Program, storage medium, information processing method, and information processing apparatus

Abstract

A program according to an aspect of the present disclosure is a program for causing a computer to execute accepting a prompt to request a presentation of a fixing method for a problem of an information processing apparatus from a user, obtaining information representing an operation history of the information processing apparatus, and displaying a display for making a query to the user to request additional information associated with the information processing apparatus that is additional information used for a reply regarding the fixing method, in which the accepting includes further accepting the additional information input by the user, and the displaying includes displaying the reply generated based on the information representing the operation history and the additional information.

Description

PROGRAM, STORAGE MEDIUM, INFORMATION PROCESSING METHOD, AND INFORMATION PROCESSING APPARATUS

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

[0002] Use cases for attempting to fix a problem that has occurred in a device or a service by using a generative artificial intelligence (AI) have been suggested. Upon fixing the problem, for the generative AI to output a reply which contributes to fixing the problem, a user is required to input a situation of the ongoing problem, an operation that has been performed, and the like into the generative AI correctly and without contradicting facts.

[0003] As an example of processing of fixing a problem, PTL 1 proposes a method of displaying, when a user makes an inquiry to an operator, a past operation history to the operator to facilitate understanding of a situation of the problem.

[0004] Japanese Patent Laid-Open No. 2022-65729

[0005] For example, a history of an operation such as restart of an external apparatus is recorded in a recording medium as a log. However, for example, a history of an operation such as cleaning of the external apparatus by a user is not recorded in the recording medium as a log. For this reason, a generative AI can understand the operation recorded as the log through communication, but does not understand an operation that is not recorded as a log through the communication.

[0006] As a result, there may be a situation where the generative AI does not output a reply effective for fixing a problem, and the user is unable to fix the problem.

[0007] A program according to an aspect of the present disclosure is a program for causing a computer to execute accepting a prompt to request a presentation of a fixing method for a problem of an information processing apparatus from a user, obtaining information representing an operation history of the information processing apparatus, and displaying a display for making a query to the user to request additional information associated with the information processing apparatus that is additional information used for a reply regarding the fixing method, in which the accepting includes further accepting the additional information input by the user, and the displaying includes displaying the reply generated based on the information representing the operation history and the additional information.

[0008] Features of the present disclosure will become apparent from the following description of embodiments with reference to the attached drawings. The following description of embodiments is described by way of example.

[0009] Fig. 1 illustrates examples of a system configuration and a hardware configuration in a first embodiment.Fig. 2 illustrates an example of a software configuration in the first embodiment.Fig. 3A illustrates an example of a database configuration in the first embodiment.Fig. 3B illustrates an example of the database configuration in the first embodiment.Fig. 3C illustrates an example of the database configuration in the first embodiment.Fig. 3D illustrates an example of the database configuration in the first embodiment.Fig. 3E illustrates an example of the database configuration in the first embodiment.Fig. 4 illustrates an example of an agent manifest in the first embodiment.Fig. 5A illustrates an example of a Plugin application manifest in first and second embodiments.Fig. 5B illustrates an example of the Plugin application manifest in the first and second embodiments.Fig. 6A is a flowchart diagram of input verification processing in the first embodiment.Fig. 6B is a flowchart diagram of the input verification processing in the first embodiment.Fig. 7 illustrates an example of a screen displayed when the input verification processing is executed in the first embodiment.Fig. 8 illustrates examples of a system configuration and a hardware configuration in the second embodiment.Fig. 9 illustrates an example of a software configuration in the second embodiment.Fig. 10A illustrates an example of a database configuration in the second embodiment.Fig. 10B illustrates an example of the database configuration in the second embodiment.Fig. 10C illustrates an example of the database configuration in the second embodiment.Fig. 10D illustrates an example of the database configuration in the second embodiment.Fig. 10E illustrates an example of the database configuration in the second embodiment.Fig. 11 illustrates an example of an agent manifest in the second embodiment.Fig. 12 illustrates an example of a screen displayed when the input verification processing is executed in the second embodiment

[0010] Hereinafter, embodiments for carrying out the present disclosure will be described with reference to the drawings.First Embodiment

[0011] An embodiment of a device / service support chatbot system using a generative AI according to the present disclosure (hereinafter, a support system) will be described. Herein, as an example of the support system, a device management service and a generative AI service that are operated on a cloud are exemplified to be described. In addition, as an example of a device set as a target of the support system, a printer is exemplified to be described in the present embodiment. It is noted that an example of the device includes a device other than the printer, such as a multifunction peripheral (MFP), a composite machine, a facsimile (FAX), or a projector. It is noted that hereinafter, the support system may be referred to as a device / service support chatbot system.

[0012] In addition, each of a generative AI cloud 120, a client computer 140, and a printer 160 is an example of an information processing apparatus or a control apparatus. It is noted that the support system according to the embodiment of the present disclosure can be used not only for a query related to a device but also for a query related to a service.

[0013] It is noted that the generative AI in the present application refers to a technique that uses deep learning and machine learning approaches to automatically generate various types of content, such as a text, an image, music, and video that are as if created by humans.

[0014] It is noted that in the present embodiment, "contradiction with facts" refers to a situation in which content input by a user differs from an operation history recorded in a log or the content input by the user is insufficient based on a comparison with an actual operation history.

[0015] Fig. 1 is a block diagram for describing examples of a system configuration and a hardware configuration of the support system of the present embodiment.

[0016] The support system is configured by including a device management cloud 100, the generative AI cloud 120, the client computer 140, and the printer 160 which are connected by a network 180. Herein, a configuration of a general-purpose computer which realizes the device management cloud 100 and the generative AI cloud 120 is realized by using a hardware resource supplied on demand by a virtualization technique, for example. It is noted that the device management cloud 100 and the generative AI cloud 120 may be servers. The client computer 140 has, for example, a configuration of a general-purpose computer such as a personal computer. The network 180 may be either a wired network or a wireless network.

[0017] In the device management cloud 100, a CPU 101 executes processing such as control or computation based on an application program or the like stored in a ROM 103 or an external memory 110. It is noted that CPU and ROM are respectively abbreviations of central processing unit and read only memory. Furthermore, the CPU 101 controls each device connected to a system bus 111 in an overall manner. In addition, the CPU 101 opens various registered windows based on commands instructed by a mouse cursor or the like which is not illustrated in the drawing on a display 109 to execute various types of data processing.

[0018] Herein, the display 109 functions as a display unit. The display 109 may further function as an operation unit. In addition, the display 109 may execute each processing when an input is supplied not only by the mouse cursor but also via a keyboard 108.

[0019] A RAM 102 functions as a main memory, a work area, or the like of the CPU 101. It is noted that RAM is an abbreviation of random access memory. The ROM 103 is a read only memory functioning as a storage area of a basic I / O program or the like. It is noted that I / O is an abbreviation of input / output and means an input and / or an output. An operating system program (hereinafter, an OS) that is a control program of the CPU 101 or the like is stored in the ROM 103 or the external memory 110. A file and various types of other data used for processing based on the above-described application program or the like is performed are further stored in the ROM 103 or the external memory 110.

[0020] A network interface (I / F) 104 connects to the network 180 to perform network communication.

