Terminal, control method of terminal, and program

Abstract

To provide a terminal that enables a user to easily learn how to use an application installed on a smartphone or the like.SOLUTION: A terminal comprises acquisition means and control means. The acquisition means acquires an operation history of each of a plurality of applications installed on an own device. The control means generates a prompt to be input into a language model by using the operation history of an application selected from the plurality of applications as an application for which usage instructions are requested by a user. The control means presents the user with the instructions on how to use the selected application obtained from the language model by using the generated prompt.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a terminal, a terminal control method, and a program. [Background technology]

[0002] There are technologies that provide support for using programs (applications) installed on personal computers and the like.

[0003] For example, Patent Document 1 describes a support data display system that can present appropriate support information, particularly to users who are not familiar with using programs. The system in Patent Document 1 pre-stores support data corresponding to each of multiple error information that occurs during program operation, and stores the program's startup history when the program is launched. When the program starts, the system counts the number of occurrences of each error information. Furthermore, when displaying support data, the system selects and displays support data corresponding to the error information from the error information corresponding to the most recently launched program in descending order of the number of errors that occurred. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2006-285820 Summary of the Invention [Problem to be solved by the invention]

[0005] A wide variety of applications are installed on devices such as smartphones. Because so many applications are installed on devices, even users who are accustomed to using smartphones may not know how to use the applications. In such cases, users can refer to the application's instruction manual, but it can be difficult to identify the required item from the many items listed in the instruction manual.

[0006] The main object of the present invention is to provide a terminal, a terminal control method, and a program that contribute to enabling users to easily learn how to use applications installed on smartphones and the like. [Means for solving the problem]

[0007] According to a first aspect of the present invention, there is provided a terminal comprising: an acquisition means for acquiring an operation history of each of a plurality of applications installed on the terminal; and a control means for generating a prompt to be input into a language model using the operation history of an application selected from the plurality of applications as an application for which a user requests instructions on how to use the application, and presenting to the user an explanation on how to use the selected application obtained from the language model using the generated prompt.

[0008] According to a second aspect of the present invention, there is provided a method for controlling a terminal, comprising: an acquisition step of acquiring operation history of each of a plurality of applications installed on the terminal; and a control step of generating a prompt to be input into a language model using the operation history of an application selected from the plurality of applications as an application for which a user requests instructions on how to use the application, and presenting to the user an explanation on how to use the selected application obtained from the language model using the generated prompt.

[0009] According to a third aspect of the present invention, there is provided a program for causing a computer mounted on a terminal to execute an acquisition process for acquiring operation history of each of a plurality of applications installed on the terminal, and a control process for generating a prompt to be input into a language model using the operation history of an application selected from the plurality of applications as an application for which a user requests instructions on how to use the application, and presenting to the user an explanation on how to use the selected application obtained from the language model using the generated prompt. [Effects of the Invention]

[0010] According to each aspect of the present invention, a terminal, a terminal control method, and a program are provided that contribute to enabling a user to easily learn how to use an application installed on a smartphone or the like. Note that the effects of the present invention are not limited to those described above. The present invention may achieve other effects instead of or in addition to the effects described above. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram for explaining an outline of an embodiment. [Figure 2] FIG. 2 is a flowchart for explaining an outline of the operation of one embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of a schematic configuration of an information processing system according to an embodiment of the present disclosure. [Figure 4] FIG. 4 is a diagram illustrating an example of a display on a terminal according to an embodiment of the present disclosure. [Figure 5] FIG. 5 is a diagram for explaining the operation of the information processing system according to the embodiment of the present disclosure. [Figure 6] FIG. 6 is a diagram illustrating an example of a display on a terminal according to an embodiment of the present disclosure. [Figure 7] FIG. 7 is a diagram illustrating an example of a processing configuration of a terminal according to an embodiment of the present disclosure. [Figure 8]FIG. 8 is a diagram illustrating an example of an operation history management database according to an embodiment of the present disclosure. [Figure 9] FIG. 9 is a flowchart illustrating an example of the operation of the usage control unit according to an embodiment of the present disclosure. [Figure 10] FIG. 10 is a diagram illustrating an example of a processing configuration of a terminal according to an embodiment of the present disclosure. [Figure 11] FIG. 11 is a diagram illustrating an example of a hardware configuration of a terminal according to the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0012] First, an overview of one embodiment will be described. Note that the reference numerals in the drawings are added to each element for convenience as an example to facilitate understanding, and the description of this overview is not intended to be limiting in any way. Furthermore, unless otherwise specified, the blocks shown in each drawing represent functional units, not hardware units. Connection lines between blocks in each drawing include both bidirectional and unidirectional lines. Unidirectional arrows are used to schematically indicate the flow of main signals (data) and do not exclude bidirectionality. Note that in this specification and drawings, elements that can be similarly described may be assigned the same reference numerals to avoid redundant explanation.

