Information processing apparatus, information processing method, and program

Abstract

To solve the problem that it is not easy to obtain an answer for solving a user's question about a program.SOLUTION: By an information processor 1 including an operation acquiring unit 132 that acquires operation information on an operation of a user, a question accepting unit 123 that accepts question information from the user, a prompt constructing unit 134 that constructs a prompt having the operation information acquired by the operation acquiring unit 132 and the question information accepted by the question accepting unit 123, an answer acquiring unit 135 that passes the prompt to a generation AI and acquires an answer from the generation AI, an output-answer acquiring unit 136 that acquires an output-answer based on the answer acquired by the answer acquiring unit 135, and an answer outputting unit 142 that outputs the output-answer acquired by the output-answer acquiring unit 136, To easily obtain an answer capable of solving a user's question about a program.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present invention relates to an information processing device that uses a generation AI to obtain and output answers to user questions. [Background technology]

[0002] In the past, in order for users of a certain program to solve their own questions, there were multiple data sets to search, such as help from the product, Q&A from the support center, and case studies from the support center, and it took time and effort to arrive at a solution.

[0003] The use of generative AI is becoming more widespread, for example, by using it to generate explanations for answers to questions (see Patent Document 1). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 7456589 Summary of the Invention [Problem to be solved by the invention]

[0005] However, in the prior art, it was not easy for users to obtain answers to resolve their questions about the program. [Means for solving the problem]

[0006] The information processing device of the first invention is an information processing device that includes an operation acquisition unit that acquires operation information related to user operations, a question reception unit that receives question information from the user, a prompt construction unit that constructs a prompt having the operation information acquired by the operation acquisition unit and the question information received by the question reception unit, an answer acquisition unit that passes the prompt to a generation AI and acquires an answer from the generation AI, an output answer acquisition unit that acquires an output answer based on the answer acquired by the answer acquisition unit, and an answer output unit that outputs the output answer acquired by the output answer acquisition unit.

[0007] With this configuration, by providing the user's operation information to the generation AI and receiving a response from the generation AI, it is possible to easily obtain a response that can resolve the user's questions about the program.

[0008] In addition, the information processing device of the second invention is an information processing device in which, compared to the first invention, the operation acquisition unit acquires transition information, which is operation information regarding screen transitions, and the prompt construction unit constructs a prompt having the transition information and question information.

[0009] With this configuration, by providing operation information about screen transitions to the generation AI and receiving a response from the generation AI, a response that can resolve the user's questions about the program can be easily obtained.

[0010] In addition, the information processing device of the third invention is an information processing device in which, compared to the second invention, the operation acquisition unit is transition information regarding the user's menu transition, and acquires transition information including the character string of the menu item selected by the user.

[0011] With this configuration, by providing operation information about menu transitions to the generation AI and receiving a response from the generation AI, a response that can resolve the user's questions about the program can be easily obtained.

[0012] Furthermore, the information processing device of the fourth invention is an information processing device according to any one of the first to third inventions, further comprising a learning unit that causes the generating AI to learn two or more types of data sets related to the explanation of a program operated by a user.

[0013] With this configuration, by obtaining answers from a generation AI that has been trained on two or more types of data sets related to program explanations, it is possible to easily obtain answers that can resolve the user's questions about the program.

[0014] In addition, the information processing device of the fifth invention is an information processing device that, compared to the fourth invention, further includes a screen acquisition unit that acquires screen information of a screen for inputting question information, the screen information including data set symbols indicating each of two or more types of data sets, and a screen output unit that outputs the screen information acquired by the screen acquisition unit.

[0015] With this configuration, the dataset used by the generation AI can be shown to the user, thereby encouraging direct use of the dataset by the user.

[0016] Furthermore, the information processing device of the sixth invention is an information processing device in which, compared to any one of the first to fifth inventions, each of two or more screens operated by a user has a UI component that calls up a question screen for passing question information to the generation AI, and further includes a selection receiving unit that receives the selection of the UI component, a screen acquisition unit that, when the selection receiving unit receives the selection of the UI component, uses the operation information to construct question screen information, which is screen information of a screen including target-related information that can grasp the target of the question, and is screen information of a question screen for inputting question information to be passed to the generation AI, and a screen output unit that outputs the question screen information.