[0021] With this configuration, the CPU 101 can communicate with an external apparatus via the network I / F 104. A keyboard I / F 105 controls an input from the keyboard 108 or a pointing device which is not illustrated in the drawing. A display I / F 106 controls a display of the display 109. An external memory I / F 107 controls access to the external memory 110 such as a hard disk drive (HDD) or a solid state drive (SSD). The external memory 110 stores a boot program, various types of applications, a user file, an editing file, or the like.

[0022] The device management cloud 100 operates in a state in which the CPU 101 executes the basic I / O program and the OS written in the ROM 103 or the external memory 110. The basic I / O program is written in the ROM 103, and the OS is written in the ROM 103 or the external memory 110. When a power supply of a computer is turned on, based on an initial program load function in the basic I / O program, the OS is written into the RAM 102 from the ROM 103 or the external memory 110, and an operation of the OS is started.

[0023] The system bus 111 connects each device, and with this configuration, each unit is communicable with each other. It is noted that hardware resources such as the CPU 101 and the ROM 103 configuring the device management cloud 100 and the external memory 110 are supplied on demand by the virtualization technique. When these hardware resources are supplied on demand by the virtualization technique, the device management cloud 100 is configured as a virtual server on a cloud computing environment.

[0024] The hardware configurations of the generative AI cloud 120 and the client computer 140 are similar to that of the device management cloud 100, and the descriptions thereof are omitted.

[0025] In the printer 160, a network I / F 161 connects to the network 180 to perform network communication. A universal serial bus (USB) I / F 162 directly connects to and communicates with the client computer 140. The printer 160 supports connection methods of both a network connection via the network I / F 161 and a USB connection via the USB I / F 162.

[0026] A CPU 163 outputs, to a printer 169, an image signal as output information via a printer I / F 168 connected to a system bus 172 based on the control program or the like. It is noted that the control program is stored in a ROM 165, an external memory 171, or the like. The CPU 163 is configured to be able to perform communication processing with the computer via the network I / F 161 or the USB I / F 162. The CPU 163 further executes processing based on an application program or the like stored in the ROM 165 or the external memory 171.

[0027] A RAM 164 is configured to function as a main memory, a work area, or the like of the CPU 163 and to be able to expand a memory capacity by an optional RAM connected to an extension port which is not illustrated in the drawing. It is noted that the RAM 164 is used as an output information expansion area, an environment data retention area, a non-volatile random access memory (NVRAM), or the like. The ROM 165 is a read only memory which functions as a storage area of the basic I / O program or the like.

[0028] The external memory 171 is equivalent to a hard disk drive (HDD), a solid state drive (SSD), an IC card, or the like and stores various data such as a boot program, various types of applications, a user file, and an editing file. The control program and the application program of the CPU 163, font data used when the above-described output information is generated, information used on the printer 160, and the like are stored in the ROM 165 or the external memory 171.

[0029] An operation unit I / F 166 governs an interface with an operation unit 167 and outputs image data that is to be displayed to the operation unit 167. The operation unit I / F 166 also receives information input by the user via the operation unit 167. The operation unit 167 is equivalent to an operation panel, a touch panel, or the like on which a switch, a light emitting diode (LED) display device, or the like for operations is arranged, and sends the information input by the user to the operation unit I / F 166. The operation unit 167 may include a keyboard or a display. In the present embodiment, the operation unit 167 includes a display unit such as a display or a touch panel on which various types of screen and information are displayed.

[0030] The printer I / F 168 outputs an image signal (example of output information) to the printer (printer engine) 169. An external memory I / F (memory controller) 170 controls an access to the hard disk drive (HDD), the solid state drive (SSD), or the external memory 171 such as the IC card. In addition, the above-described external memory is not limited to a single external memory and includes at least one external memory. A configuration may be adopted in which a plurality of external memories can be connected to each other. Furthermore, the printer 160 may be configured to include an NVRAM which is not illustrated in the drawing and store printer mode setting information from the operation unit 167. The system bus 172 connects each device, and with this configuration, each unit is communicable with each other.

[0031] It is noted that the device management cloud 100, the generative AI cloud 120, the client computer 140, and the printer 160 in the present system can be connected in any number, and each may have multiple components connected.

[0032] Fig. 2 is a block diagram for describing an example of a software configuration of the support system of the present embodiment.

[0033] First, a software configuration of the device management cloud 100 is illustrated. It is noted that with regard to each software, each function is realized by the control of the CPU 101 of the device management cloud 100.

[0034] In the device management cloud 100, a device management application 202 and each module are saved and managed in the external memory 110, for example. It is noted that their saving locations are not limited to the external memory 110 and may be another storage medium or the like. A configuration may also be adopted in which the device management application 202 and each module are saved outside the device management cloud 100, and each software is used by being accessed as needed.

[0035] These modules are program modules which are loaded upon execution into the RAM 102 by a module using the OS or the module and which are then executed. In addition, the device management application 202 can be added to the HDD or the SSD of the external memory 110 which is supplied on demand by the virtualization technique on the cloud computing environment.

[0036] A network module 200 performs network communication with the generative AI cloud 120 or the printer 160 by using any communication protocol.

[0037] A web server service module 201 provides a service for returning an HTTP response when an HTTP request is received. It is noted that the web server service module 201 may request the device management application 202 to generate an HTTP response. It is noted that HTTP is an abbreviation of Hypertext Transfer Protocol and is a type of communication protocols.

[0038] The device management application 202 is an application configured to manage the printer 160 connected to the device management cloud 100 by the network 180. The device management application 202 is implemented, for example, as a program for executing processing by responding to a request to a Web API provided by the web server service module 201. It is noted that API is an abbreviation of application programming interface.

[0039] As described above, the device management application 202 realizes a cloud service for managing the printer 160 together with the web server service module 201. In the device management application 202, a Web API module 203 invokes each module as needed in response to a request from the web server service module 201 to generate an HTTP response.

[0040] A device management module 204 is exemplified to be described as an example of the module invoked by the Web API module 203. The Web API module 203 may of course invoke a module other than the device management module 204.

[0041] The device management module 204 obtains device information and log from the printer 160 connected to the device management cloud 100 by the network 180 via the network module 200. It is noted that to obtain the device information and log from the printer 160, any communication protocol can be used. An example of the communication protocol used by the device management module 204 includes Hypertext Transfer Protocol Secure (HTTPS) or the like.

[0042] The device management module 204 retains the device information obtained from each module of the printer 160 in each table of a database server service module 205 which will be described below. The device management module 204 also retrieves (obtains) the device information from each table as needed.

[0043] The database server service module 205 manages data and stores (retains) and retrieves the data in response to a request from another module. The database server service module 205 may be located on a device other than the device management cloud 100 as long as an access can be made from the device management application 202. The database server service module 205 may be a database service on a cloud computing environment.

[0044] Examples of table configurations in the database server service module 205 are illustrated in Figs. 3A to 3E. Fig. 3A illustrates a device management table 300, Fig. 3B illustrates a job log management table 301, Fig. 3C illustrates an operational log management table 302, Fig. 3D illustrates a sensor log management table 303, and Fig. 3E illustrates a troubleshooting task rule management table 304. It is noted that the table configurations of Figs. 3A to 3E are merely examples and may be table configurations different from the present examples.

[0045] The device management table 300 is a table stored in the external memory 171 of the device management cloud 100 that is table for managing device information related to the printer 160 managed by the device management application 202.