[0013] A terminal 100 according to one embodiment includes an acquisition unit 101 and a control unit 102 (see FIG. 1). The acquisition unit 101 acquires operation histories of each of a plurality of applications installed on the terminal (step S1 in FIG. 2). The control unit 102 generates a prompt to be input into a language model using the operation history of an application selected from the plurality of applications as an application for which the user requests instructions on how to use the application (step S2). The control unit 102 presents to the user an explanation on how to use the selected application, obtained from the language model using the generated prompt (step S3).

[0014] Terminal 100 acquires and stores a history of operations performed by a user on an application. When a user requests an explanation of how to use an application, terminal 100 generates a prompt using the operation history of the application, and generates an explanation of the application using the generated prompt and a language model, and presents it to the user. Using the operation history of the application, terminal 100 infers what the user wants to know about the application, and generates a prompt that allows the user to obtain an explanation of the inferred information. As a result, the user can obtain an explanation of how to use the application that they really want to know, among the applications installed on their smartphones, etc.

[0015] Specific embodiments will be described in more detail below with reference to the drawings.

[0016] [First embodiment] The first embodiment will be described in more detail with reference to the drawings.

[0017] [System Configuration] 3 is a diagram illustrating an example of a schematic configuration of an information processing system according to an embodiment of the present disclosure. As illustrated in FIG. 3, the information processing system includes a server device 10.

[0018] The server device 10 is a server that provides various information to users. More specifically, the server device 10 is a server that provides an interactive AI (Artificial Intelligence) service using a language model. For example, a large language model (LLM) is implemented in the server device 10. The server device 10 is installed on a network (on the cloud), for example.

[0019] A user has a terminal 20 such as a smartphone. Various applications are installed on the terminal 20. The user uses the applications installed on the terminal 20 to communicate with others using a social networking service (SNS) or to do online shopping on an electronic commerce (EC) site.

[0020] The devices (server device 10, terminal 20) shown in FIG. 3 are connected by wired or wireless communication means and are configured to be able to communicate with each other.

[0021] 3 is an example and is not intended to limit the configuration. For example, the system may include multiple server devices 10. Load balancing and redundancy may be achieved by using multiple server devices 10.

[0022] [General operation] Next, the general operation of the information processing system according to the first embodiment will be described.

[0023] <Enter user information> The user operates the terminal 20 to register his / her own information in the terminal 20. For example, the user registers his / her name, sex, date of birth, address, biometric information (for example, a facial image) and the like in the terminal 20. The terminal 20 stores the acquired name and the like internally.

[0024] <Application operation history> A user uses an application installed on the terminal 20. Here, each application installed on the terminal 20 generates a history of operations performed by the user. More specifically, an operation history including the date and time of operation, operation details (selected menu, information on pressed buttons and links, page from which transition was made, page to which transition was made), etc. is generated for each application.

[0025] <How to use the application> There are cases where a user does not know how to use an application. In such cases, the user performs an operation on the terminal 20 to request an explanation on how to use the application. For example, the user requests an explanation of the application by long pressing an icon corresponding to the application displayed on the screen of the terminal 20 (see FIG. 4).

[0026] The terminal 20 generates an explanatory text about how to use the application by using the user's attribute information and / or the operation history of the application. More specifically, the terminal 20 acquires an explanatory text about how to use the application from the server device 10 that provides an interactive service using a large-scale language model.

[0027] For example, the terminal 20 generates a prompt that acquires how to use the application from a large-scale language model using the user's attribute information and the operation history of the application.

[0028] The terminal 20 transmits a "request for providing explanation" including the generated prompt to the server device 10 (see FIG. 5). The server device 10 generates an explanation about how to use the application by inputting the prompt included in the received request for providing explanation into a large-scale language model. The server device 10 transmits the generated explanation to the terminal 20.

[0029] The terminal 20 presents the received explanatory text to the user. For example, the terminal 20 displays a screen such as that shown in Fig. 6, showing explanatory text on how to use an application that the user does not know how to use.

[0030] Next, details of each device included in the information processing system according to the first embodiment will be described.

[0031] [Device] Examples of the terminal 20 include a smartphone, a mobile phone, a game console, a mobile terminal device such as a tablet, a computer (personal computer, laptop computer), etc. The terminal 20 can be any equipment or device that can accept user operations and communicate with the server device 10, etc.

[0032] 7 is a diagram illustrating an example of a processing configuration (processing module) of the terminal 20 according to the embodiment of the present disclosure. Referring to FIG. 7, the terminal 20 includes a communication control unit 201, a user registration control unit 202, an operation history control unit 203, a usage method control unit 204, and a storage unit 205.

