Information processing device, information processing method, and program

Abstract

The aim is to reduce the effort required to input prompts in order to obtain responses from the generated AI that are appropriate for the target device. [Solution] In order to solve the above problems, the information processing device of the present invention is characterized by having a receiving means for receiving natural language prompts from a user, an acquisition means for acquiring information on equipment corresponding to the organization to which the user belongs from a cloud service, and a display means for displaying a response generated by a language model based on the received prompt and the acquired equipment information on a display unit.

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and a program.

Background Art

[0002] Generative AI accesses Microsoft Graph (registered trademark), web information, databases, plugins, etc. for a prompt input by a user, and performs preprocessing called Grounding. Generative AI searches for specific information related to the input prompt by Grounding, adds the information obtained by the search to the prompt, and inputs it to a large language model, thereby realizing a mechanism by which a user can obtain a more practical answer. Patent Document 1 describes a technique in which when a user inputs a natural language question to a chatbot operated by a server that performs machine learning, an answer to the question is provided.

Prior Art Documents

[0004]

Patent Documents

Patent Document 1

Summary of the Invention

[0005]

Problems to be Solved by the Invention

[0006] When a user asks a question about a device to generative AI, if the device information in the input prompt is ambiguous, a general answer that does not match the target device may be given, and an appropriate answer specialized for the target device may not be obtained. However, in order for the user to obtain an appropriate answer, it is necessary to input a natural language that can identify the target device, so the input of the prompt is time-consuming and complicated.

[0007] This invention was made in view of the above problems, and aims to reduce the effort required to input prompts in order to obtain a response from the generated AI that is appropriate for the target device. [Means for solving the problem]

[0007] To solve the above problems, the information processing device of the present invention is characterized by comprising: a receiving means for receiving natural language prompts from a user; an acquisition means for acquiring information on equipment corresponding to the organization to which the user belongs from a cloud service; and a display means for displaying a response generated by a language model based on the received prompt and the acquired equipment information on a display unit. [Effects of the Invention]

[0008] According to the present invention, users can reduce the effort required to input prompts in order to obtain responses from the generated AI that are appropriate for the target device. [Brief explanation of the drawing]

[0009] [Figure 1] A diagram showing an example of the system configuration and hardware configuration in Example 1. [Figure 2] A diagram showing an example of the software configuration in Example 1. [Figure 3] A diagram showing an example of the table configuration in Examples 1 and 2. [Figure 4] A diagram showing an example of the application manifest for the Plugin application in Examples 1 and 3. [Figure 5] A flowchart showing an example of the processing during response generation in Example 1. [Figure 6] This figure shows an example of the screen displayed when generating an answer in Example 1. [Figure 7] A diagram showing an example of the system configuration and hardware configuration in Example 2. [Figure 8] A diagram showing an example of the software configuration in Example 2. [Figure 9]Flowchart showing an example of the process during answer generation in Example 2 [Figure 10] Example of a screen displayed during answer generation in Example 2 [Figure 11] Diagram showing an example of the system configuration and hardware configuration in Example 3 [Figure 12] Diagram showing an example of the software configuration in Example 3 [Figure 13] Diagram showing an example of the table configuration in Example 3 [Figure 14] Flowchart showing an example of the process during answer generation in Example 3 [Figure 15] Example of a screen displayed during answer generation in Example 3

Mode for Carrying Out the Invention

[0010] <G Hereinafter, the mode for carrying out the present invention will be described with reference to the drawings. <G

Examples

[0011] <G An embodiment of a support system using the generation AI according to the present invention will be described. Here, as an example of the support system, a device management service and a generation AI service operating on the cloud will be taken up and described. In addition, as an example of the device targeted by the support system, in this embodiment, an MFP (Multifunction Peripheral), a multifunction device will be taken as an example for description. Note that the devices include image forming apparatuses and image processing apparatuses other than MFPs such as printers, FAX, and projector. <G <G

[0012] <G In addition, the generation AI cloud 120 and the client computer 140 are examples of an information processing apparatus and a control apparatus. Note that the support system according to the present invention can be used not only for inquiries regarding devices but also for inquiries regarding services. <G <G

[0013] <G In this application, generative AI refers to a technology that automatically generates various contents such as text, images, music, and videos, which are created by humans, by making full use of deep learning and machine learning techniques.

[0014] In this embodiment, the official names of products and services are described as an example of natural language that can identify the target device. The natural language that can identify the target device is not limited to the official name, and may also be other general names, model numbers, keywords, etc. of products and services, as long as it is natural language that can identify the target device.

[0015] FIG. 1 is a block diagram for explaining an example of the system configuration and hardware configuration of the support system according to this embodiment.

[0016] The support system includes a device management cloud 100, a generative AI cloud 120, a client computer 140, and an MFP 160 connected by a network 180. Here, the configuration of the general-purpose computers that realize the device management cloud 100 and the generative AI cloud 120 is realized by using hardware resources supplied on demand by, for example, virtualization technology. Note that the device management cloud 100 and the generative AI cloud 120 may be servers. The client computer 140 has the configuration of a general-purpose computer.

[0017] In the device management cloud 100, the CPU 101 executes processes such as control and calculation based on application programs and the like stored in the ROM 103 or the external memory 110. Here, CPU is an abbreviation for Central Processing Unit, and ROM is an abbreviation for Read Only Memory, respectively.

[0018] Furthermore, the CPU 101 comprehensively controls each device connected to the system bus 111. The CPU 101 also opens various registered windows based on commands indicated by a mouse cursor (not shown) on the display 109 and performs various data processing operations. Here, the display 109 functions as a display unit. It may also function as an operation unit. Moreover, the processing may be performed not only by the mouse cursor but also by input via the keyboard 108.

[0019] RAM102 functions as the main memory and work area of ​​the CPU101. RAM stands for Random Access Memory. ROM103 is a read-only memory that functions as a storage area for basic I / O programs, etc. I / O stands for Input / Output. The ROM103 or external memory 110 stores the operating system program (OS), which is the control program for the CPU101. Furthermore, the ROM103 or external memory 110 stores files and other various data used during processing based on the above application programs.

[0020] The network interface 104 connects to the network 180 and performs network communication. This allows the CPU 101 to communicate with external devices via the network interface 104. The keyboard interface 105 controls input from the keyboard 108 and a pointing device (not shown). The display interface 106 controls the display of the display 109. The external memory interface 107 controls access to external memory 110, such as a hard disk drive (HDD) or solid-state drive (SSD). External memory 110 stores various data such as boot programs, various applications, user files, and editing files.