[0046] The information managed in the device management table 300 is as follows. For example, the information includes a device identifier (Device ID), a device name (Name), a model name (Model Name), an IP address (IP Address), a serial number (Serial No.), and last updated date and time (Last Updated). Herein, the device identifier (Device ID) is an identifier for uniquely identifying the printer 160, and the last updated date and time (Last Updated) indicate last updated date and time when a record is updated by information obtained from the printer 160.

[0047] The job log management table 301 is a table stored in the external memory 171 of the device management cloud 100 that is table retaining a job log obtained by the device management module 204 from the printer 160.

[0048] The information managed in the job log management table 301 includes, for example, a device identifier (Device ID), a job log identifier (Job Log ID), a job type (Job Type), and the like. In addition to the above, job execution start date and time (Start Time), job execution end date and time (End Time), a job execution user name (User Name), a job execution result (Result), and a job execution result error code (Error Code) are managed.

[0049] Herein, the job refers to a processing task such as print that can be executed by the user on the printer 160, and the job log identifier (Job Log ID) is an identifier for uniquely identifying a log of the job. In addition, the job execution result error code (Error Code) is a code for uniquely specifying an error cause of the job.

[0050] The operational log management table 302 is a table stored in the external memory 171 of the device management cloud 100 that is table retaining an operational log obtained by the device management module 204 from the printer 160.

[0051] The information managed in the operational log management table 302 is as follows. For example, the information includes a device identifier (Device ID), an operational log identifier (Operational Log ID), an operation type (Operation Type), operation execution date and time (Date Time), and an operation execution user name (User Name).

[0052] Herein, the operational log identifier (Operational Log ID) is an identifier for uniquely identifying an operational log. In addition, the operation type (Operation Type) is a type of an operation that can be executed on the printer 160 and includes, for example, restart or the like.

[0053] The sensor log management table 303 is a table stored in the external memory 171 of the device management cloud 100 that is table retaining a sensor log obtained by the device management module 204 from the printer 160.

[0054] The information managed in the sensor log management table 303 is as follows. For example, the information includes a device identifier (Device ID), a sensor log identifier (Sensor Log ID), a sensor type (Sensor Type), sensor information (Sensor Information), and log obtaining date and time (Date Time).

[0055] Herein, the sensor log identifier (Sensor Log ID) is an identifier for uniquely identifying a log of a sensor. In addition, the sensor type (Sensor Type) is a type of sensor information that can be obtained from the printer 160 and includes, for example, a Wi-Fi signal strength or the like.

[0056] The troubleshooting task rule management table 304 is a table stored in the external memory 171 of the device management cloud 100 that is table for managing a task rule recommended in troubleshooting of the printer 160.

[0057] The information managed in the troubleshooting task rule management table 304 includes, for example, a rule identifier (Rule ID), a troubleshooting type (Troubleshooting Type), and a rule (Rule).

[0058] Herein, the rule identifier (Rule ID) is an identifier for uniquely identifying a task rule. In addition, the troubleshooting type (Troubleshooting Type) is a type of troubleshooting used for the printer 160 and includes, for example, a solution or the like of a Wi-Fi connection problem. The rule (Rule) is a task rule actually recommended in the troubleshooting and includes, for example, restart of the printer 160 or a Wi-Fi router, check of a Wi-Fi connection status, re-setup of a printer driver, or the like in the solution of the Wi-Fi connection problem.

[0059] Next, with reference to Fig. 2 again, an example of a software configuration of the generative AI cloud 120 is illustrated. It is noted that with regard to each software, each function is realized by the control of the CPU 101 of the generative AI cloud 120. In addition, each application and each module which configure the generative AI cloud 120 are saved and managed in the external memory 110.

[0060] These modules are program modules which are loaded upon execution into the RAM 102 by a module using the OS or the module and which are then executed. In addition, each application configuring the generative AI cloud 120 can be added to the HDD or the SSD of the external memory 110 supplied on demand by the virtualization technique on the cloud computing environment.

[0061] A network module 220 performs network communication with the device management cloud 100 and the client computer 140 by using any communication protocol. When an HTTP request from a generative AI client application 242 of the client computer 140 is received, a web server service module 221 provides a service for delivering an HTTP response. It is noted that the web server service module 221 may request a generative AI application 223 to generate an HTTP response.

[0062] An agent 222 is an artificial intelligence system application configured to generate a response to a user input such as a text and adopts a configuration that can be customized according to a purpose or a use. In the present embodiment, the agent 222 is configured by the generative AI application 223, an AI orchestrator 227, a user data layer 228, an AI foundation model 229, an agent manifest including an explanation of the agent, and the like which will be described below.

[0063] Fig. 4 illustrates an implementation example of the agent manifest of the agent 222 in the present embodiment. It is described in the agent manifest that the agent 222 is an agent aimed at pointing out a contradiction between a claim by the user and facts based on the log of the printer 160 and the task rule of the troubleshooting and urging the user to check and correct the claim. In the present embodiment, an action in response to an input by the user based on content of this agent manifest is decided by processing which will be described below with reference to Figs. 6A and 6B.

[0064] The generative AI application 223 is an artificial intelligence system application governing a user experience (UX) for generating a response to a user input such as a text. The generative AI application 223 is an element configuring the agent 222 and operates in cooperation with the AI orchestrator 227, the AI foundation model 229, an AI infrastructure 230, or the like which will be described below. The generative AI application 223 is implemented, for example, as a program for executing processing by responding to a request to a Web API provided by the web server service module 221. As described above, the generative AI application 223 realizes the cloud service of the generative AI together with the web server service module 221.

[0065] A front-end application 224 in the generative AI application 223 receives an input from the user and generates a response in cooperation with the AI orchestrator 227, the AI foundation model 229, the AI infrastructure 230, or the like to return the response. A Web API module 225 in the front-end application 224 invokes each module as needed in response to a request from the web server service module 221 to generate an HTTP response.

[0066] The generative AI application 223 is capable of extending, enhancing, and customizing knowledge, skills, and experiences of the generative AI through additions thereof. As one of the function extension methods of the generative AI application 223, a plugin mechanism to extend skills by interacting with an external web service using a natural language has been proposed.

[0067] A Plugin application 226 is an application configured to add a specific function to the generative AI application 223 by the plugin mechanism of the generative AI application 223. The Plugin application 226 in the present embodiment realizes a management function of the printer 160 by invoking a web service of the device management application 202 on the device management cloud 100. The Plugin application 226 then adds the management function of the printer 160 to the generative AI application 223 by the plugin mechanism of the generative AI application 223.

[0068] The Plugin application 226 is configured by an application manifest or the like including an explanation of the application in a natural language. Figs. 5A and 5B illustrate implementation examples of the application manifest of the Plugin application 226 in the present embodiment. The application manifest describes that the Plugin application 226 is an application having a skill to provide the log or the task rule of the printer 160. The application manifest also describes a command for invoking an integration target web service and a parameter used when the web service is invoked.

[0069] By the processing which will be described below with reference to Figs. 6A and 6B, a plugin having a skill appropriate for generation of a reply to the input of the user based on this application manifest content is selected, and a command is executed.

[0070] It is noted that as processing of fixing a Wi-Fi problem of the present embodiment, restart of the printer, restart of the Wi-Fi router, checking of the Wi-Fi connection status, re-setup of the printer driver, and the like are described in the task rule.