[0033] The communication control unit 201 is a means for controlling communication with other devices. For example, the communication control unit 201 receives data (packets) from the server device 10. The communication control unit 201 also transmits data to the server device 10. The communication control unit 201 passes data received from other devices to other processing modules. The communication control unit 201 transmits data acquired from other processing modules to other devices. In this way, other processing modules transmit and receive data to and from other devices via the communication control unit 201. The communication control unit 201 has a function as a receiving unit that receives data from other devices and a function as a transmitting unit that transmits data to other devices.

[0034] Here, among the processing modules of the terminal 20, the user registration control unit 202, the operation history control unit 203, and the usage method control unit 204 may be implemented as functions of an OS (Operating System) installed in the terminal 20.

[0035] The user registration control unit 202 is a means for controlling the registration of user information. When the user operates the terminal 20 to perform a predetermined action (for example, pressing the user registration button), the user registration control unit 202 acquires user information.

[0036] For example, the user registration control unit 202 displays a GUI (Graphical User Interface) on the terminal 20 to acquire the name, sex, date of birth, address, biometric information, etc. The user registration control unit 202 stores the acquired name, etc. in the storage unit 205.

[0037] The operation history control unit 203 is a means for controlling the history generated when a user uses each application. The operation history control unit 203 has a function as an acquisition means for acquiring the operation history of each of a plurality of applications installed on its own device (terminal 20).

[0038] When each application installed on the terminal 20 acquires an operation by a user, it notifies the operation history control unit 203 of the content (details) of the acquired operation.

[0039] For example, when each application is started by a user, it notifies the operation history control unit 203 of the application name (application ID) and the date and time of start as an operation history. Alternatively, when a user presses a button, each application notifies the operation history control unit 203 of the application name, the date and time of operation, the type of button pressed, etc. as an operation history. Alternatively, when a user presses a link, each application notifies the operation history control unit 203 of the application name, the date and time of operation, the page from which the link was transitioned, the page to which the link was transitioned, etc. as an operation history.

[0040] The operation history control unit 203 stores the operation history acquired from each application for each application. The operation history control unit 203 stores the operation history in an operation history management database prepared for each application (see FIG. 8).

[0041] The operation history management database shown in Fig. 8 is an example of a database that manages operation histories related to application A. The operation history management database shown in Fig. 8 is an example and is not intended to limit the items to be stored. For example, the operation histories of multiple applications may be managed and stored in the same database.

[0042] The usage control unit 204 is a means for controlling the usage of each application installed on the terminal 20 .

[0043] The usage method control unit 204 generates a prompt to be input into the language model using the operation history of an application selected from among multiple applications as an application for which the user requests instructions on how to use the application. The usage method control unit 204 presents to the user an explanation on how to use the selected application obtained from the language model using the generated prompt.

[0044] 9 is a flowchart showing an example of the operation of the usage control unit 204 according to an embodiment of the present disclosure. The operation of the usage control unit 204 will be described with reference to FIG.

[0045] The usage control unit 204 detects an application for which the user requests an explanation of how to use it (step S101).

[0046] For example, the usage control unit 204 detects a predetermined action performed by the user on an icon corresponding to each application on the home screen. For example, the usage control unit 204 detects a long press on an icon by the user. The usage control unit 204 identifies the application corresponding to the icon long pressed by the user as an application for which an explanation of how to use the application is requested.

[0047] The usage control unit 204 generates a prompt to be sent to the server device 10 using the user's attribute information and / or the operation history of the application for which an explanation of usage has been requested (step S102).

[0048] Specific examples of prompts generated by the usage control unit 204 will be described later.

[0049] The usage control unit 204 transmits a "request to provide explanation" including the generated prompt to the server device 10 (step S103).

[0050] The usage method control unit 204 acquires an explanation (a response to the explanation provision request) from the server device 10 (step S104).

[0051] The usage control unit 204 presents the acquired explanation to the user (step S105). For example, as shown in Fig. 6, the usage control unit 204 displays the explanation of the application in the vicinity of the icon corresponding to the application for which the user requests an explanation.

[0052] In this way, the usage method control unit 204 obtains an explanation of how to use the application selected by the user by sending the generated prompt to the server device 10 in which the large-scale language model is implemented.

[0053] The storage unit 205 is a means for storing information necessary for the operation of the terminal 20.

[0054] [Server device] Detailed description of the server device 10 will be omitted. The server device 10 is a server that provides an interactive AI (Artificial Intelligence) service using a general-purpose (commercial) large-scale language model. The server device 10 is equipped with a language model obtained by machine learning using a huge amount of learning data, including instruction manuals for various applications that can be installed on smartphones, etc.