[0021] The device management cloud 100 operates with the CPU 101 executing the basic I / O program and OS written to ROM 103 or external memory 110. The basic I / O program is written to ROM 103, and the OS is written to either ROM 103 or external memory 110. When the computer is powered on, the initial program load function in the basic I / O program writes the OS from ROM 103 or external memory 110 to RAM 102, and the OS starts running.

[0022] The system bus 111 connects each device, enabling each part to communicate with one another. Hardware resources such as the CPU 101, ROM 103, and external memory 110 that constitute the device management cloud 100 are supplied on demand using virtualization technology. Because these hardware resources are supplied on demand using virtualization technology, the device management cloud 100 is configured as a virtual server on a cloud computing environment.

[0023] The hardware configuration of the generation AI cloud 120 and client computer 140 is the same as that of the equipment management cloud 100, so the explanation is omitted.

[0024] In the MFP160, the network interface 161 connects to network 180 for network communication. The USB (Universal Serial Bus) interface 162 connects directly to client computer 140 for communication. The MFP160 supports both network connections via the network interface 161 and USB connections via the USB interface 162.

[0025] The CPU 163 outputs an image signal as output information to the printer 169 via the printer I / F 168 connected to the system bus 174, based on a control program. The control program is stored in ROM 165 or external memory 173. The CPU 163 is configured to communicate with a computer via network I / F 161 or USB I / F 162. Furthermore, the CPU 163 executes processing based on application programs stored in ROM 165 or external memory 173.

[0026] RAM164 functions as the main memory and work area of ​​the CPU163, and is configured to allow memory capacity expansion by optional RAM connected to an expansion port (not shown). RAM164 is used for output information expansion area, environment data storage area, NVRAM (Non-Volatile Random Access Memory), etc. ROM165 is a read-only memory that functions as a storage area for basic I / O programs, etc.

[0027] External memory 173 corresponds to a hard disk drive (HDD), solid state drive (SSD), IC card, etc., and stores various data such as boot programs, various applications, user files, and editing files. This ROM 165 or external memory 173 stores the control program and application programs for the CPU 163, font data used when generating the above output information, and information used on the MFP 160.

[0028] The operation unit I / F 166 manages the interface with the operation unit 167 and outputs image data to be displayed to the operation unit 167. It also receives information input by the user via the operation unit 167. The operation unit 167 corresponds to an operation panel or touch panel equipped with switches and LED indicators for operation, and transmits information input by the user to the operation unit I / F 166. The operation unit 167 may include a keyboard or a display. In this embodiment, the operation unit 167 has a display unit such as a display or touch panel, and various screens and information are displayed on it.

[0029] The printer interface 168 outputs an image signal (an example of output information) to the printer 169 (printer engine). The scanner interface 170 receives an image signal (an example of input information) from the scanner 171 (scanner engine).

[0030] The external memory interface (memory controller) 172 controls access to external memory 173 such as hard disk drives (HDDs), solid-state drives (SSDs), and IC cards. Furthermore, the aforementioned external memory is not limited to one; at least one or more may be provided, and the system may be configured to allow connection of multiple external memory devices. It is also possible to omit external memory if it is not necessary. Additionally, the MFP 160 may have an NVRAM (not shown) to store printer mode setting information from the operation unit 167. The system bus 174 connects each device, enabling each part to communicate with the others.

[0031] In this system, any number of devices can be connected to the device management cloud 100, the generation AI cloud, the client computers 140, and the MFP 160, and multiple units of each may be connected. In this embodiment, it is assumed that multiple MFP 160 units are connected to the network 180.

[0032] Figure 2 is a block diagram illustrating an example of the software configuration of the support system in this embodiment.

[0033] First, we will explain the software configuration of the device management cloud 100. Each software program's functions are implemented through the control of the CPU 101 of the device management cloud 100.

[0034] In the device management cloud 100, the device management application 202 and each module are stored and managed, for example, in external memory 110. However, the storage location is not limited to external memory 110; other storage media may be used, or the software may be stored outside the device management cloud 100 and accessed when needed.

[0035] These are program modules that are loaded into RAM 102 and executed at runtime by the OS or modules that utilize it. Furthermore, the device management application 202 can be added to external memory 110 HDDs or SSDs supplied on demand via virtualization technology in a cloud computing environment.

[0036] The network module 200 communicates with the generated AI cloud 120 and MFP 160 via the network using any communication protocol.

[0037] The web server service module 201 provides a service that responds with an HTTP response when it receives an HTTP request. The web server service module 201 may also request the device management application 202 to generate the HTTP response. HTTP stands for HyperText Transfer Protocol, and is a type of communication protocol.

[0038] The device management application 202 is an application that manages the MFP 160 connected to the device management cloud 100 via network 180. The device management application 202 is implemented as a program that processes requests to a Web API provided, for example, by the Web server service module 201. API stands for Application Programming Interface.

[0039] As described above, the device management application 202, together with the Web server service module 201, provides a cloud service for managing the MFP160. In the device management application 202, the Web API module 203 calls each module as needed in response to requests from the Web server service module 201 to generate HTTP responses.

[0040] As an example of a module called from Web API module 203, we will explain using the device management module 204. Of course, Web API module 203 may call other modules as well.

[0041] The device management module 204 obtains device information and logs from the MFP 160, which is connected to the device management cloud 100 via network 180, through the network module 200. Any communication protocol can be used to obtain device information and logs from the MFP 160. An example of a communication protocol used by the device management module 204 is HTTPS (Hypertext Transfer Protocol Secure).

[0042] The device management module 204 stores device information obtained from each module of the MFP160 in the device management table 300 and log management table 301 of the database server service module 205, which will be described later. It also retrieves (obtains) device information from the device management table 300 and log management table 301 as needed.

[0043] The database server service module 205 manages the data and stores and retrieves it in response to requests from other modules. The database server service module 205 may reside on a different device from the device management cloud 100, or it may be a database service on a cloud computing environment, as long as it is accessible from the device management application 202.

[0044] Figure 3 shows an example of the table structure within the database server service module 205. Figure 3(a) shows the device management table 300, and Figure 3(b) shows the log management table 301. Note that the table structure in Figure 3 is merely an example, and a different table structure is possible. The device management table 300 is a table that manages device information related to the MFP160 managed by the device management application 202. In this embodiment, device information refers to various information about the device, such as the model name, as shown in the device management table 300.

[0045] The information managed in the device management table 300 includes, for example, the device identifier (Device ID), device / model name (Name), vendor name (Vendor), model name (Model Name), and IP address (IP Address). Other information includes the serial number (Serial No.), installation location information (City, Building, Floor), status, and last updated date and time (Last Updated).

