server terminal on the basis of the request information; searching knowledge data including the operation flow of the application; receiving answer information generated by the natural language analysis model on the basis of the search result; and transmitting the generated answer information to the user terminal.SELECTED DRAWING: Figure 6

Description

Technical Field

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

Background Art

[0002] Conventionally, in response to inquiries such as usage methods and troubles from users who use applications, the person in charge (operator) involved in system operation work refers to knowledge data each time for the inquiries received as requests, checks the operation flow, and transmits data to the application to complete the request content.

[0003] However, when the request content increases, it becomes difficult to carry out such operations. As one of the methods for improving the work efficiency of the help desk, for example, a help desk system that determines FAQs based on user attributes in response to inquiries from users is disclosed in Patent Document 1.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, especially in system operation work, the request content from users has become complicated, and it is difficult to respond to the request content only by referring to FAQs as in the technology disclosed in Patent Document 1.

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

Means for Solving the Problems

[0007] A method for supporting system operation by AI provided in a system for supporting system operation, which includes a user terminal of a user who uses an application in one aspect of the present invention, a server terminal of a system operation provider who performs operation services of the application, and an operator terminal of the person in charge of the operation service, and the user terminal, the server terminal, and the operator terminal are connected by a network. The server terminal receives request information from the user terminal, refers to 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 response information generated by the natural language analysis model based on the search result, and transmits the generated response information to the user terminal.

Advantages of the Invention

[0008] According to the present invention, there is provided a method for supporting system operation by AI, which can achieve further improvement in business efficiency.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Embodiments for Carrying Out the 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. Also, not all of the components shown in the embodiments are essential components of the present invention.

[0011] <Configuration> FIG. 1 is a block configuration diagram showing a system for assisting system operation work by AI according to the first embodiment of the present invention. This system 1 receives requests regarding inquiries such as how to use an application, how to use a workflow, and usage troubles from a user (for example, an employee of a specific company) who uses an application implementing an in-company workflow, from a user terminal or from another terminal via an API (Applicaton Progamming Interface), analyzes the request content, generates an answer to the request by a large language model (LLM, for example, GPT) 400, and executes a process of outputting the answer via a chatbot or the like. The system includes a server terminal 100, a user terminal 200 managed by the user, an operator terminal 300 of a person in charge of system operation, and the LLM 400. Also, an application server 500 of an application implementing a workflow used by the user may be connected to each terminal constituting the system 1 via an API (Applicaton Progamming Interface). For convenience of explanation, each terminal is described as a single one, but the number of each is not limited.

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

[0013] The server terminal 100, the LLM 400, and the application server 500 may be general-purpose computers such as workstations or personal computers, or may be composed of cloud computing, or a cluster or multi-computer composed of multiple computers, a virtual machine or a quantum computer virtually constructed by software.

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

[0015] In the present embodiment, the system 1 includes the server terminal 100, the user terminal 200, the operator terminal 300, the LLM 400, and the application server 500, and will be described as a configuration in which users of each terminal use their respective terminals to operate on the server terminal 100. However, the server terminal 100 may be configured as a stand-alone device, and the server terminal itself may be provided with a function for each user to directly perform operations.

[0016] FIG. 2 is a functional block configuration diagram of the server terminal 100 in 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 programs for executing various control processes and each function within the control unit 130, input data, etc., and is composed of a RAM (Random Access Memory), a ROM (Read Only Memory), etc. Further, the storage unit 120 has a user data storage unit 121 that stores various data related to the user, 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 the programs stored in the storage unit 120, and is composed of a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), etc. As functions of the control unit 130, it has an information reception unit 131 that receives information from each user terminal, and an information processing unit 132 that processes information. This information reception unit 131 and information processing unit 132 are activated by the programs stored in the storage unit 120 and executed by the server terminal 100 which is a computer (electronic calculator).

[0020] The information reception unit 131 receives information from the user terminal 200 via the communication unit 110. For example, from the user terminal 200, request information including an inquiry (question text, conversation text, etc.) regarding the usage method of the application is received via the chat interface displayed on the user terminal 200.