[0055] The server device 10 may input the prompt included in the “explanation provision request” received from the terminal 20 into the large-scale language model, and transmit the response from the large-scale language model to the terminal 20 .

[0056] <Example> Next, a specific example of a prompt generated by the usage control unit 204 of the terminal 20 will be described.

[0057] For example, the usage control unit 204 acquires the operation content immediately before the target application for which the provision of an explanation is requested, and generates a prompt to be sent to the server device 10 using the acquired operation content.

[0058] For example, if the user presses the "withdraw button" in application A, the usage control unit 204 generates a prompt such as "Please create an explanation for when the withdrawal button of application A is pressed."

[0059] In this case, the server device 10 generates, for example, an explanation of the procedure for canceling membership in the service provided using the application A.

[0060] Alternatively, the usage control unit 204 identifies the most recent screen transition in the target application based on the operation history of the application. For example, the usage control unit 204 determines that the display on the terminal 20 has transitioned from a menu screen to a settings screen when the user presses a link embedded in application A. In this case, the usage control unit 204 generates a prompt such as, "Please generate a detailed explanation regarding the settings of application A."

[0061] In this case, the server device 10 generates a description of the items that can be set for the application A.

[0062] In this way, the usage control unit 204 may generate a prompt using the most recent operation content of the application selected by the user (the operation history of the operation performed immediately before the time when the user requested an explanation).

[0063] Alternatively, the usage control unit 204 may calculate the cumulative usage time of the target application based on the operation history of the application, and generate a prompt using the calculated cumulative usage time. For example, immediately after application A is installed on the terminal 20 and launched for the first time (when the cumulative usage time is substantially zero), the usage control unit 204 generates a prompt such as "Please tell me an overview of application A."

[0064] In this case, the server device 10 generates a description including the outline of the functions of the application A, information about the business that provides the application A, and the like.

[0065] In this way, the usage method control unit 204 may calculate the cumulative usage time of the selected application based on the operation history of the application selected by the user, and generate a prompt using the calculated cumulative usage time.

[0066] Alternatively, the usage control unit 204 may calculate the frequency of use of the target application based on the operation history of the application, and generate a prompt using the calculated frequency of use. For example, if application A is a frequently used application (e.g., an application that is launched 10 or more times a day), the usage control unit 204 may generate a prompt such as "Please tell me about some lesser-known features of application A."

[0067] In this case, the server device 10 generates a description about the minor functions of the application A.

[0068] Alternatively, the usage control unit 204 may generate a prompt requesting the provision of an explanation of the target application based on the operation histories of multiple applications. For example, the usage control unit 204 calculates the frequency of use of each of the target application and applications similar to it. If the frequency of use of the similar application is high, the usage control unit 204 generates a prompt to obtain the difference in operation between the similar application and the target application as an explanation.

[0069] For example, consider a case where application A and application B are similar applications, application B is used frequently, and an explanation of application A is requested. In this case, the usage method control unit 204 generates a prompt such as, "Please generate an explanation of the differences between the operation of application A and the operation of application B."

[0070] In this case, the server device 10 generates explanatory text about the different functions and usage of the applications A and B.

[0071] In this way, the usage control unit 204 may generate a prompt using the operation history of an application selected by the user and the operation history of an application different from the selected application.

[0072] Alternatively, the usage method control unit 204 may generate a prompt requesting the user to provide an explanation of the target application based on the user's attribute information (e.g., age, gender, etc.) For example, the usage method control unit 204 may generate a prompt such as "Please generate an explanation of application A for a man in his 70s."

[0073] In this case, the server device 10 generates an explanation of how to use the application A according to the age and sex of the user.

[0074] Alternatively, the usage method control unit 204 may generate a prompt requesting the user to provide an explanation of the target application using the user's attributes and the operation history of the application. For example, the usage method control unit 204 may generate a prompt such as "Please generate an explanation for a man in his 70s who is using application A for the first time."

[0075] As described above, the terminal 20 according to the first embodiment accumulates a history of operations performed by a user on an application. When a predetermined operation by the user (for example, long pressing of an icon) is detected, the terminal 20 generates a prompt using the operation history of the application and transmits the generated prompt to the server device 10. The server device 10 inputs the acquired prompt into a large-scale language model to generate an explanation of the application and transmits it to the terminal 20. The terminal 20 presents the acquired explanation to the user. The terminal 20 uses the operation history of the application to infer matters that the user wants to know about the application and to estimate the user's usage status (state) of the application. The terminal 20 generates a prompt so that an explanation of the inferred matters or an explanation appropriate to the user's usage status can be obtained from the large-scale language model. As a result, the terminal 20 can present an explanation appropriate to the user.