[0046] Here, the Device ID is an identifier that uniquely identifies the MFP160, and the installation location information (City, Building, Floor) refers to the address, building name, floor information, etc., that indicates the installation location of the MFP160. The Status is information that indicates the status of the MFP160, and the Last Updated date and time indicates the last update date and time when the record was updated with information obtained from the MFP160.

[0047] The log management table 301 is a table that stores logs acquired by the device management module 204 from the MFP160. The information managed in the log management table 301 includes, for example, the device identifier (Device ID), job identifier (Job ID), and job type. Other information includes the job execution start time (Start Time), job execution end time (End Time), job execution user name (User Name), job execution result (Result), and job execution result error code (Error Code).

[0048] Here, a "job" refers to a processing task that a user can perform on the MFP160, such as printing, scanning, sending, or faxing. The Job ID is a unique identifier for each job. The Error Code is a code used to uniquely identify the cause of an error in a job.

[0049] Next, returning to Figure 2, an example of the software configuration of the generation AI cloud 120 is shown. Each software function is implemented under the control of the CPU 101 of the generation AI cloud 120. Furthermore, each application module constituting the generation AI cloud 120 is stored and managed in external memory 110.

[0050] These are program modules that are loaded into RAM 102 and executed at runtime by the OS or modules that utilize it. Furthermore, each application constituting the generated AI cloud 120 can be added to external memory 110 (HDD or SSD) supplied on demand via virtualization technology on the cloud computing environment.

[0051] The network module 220 communicates with the device management cloud 100 and the client computer 140 using any communication protocol. The web server service module 221 provides a service that responds with an HTTP response when it receives an HTTP request from the generation AI client application 242 on the client computer 140. The web server service module 221 may also request the generation AI application 222 to generate an HTTP response.

[0052] The generation AI application 222 is an artificial intelligence system application that generates responses in cooperation with the AI ​​orchestrator 226, AI base model 228, AI infrastructure 229, etc., described later, in response to user input such as characters. The generation AI application 222 is implemented, for example, as a program that executes processing in response to requests to a Web API provided by the Web server service module 221.

[0053] As described above, the generation AI application 222, together with the web server service module 221, realizes a cloud service for generation AI.

[0054] In the generation AI application 222, the front-end application 223 receives input from the user and generates and returns a response in cooperation with the AI ​​orchestrator 226, AI base model 228, AI infrastructure 229, etc. In the front-end application 223, the Web API module 224 generates an HTTP response by calling each module as necessary in response to a request from the Web server service module 221.

[0055] The Generative AI Application 222 can be extended, enhanced, and customized by adding Generative AI knowledge, skills, and experiences. One way to extend the functionality of the Generative AI Application 222 is through a plug-in mechanism that extends its skills by interacting with external web services using natural language.

[0056] Plugin application 225 is an application that adds specific functions to generation AI application 222 through the plug-in mechanism of generation AI application 222. In this embodiment, Plugin application 225 implements management functions for MFP160 by calling the web service of device management application 202 on device management cloud 100. Plugin application 225 then adds management functions for MFP160 to generation AI application 222 through the plug-in mechanism of generation AI application 222.

[0057] The Plugin application 225 consists of an application manifest, which includes a description of the application in natural language. Figure 4 shows an example implementation of the application manifest for Plugin application 225 in this embodiment. The application manifest states that Plugin application 225 is an application that has the skill to provide information such as the MFP160 printer available to the user in the user's environment. The application manifest also includes commands for calling the linked web service and parameters for calling the web service.

[0058] As shown in Figure 5, the process described later selects a plugin with the skills suitable for generating responses to user input based on the contents of this application manifest, and the command is executed.

[0059] Returning to Figure 2, the AI ​​orchestrator 226 operates in the background from the user's natural language input to the natural language output (response), controlling business logic such as selecting and executing plugins suitable for response generation.

[0060] The user data layer 227 provides a means for storing and accessing user data. User data is information associated with a user's login account, such as the user's email address, calendar information, the team the user belongs to, colleagues, and accessible files. The AI ​​foundation model 228 consists of generative AI models such as LLMs (Large Language Models). The AI ​​infrastructure 229 configures and manages the cloud and GPUs (Graphics Processing Units) that constitute the infrastructure of the generative AI cloud.

[0061] Next, an example of the software configuration of client computer 140 is shown. Each software program's function is implemented under the control of the client computer 140's CPU 101. Furthermore, each module constituting client computer 140 is stored and managed in external memory 110. These are program modules that are loaded into RAM 102 and executed at runtime by the OS or modules that utilize them.

[0062] The network module 240 communicates with the AI ​​cloud 120 and MFP 160 via a network using any communication protocol. The printer driver 241 generates a print job and sends it to the MFP 160 via the network module 240.

[0063] The printer driver 241 receives the print job execution results from the MFP 160 via the network module 240, and the received results are displayed on the display 109 of the client computer 140. The generation AI client application 242 sends an HTTP request message to the generation AI cloud 120 via the network module 240 and receives an HTTP response message from the generation AI cloud 120. The received HTTP response message is displayed on the display 109 of the client computer 140. Access from the client computer 140 to the generation AI cloud 120 is performed through the generation AI client application 242.

[0064] Next, an example of the MFP160's software configuration is shown. Note that each function of the MFP160's software is implemented under the control of the MFP160's CPU 163. Furthermore, in the MFP160, various modules are stored and managed in ROM 165 or external memory 173, and are loaded into RAM 164 and executed at runtime.

[0065] The I / F module 260 communicates with the device management cloud 100 and client computers 140 using any communication protocol via the USB module 261 or the network module 262. The USB (Universal Serial Bus) module 261 connects directly to the client computer 140 for communication. The network module 262 connects to the network 180 for network communication.

[0066] The MFP160 supports both USB connection via USB module 261 and network connection via network module 262, and the connection method can be switched in the device settings.

[0067] The print module 263 receives print jobs sent from the printer driver 241 of the client computer 140 via the I / F module 260 and executes the print jobs. The print module 263 also creates a log of the print job execution results and saves it to the device management module 266.

[0068] The scan transmission module 264 receives scan commands from the user via the UI module 267 (described later) and generates and executes scan jobs and scan data transmission jobs. For transmitting scan data, protocols such as email or SMB (Server Message Block) are used. The scan transmission module 264 also creates logs of the scan job and transmission job execution results and saves them to the device management module 266.