[0021] The information processing unit 132 performs predetermined information processing such as analyzing the request information received from the user terminal 200 and generating a response text for the request information. Note that the server terminal 100 can also perform predetermined processing while cooperating with an external API server (LLM300) connected by an API.

[0022] In addition, the control unit 130 may also include a screen generation unit (not shown) and generate screen information to be displayed via the user interface of the user terminal 200 as required. For example, using the images and text data (not shown) stored in the storage unit 120 as materials, various images and texts are arranged in a predetermined area of the user interface based on a predetermined layout rule to generate the user interface. The processing related to the image generation unit can also be executed by a GPU (Graphics Processing Unit).

[0023] FIG. 3 is a functional block configuration 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 the user to input instructions, analyze the input data according to the input data such as text, voice, and images from the control unit 240, and display text, voice, images, etc. as output. When the user terminal 200 is composed of a personal computer, it is composed of a display, a keyboard, and a mouse. When the user terminal 200 is composed of a smartphone or a tablet terminal, it is composed of a touch panel, etc. This display operation unit 220 is activated by a control program stored in the storage unit 230 and executed by the user terminal 200 which is a computer (electronic computer).

[0026] The storage unit 230 stores programs for executing various control processes and each function in the control unit 240, input data, etc., and is composed of a RAM, a ROM, etc. In addition, the storage unit 230 temporarily stores the communication content with the server terminal 100.

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

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

[0029] The user data 1000 shown in FIG. 4 stores various data related to the user. In FIG. 4, for convenience of explanation, an example of one user (for example, per user) (a user identified by the user ID "10001") is shown, but information of a plurality of users can be stored. The various data related to the user can include, for example, basic information about the user (for example, company ID, employee ID, name, company (corporation) name, department, position, date of birth (age), address, contact information (email address, phone number), name of the application to be used, authentication information for using the application (login ID, password), etc.), and conversation information (for example, conversation history via a chat interface, etc.), but is not limited thereto.

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

[0031] Chatbot data 2000 stores various data related to the operation of the chatbot. Examples of various data related to the operation of the chatbot include, for example, prompt data (conditional statements for controlling the response sentences generated by the language model), request information (question sentences, conversation sentences, etc.), and conversation history data (natural language and / or data and datasets obtained by vectorizing natural language) including response sentences, and knowledge data (knowledge related to system operation (how to use applications, how to use workflows, information for troubleshooting, etc.), and information related to the operation flow for performing system operation, etc., but not limited thereto). As a feature of this embodiment, knowledge data for generating appropriate response sentences for question sentences is recorded for each user (business operator) and / or for each dataset, and a prompt for controlling the response sentences generated by the language model is recorded. Here, the knowledge data can be generated and updated based on usage manual data such as FAQs of applications and the conversation history with users.

[0032] <Flow of processing> With reference to the figures after FIG. 6, the flow of processing of a method for generating a response sentence by a chatbot for request information including an inquiry (question sentence, conversation sentence) by a user, which is executed by the system 1 of this embodiment, will be described. FIG. 6 is a flowchart showing a basic flow as an example of a method for assisting system operation services by AI according to the first embodiment of the present invention.

[0033] First, as the process of step S101, a user who is a user using an application within the company inputs request information (question text, conversation text, etc.) regarding the usage method of the system via a chat interface implemented in a web browser or an application, etc., of the user terminal 200. Then, the information reception unit 131 of the control unit 130 of the server terminal 100 receives the request information (for example, "I want a paid account to be assigned to Zoom (registered trademark) (a specific application)") input by the user 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 as user data 1000 and / or chatbot data 2000 in the user data storage unit 121 and / or the chatbot data storage unit 122 of the storage unit 120.

[0034] Subsequently, as the process of step S102, the information processing unit 132 refers to the knowledge data stored in the chatbot data storage unit 122 (or an external database) of the storage unit 120 based on the vector data obtained by vectorizing the above request information via the LLM400, and searches for approximate vector data. Examples of the knowledge data include knowledge such as "Zoom (registered trademark) (a specific application) cannot be assigned to dispatched employees. Please make an application after confirmation by the supervisor." for the above request example.