[0076] A user may sometimes not know how to use an application installed on terminal 20. In this case, the user performs a predetermined operation on terminal 20 (for example, long press on the icon of the application that the user does not know how to use). When terminal 20 detects this predetermined operation, it presents an explanation suited to the user, taking into consideration the user's attributes and the situation regarding the application, rather than the normal manual for the application. In other words, terminal 20 presents a personalized explanation (explanatory information) to the user using the operation history of the application, etc. The user can instantly access the information they want, improving convenience for the user.

[0077] [Second embodiment] Next, the second embodiment will be described in detail with reference to the drawings.

[0078] In the first embodiment, a case has been described in which a language model (large-scale language model) that generates description sentences for an application is implemented in the server device 10. In the second embodiment, a case in which the language model is implemented inside the terminal 20 will be described.

[0079] The following description will focus on the differences between the first and second embodiments.

[0080] 10 is a diagram illustrating an example of a processing configuration (processing module) of the terminal 20 according to the embodiment of the present disclosure. Referring to FIG. 10, a language model management unit 206 is added to the configuration of the terminal 20 according to the first embodiment.

[0081] The language model management unit 206 is a means for controlling and managing the language model used in the description of the application.

[0082] The language model management unit 206 acquires a language model prepared by a system administrator or the like. For example, the language model management unit 206 acquires a language model using a GUI or the like. Alternatively, the language model management unit 206 may acquire a language model via a USB (Universal Serial Bus) memory or the like.

[0083] A language model is a machine learning model (also called a generative model) that takes language as input and outputs language. A language model learns the relationships between words in a sentence and generates related strings from a target string. By using a language model that has been trained on sentences and sentences from various contexts, it is possible to generate related strings with appropriate content that are related to the target string.

[0084] The learning method of the language model is not particularly limited, but as an example, the language model may be learned to output at least one sentence including an input string. As a specific example, the language model is a GPT (Generative Pre-Transformer) that outputs a sentence including an input string by predicting a string that is likely to follow the input string.

[0085] Other examples of language models include T5 (Text-to-Text Transfer Transformer), BERT (Bidirectional Encoder Representations from Transformers), RoBERTa (Robustly optimized BERT approach), and ELECTRA (Efficiently Learning an Encoder that Classifies Token Replacements Accurately).

[0086] The language model is generated based on learning data. For example, a language model (small-scale language model) specialized for generating application descriptions is implemented in the terminal 20. In this case, various learning data such as manuals for applications that may be installed in the terminal 20 and information on the Internet (for example, information posted on SNS or blogs) are utilized to train and learn the learning model.

[0087] The usage method control unit 204 according to the second embodiment inputs a prompt generated based on the operation history of the application, etc., into a language model implemented in the device itself, instead of sending a request for providing an explanation to the server device 10. The usage method control unit 204 presents the answer (explanation of the application) obtained by inputting the information into the language model to the user.

[0088] As described above, in the second embodiment, the terminal 20 obtains an explanatory text about how to use an application selected by a user by inputting a prompt generated in a language model implemented in the terminal 20. Because the language model is implemented in the terminal 20, the terminal 20 can provide the explanatory text of the application to the user even when the terminal 20 is offline.

[0089] Next, the hardware of each device constituting the information processing system will be described. Fig. 11 is a diagram showing an example of the hardware configuration of the terminal 20.

[0090] The terminal 20 can be configured by an information processing device (so-called a computer), and has the configuration exemplified in Fig. 11. For example, the terminal 20 has a processor 311, a memory 312, an input / output interface 313, a communication interface 314, etc. The components such as the processor 311 are connected by an internal bus or the like, and are configured to be able to communicate with each other.

[0091] However, the configuration shown in Fig. 11 is not intended to limit the hardware configuration of the terminal 20. The terminal 20 may include hardware not shown, and may not include the input / output interface 313 as necessary. Furthermore, the number of processors 311 and the like included in the terminal 20 is not intended to be limited to the example shown in Fig. 11, and for example, the terminal 20 may include multiple processors 311.

[0092] The processor 311 is a programmable device such as a central processing unit (CPU), a micro processing unit (MPU), or a digital signal processor (DSP). Alternatively, the processor 311 may be a device such as a field programmable gate array (FPGA) or an application specific integrated circuit (ASIC). The processor 311 executes various programs including an operating system (OS).

[0093] The memory 312 is a random access memory (RAM), a read only memory (ROM), a hard disk drive (HDD), a solid state drive (SSD), etc. The memory 312 stores an OS program, application programs, and various data.

[0094] The input / output interface 313 is an interface for a display device and an input device (not shown). The display device is, for example, a liquid crystal display. The input device is, for example, a keyboard, a mouse, a touch panel, or the like that accepts user operations.