[0069] The FAX module 265 receives FAX jobs sent from FAX devices or MFPs (not shown) via the network module 262. These received FAX jobs are either printed via the print module 263 or forwarded to other FAX devices or MFPs via the network module 262. In addition, it receives FAX transmission instructions from users via the UI module 267 and generates and executes FAX transmission jobs. The FAX module 265 also creates logs of FAX reception and transmission job execution results and saves them to the device management module 266.

[0070] The device management module 266 manages the device information of the MFP160. The device management module 266 receives requests for device information acquisition from the device management module 204 of the device management cloud 100 via the network module 262 and returns the device information. The device management module 266 also receives requests for log acquisition from the device management module 204 of the device management cloud 100 via the network module 262 and returns the job execution result log. The UI module 267 draws the UI displayed on the operation unit 167 of the MFP160 and receives user input values ​​entered by the user through UI operations on the operation unit 167.

[0071] Next, using Figure 5, an example of the operation of the generation AI cloud 120 from receiving a prompt about the MFP 160 input by the user to providing a response will be explained. In addition, using Figure 6, an example of the screen display of the generation AI client application 242 shown to the user will be shown. Figure 6 is a diagram showing an example of a screen generated by the generation AI client application 242 controlled by the CPU 101 of the client computer 140 in this embodiment, and this screen is displayed on the display 109 of the client computer 140. Note that this screen may also be displayed on the operation unit 167 of the MFP 160. In this case, the response generated by the language model through the following process will be displayed on the operation unit 167 of the MFP 160.

[0072] Figure 5 is a flowchart showing an example of a series of processes in this embodiment, from the generation AI to its response to a prompt. This operation is triggered when the user enters a prompt regarding the MFP160 on the generation AI client application 242. The software programs 220-229 of the generation AI cloud 120 are executed and operated by the CPU 101 of the generation AI cloud 120. The software programs 201-205 of the device management cloud 100 are executed and operated by the CPU 101 of the device management cloud 100.

[0073] In S500, the front-end application 223 of the generation AI application 222 receives a prompt from the generation AI client application 242. Here, a prompt refers to an instruction entered by the user using natural language on the generation AI client application 242. In other words, the front-end application 223 receives a natural language prompt from the user. The prompt is adjusted as needed and entered into the LLM. In this embodiment, an example is given where the user enters a prompt stating, "I tried to scan and send a print document on the MFP160, but it failed, so I would like to troubleshoot it," without specifying the official name of the MFP160. Note that the input prompt is not limited to troubleshooting the scanning and sending of print documents.

[0074] In the example screen display in Figure 6, the logged-in username 600 is displayed, and the prompt area 601 displays the prompt content entered by the user and the response from the generating AI. The user logs in to the generating AI application 222 or the account linked to the generating AI application 222. The account used to log in to the client computer 140 or MFP 160 may be the same as the account used for the generating AI application or its linked account.

[0075] In S501, the front-end application 223 checks the prompt entered in S500 from the perspectives of fairness, reliability, safety, privacy, security, inclusivity, transparency, and accountability. If any of the prompt checks fail, the conversation is terminated, and this operation is also terminated. In this case, a warning message such as "The conversation will be terminated because the check failed" or "The prompt is inappropriate" may be displayed.

[0076] If the prompt check by frontend application 223 is successful, proceed to S502.

[0077] In S502, the AI ​​orchestrator 226 acquires the context. Context refers to information that indicates the context, background, and situation related to the user's conversation. Specifically, it includes various types of information such as information about the user, such as the language the user is using, and information about the pages the user is accessing or displaying on the AI ​​client application 242 that the user is generating.

[0078] In S503, the AI ​​orchestrator 226 updates the context based on user data obtained from the user data layer 227. Context updating refers to adding new information to the context obtained in S502, organizing it, or both. The AI ​​orchestrator 226 then adjusts the prompt based on the updated context and sends the adjusted prompt to the LLM of the AI ​​platform model 228. Prompt adjustment here refers to actions such as removing forbidden words or editing the context to make it easier for the LLM to interpret; this adjustment is not a mandatory process. The AI ​​orchestrator 226 receives a response from the LLM to the sent prompt.

[0079] In S504, the AI ​​orchestrator 226 requests Plugin application 225 to retrieve Plugin information. This is done to identify Plugin application 225 that can retrieve device information in order to respond to user prompts. Therefore, if multiple Plugin applications 225 are being managed, the AI ​​orchestrator 226 will usually request all of them to retrieve Plugin information. However, if it is possible to identify Plugin application 225 that can retrieve device information in order to respond to user prompts, it is not necessary to request all Plugin applications 225 to retrieve Plugin information.

[0080] At S520, the Plugin application 225 receives a request from the AI ​​orchestrator 226 to retrieve Plugin information. At S521, the Plugin application 225 returns Plugin information, including the application manifest, to the AI ​​orchestrator 226. At S505, the AI ​​orchestrator 226 receives the Plugin information returned from the Plugin application 225. As a result, the AI ​​orchestrator 226 retrieves the Plugin information.

[0081] In S506, the AI ​​orchestrator 226 determines whether or not to call Plugin application 225 based on the description of the application command contained in the application manifest of Plugin application 225. If Plugin information is received from multiple Plugin applications 225, the AI ​​orchestrator further determines which Plugin application 225 to call. If the AI ​​orchestrator 226 determines to call Plugin application 225, it proceeds to S507; otherwise, it proceeds to S511.

[0082] In this embodiment, although the input prompt is a question about the MFP160, it does not include the official name of the device, so it is assumed that the Plugin application 225, which has management functions for the MFP160, will be called in order to identify the device. In other words, it is assumed that the input prompt will be judged as not containing the information necessary to identify the target device. The AI ​​orchestrator 226 may perform control other than the above, as long as there is a way to ensure that the Plugin application 225, which has management functions for the MFP160, is called in response to a question about the MFP160.

[0083] In S507, the AI ​​orchestrator 226 inputs the user-entered prompt, the updated context, and information from the Plugin application 225 into the LLM of the AI ​​platform model 228. Based on the LLM's response to the input information, the AI ​​orchestrator 226 obtains the function and parameters for calling the Web service declared in the Plugin application 225.

[0084] In S508, the AI ​​orchestrator 226 uses the function and parameters obtained in S507 to invoke the web service declared in the Plugin application 225. In S540, the invocation of the web service causes the device management application 202 of the device management cloud 100 to receive the device estimation request. Then, in S541, the device management application 202 retrieves the device information of the MFP 160 stored in the device management table 300 of the database server service module 205 via the device management module 204.