[0035] Subsequently, as the process of step S103, the information processing unit 132 obtains a response sentence generated by the LLM400 based on the data corresponding to the approximation value extracted as the knowledge search result.

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

[0037] FIG. 7 is a diagram for explaining another example of a method for supporting system operation services by AI.

[0038] First, as the process of step S201, a user who is a user using an application within the company inputs request information (question sentence, conversation sentence, etc.) regarding the usage method of the system via a chat interface implemented in a web browser or an application of the user terminal 200. Then, the information reception unit 131 of the control unit 130 of the server terminal 100 receives the request information (for example, "I want a paid account to be assigned to Zoom (registered trademark) (a specific application)") input by the user 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 as user data 1000 and / or chatbot data 2000 in the user data storage unit 121 and / or the chatbot data storage unit 122 of the storage unit 120.

[0039] Subsequently, as the process of step S202, the information processing unit 132 refers to the knowledge data stored in the chatbot data storage unit 122 of the storage unit 120 (or an external database) based on the vector data obtained by vectorizing the above request information via the LLM 400, and searches for approximate vector data. Examples of the knowledge data include knowledge such as "A dispatched employee cannot be assigned Zoom (registered trademark) (a specific application). Please make an application after confirmation by the supervisor." for the above request example.

[0040] As a search result of step S202, if knowledge data is detected, as a process of step S204, the information processing unit 132 acquires a response sentence generated by the LLM400 based on the data corresponding to the approximation value extracted as the knowledge search result. On the other hand, as a search result of step S202, if knowledge data is not detected (or when the matching rate of the detected approximation value is equal to or less than a certain threshold), as a process of step S205, the information processing unit 132 issues a ticket to the operator terminal 300 of the person in charge of system operation, transmits the request information, and sends a notification to prompt confirmation. The person in charge of system operation responds to the request information. At this time, the information processing unit 132 can also transmit a procedure manual based on the operation flow to the operator terminal 200. Examples of the procedure manual include information describing procedures such as "1. Log in to Zoom (registered trademark) with the administrator account. 2. Add the requester's address from https: / / zoom.us / account / user# / . 3. Specify the license user." At this time, when the server terminal 100 and the application server 500 are linked via the API, as shown in FIG. 8, on the application provided by the server terminal 100, by approving the registration of the requester to the target application (in this example, Zoom (registered trademark)), the requester's address is registered in the target application, and a series of flows is completed. When a response sentence to the user's request information is sent via the chatbot or via the operator or application, the user is notified that the response has been completed, and a series of flows is completed.

[0041] As described above, according to the present embodiment, it is possible to improve the business efficiency by introducing AI for the request information from the user, which has conventionally been handled manually by the person in charge of system operation, and by referring to the knowledge data and operation flow regarding the usage methods of the application and workflow, it is possible to achieve not only efficiency but also a more accurate response.

[0042] Although the embodiments according to the invention have been described above, they can be implemented in various other forms, and can be implemented with various omissions, substitutions, and changes. These embodiments, variations, and omissions, substitutions, and changes are included in the technical scope of the claims and the equivalent scope thereof.

Explanation of Reference Numerals

[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. A method for supporting a system operation using AI, which is provided to a system that supports system operation, the system operation including a user terminal of a user who uses an application, a server terminal of a system operation company that operates the application, and an operator terminal of a person in charge of the operation, the user terminal, the server terminal, and the operator terminal being connected via a network, The server terminal includes: receiving request information from the user terminal; referring to a natural language analysis model connected to the server terminal based on the request information, and searching for knowledge data including an operational flow of the application; receiving answer information generated by the natural language analysis model based on the search results; The method further comprises transmitting the generated answer information to the user terminal.

2. The method of claim 1 , further comprising transmitting the answer information to the user terminal via the application.

3. The method according to claim 1 , further comprising the step of: sending a notification to the operator terminal to generate answer information when no knowledge data is detected as the search result.

4. The method according to claim 3 , further comprising the step of transmitting the response information received from the operator terminal 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