[0095] The communication interface 314 is a circuit, module, etc. that communicates with other devices. For example, the communication interface 314 includes a network interface card (NIC).

[0096] The functions of the terminal 20 are realized by various processing modules. The processing modules are realized, for example, by the processor 311 executing a program stored in the memory 312. The program can be recorded on a computer-readable storage medium. The storage medium can be a non-transitory medium such as a semiconductor memory, a hard disk, a magnetic recording medium, or an optical recording medium. That is, the present invention can also be embodied as a computer program product. The program can be downloaded via a network or updated using a storage medium storing the program. The processing modules can also be realized by a semiconductor chip.

[0097] The server device 10 can also be configured by an information processing device, just like the terminal 20, and its basic hardware configuration is no different from that of the terminal 20, so a description thereof will be omitted.

[0098] The terminal 20 is equipped with a computer, and the functions of the terminal 20 can be realized by causing the computer to execute a program. The terminal 20 also executes a control method for the terminal 20 by the program.

[0099] [Variations] The configuration, operation, etc. of the information processing system described in the above embodiment are merely examples, and are not intended to limit the configuration, etc. of the system.

[0100] When presenting an explanation of an application to a user, the terminal 20 may change the display mode of the explanation to be presented according to the attribute information of the user. For example, the usage method control unit 204 may change the font, character size, character color, etc. of the explanation to be presented according to the age (generation) and gender of the user.

[0101] In the above embodiment, the terminal 20 transmits a prompt to the server device 10 for input into a language model. However, the terminal 20 may transmit information used in generating the prompt (for example, user attribute information, application operation history) to the server device 10. The server device 10 may generate a prompt based on the acquired application operation history.

[0102] In the above embodiment, the explanation has been given for the case where the explanatory text presentation function of the terminal 20 is realized by the OS installed on the terminal 20. However, the explanatory text presentation function may be realized by each application. That is, the explanatory text presentation function described above may be implemented in each of a plurality of applications.

[0103] In the above embodiment, the terminal 20 transmits a request for providing an explanation including a prompt to the server device 10 in which a general-purpose large-scale language model is implemented. However, the terminal 20 may transmit the request for providing an explanation including a prompt to a server (application server; not shown in FIG. 3, etc.) managed and operated by a business providing a target application. The application server may generate an answer (explanation) using a language model obtained from an instruction manual for an application provided by the application server, and transmit the generated explanation to the terminal 20.

[0104] The terminal 20 may accumulate explanatory sentences (answers) obtained from the language model and generate an answer history. The usage control unit 204 may generate a prompt to be input to the language model using the answer history in addition to the user's attribute information and the application operation history. Specifically, the usage control unit 204 may generate a prompt so that the language model does not output duplicate answers.

[0105] The language model implemented in the server device 10 or the like may provide the terminal 20 with the confidence level of the answer (the appropriateness of the answer) along with the generated explanation. The usage control unit 204 may determine the manner in which to display the explanation based on the acquired confidence level. For example, the usage control unit 204 may use large-sized characters to present an explanation with a high confidence level and small-sized characters to present an explanation with a low confidence level.

[0106] The server device 10 and the terminal 20 may retrain the language model. For example, the terminal 20 presents a prompt to be input to the language model and an explanatory sentence obtained from the language model to an application developer or the like. The application developer or the like evaluates the relationship between the input (prompt) and output (explanatory sentence) of the language model and inputs the evaluation result to the terminal 20. The terminal 20 retrains the language model using the prompt, the explanatory sentence, and the evaluation result by the application developer. As a result, the performance (output accuracy) of the language model is improved.

[0107] The terminal 20 may acquire an evaluation (evaluation from the user) of the explanatory text presented to the user. For example, the usage method control unit 204 may acquire an evaluation from the user, such as whether the explanatory text was "useful" or "not useful." The usage method control unit 204 may also transmit the acquired evaluation to the server device 10 or the like. For example, the usage method control unit 204 transmits to the server device 10 the prompt sent to the server device 10, the answer (explanatory text) acquired from the server device 10, and the user's evaluation of the explanatory text. The server device 10 may retrain (feedback) the language model using the acquired evaluation or the like to improve the answer accuracy of the language model.

[0108] Alternatively, if the terminal 20 receives an evaluation such as "not useful" from the user, the terminal 20 may re-present another explanatory sentence different from the previously presented explanatory sentence. For example, the usage method control unit 204 may send a prompt to the server device 10 instructing the server device 10 to generate an explanatory sentence for a different matter from the previous explanatory sentence, and acquire the other explanatory sentence. Alternatively, the usage method control unit 204 may send a prompt to the server device 10 instructing the server device 10 to generate explanatory sentences for a plurality of matters, and acquire explanatory sentences for the plurality of matters. The usage method control unit 204 may present the acquired plurality of explanatory sentences to the user. In this case, the usage method control unit 204 may acquire the explanatory sentence that the user considers to be the most useful from among the multiple explanatory sentences. Re-learning may be performed using the acquired most useful explanatory sentence.