[0017] With this configuration, a screen including subject-related information that enables the user to grasp the subject of the question is output to the user, thereby assisting the user in inputting an appropriate question that can resolve the user's doubt.

[0018] In addition, the information processing device of the seventh invention is an information processing device in which, compared to the sixth invention, the object-related information is a question guide including a string of characters that enables the user to understand the object of the question to be entered, or title information of the screen information.

[0019] With this configuration, by outputting to the user a question guide including a string of characters that enables the user to understand the subject of the question or a screen including title information for the screen, the user can be assisted in entering an appropriate question that will resolve their doubt. [Effects of the Invention]

[0020] According to the information processing device of the present invention, answers that can resolve the user's questions about the program can be easily obtained. [Brief explanation of the drawings]

[0021] [Figure 1] Conceptual diagram of information system A in embodiment 1 [Figure 2] Block diagram of Information System A [Figure 3] Block diagram of the information processing device 1 [Figure 4] A flowchart illustrating an example of the operation of the information processing device 1. [Figure 5] A flowchart illustrating an example of the question screen acquisition process [Figure 6] A flowchart illustrating an example of the prompt configuration process. [Figure 7] A flowchart illustrating an example of the operation of the terminal device 2 [Figure 8] Figure showing the data set management table [Figure 9] Figure showing an example of the prompt template [Figure 10] A diagram showing an example of the screen [Figure 11] Conceptual diagram of an example of operation of the information processing device 1 [Figure 12] A diagram showing an example of the screen [Figure 13] An example of the prompt is shown below. [Figure 14] Figure showing an example of the answer [Figure 15] Figure showing an example of the output [Figure 16] Block diagram of the computer system DETAILED DESCRIPTION OF THE INVENTION

[0022] Hereinafter, embodiments of an information processing device and the like will be described with reference to the drawings. Note that components with the same reference numerals in the embodiments perform similar operations, and therefore repeated description may be omitted.

[0023] (Embodiment 1) In this embodiment, we will explain an information processing device that acquires operation information related to user operations on a program, constructs a prompt using question information from the user and the operation information, passes the prompt to a generation AI, receives an answer from the generation AI, and outputs it. Note that the operation information is, for example, information on transitions in a program with screen transitions, information on selected menu items, etc.

[0024] In addition, in this embodiment, an information processing device will be described in which the generating AI is made to learn two or more data sets related to the explanation of a program, so that an appropriate answer can be obtained from the generating AI.

[0025] In this embodiment, an information processing device that outputs images of two or more data sets on a screen will be described.

[0026] Furthermore, in this embodiment, we will explain an information processing device that includes a button for asking a question to the generation AI on two or more screens, and when the button is pressed, uses operation information to configure screen information for inputting question information.

[0027] In this specification, information X being associated with information Y means that information Y can be obtained from information X, or information X can be obtained from information Y, and the method of association is not important. Information X and information Y may be linked, may exist in the same buffer, information X may be included in information Y, or information Y may be included in information X, etc.

[0028] Furthermore, in this specification, selecting or determining information Z means obtaining information Z, obtaining a pointer to information Z, obtaining the ID of information Z, setting a flag on information Z, etc., and it is sufficient if information Z can be accessed.

[0029] 1 is a conceptual diagram of an information system A according to this embodiment. The information system A includes an information processing device 1, one or more terminal devices 2, and a generation AI device 3.

[0030] The information processing device 1 is a device that receives question information about a program from the terminal device 2, constructs a prompt using the question information, passes the prompt to a generation AI, obtains an answer from the generation AI, and outputs the output answer to the terminal device 2. The program here is preferably software such as accounting software, payroll software, or human resources management software. The information processing device 1 is, for example, a cloud server or an ASP server, but the type is not important. If the information processing device 1 is a terminal, it can be considered that the terminal device 2 is not necessary for the information system A, or that the information processing device 1 also serves as the terminal device 2. If the information processing device 1 is a terminal, the information processing device 1 is, for example, a so-called personal computer, smartphone, or tablet terminal, but the type is not important.