[0085] In this embodiment, the device management cloud 100 performs filtering using location information included in the device information. Specifically, it selectively retrieves device information only from MFP160s that belong to (correspond to) the account corresponding to the organization to which the user belongs, and that are thought to be physically close to the user. The organization is, for example, a legal entity such as the company to which the user belongs, and in this embodiment, the location of the user's desk is also managed by the device management cloud 100, and Figure 6 shows an example where the user's desk is on the 2nd floor of the head office. In addition, the location information of the information processing device used by the user, such as a personal computer, may be determined from the network to which it is connected, and this user location information may also be used during filtering.

[0086] Of course, the target MFP160 can be filtered using information other than the physical distance from the user. For example, information about the MFP160 can be obtained by filtering based on the device status, the functions of the device, the vendor information of the device, or a pre-configured priority. Alternatively, information about the MFP160 can be obtained by filtering based on usage frequency, usage history, etc., using log information stored in the log management table 301 of the database server service module 205. Or, information about the MFP160 can be obtained by filtering only those MFP160 that have a high correlation with prompt queries, such as prioritizing MFP160s that frequently experience problems with prompt queries (a large number of queries).

[0087] In S542, the device management application 202 returns the device information of MFP160 acquired in S541 to the AI ​​orchestrator 226. Filtering may also be performed by the generating AI cloud 120 selecting the necessary information after the device information of MFP160 stored in the device management table 300 has been sent to the AI ​​orchestrator 226.

[0088] In S509, the AI ​​orchestrator 226 receives device information returned from the device management cloud 100. In other words, the AI ​​orchestrator 226 obtains device information corresponding to the organization to which the user belongs. In S510, the AI ​​orchestrator 226 updates the context based on the device information received in S509. Thus, according to the present invention, when a prompt is received from the user in S500, device information can be obtained without receiving an instruction to obtain device information.

[0089] In S511, the AI ​​orchestrator 226 determines whether it is appropriate to generate an answer. If it determines that it is appropriate to generate an answer, it proceeds to S512; otherwise, it returns to S503 and continues to repeat the inference process using the LLM.

[0090] In S512, the AI ​​orchestrator 226 inputs all the information collected in the above process into the LLM of the AI ​​platform model 228 to generate a response. In other words, the AI ​​orchestrator 226 inputs information such as prompts and context into the LLM, causing the LLM to generate a response. In this embodiment, the LLM generates a response based on the prompt received in S500 and the device information acquired in S509. The AI ​​orchestrator 226 then checks the response generated by the LLM from the perspectives of fairness, reliability, safety, privacy, security, inclusiveness, transparency, and accountability.

[0091] In S513, the AI ​​orchestrator 226 returns a final response to the front-end application 223. The front-end application 223 returns the answer to the generating AI client application 242. As a result, the generating AI client application 242 displays the answer. This displays the answer generated based on the prompt received in S500 and the device information acquired in S509.

[0092] In the example screen display in Figure 6, the response from the generating AI is displayed in natural language in the prompt area 601, stating that there are 30 MFP160s in the user's environment and 4 MFP160s on the second floor of the head office where the user's desk is located. The device selection 602 then displays information on the 4 MFP160s located on the second floor of the head office where the user's desk is located, allowing the user to select one or more MFP160s. Here, the prompt area 601 displays multiple options, including devices corresponding to the device information acquired in S509.

[0093] As mentioned above, in S541, the device management application 202 selects only the MFP160 that is physically close to the user and retrieves the device information. Therefore, the device selection 602 displayed here shows only the MFP160 that is physically close to the user. Furthermore, this information is used to display the devices in order of proximity to the MFP160.

[0094] Additionally, if you filter MFP160 by device status to retrieve device information, for example, options 602 of MFP160s with the desired device status will be displayed based on the retrieved device information. If you filter MFP160 by device functions, vendor information, or pre-configured priority to retrieve device information, options 602 will be displayed of MFP160s with the desired functions, MFP160s from the desired vendor, or MFP160s with high priority. In other words, options 602 are displayed according to the priority set by the user.

[0095] If you filter MFP160s by usage frequency or usage history to retrieve device information, the options 602 will display the most frequently used MFP160s or the most recently used MFP160s based on the retrieved device information. In other words, options 602 will be displayed in order of the frequency of device use. If you filter MFP160s that have a high correlation with prompt inquiries to retrieve device information, the options 602 will display the MFP160s that have frequently experienced problems in prompt inquiries based on the retrieved device information. In other words, options 602 will be displayed in order of the number of inquiries made about the device.

[0096] It should be noted that displaying option 602 is not mandatory; the system may be configured to allow the user to identify the target device through other means, such as entering the device name or corresponding information. Furthermore, if, for example, a user or their account only has one device, or if there are multiple devices of the same model, the system may proceed without accepting device specification via option 602 from the user, and the answer may be displayed.

[0097] Furthermore, at this time, information about the identified device may be displayed, and the user may respond with YES or NO to a question such as "Is this the correct model?", and the method of handling that device may be displayed as the answer. In addition, the answer may include an image, and the usability is improved if the answer includes both text (strings) and images.

[0098] In S514, the front-end application 223 determines whether to end the conversation. If the user selects any option 602 corresponding to the MFP160 and selects the select button, the front-end application 223 determines that the conversation will continue and returns to S500. In other words, when the user selects a device from the displayed options 602, the front-end application 223 accepts this. At this time, the information of the MFP160 selected by the user becomes a prompt in S500, which the front-end application 223 receives. Specifically, the information of the device corresponding to the device (option) selected by the user is treated as a prompt. The information identified by the user's selection here is, for example, the official name of the MFP160. It may also be the model number, serial number, version information, etc.

[0099] Subsequently, the LLM inference process is repeated continuously in steps S501-513, and the final response from the LLM is displayed in prompt area 601. This allows the user to obtain a troubleshooting response for scan transmission failures based on the information of the selected MFP160.

[0100] On the other hand, if the user starts a new conversation on the generated AI client application or exits the generated AI client application 242, the front-end application 223 determines in S514 that the conversation has ended and terminates processing.

[0101] Through the above process, the generating AI cloud 120 identifies the target device using the acquired device information and generates an answer by inputting information based on the identified device into the LLM. As a result, the user can obtain an appropriate answer equivalent to that obtained by inputting the official name of the target device, without having to input the official name of the target device. To give a specific example, when the user inputs a troubleshooting question for a device at the prompt in S500, the LLM generates an answer to the troubleshooting question in S512. The answer to the troubleshooting question is an answer that indicates the actions that can be performed on the MFP160.