[0071] The following description is provided with reference to Fig. 2 again. The AI orchestrator 227 is an element configuring the agent 222 and operates in the background to perform business logic control such as selection and execution of a plugin appropriate for generation of a reply during a period from a natural language input by the user until a natural language output (reply).

[0072] The user data layer 228 saves data of the user and provides a unit configured to access the data. The user data is information linked to a login account of the user and includes, for example, an electronic mail (e-mail) address and calendar information of the user, a team to which the user belongs, a colleague, a file that can be accessed, or the like. The AI foundation model 229 is configured by a generative AI model such as a large language model (LLM). The AI infrastructure 230 performs setting and management of a cloud or a graphics processing unit (GPU) equivalent to an infrastructure of the generative AI cloud.

[0073] Next, an example of a software configuration of the client computer 140 is illustrated. It is noted that with regard to each software, each function is realized by the control of the CPU 101 of the client computer 140. In addition, each module configuring the client computer 140 is saved and managed in the external memory 110. These modules are program modules which are loaded upon execution into the RAM 102 by a module using the OS or the module and which are then executed.

[0074] A network module 240 performs network communication with the generative AI cloud 120 and the printer 160 by using any communication protocol. The printer driver 241 generates a print job and sends the print job to the printer 160 via the network module 240.

[0075] The printer driver 241 receives a print job execution result of the printer 160 via the network module 240, and the received result is displayed on the display 109 of the client computer 140.

[0076] The generative AI client application 242 sends an HTTP request message to the generative AI cloud 120 via the network module 240 and receives an HTTP response message from the generative AI cloud 120. The HTTP response message received by the generative AI client application 242 is displayed on the display 109 of the client computer 140. An access from the client computer 140 to the generative AI cloud 120 is performed through the generative AI client application 242.

[0077] Subsequently, an example of a software configuration of the printer 160 is illustrated. It is noted that with regard to each software of the printer 160, each function is realized by the control of the CPU 163 of the printer 160.

[0078] In addition, in the printer 160, various types of modules are saved in and managed by the ROM 165 or the external memory 171 and loaded into the RAM 164 upon execution to be then executed.

[0079] An I / F module 260 communicates with the device management cloud 100 and the client computer 140 based on any communication protocol by using a universal serial bus (USB) module 261 or a network module 262. The USB module 261 directly connects to the client computer 140 to perform communication. The network module 262 connects to the network 180 to perform network communication.

[0080] The printer 160 supports connection methods of any one of a USB connection via the USB module 261 or a network connection via the network module 262 and is capable of switching the connection method based on a device setting.

[0081] A print module 263 receives a print job sent from the printer driver 241 of the client computer 140 via the I / F module 260 and executes the print job. In addition, the print module 263 creates a log of the print job execution result and saves the log in a device management module 264.

[0082] The device management module 264 manages device information of the printer 160. The device management module 264 receives a request to obtain information of the device from the device management module 204 of the device management cloud 100 via the network module 262 and returns the information of the device. In addition, the device management module 264 receives a request to obtain a log from the device management module 204 of the device management cloud 100 via the network module 262 and returns the log of the job execution result. A UI module 265 performs rendering of a UI displayed on the operation unit 167 of the printer 160 and reception of a user input value input by a UI operation of the user on the operation unit 167.

[0083] Next, with reference to Figs. 6A and 6B, an example of processing will be described up to a point where the generative AI cloud 120 performs fact verification on a prompt input by the user for explaining a problem situation related to the printer 160 and points out a contradiction between the prompt and facts to urge the user to perform a check and a correction of the explanation. Additionally, a screen display example of the generative AI client application 242 to be displayed to the user is illustrated with reference to Fig. 7. The screen of Fig. 7 is an example of the screen generated by the generative AI client application 242 controlled by the CPU 101 of the client computer 140 and is displayed on the display 109.

[0084] It is noted that a configuration may be adopted in which this screen is displayed on the operation unit 167 of the printer 160.

[0085] In this case, a reply generated by the language model through the following processing is displayed on the operation unit 167 of the printer 160. In addition, the present processing is started by using, as a trigger, the input of the prompt for explaining the problem situation related to the printer 160 by the user on the generative AI client application 242.

[0086] It is noted that each of the software 220 to 230 operates by being executed by the CPU 101 of the generative AI cloud 120. In addition, each of the software 200 to 205 of the device management cloud 100 operates by being executed by the CPU 101 of the device management cloud 100.

[0087] In S600, the front-end application 224 of the generative AI application 223 operating on the generative AI cloud 120 receives a prompt from the generative AI client application 242 operating on the client computer 140. It is noted that the prompt herein refers to an instruction sentence input by the user by using a natural language on the generative AI client application 242. In other words, the front-end application 224 accepts a prompt in a natural language from the user.

[0088] In the present embodiment, troubleshooting of the Wi-Fi connection related to the printer 160 will be described. For this reason, in the present embodiment, an example in which the user inputs a prompt including a character string for explaining the situation of the problem that has occurred in the printer 160 is exemplified to be described. It is noted that the input prompt for explaining the situation of the problem related to the printer 160 is not limited to the Wi-Fi connection as described in the present embodiment and may be other content.

[0089] It is noted that the prompt that is to be input by the user may be a character string of contextual information for explaining the situation of the problem that has occurred, a character string of contextual information for asking a question such as, for example, "How can I do to deal with what?", or a character string of contextual information for issuing an instruction such as "Please provide a solution for what". In any contextual information, it may be regarded that a behavior of the user who inputs a prompt to demand a reply from the generative AI is to request a presentation of information.

[0090] In the screen display example of Fig. 7, a login user name 700 is displayed, and content of the prompt input by the user is displayed in a prompt area 701. It is noted that the user can issue an instruction to input (send) a prompt into the generative AI by inputting a character string (prompt) in an input field which is not illustrated in the drawing by using, for example, a keyboard or the like, and selecting a send button (object) which is not illustrated in the drawing.

[0091] In S601, the front-end application 224 performs checks on the prompt input in S600 from perspectives such as fairness, reliability, safety, privacy, security, inclusiveness, transparency, and accountability. In a case where any of the prompt checks fails, a conversation is ended to end the present processing. It is noted that at this time, for example, a warning message such as "Conversation is to be ended because the check has failed" or "Prompt is not appropriate" may be displayed. When the prompt check by the front-end application 224 succeeds, the flow proceeds to S602.

[0092] In S602, the AI orchestrator 227 adjusts the prompt based on an operation method of the agent 222 defined in the agent manifest. It is noted that in the case of the present embodiment, based on the agent manifest description content of Fig. 4, the prompt is adjusted to point out a contradiction between the prompt input by the user for explaining the problem situation and facts based on the log of the printer 160 and the task rule of the troubleshooting.

[0093] In S603, the AI orchestrator 227 obtains context. The context herein is information that indicates contextual information, a background, a situation, or the like associated with the conversation of the user. An example of the context obtained herein includes information related to the conversation with the generative AI and the activity of the user in the past which are used to provide a response and a suggestion that are personalized based on needs and preferences of the user, or the like.

[0094] In S604, the AI orchestrator 227 updates the context based on the user data obtained from the user data layer 228. The user data obtained herein also includes the user, an activity of the user, and information related to a relationship among data within an organization to which the user belongs, such as, for example, an e-mail or a chat of the user in the past, a document handled by the user, information of a meeting attended by the user, or the like. In addition, the update refers to processing of performing addition of new information to the obtained context, sorting of the obtained context, both the addition and the sorting, or the like.