[0031] The terminal device 2 is a terminal used by a user. The user is a person who operates a program. The terminal device 2 may be, for example, a personal computer, a smartphone, or a tablet terminal, but the type is not important.

[0032] The generation AI device 3 is a device that has the function of a generation AI. Here, the generation AI device 3 typically has the function of a text generation AI. The generation AI may be, for example, ChatGPT or Google Bard, but this does not matter. Google is a registered trademark. The generation AI device 3 may be, for example, a cloud server or an ASP server, but the type does not matter. The generation AI device 3 will be referred to as a generation AI as appropriate. The information processing device 1 may also have the function of a generation AI. In such a case, the generation AI device 3 is not necessary.

[0033] The information processing device 1 and one or more terminal devices 2, and the information processing device 1 and generation AI device 3, can communicate with each other via a network such as the Internet.

[0034] 2 is a block diagram of an information system A according to the present embodiment. FIG. 3 is a block diagram of an information processing device 1.

[0035] The information processing device 1 includes a storage unit 11, a reception unit 12, a processing unit 13, and an output unit 14. The storage unit 11 includes a dataset management unit 111 and a template management unit 112. The reception unit 12 includes an operation reception unit 121, a selection reception unit 122, and a question reception unit 123. The processing unit 13 includes a learning unit 131, an operation acquisition unit 132, a screen acquisition unit 133, a prompt construction unit 134, an answer acquisition unit 135, and an output answer acquisition unit 136. The output unit 14 includes a screen output unit 141 and an answer output unit 142.

[0036] The terminal device 2 includes a terminal storage unit 21, a terminal reception unit 22, a terminal processing unit 23, a terminal transmission unit 24, and a terminal reception unit 25.

[0037] Various types of information are stored in the storage unit 11 that constitutes the information processing device 1. The various types of information are, for example, a data set (to be described later) and a prompt template (to be described later).

[0038] The data set management unit 111 stores one or more types of data sets. A data set is a set of information to help the user use the program. A data set is, for example, a set of Q&As, a set of inquiry history information to the support center, a program operation guide, a program manual, development specifications, development inquiry history, and a set of help. Q&As are information sets of questions and answers. Inquiry history information is information sets of information indicating the content of an inquiry made by a user and the answers given by a support center staff member. Development inquiry history is information sets of inquiries and answers made within a development group during the development stage. Help is program help information.

[0039] The template management unit 112 stores one or more prompt templates.

[0040] A prompt template is information for creating a prompt to be given to the generation AI. A prompt template is, for example, template information for creating a prompt. For example, a prompt is completed using a prompt template and question information from a user. For example, a prompt is completed using a prompt template and question information and operation information from a user. A prompt template includes, for example, one or more variables. One or more variables in the prompt template are given question information, operation information, or question information and operation information corresponding to the variable, to complete the prompt.

[0041] The question information is information about a question entered by a user. The question information is usually a character string, but may also include an image, etc. The question is usually a question about a program used by the user. For example, the question is a question asking how the user should operate the program to realize the program.

[0042] Operation information is information related to operations on a program. Operation information is usually information obtained as a result of an operation by a user. For example, operation information is a character string in a menu item selected by a user in an operation menu related to screen transitions. Note that a screen may be a window or a menu, and is broadly understood as such.

[0043] The reception unit 12 receives various types of information and instructions. For example, the reception unit 12 receives various types of information and instructions from the terminal device 2. The various types of information and instructions include, for example, operations described below, selection of UI components described below, and question information.

[0044] Here, acceptance typically refers to the reception of information transmitted via a wired or wireless communication line, but may also be a concept that includes the reception of information input from an input device such as a keyboard, mouse, or touch panel, or the reception of information read from a recording medium such as an optical disk, magnetic disk, or semiconductor memory.

[0045] The operation receiving unit 121 receives an operation performed by a user. The operation here may be operation information or an operation that is the source of the operation information. The operation is an operation on a program. An operation is, for example, an instruction to press a button on a screen or a selection of a menu item. An instruction to press a button on a screen is, for example, an operation for screen transition or menu transition.