[0102] In this embodiment, the explanation is based on the MFP160 product, but the present invention is not limited to this product and is also effective for services such as applications. Furthermore, users can obtain an appropriate response equivalent to that obtained by inputting natural language that identifies the target device, even without inputting the official name or any other natural language that identifies the target device.

[0103] In this embodiment, we have shown an example in which the prompt entered by the user and the updated context are input to the LLM, but this is not the only way to do so. For example, the AI ​​orchestrator 226 may add information such as context to the prompt, and input a prompt consisting of various pieces of information, including the prompt entered by the user, to the LLM to obtain a response.

[0104] In this embodiment, the LLM is managed by the generation AI cloud 120, but it is not limited to this, and the LLM may be running on a different server. In that case, the CPU 101 sends the prompt received by S500 and the device information acquired by S509 to the server, and receives the response generated by the LLM in accordance with the transmission of these via the network interface. As a result, the response is finally displayed on the display unit. [Examples]

[0105] In Example 1, the generation AI cloud 120 was shown to obtain information about a network-connected MFP 160 by accessing the web service of the device management cloud 100 using a plug-in mechanism. In this example, even if the MFP 160 is not connected to a network, the generation AI client application 242 is shown to obtain device information for an MFP 160 that is directly connected to the client computer 140.

[0106] In this embodiment, an MFP160 connected via USB is used as an example of a device directly connected to the client computer 140. However, other direct connection methods such as Wi-Fi Direct communication or Bluetooth communication may also be used.

[0107] Figure 7 is a block diagram illustrating an example of the system configuration and hardware configuration of the support system in this embodiment. In Figure 7, the MFP160 is directly connected to the client computer 140 via USB. The other system configurations and hardware configurations are the same as those in Figure 1 of Embodiment 1, so their explanation is omitted.

[0108] Figure 8 is a block diagram illustrating an example of the software configuration of the support system in this embodiment. In Figure 8, the MFP160 is directly connected to the client computer 140 via USB module 261. The rest of the software configuration is the same as in Figure 2 of Embodiment 1, so its explanation is omitted.

[0109] Next, using Figure 9, we will explain the process from when the generating AI client application 242 receives a prompt from the user regarding the MFP160 to when a response is generated. In addition, using Figure 10, we will show an example of the screen display of the generating AI client application 242 that is shown to the user.

[0110] Figure 9 is a flowchart showing an example of a series of processes in this embodiment until the generating AI responds to a prompt. The process in Figure 9 is triggered when the user enters a prompt regarding the MFP 160 on the generating AI client application 242. Figure 10 is a diagram showing an example of a screen generated by the generating AI client application 242 controlled by the CPU 101 of the client computer 140 in this embodiment, and is displayed on the display 109 of the client computer 140.

[0111] Note that the processing steps S500 to S513 in Figure 9 are the same as those in Figure 5 of Example 1, so their explanation is omitted. Also, each software 220 to 229 of the generation AI cloud 120 is executed and operated by the CPU 101 of the generation AI cloud 120.

[0112] In the S900, the generation AI client application 242, which operates on the CPU 163 of the MFP160, receives prompts entered by the user. In this embodiment, an example is given where the user enters a prompt stating, "I tried to print with the MFP160 but it failed, so I would like to troubleshoot it." Note that the input prompt is not limited to those related to printing troubleshooting. In the example screen display in Figure 10, the logged-in username 600 is displayed, and the prompt area 601 displays the prompt content entered by the user and the response from the generation AI.

[0113] In S901, the generated AI client application 242 determines whether the prompt entered by the user is related to the MFP160. Whether a prompt is related to the MFP160 is determined by whether the prompt contains keywords related to the MFP160 or its functions such as printing and scanning. Of course, other methods may be used to determine whether a prompt is related to the MFP160. If the prompt is determined to be related to the MFP160, the process proceeds to S902; if it is determined not to be related to the MFP160, the process proceeds to S904.

[0114] The AI ​​client application 242 generated by S902 acquires device information, including the official name of the USB-connected MFP160. To acquire the MFP160 device information, methods such as bidirectional communication provided by the Windows® operating system are used. Alternatively, PJL (Printer Job Language) may be used.

[0115] The AI ​​client application 242 generated by S903 updates the prompt by adding the device information of the MFP160 acquired by S902 to the prompt. In the example screen display in Figure 10, the prompt area 601 displays the prompt content updated with the device information of the MFP160 acquired by S902.

[0116] In S904, the generation AI client application 242 sends a prompt to the generation AI cloud 120 via the network module 240. The generation AI application 222, running on the generation AI cloud 120, receives the prompt sent from the generation AI client application 242 and performs the processing in S500 to S513, thereby continuously repeating inference using LLM.

[0117] In S513, the generating AI application 222 sends the generated final response to the generating AI client application 242.

[0118] In S905, the AI ​​client application 242 receives the final response from the AI ​​client application 222 and displays it on the display 109 of the client computer 140. In the example screen display in Figure 10, the prompt area 601 displays the response from the AI ​​client application 222 regarding the USB-connected MFP 160.

[0119] Furthermore, the display rules for the MFP160 in the response displayed in the prompt area 601 may also be dynamically controlled. For example, the display order may be changed to reflect the order of most frequently used devices or the order of the number of questions asked to the generating AI application 222. Alternatively, as shown in Figure 6 of Example 1, multiple selection buttons for candidate devices may be displayed, and the response for the device corresponding to the button selected by the user may be displayed. Thus, for example, if the device the user is asking about is clear or there are few candidates, the response may be displayed without any selection options.

[0120] Alternatively, in S903, the generation AI client application 242 may treat the device information acquired in S902 as context, and in S904, send the context and the prompt entered by the user in S900 to the generation AI cloud 120. In this case, in S500, the generation AI application 222 receives the prompt and context, and ultimately generates a response based on them.

[0121] Through the above process, even if the MFP160 is not connected to a network, the generating AI client application 242 can obtain device information for the MFP160 that is directly connected to the client computer 140. This allows the generating AI client application 242 to identify the device and generate an answer by inputting information based on the identified device into the LLM. As a result, the user can obtain an appropriate answer equivalent to one obtained by entering the official name of the target device, without having to enter the official name of the target device.

[0122] The present invention in Example 2, like in Example 1, can be effective not only for devices but also for services. Furthermore, users can obtain an appropriate response equivalent to that obtained when they input natural language that identifies the target device, even without inputting natural language that identifies the target device, regardless of whether it is the official name or not. [Examples]

[0123] Examples 1 and 2 show an example where the generation AI client application 242 runs on the client computer 140 and generates an answer. In this example, the generation AI client application 242 runs on the MFP 160 and the MFP 160 generates an answer by obtaining information about the target service in response to prompts regarding the cloud service with which it is linked.