[0095] The AI orchestrator 227 adjusts the prompt based on the updated context and inputs the adjusted prompt to the LLM of the AI foundation model 229. The adjustment of the prompt herein is, for example, removal of a no good (NG) word or editing of the prompt so as to be contextual information that is easier for the LLM to interpret, and this adjustment is not mandatory processing.

[0096] When the AI orchestrator 227 receives the response (output) from the LLM, to obtain additional data, the flow proceeds to processing in S605.

[0097] In S605, the AI orchestrator 227 requests the Plugin application 226 to obtain Plugin information.

[0098] In S640, the Plugin application 226 receives the Plugin information obtaining request from the AI orchestrator 227. In S641, the Plugin application 226 returns Plugin information including the application manifest to the AI orchestrator 227.

[0099] In S606, the AI orchestrator 227 receives the Plugin information returned from the Plugin application 226. With this configuration, the AI orchestrator 227 obtains the Plugin information.

[0100] In S607, the AI orchestrator 227 determines whether or not the Plugin application 226 is invoked to obtain a log of the printer 160 based on the explanations of the application and the command described in the application manifest of the Plugin application 226. The AI orchestrator 227 may carry out the determination by making a query to the LLM of the AI foundation model 229, for example, and searching for the Plugin application 226 that is appropriate for the reply based on the explanations of the application and the command described in the application manifest. The explanations of the application and the command described in the application manifest herein are about the Plugin application 226.

[0101] In a case where the AI orchestrator 227 determines that the Plugin application 226 is invoked, the flow proceeds to S608, and in a case where the Plugin application 226 is not invoked, the flow proceeds to S612.

[0102] It is noted that in the case of the present embodiment, it is assumed that to obtain the log of the printer 160 and point out a contradiction between the input prompt and facts, the Plugin application 226 having the management function of the printer 160 is invoked.

[0103] The AI orchestrator 227 may perform control other than the above-described configuration such that the Plugin application 226 having the management function of the printer 160 is invoked with certainty. For example, the AI orchestrator 227 may regularly invoke the Plugin application 226 each time. In addition to the above, for example, in a case where the AI orchestrator 227 is communicable with the printer 160 via a network, a configuration may be adopted in which information stored in the printer 160 is directly obtained without invoking various types of applications.

[0104] In S608, the AI orchestrator 227 generates a new prompt including the prompt input by the user, the updated context, and the information of the Plugin application 226 and inputs the prompt to the LLM of the AI foundation model 229. The AI orchestrator 227 obtains a function and a parameter for invoking the web service declared in the Plugin application 226 based on a response from the LLM to the input information.

[0105] In S609, the AI orchestrator 227 invokes the web service declared by the Plugin application 226 by using the function and the parameter obtained in S608. In the screen display example of Fig. 7, an explanation about invoking the web service declared by the Plugin application 226 to the user and a request to grant a permission in S609 are displayed in the prompt area 701 as a reply from the generative AI in a natural language.

[0106] In response to this, the user can send a reply from among selection objects including "allow always", "allow once", and "cancel". In the present embodiment, the description continues where the user selects "allow always" or "allow once". It is noted that a configuration may be adopted where the processing ends in a case where the user selects "cancel".

[0107] In S660, the device management application 202 of the device management cloud 100 receives a log obtaining request through the invocation of the web service. In S661, the device management application 202 obtains the log of the printer 160 retained in the database server service module 205 via the device management module 204. In the present embodiment, the device management application 202 specifies the target printer 160 from the device management table 300 and obtains each of logs from the job log management table 301, the operational log management table 302, and the sensor log management table 303.

[0108] It is noted that a method of obtaining the log of the printer 160 does not necessarily have to be via the cloud and may be a method of causing the generative AI client application 242 to upload the log obtained by the user from the printer 160 when the prompt is input, for example. In addition, the target log to be obtained is not limited to a log retained in the printer 160 and may be a log of a device such as, for example, a PC serving as a communication destination of the printer 160, a server, or a smartphone. The device management application 202 may additionally obtain these logs.

[0109] In S662, the device management application 202 returns (sends) the log of the printer 160 which has been obtained in S661 to the AI orchestrator 227. In S610, the AI orchestrator 227 receives the log returned from the device management cloud 100. In S611, the AI orchestrator 227 integrates the log received in S610 into the context.

[0110] In S612, the AI orchestrator 227 determines whether or not the Plugin application 226 is invoked to obtain the task rule based on the explanations of the application and the command described in the application manifest of the Plugin application 226. The AI orchestrator 227 may carry out the determination by making a query to the LLM of the AI foundation model 229, for example, and searching for the Plugin application 226 that is appropriate for the reply based on the explanations of the application and the command described in the application manifest. The explanations of the application and the command described in the application manifest herein are about the Plugin application 226.

[0111] In a case where the AI orchestrator 227 determines that the Plugin application 226 is invoked, the flow proceeds to S613, and in a case where the AI orchestrator 227 determines that the Plugin application 226 is not invoked, the flow proceeds to S617.

[0112] It is noted that in the case of the present embodiment, it is assumed that the Plugin application 226 having the management function of the printer 160 is invoked to obtain the task rule and check for an omission, an oversight, or the like in the input prompt. The AI orchestrator 227 may perform control other than the above-described control such that the Plugin application 226 having the management function of the printer 160 is invoked with certainty.

[0113] In S613, the AI orchestrator 227 generates a new prompt including the prompt input by the user, the updated context, and the information of the Plugin application 226 and sends (inputs) the prompt to the LLM of the AI foundation model 229. The AI orchestrator 227 obtains a function and a parameter for invoking the web service declared by the Plugin application 226 based on a response from the LLM.

[0114] In S614, the AI orchestrator 227 invokes the web service declared by the Plugin application 226 by using the function and the parameter obtained in S613. In the screen display example of Fig. 7, an explanation about invoking the web service declared by the Plugin application 226 to the user and permission acquisition in S614 are displayed in the prompt area 701 as a reply from the generative AI in a natural language.

[0115] In response to this, the user can send a reply from among selection objects including "allow always", "allow once", and "cancel". In the present embodiment, the description continues where the user selects "allow always" or "allow once". It is noted that a configuration may be adopted where the processing ends in a case where the user selects "cancel".

[0116] It is noted that in the example of Fig. 7, the example in which the explanation and the permission acquisition in these S614 and S609 are displayed at once is illustrated but is not limited to this. That is, a configuration may be adopted in which in the respective steps, granting a permission to the log search and searching for the task rule are separately explained to and confirmed with the user.

[0117] In S663, the device management application 202 of the device management cloud 100 receives a task rule obtaining request through the web service invocation. In S664, the device management application 202 obtains the task rule that describes the character string representing the method of fixing the problem of the printer 160 which is retained in the database server service module 205 via the device management module 204. In the present embodiment, the device management application 202 obtains the task rule from the troubleshooting task rule management table 304.

[0118] In S665, the device management application 202 returns (sends) the task rule of the troubleshooting of the printer 160 which has been obtained in S664 to the AI orchestrator 227. In S615, the AI orchestrator 227 receives the task rule returned from the device management cloud 100.