[0109] In the above embodiment, the case where the operation history management database is configured inside the server device 10 has been described, but the database may also be constructed in an external database server or the like. That is, some of the functions of the server device 10 may be implemented in another device. More specifically, it is sufficient that the above-described "usage method control unit (usage method control means)" and the like are implemented in any of the devices included in the system.

[0110] The form of data transmission and reception between the devices (server device 10, terminal 20) is not particularly limited, but the data transmitted and received between these devices may be encrypted. Personal information of users and the like is transmitted and received between these devices, and in order to appropriately protect this information, it is desirable to transmit and receive encrypted data.

[0111] In the flow charts (flowcharts, sequence diagrams) used in the above explanation, multiple steps (processes) are described in order, but the execution order of the steps executed in the embodiments is not limited to the order described. In the embodiments, the order of the illustrated steps can be changed to the extent that the content is not affected, such as by executing each process in parallel.

[0112] The above-described embodiments have been described in detail to facilitate understanding of the present disclosure, and it is not intended that all of the above-described configurations are required. Furthermore, when multiple embodiments are described, each embodiment may be used alone or in combination. For example, it is possible to replace part of the configuration of one embodiment with the configuration of another embodiment, or to add the configuration of another embodiment to the configuration of one embodiment. Furthermore, it is possible to add, delete, or replace part of the configuration of one embodiment with another configuration.

[0113] From the above explanation, it is clear that the present invention has industrial applicability, and the present invention can be suitably applied to an information processing system that presents users with instructions on how to use an application.

[0114] Some or all of the above embodiments can be described as, but are not limited to, the following supplementary notes.

[0115] [Appendix 1] an acquisition means for acquiring operation histories of each of a plurality of applications installed in the device; a control means for generating a prompt to be input into a language model using the operation history of an application selected from the plurality of applications as an application for which a user requests instructions on how to use the application, and presenting to the user an explanation on how to use the selected application obtained from the language model using the generated prompt; and A terminal comprising: [Appendix 2] 2. The terminal of claim 1, wherein the control means generates the prompt using the content of a previous operation of the selected application. [Appendix 3] The terminal described in Appendix 1, wherein the control means calculates a cumulative usage time of the selected application based on the operation history of the selected application, and generates the prompt using the calculated cumulative usage time. [Appendix 4] The terminal described in Appendix 1, wherein the control means calculates a frequency of use of the selected application based on the operation history of the selected application, and generates the prompt using the calculated frequency of use. [Appendix 5] The terminal according to claim 1, wherein the control means generates the prompt using the operation history of the selected application and the operation history of an application different from the selected application. [Appendix 6] 6. The terminal according to claim 1, wherein the control means generates the prompt using attribute information of the user. [Appendix 7] 7. The terminal of claim 6, wherein the control means obtains an explanatory text on how to use the selected application by sending the generated prompt to a server device on which the language model is implemented. [Appendix 8] 7. The terminal of claim 6, wherein the control means obtains an explanatory text on how to use the selected application by inputting the generated prompt into the language model implemented therein. [Appendix 9] an acquisition step of acquiring operation histories of each of a plurality of applications installed on the device; a control step of generating a prompt to be input into a language model using the operation history of an application selected from the plurality of applications as an application for which a user requests instructions on how to use the application, and presenting to the user an explanation on how to use the selected application obtained from the language model using the generated prompt; A method for controlling a terminal, comprising: [Appendix 10] 10. The terminal control method according to claim 9, wherein the control step generates the prompt using the operation content of the selected application immediately before the operation. [Appendix 11] 10. The terminal control method of claim 9, wherein the control step calculates a cumulative usage time of the selected application based on the operation history of the selected application, and generates the prompt using the calculated cumulative usage time. [Appendix 12] 10. The terminal control method according to claim 9, wherein the control step calculates a frequency of use of the selected application based on the operation history of the selected application, and generates the prompt using the calculated frequency of use. [Appendix 13] 10. The terminal control method according to claim 9, wherein the control step generates the prompt using the operation history of the selected application and the operation history of an application different from the selected application. [Appendix 14] 14. The method for controlling a terminal according to any one of claims 9 to 13, wherein the control step generates the prompt using attribute information of the user. [Appendix 15] 15. The terminal control method of claim 14, wherein the control step obtains an explanatory text on how to use the selected application by sending the generated prompt to a server device on which the language model is implemented. [Appendix 16] 15. The method for controlling a terminal according to claim 14, wherein the control step obtains an explanatory text on how to use the selected application by inputting the generated prompt into the language model implemented therein. [Appendix 17] The computer installed in the device an acquisition process for acquiring operation histories of each of a plurality of applications installed on the device; a control process that generates a prompt to be input into a language model using the operation history of an application selected from the plurality of applications as an application for which a user requests an explanation on how to use the application, and presents to the user an explanation on how to use the selected application obtained from the language model using the generated prompt; A program to execute. [Appendix 18] 18. The program according to claim 17, wherein the control process generates the prompt using the content of an operation immediately before the selected application. [Appendix 19] The program described in Appendix 17, wherein the control process calculates a cumulative usage time of the selected application based on the operation history of the selected application, and generates the prompt using the calculated cumulative usage time. [Appendix 20] The program described in Appendix 17, wherein the control process calculates a frequency of use of the selected application based on the operation history of the selected application, and generates the prompt using the calculated frequency of use. [Appendix 21] 18. The program according to claim 17, wherein the control process generates the prompt using the operation history of the selected application and the operation history of an application different from the selected application. [Appendix 22] 22. The program according to claim 17, wherein the control process generates the prompt using attribute information of the user. [Appendix 23] 23. The program of claim 22, wherein the control process obtains an explanatory text on how to use the selected application by sending the generated prompt to a server device on which the language model is implemented. [Appendix 24] 23. The program of claim 22, wherein the control process obtains an explanatory text on how to use the selected application by inputting the generated prompt into the language model implemented therein.