[0124] Figure 11 is a block diagram illustrating an example of the system configuration and hardware configuration of the support system in this embodiment. The support system consists of a device management cloud 100, a generation AI cloud 120, cloud storage 1100, client computers 140, and an MFP 160, all connected by a network 180.

[0125] The configuration of the general-purpose computer that implements the equipment management cloud 100, the generation AI cloud 120, and the cloud storage 1100 is realized using hardware resources supplied on demand through virtualization technology. The hardware configuration of the cloud storage 1100 is the same as that of the equipment management cloud 100 in Example 1, so its explanation is omitted. The other system configurations and hardware configurations are the same as those in Figure 1 of Example 1, so their explanation is omitted.

[0126] Figure 12 is a block diagram illustrating an example of the software configuration of the support system in this embodiment.

[0127] Cloud Storage 1100 manages files in a cloud computing environment and stores and retrieves files in response to requests from other modules. MFP160 accesses and interacts with Cloud Storage 1100 when sending prints and scans.

[0128] In the device management cloud 100, the device management module 204 acquires information about the cloud storage 1100 that the MFP 160 is linked to, in addition to the functions of Example 1. The acquired information about the cloud storage 1100 is stored in the linked service management table 1300 and the device-linked service management table 1301 of the database server service module 205, as described later. The device management module 204 also acquires information from the linked service management table 1300 and the device-linked service management table 1301 as needed.

[0129] Figure 13 shows an example of the table configuration within the database server service module 205 in this embodiment. Figures 13(a) to (d) show the device management table 300, log management table 301, collaboration service management table 1300, and device-to-collaboration service management table 1301, respectively. Note that the table configuration in Figure 13 is merely an example, and a different table configuration may be used. The device management table 300 and log management table 301 are the same as in Figure 3, so their explanation is omitted.

[0130] The Linked Service Management Table 1300 is a table that manages information about the cloud storage 1100 that can be linked to by the MFP 160 managed by the device management application 202. The information managed in the Linked Service Management Table 1300 includes, for example, the Linked Service Identifier (Service Connector ID), the Linked Service Name (Service Connector Name), and various settings (Settings).

[0131] Here, the Service Connector ID is an identifier that uniquely identifies the cloud storage 1100 that the MFP160 can connect to. The Settings are the configuration information, such as authentication information, required for the MFP160 to access the cloud storage 1100.

[0132] The device-to-service integration management table 1301 is a table that manages correspondence information regarding which MFP 160 can integrate with which cloud storage 1100. The information managed in the device-to-service integration management table 1301 includes, for example, the device identifier (Device ID) and the service connector identifier (Service Connector ID). Note that multiple service connector identifiers may be associated with and managed for one device identifier, and multiple device identifiers may be associated with and managed for one service connector identifier.

[0133] In the MFP160, the generation AI client application 1200 sends an HTTP request message to the generation AI cloud 120 via the network module 262 and receives an HTTP response message from the generation AI cloud 120. The HTTP response message received by the MFP160 from the generation AI cloud 120 is displayed on the operation unit 167. Access from the MFP160 to the generation AI cloud 120 is performed through the generation AI client application 1200. The rest of the software configuration is the same as in Figure 2 of Example 1, so a description is omitted.

[0134] Next, using Figure 14, we will explain the process by which the generating AI cloud 120 receives a prompt from the user regarding the MFP 160 and provides a response. In addition, using Figure 15, we will show an example of the screen display of the generating AI client application 1200 that is shown to the user.

[0135] Figure 14 is a flowchart showing an example of a series of processes in this embodiment, from generation to response to a prompt. The process in Figure 14 is triggered when the user enters a prompt regarding a cloud storage service that the MFP160 is linked to on the generation AI client application 1200. Figure 15 shows an example of a screen generated by the generation AI client application 1200 controlled by the CPU 163 of the MFP160 in this embodiment, and this screen is displayed on the operation unit 167 of the MFP160.

[0136] Note that the processing steps S500 to S513 in Figure 14 are the same as those in Figure 5 of Example 1, so their explanation is omitted. Also, the software operations 260 to 267 and 1200 of the MFP160 are executed and operated by the CPU 163 of the MFP160.

[0137] In S500, the front-end application 223 of the generation AI application 222, which runs on the generation AI cloud 120, receives prompts from the generation AI client application 1200, which runs on the MFP 160. That is, prompts entered by the user are sent to the front-end application 223 by the generation AI client application 1200.

[0138] In this embodiment, we provide an example where the user enters a prompt on the MFP160 stating, "I want to know how to scan in conjunction with Cloud Storage 1100," without specifying the official name of the Cloud Storage 1100 service on the prompt. Here, Cloud Storage 1100 is a service that works in conjunction with the MFP160. Note that the input prompt is not limited to how to scan in conjunction with Cloud Storage 1100.

[0139] In the example screen display in Figure 15, the logged-in username 1500 is displayed, and the prompt area 1501 displays the prompt content entered by the user.

[0140] In S508, when the AI ​​orchestrator 226 invokes the web service, in S1440, the device management application 202 of the device management cloud 100 receives a collaboration service estimation request as a result of the web service being invoked. Then, in S1441, the device management application 202 retrieves information stored in the database server service module 205 regarding the available collaboration cloud storage 1100 for the MFP 160.

[0141] Furthermore, information regarding the cloud storage 1100 that MFP160 can use is obtained from the information stored in the integration service management table 1300 and the device-integration service management table 1301 of the database server service module 205.

[0142] In S1442, the device management application 202 returns the information about the MFP160's linked cloud storage 1100, which was acquired in S1441, to the AI ​​orchestrator 226.

[0143] In S509, the AI ​​orchestrator 226 receives information about the MFP 160's linked cloud storage 1100, which was returned from the equipment management cloud 100 in S1442. The generating AI application 222 then performs the processing from S509 onward, continuously repeating inference using LLM, generating a final response in S512, and sending it to the generating AI client application 1200 in S513. In the example screen display in Figure 15, the prompt area 1501 displays the final response from the generating AI application 222, which is the answer regarding the linked cloud storage 1100 available to the MFP 160.

[0144] Through the above process, even when the generating AI client application runs on the MFP160, information about the target service is acquired, and the response is created with a prompt that includes the acquired service information. As a result, the user can obtain an appropriate response equivalent to one obtained by entering the official name of the target MFP160-linked cloud service, without having to enter the official name.