[0119] In S616, the AI orchestrator 227 integrates the task rule received in S615 into the context.

[0120] In S617, the AI orchestrator 227 determines whether or not generation of a response (reply) is appropriate. In a case where the AI orchestrator 227 determines that generation of a response is appropriate, the flow proceeds to S618, and in a case where the AI orchestrator 227 determines that generation of a response is not appropriate, the flow returns to S604. That is, in a case where the AI orchestrator 227 determines that generation of a response is not appropriate, by repeating necessary processing in S604 to S616, an inference based on the LLM is continuously repeated until it is determined in S617 that generation of a response is appropriate.

[0121] In S618, the AI orchestrator 227 sends (inputs) all the information collected in the above-described processing to the LLM of the AI foundation model 229 to generate a response. It is noted that input of all the information collected in the above-described processing to the LLM is not mandatory, and when information that is not necessary for the generation of the response exists, it is not necessary to input the information to the LLM.

[0122] The AI orchestrator 227 performs checks on the generated response from perspectives such as fairness, reliability, safety, privacy, security, inclusiveness, transparency, and accountability.

[0123] In S619, the AI orchestrator 227 returns the response to the front-end application 224. The front-end application 224 returns the response to the generative AI client application 242 operating on the client computer 140. As a result, the response (reply) is displayed on the generative AI client application 242.

[0124] It is noted that the response is a method of fixing a problem which is generated in accordance with content of the problem, and because the content widely varies, the description using the drawing is omitted. For example, the response (reply) includes a general problem fixing method to deal with a problem, such as "Please perform operation X", "Please press button X", "Please check connection status of X", or the like. The problem is fixed when the user performs the operation following the displayed problem fixing method.

[0125] In the screen display example of Fig. 7, information indicating that it can also be confirmed based on the obtained logs that a print success record exists up to three days ago and restart of the printer 160 and check on the Wi-Fi connection status have been implemented is displayed in a natural language in the prompt area 701 as a reply from the generative AI.

[0126] On the other hand, with regard to the presence or absence of restart implementation of the Wi-Fi router and the presence or absence of re-setup implementation of the printer driver which are included in the obtained task rules, the generative AI application 223 does not confirm the implementation status based on the input prompt of the user and the logs.

[0127] For this reason, Fig. 7 illustrates an example in which the AI orchestrator 227 determines in S617 that the current state is not appropriate for generation of a response. The flow then returns to S604, and it is attempted to obtain additional information by making a query to the user on the prompt area 701.

[0128] Herein, a query display to the user to ask whether or not a predetermined operation has been performed is displayed on the generative AI application 223. A character string "Have you tried restarting the Wi-Fi router?" in Fig. 7 is equivalent to this query. It is noted that displayed content is not limited to this, and a configuration may be adopted in which, for example, a query display to ask what operation has been performed such as "What operation have you performed?" is displayed.

[0129] When these query displays are displayed, the user provides additional information in response. In Fig. 7, a character string "Yes, but it has failed." or a character string "No, I have not tried it yet." is equivalent to the additional information. When the query is displayed, the user inputs these character strings as prompts. It is noted that when the user inputs this prompt in the input field which is not illustrated in the drawing, the additional information associated with the information processing apparatus is accepted.

[0130] As a result of the exchange with the user on the prompt area 701, the AI orchestrator 227 can confirm that restart of the Wi-Fi router has been implemented, and re-setup of the printer driver has not been implemented. When this is confirmed, in S617, the AI orchestrator 227 determines that generation of a response can be performed.

[0131] In addition, by using the response by the AI orchestrator 227 in S618 as a generation result, a result of fact-checking performed on the user input prompt on the prompt area 701 is displayed in a natural language in Fig. 7. Herein, information is displayed indicating that it can be confirmed based on the logs that the print success record up to three days ago exists and restart of the printer 160 and check on the Wi-Fi connection status have been implemented, and restart of the Wi-Fi router which is included in the task rule has been also implemented. On the other hand, information indicating that re-setup of the printer driver which is included in the task rule is not implemented is displayed.

[0132] Furthermore, the prompt input by the user includes that the problem is not fixed by hitting the casing, but the LLM determines that this information does not comply with the task rule and does not contribute to fixing the problem, and this information is excluded from a fact-checking result.

[0133] It is noted that only tasks that have been fact-checked are displayed on the prompt area 701 in the example of Fig. 7, but for example, tasks that have been fact-checked and tasks that have not been fact-checked may be displayed in a distinguished manner. In addition, it may be displayed that tasks that do not comply with the task rule do not contribute to fixing the problem and do not necessarily need to be performed, and it may be possible to configure which to prioritize in a case where the fact-checking based on the logs contradicts the information claimed by the user and switch whether or not the fact-checking is to be implemented.

[0134] Finally, in S620, the front-end application 224 determines whether or not the conversation is ended, and in a case where the front-end application 224 determines based on the user input or the like that the conversation continues (S620: Yes), the flow returns to S600. In a case where the front-end application 224 determines that the conversation ends, the processing is ended.

[0135] By the above-described processing, in response to the prompt for requesting the presentation of the method of fixing the problem, the generative AI cloud 120 makes a query to ask for additional information based on the logs indicating the operation history of the apparatus and the task rules for fixing the problem and urges the user to check and correct the explanation. In addition, in a case where the operation history revealed by the logs contradicts the reply content by the user, it is possible to ask the user about the contradiction.

[0136] As a result, the generative AI can specify the cause of the problem based on the sufficient information and provide the reply regarding the method of fixing the problem. That is, the likelihood of obtaining the effective reply from the generative AI is improved.Second Embodiment

[0137] In the first embodiment, the example has been illustrated in which in response to the prompt for explaining the problem situation which is input by the user of the printer 160 to request the presentation of the method of fixing the problem, the generative AI cloud 120 asks for the additional information and urges the user to check and correct the explanation.

[0138] The present technique is not limited to the above-described example and is also applicable to a case where after a service technician of a multifunction peripheral (MFP) performs troubleshooting of the MFP, for example, the generative AI cloud 120 is used to create a task record.

[0139] In view of the above, in the present embodiment, an example is illustrated in which in response to a prompt for explaining task content input by the service technician of the MFP, the generative AI cloud 120 points out a contradiction between the prompt and facts and urges the service technician to check and correct the explanation. It is noted that a difference from the first embodiment will be mainly described.

[0140] Fig. 8 is a block diagram for describing examples of a system configuration and a hardware configuration of the support system of the present embodiment.

[0141] The support system is configured by including the device management cloud 100, the generative AI cloud 120, the client computer 140, and an MFP 800 which are connected by the network 180.

[0142] In the MFP 800, a scanner I / F 801 receives an image signal (example of input information) from a scanner 802 (scanner engine). The hardware configuration other than the scanner I / F 801 is similar to the hardware configuration of the printer 160 in Fig. 1 of the first embodiment, and the description thereof is omitted. The system configuration and the hardware configuration other than the MFP 800 are similar to those of Fig. 1 of the first embodiment, and the descriptions thereof are omitted.

[0143] Fig. 9 is a block diagram for describing an example of a software configuration of the support system of the present embodiment.