[0046] The selection receiving unit 122 receives the selection of a UI widget. A UI widget is a component of a user interface on a screen. Examples of UI widgets include buttons, menu items, icons, and fields. Examples of UI widgets include a UI widget that calls up a question screen for passing question information to the generation AI. Examples of UI widgets that call up a question screen for passing question information to the generation AI include a button.

[0047] The question receiving unit 123 receives question information from a user. Receiving from a user means receiving from the terminal device 2, for example.

[0048] The processing unit 13 performs various types of processing. The various types of processing are, for example, processing performed by the learning unit 131, the operation acquisition unit 132, the screen acquisition unit 133, the prompt construction unit 134, the answer acquisition unit 135, or the output answer acquisition unit 136.

[0049] The learning unit 131 causes the generation AI to learn one or more types of data sets related to the explanation of the program operated by the user. Since the technology for causing the generation AI to learn information is a well-known technology, detailed explanation will be omitted. The processing of the learning unit 131 is performed before the user uses the program.

[0050] The operation acquisition unit 132 acquires operation information related to a user's operation. The operation acquisition unit 132 usually acquires operation information based on an operation accepted by the operation acceptance unit 121.

[0051] The operation acquisition unit 132 acquires transition information, which is, for example, operation information related to screen transitions. The operation acquisition unit 132 acquires transition information, which is, for example, transition information related to user menu transitions, including character strings of menu items selected by the user.

[0052] It is preferable that the operation acquisition unit 132 temporarily stores the acquired operation information in a buffer (not shown).

[0053] For example, it is preferable that the operation acquisition unit 132 acquires operation information only when the acquired operation information matches an acquisition condition. An acquisition condition is a condition for acquiring operation information. That is, an acquisition condition is, for example, that the accepted operation is a specific operation. A specific operation is, for example, a screen transition operation or a menu transition operation. An acquisition condition is, for example, that information to be passed to the generation AI can be acquired.

[0054] The screen acquisition unit 133 acquires question screen information when the selection receiving unit 122 receives a selection of a UI widget.

[0055] When the selection receiving unit 122 receives the selection of a UI widget, the screen acquiring unit 133 generates question screen information using the operation information acquired by the operation acquiring unit 132. The question screen information includes, for example, all or part of the operation information acquired by the operation acquiring unit 132.

[0056] The question screen information is screen information of a question screen for inputting question information to be passed to the generation AI. The question screen information is screen information of a screen on which a user inputs question information. It is preferable that the question screen information includes a data set symbol indicating each of two or more types of data sets that the learning unit 131 has made the generation AI learn. It is preferable that the question screen information includes target-related information.

[0057] Screen information is information for configuring a screen. Screen information is written in, for example, HTML, XML, or a program, but the means of realization is not important.

[0058] A data set symbol is information that clearly indicates a data set so that the user can understand it. The data set symbol is, for example, an icon that symbolizes the data set or a character string that indicates the name of the data set.

[0059] The subject-related information is information that allows the subject of the question to be understood. The subject-related information is, for example, a question guide that includes a character string that allows the user to understand the subject of the question to be entered, or title information of the screen information.

[0060] The prompt composition unit 134 composes a prompt having the operation information acquired by the operation acquisition unit 132 and the question information accepted by the question acceptance unit 123 .

[0061] The prompt construction unit 134 constructs a prompt having, for example, transition information and question information.

[0062] The prompt construction unit 134 constructs a prompt by, for example, substituting operation information and question information into the variables of the prompt template in the template management unit 112.

[0063] The answer acquisition unit 135 passes the prompt acquired by the prompt composition unit 134 to the generation AI and acquires an answer from the generation AI. For example, the answer acquisition unit 135 assigns the prompt composed by the prompt composition unit 134 to an argument of an API for accessing the generation AI, executes the API, and acquires an answer from the generation AI.

[0064] The output answer acquisition unit 136 acquires an output answer based on the answer acquired by the answer acquisition unit 135. The output answer is, for example, information obtained by removing character strings that do not need to be presented to the user from the answer. The output answer is, for example, information obtained by adding other information to the answer. The other information is not important. The output answer may be the same as the answer acquired by the answer acquisition unit 135.