[0145] <Other examples> The present invention can also be realized by supplying a program that implements one or more of the functions of the above-described embodiments to a system or device via a network or storage medium, and by having one or more processors in the computer of that system or device read and execute the program. It can also be realized by a circuit (e.g., an ASIC) that implements one or more functions. [Explanation of Symbols]

[0146] 100 Device Management Cloud 120 Generation AI Cloud 140 client computers 160 MFP 202 Equipment Management Application (Equipment Management Cloud) 222 Generative AI Applications (Generative AI Cloud) 225 Plugin applications (Generating AI cloud) 242. Generate AI client applications (client computers) 1100 Cloud Storage 1200 Generating AI Client Applications (MFPs)

Claims

1. A means of receiving natural language prompts from the user, A means for obtaining information about equipment corresponding to the organization to which the user belongs from a cloud service, A display means that displays the response generated by the language model based on the received prompt and the acquired device information on the display unit. An information processing device characterized by having the following features.

2. The display means displays a plurality of options, including the equipment, on the display unit in order of proximity between the information processing device and the equipment. The receiving means further accepts the selection of equipment when the user has selected the option. The display means causes the display unit to display the response generated by the language model based on the device information corresponding to the selected option. The information processing apparatus according to feature 1.

3. The display means displays a plurality of options, including the equipment, on the display unit according to the priority set by the user. The receiving means further accepts the selection of equipment when the user has selected the option. The display means causes the display unit to display the response generated by the language model based on the device information corresponding to the selected option. The information processing apparatus according to feature 1.

4. The display means displays a plurality of options, including the device, on the display unit in order of the frequency of use of the device. The receiving means further accepts the selection of equipment when the user has selected the option. The display means causes the display unit to display the response generated by the language model based on the device information corresponding to the selected option. The information processing apparatus according to feature 1.

5. The display means displays a plurality of options, including the device, on the display unit in order of the number of inquiries made about the device. The receiving means further accepts the selection of equipment when the user has selected the option. The display means causes the display unit to display the response generated by the language model based on the device information corresponding to the selected option. The information processing apparatus according to feature 1.

6. The information processing apparatus according to claim 1, characterized in that the acquisition means acquires information about the device without receiving an instruction from the user to acquire information about the device, upon receipt of the prompt by the receiving means.

7. The aforementioned prompt is a troubleshooting question for the device. The information processing apparatus according to claim 1, wherein the response is a response indicating a process that can be executed by the device corresponding to the acquired device information, and is a response to the troubleshooting question generated by the language model.

8. The information processing device according to claim 1, characterized in that the aforementioned organization is the company to which the user belongs.

9. The above answer is an information processing device according to claim 1, characterized in that it includes text.

10. The above answer further includes equipment options, The receiving means further accepts the selection of equipment when the user selects the option. The display means causes the display unit to display the response generated by the language model based on the device information corresponding to the selected option. The information processing apparatus according to feature 9.

11. It further comprises a transmitting means and a receiving means, The aforementioned language model operates on a server, The transmission means transmits the received prompt and the acquired device information to the server. The information processing apparatus according to claim 1, characterized in that the receiving means receives the response generated in accordance with the transmission of the received prompt and the acquired device information by the transmitting means.

12. The information processing device according to claim 1, characterized in that the aforementioned device is a multifunction device.

13. The information processing apparatus according to claim 1, characterized in that the display means causes the response generated by the language model based on the received prompt and the acquired device information to be displayed on the display unit of the device.

14. A reception process that receives natural language prompts from the user, A process of acquiring information from a cloud service to obtain information about equipment corresponding to the organization to which the user belongs, A display step in which the response generated by the language model based on the received prompt and the acquired device information is displayed on the display unit. A program characterized by causing a computer to execute something.

15. The display step involves displaying a plurality of options, including the equipment, on the display unit in order of proximity between the information processing device that executes the program and the equipment. The aforementioned acceptance process, upon the user's selection of the option, further accepts the selection of equipment. The display step causes the display unit to display the response generated by the language model based on the device information corresponding to the selected option. The program according to feature 14.

16. The display step involves displaying a plurality of options, including the equipment, on the display unit according to the priority set by the user. The aforementioned acceptance process, upon the user's selection of the option, further accepts the selection of equipment. The display step causes the display unit to display the response generated by the language model based on the device information corresponding to the selected option. The program according to feature 14.

17. The display step involves displaying a plurality of options, including the equipment, on the display unit in order of the frequency of use of the equipment. The aforementioned acceptance process, upon the user's selection of the option, further accepts the selection of equipment. The display step causes the display unit to display the response generated by the language model based on the device information corresponding to the selected option. The program according to feature 14.

18. The display step involves displaying a plurality of options, including the equipment, on the display unit in order of the number of inquiries made about the equipment, The aforementioned acceptance process, upon the user's selection of the option, further accepts the selection of equipment. The display step causes the display unit to display the response generated by the language model based on the device information corresponding to the selected option. The program according to feature 14.

19. The program according to claim 14, characterized in that the acquisition step acquires information about the device without receiving an instruction from the user to acquire information about the device, as the prompt has been received in the reception step.

20. The aforementioned prompt is a troubleshooting question for the device. The program according to claim 14, characterized in that the response is a response indicating a process that can be executed on the device corresponding to the acquired device information, and is a response to the troubleshooting question generated by the language model.

21. The program according to claim 14, characterized in that the aforementioned organization is the company to which the user belongs.

22. The above answer is the program according to 14, characterized in that it includes text.

23. The above answer further includes equipment options, The aforementioned reception process further accepts the selection of equipment once the user has selected the option. The display step causes the display unit to display the response generated by the language model based on the device information corresponding to the selected option. The program according to feature 22.

24. It further comprises a transmission process and a reception process, The aforementioned language model operates on a server, The transmission step involves sending the received prompt and the acquired device information to the server. The program according to claim 14, characterized in that the receiving step receives the response generated in accordance with the transmission of the received prompt and the acquired device information in the transmission step.

25. The program according to claim 14, characterized in that the device is a multifunction printer.

26. The program according to claim 14, wherein the display step causes the response generated by the language model based on the received prompt and the acquired device information to be displayed on the display unit of the device.

27. A reception process that receives natural language prompts from the user, A process of acquiring information from a cloud service to obtain information about equipment corresponding to the organization to which the user belongs, A display step in which the response generated by the language model based on the received prompt and the acquired device information is displayed on the display unit. An information processing method characterized by having the following features.

Images