[0144] In the MFP 800, a scan sending module 900 receives a scan instruction from the user via the UI module 265 and generates and executes a scan job and a scan data sending job. Herein, to send the scan data, for example, a communication protocol such as an e-mail or Server Message Block (SMB) is used. In addition, the scan sending module 900 creates logs of the scan job and a sending job execution result and saves the logs in the device management module 264.

[0145] A FAX module 901 receives FAX jobs sent from a FAX apparatus, an MFP, and the like which are not illustrated in the drawing via the network module 262. A FAX reception job received here is subjected to print execution via the print module 263 or transfer to another FAX apparatus, MFP, or the like via the network module 262. The FAX module 901 also receives a FAX sending instruction from the user via the UI module 265 and generates and executes the FAX sending instruction. In addition, the FAX module 901 creates logs of execution results of the FAX reception job and the FAX sending job and saves the logs in the device management module 264.

[0146] The software configuration of the MFP 800 other than the FAX module 901 is similar to the software configuration of the printer 160 in Fig. 2 according to the first embodiment, and the description thereof is omitted. The software configurations other than the MFP 800 are similar to those illustrated in Fig. 2 according to the first embodiment, and the descriptions thereof are omitted.

[0147] Figs. 10A to 10E illustrate examples of table configurations in the database server service module 205 according to the present embodiment. The table configurations of Figs. 10A to 10E are similar to those illustrated in Figs. 3A to 3E according to the first embodiment, and the descriptions thereof are omitted, but data corresponding to the present embodiment is retained in each table. It is noted that the table configurations of Figs. 10A to 10E are merely examples and may be table configurations different from the present examples.

[0148] The device management table 300 retains device information related to the MFP 800, and the job log management table 301 retains a job such as copying that can be executed by the MFP 800. The operational log management table 302 retains operation logs such as drum replacement and automatic gradation correction which are operated in the MFP 800. The sensor log management table 303 retains a sensor log such as a drum life warning that can be obtained from the MFP 800. The troubleshooting task rule management table 304 retains rules such as checking an image quality using a copy test, checking the drum life, replacing a drum unit, cleaning an automatic document feeder (ADF) and the casing as the task rules recommended in the troubleshooting of the MFP 800.

[0149] Fig. 11 illustrates an implementation example of the agent manifest of the agent 222 in the present embodiment. This manifest describes that the agent 222 is an agent for a purpose of assisting task recording which is configured to point out a contradiction between a claim by a service technician and facts based on the log of the MFP 800 and the task rule representing a method of fixing the problem and to urge the service technician to check and correct the claim.

[0150] Fig. 12 illustrates a screen display example of the generative AI client application 242 displayed to the service technician. The screen of Fig. 12 is displayed on the generative AI client application 242 operating on the client computer 140. In the present embodiment, it is assumed that after repair of a device is completed by performing the procedures of the first embodiment or the like at a customer site, for example, the service technician uses this application once to record the repair.

[0151] It is noted that the processing for the generative AI cloud 120 to perform fact-checking of the prompt for explaining the troubleshooting task content related to the MFP 800, check additional information, and point out a contradiction to the facts is similar to the processing of Figs. 6A and 6B according to the first embodiment, and the description thereof is omitted.

[0152] In S600, the front-end application 224 of the generative AI application 223 operating on the generative AI cloud 120 receives a prompt from the generative AI client application 242 operating on the client computer 140. In the present embodiment, an example is used to describe a case where after the service technician completes a task of replacing the drum unit of the MFP 800, a prompt for requesting creation of a task record is input.

[0153] It is noted that the input prompt for requesting creation of a task record is not limited to the example of Fig. 12. In the screen display example of Fig. 12, the login user name 700 is displayed, and content of the prompt input by the service technician is displayed in the prompt area 701.

[0154] In S609, the AI orchestrator 227 invokes the web service declared by the Plugin application 226 by using the function and the parameter which are obtained in S608. In the screen display example of Fig. 12, the explanation about invoking the web service declared by the Plugin application 226 to the service technician and the permission acquisition in S609 are displayed in the prompt area 701 as a reply from the generative AI in a natural language.

[0155] In S614, the AI orchestrator 227 invokes the web service declared by the Plugin application 226 by using the function and the parameter which are obtained in S613. In the screen display example of Fig. 12, the explanation about invoking the web service declared by the Plugin application 226 to the service technician and the permission acquisition in S614 are displayed in the prompt area 701 as a reply from the generative AI in a natural language.

[0156] It is noted that in the example of Fig. 12, the example in which the explanation and the permission acquisition in these S614 and S609 are displayed at once is illustrated but is not limited to this. That is, a configuration may be adopted in which in the respective steps, granting a permission to the log search and searching for the task rule are separately explained to and confirmed with the user.

[0157] In S619, the AI orchestrator 227 returns the response to the front-end application 224. The front-end application 224 returns the response to the generative AI client application 242 operating on the client computer 140. As a result, the response is displayed in the generative AI client application 242.

[0158] In the screen display example of Fig. 12, information indicating that it can also be confirmed based on the obtained logs that the drum life warning is sensed and that the copy test, the drum replacement, and the automatic gradation correction have been implemented is displayed in the prompt area 701 as a reply from the generative AI in a natural language. On the other hand, with regard to the cleaning of the ADF and the casing, the generative AI application 223 does not confirm the implementation status based on the input prompt by the service technician and the logs. Fig. 12 illustrates an example in which for this reason, the AI orchestrator 227 determines in S617 that the current state is not appropriate for generation of a response, and the flow returns to S604 to attempt to obtain additional information by making a query to the service technician on the prompt area 701.

[0159] As a result of the exchange with the user on the prompt area 701, the AI orchestrator 227 can confirm that the cleaning of the ADF and the casing has also been implemented. At the timing at which this state is confirmed, the AI orchestrator 227 can determine in S617 that a response can be generated.

[0160] In Fig. 12, as a result of the response by the AI orchestrator 227 in S618, a result of the fact-checking performed on the user input prompt on the prompt area 701 is displayed in a natural language. Here, information indicating that the drum life warning is sensed, the copy test, the drum replacement, and the automatic gradation correction have been implemented, and the cleaning of the ADF and the casing included in the task rule has also been implemented is displayed.

[0161] By the above-described processing, in response to the prompt for explaining the troubleshooting task content which is input by the service technician of the MFP, the generative AI cloud 120 makes a query to ask for additional information and points out a contradiction with the facts to urge the service technician to check and correct the explanation. As a result, it is possible to reduce the likelihood of producing a contradiction between the troubleshooting task content input by the service technician into the generative AI and facts, and the likelihood of obtaining more accurate task records from the generative AI can be increased.Other Embodiments

[0162] The present disclosure can also be realized by processing in which a program for realizing one or more functions of the above-described embodiments is supplied to a system or an apparatus via a network or a storage medium, and one or more processors in a computer in the system or the apparatus read out and execute the program. In addition, the present disclosure can also be realized by a circuit (for example, an application-specific integrated circuit (ASIC)) configured to realize one or more functions.