[0116] Furthermore, some or all of the configurations described in Supplementary Notes 2 to 8, which are dependent on Supplementary Note 1, may also be dependent on Supplementary Notes 9 and 17 in the same dependent relationship as Supplementary Notes 2 to 8. Furthermore, not limited to Supplementary Notes 1, 9, and 17, but within the scope of each of the above-mentioned embodiments, some or all of the configurations described as Supplements may also be dependent on various hardware, software, various recording means for recording software, or systems.

[0117] The disclosures of the above-cited prior art documents are incorporated herein by reference. Although the embodiments of the present invention have been described above, the present invention is not limited to these embodiments. Those skilled in the art will understand that these embodiments are merely illustrative and that various modifications are possible without departing from the scope and spirit of the present invention. In other words, the present invention naturally includes various modifications and alterations that may be made by those skilled in the art in accordance with the entire disclosure, including the claims, and the technical concepts thereof. [Explanation of symbols]

[0118] 10 Server device 20 terminals 100 devices 101 Acquisition method 102 Control means 201 Communication control unit 202 User registration control unit 203 Operation history control section 204 Usage control section 205 Storage section 206 Language Model Management Unit 311 processor 312 memory 313 Input / Output Interface 314 Communication Interface

Claims

1. an acquisition means for acquiring operation histories of each of a plurality of applications installed in the device; a control means for generating a prompt to be input into a language model using the operation history of an application selected from the plurality of applications as an application for which a user requests instructions on how to use the application, and presenting to the user an explanation on how to use the selected application obtained from the language model using the generated prompt; and A terminal comprising:

2. The terminal according to claim 1 , wherein the control means generates the prompt using a previous operation of the selected application.

3. 2. The terminal according to claim 1, wherein the control means calculates a cumulative usage time of the selected application based on the operation history of the selected application, and generates the prompt using the calculated cumulative usage time.

4. The terminal according to claim 1 , wherein the control means calculates a frequency of use of the selected application based on the operation history of the selected application, and generates the prompt using the calculated frequency of use.

5. The terminal according to claim 1 , wherein the control means generates the prompt using the operation history of the selected application and the operation history of an application different from the selected application.

6. The terminal according to claim 1 , wherein the control means generates the prompt using attribute information of the user.

7. The terminal according to claim 6 , wherein the control means obtains an explanation about how to use the selected application by transmitting the generated prompt to a server device on which the language model is implemented.

8. The terminal according to claim 6 , wherein the control means obtains an explanation about how to use the selected application by inputting the generated prompt into the language model implemented therein.

9. an acquisition step of acquiring operation histories of each of a plurality of applications installed on the device; a control step of generating a prompt to be input into a language model using the operation history of an application selected from the plurality of applications as an application for which a user requests instructions on how to use the application, and presenting to the user an explanation on how to use the selected application obtained from the language model using the generated prompt; A method for controlling a terminal, comprising:

10. The computer installed in the device an acquisition process for acquiring operation histories of each of a plurality of applications installed on the device; a control process that generates a prompt to be input into a language model using the operation history of an application selected from the plurality of applications as an application for which a user requests an explanation on how to use the application, and presents to the user an explanation on how to use the selected application obtained from the language model using the generated prompt; A program to execute.

Images