[0163] Embodiment(s) of the present disclosure can also be realized by a computer of a system or apparatus that reads out and executes computer executable instructions (e.g., one or more programs) recorded on a storage medium (which may also be referred to more fully as a 'non-transitory computer-readable storage medium') to perform the functions of one or more of the above-described embodiment(s) and / or that includes one or more circuits (e.g., application specific integrated circuit (ASIC)) for performing the functions of one or more of the above-described embodiment(s), and by a method performed by the computer of the system or apparatus by, for example, reading out and executing the computer executable instructions from the storage medium to perform the functions of one or more of the above-described embodiment(s) and / or controlling the one or more circuits to perform the functions of one or more of the above-described embodiment(s). The computer may comprise one or more processors (e.g., central processing unit (CPU), micro processing unit (MPU)) and may include a network of separate computers or separate processors to read out and execute the computer executable instructions. The computer executable instructions may be provided to the computer, for example, from a network or the storage medium. The storage medium may include, for example, one or more of a hard disk, a random-access memory (RAM), a read only memory (ROM), a storage of distributed computing systems, an optical disk (such as a compact disc (CD), digital versatile disc (DVD), or Blu-ray Disc (BD)TM), a flash memory device, a memory card, and the like.

[0164] While the present disclosure has been described with reference to embodiments, it is to be understood that the present disclosure is not limited to the disclosed embodiments. The scope of the following claims is to be accorded the broadest interpretation so as to encompass all such modifications and equivalent structures and functions.

[0165] This application claims the benefit of Japanese Patent Application No. 2025-050808, filed March 25, 2025, which is hereby incorporated by reference herein in its entirety.

Claims

1. A program for causing a computer to execute: accepting a prompt to request a presentation of a fixing method for a problem of an information processing apparatus from a user; obtaining information representing an operation history of the information processing apparatus; and displaying a display for making a query to the user to request additional information associated with the information processing apparatus that is additional information used for a reply regarding the fixing method, wherein the accepting includes further accepting the additional information input by the user, and the displaying includes displaying the reply generated based on the information representing the operation history and the additional information.

2. The program according to claim 1, wherein the obtaining includes further obtaining information representing an operation method of the information processing apparatus.

3. The program according to claim 2, wherein the displaying includes displaying the display for making a query to the user to request additional information used for the reply regarding the fixing method based on the information representing the operation history and the information representing the operation method.

4. The program according to claim 3, wherein the information representing the operation method is a character string representing a method of fixing the problem.

5. The program according to claim 1, wherein the obtaining includes obtaining the information representing the operation history from the information processing apparatus.

6. The program according to claim 1, wherein the prompt to request the presentation of the fixing method for the problem is a prompt including a character string for explaining a situation of the problem that has occurred in the information processing apparatus.

7. The program according to claim 1, wherein the additional information is information representing an operation by the user, the operation not being able to be represented by the information representing the operation history of the information processing apparatus which is obtained in the obtaining.

8. The program according to claim 1, wherein the display to make the query to the user is a display to make a query to ask whether or not a predetermined operation has been performed.

9. The program according to claim 1, wherein the display to make the query to the user is a display to make a query to ask what operation has been performed.

10. The program according to claim 1, wherein the additional information is accepted in the accepting when the user inputs the prompt.

11. The program according to claim 1, wherein the obtaining includes further obtaining information representing an operation history of an apparatus with which the information processing apparatus communicates.

12. The program according to claim 1, wherein the reply is generated by a generative artificial intelligence, AI.

13. An information processing method comprising: accepting a prompt to request a presentation of a fixing method for a problem of an information processing apparatus from a user; obtaining information representing an operation history of the information processing apparatus; and displaying a display for making a query to the user to request additional information associated with the information processing apparatus that is additional information used for a reply regarding the fixing method, wherein the accepting includes further accepting the additional information input by the user, and the displaying includes displaying the reply generated based on the information representing the operation history and the additional information.

14. The information processing method according to claim 13, wherein the obtaining includes further obtaining information representing an operation method of the information processing apparatus.

15. The information processing method according to claim 14, wherein the displaying includes displaying the display for making a query to the user to request additional information used for the reply regarding the fixing method based on the information representing the operation history and the information representing the operation method.

16. The information processing method according to claim 15, wherein the information representing the operation method is a character string representing a method of fixing the problem.

17. The information processing method according to claim 13, wherein the obtaining includes obtaining the information representing the operation history from the information processing apparatus.

18. The information processing method according to claim 13, wherein the prompt to request the presentation of the fixing method for the problem is a prompt including a character string for explaining a situation of the problem that has occurred in the information processing apparatus.

19. The information processing method according to claim 13, wherein the additional information is information representing an operation by the user, the operation not being able to be represented by the information representing the operation history of the information processing apparatus which is obtained in the obtaining.

20. The information processing method according to claim 13, wherein the display to make the query to the user is a display to make a query to ask whether or not a predetermined operation has been performed.

21. The information processing method according to claim 13, wherein the display to make the query to the user is a display to make a query to ask what operation has been performed.

22. The information processing method according to claim 13, wherein the additional information is accepted in the accepting when the user inputs the prompt.

23. The information processing method according to claim 13, wherein the obtaining includes further obtaining information representing an operation history of an apparatus with which the information processing apparatus communicates.

24. The information processing method according to claim 13, wherein the reply is generated by a generative artificial intelligence, AI.

25. An information processing apparatus comprising: an acceptance unit configured to accept a prompt to request a presentation of a fixing method for a problem of an apparatus from a user; an obtaining unit configured to obtain information representing an operation history of the apparatus; and a display unit configured to display a display for making a query to the user to request additional information associated with the apparatus that is additional information used for a reply regarding the fixing method, wherein the acceptance unit further accepts the additional information input by the user, and the display unit displays the reply generated based on the information representing the operation history and the additional information.

26. A non-transitory storage medium storing a program for causing a computer to execute: accepting a prompt to request a presentation of a fixing method for a problem of an information processing apparatus from a user; obtaining information representing an operation history of the information processing apparatus; and displaying a display for making a query to the user to request additional information associated with the information processing apparatus that is additional information used for a reply regarding the fixing method, wherein the accepting includes further accepting the additional information input by the user, and the displaying includes displaying the reply generated based on the information representing the operation history and the additional information.

27. The storage medium according to claim 26, wherein the obtaining includes further obtaining information representing an operation method of the information processing apparatus.

28. The storage medium according to claim 27, wherein the displaying includes displaying the display for making a query to the user to request additional information used for the reply regarding the fixing method based on the information representing the operation history and the information representing the operation method.

29. The storage medium according to claim 28, wherein the information representing the operation method is a character string representing a method of fixing the problem.

30. The storage medium according to claim 26, wherein the obtaining includes obtaining the information representing the operation history from the information processing apparatus.

31. The storage medium according to claim 26, wherein the prompt to request the presentation of the fixing method for the problem is a prompt including a character string for explaining a situation of the problem that has occurred in the information processing apparatus.

32. The storage medium according to claim 26, wherein the additional information is information representing an operation by the user, the operation not being able to be represented by the information representing the operation history of the information processing apparatus which is obtained in the obtaining.

33. The storage medium according to claim 26, wherein the display to make the query to the user is a display to make a query to ask whether or not a predetermined operation has been performed.

34. The storage medium according to claim 26, wherein the display to make the query to the user is a display to make a query to ask what operation has been performed.

35. The storage medium according to claim 26, wherein the additional information is accepted in the accepting when the user inputs the prompt.

36. The storage medium according to claim 26, wherein the obtaining includes further obtaining information representing an operation history of an apparatus with which the information processing apparatus communicates.

37. The storage medium according to claim 26, wherein the reply is generated by a generative artificial intelligence, AI.

Images