[0065] The output unit 14 outputs various types of information, such as screen information and output responses.

[0066] Here, output usually means transmission to terminal device 2, but it may also be a concept that includes display on a display, projection using a projector, printing on a printer, sound output, transmission to other external devices, storage on a recording medium, and handing over of processing results to other processing devices or other programs.

[0067] The screen output unit 141 outputs the screen information acquired by the screen acquisition unit 133. The screen output unit 141 outputs, for example, question screen information. When the information processing device 1 operates in a standalone mode, the output of the screen information is the same as the output of the screen.

[0068] The response output unit 142 outputs the output response acquired by the output response acquisition unit 136 .

[0069] Various types of information are stored in the terminal storage unit 21 included in the terminal device 2. The various types of information include, for example, a user identifier.

[0070] The terminal receiving unit 22 receives various types of information, instructions, etc. Examples of the various types of information, instructions, etc. include operations performed by the user, selection of UI components, and question information.

[0071] The means for inputting various information and instructions may be any means, such as a touch panel, keyboard, mouse, or menu screen.

[0072] The terminal processing unit 23 performs various types of processing. For example, the various types of processing are processing to convert received information, instructions, etc. into information, instructions, etc. with a structure to be transmitted. For example, the various types of processing are processing to convert received information into information with a structure to be output.

[0073] The terminal transmitting unit 24 transmits various types of information, instructions, etc. to the information processing device 1. The various types of information, instructions, etc. are, for example, operations performed by the user, selection of UI components, and question information.

[0074] The terminal receiving unit 25 receives various types of information, such as various types of screen information and output responses.

[0075] The terminal output unit 26 outputs various types of information, such as various screens and output responses.

[0076] The storage unit 11, data set management unit 111, template management unit 112, and terminal storage unit 21 are preferably non-volatile recording media, but may also be realized as volatile recording media.

[0077] There is no restriction on the process by which information is stored in the storage unit 11 etc. For example, information may be stored in the storage unit 11 etc. via a recording medium, information transmitted via a communication line etc. may be stored in the storage unit 11 etc., or information input via an input device may be stored in the storage unit 11 etc.

[0078] The reception unit 12, operation reception unit 121, selection reception unit 122, and question reception unit 123 are preferably realized by wireless or wired communication means, but may also be realized by a means for receiving broadcasts, a device driver for an input means such as a touch panel or keyboard, or control software for a menu screen.

[0079] The processing unit 13, learning unit 131, operation acquisition unit 132, screen acquisition unit 133, prompt configuration unit 134, answer acquisition unit 135, output answer acquisition unit 136, and device processing unit 23 can usually be realized by a processor, memory, etc. The processing procedures of the processing unit 13, etc. are usually realized by software, and the software is recorded on a recording medium such as a ROM. However, they may also be realized by hardware (dedicated circuit). The processor may be a CPU, MPU, GPU, etc., and the type is not important.

[0080] The output unit 14, the screen output unit 141, and the answer output unit 142 are usually realized by wireless or wired communication means, but may also be realized by driver software for an output device such as a display or speaker, or by a combination of driver software for an output device and the output device.

[0081] The terminal reception unit 22 can be realized by a device driver for an input means such as a touch panel or a keyboard, or control software for a menu screen.

[0082] The terminal transmitting unit 24 is usually realized by a wireless or wired communication means, but may also be realized by a broadcasting means.

[0083] The terminal receiving unit 25 is usually realized by a wireless or wired communication means, but may also be realized by a means for receiving broadcasts.

[0084] The terminal output unit 26 may be realized by, for example, driver software for an output device such as a display or speaker, or driver software for an output device and an output device.

[0085] Next, an example of the operation of the information processing device 1 will be described with reference to the flowchart of FIG.

[0086] (Step S401) The operation accepting unit 121 determines whether or not an operation performed by the user has been accepted. If the operation has been accepted, the process proceeds to step S402, and if the operation has not been accepted, the process proceeds to step S406.

[0087] (Step S402) The processing unit 13 performs processing according to the operation accepted in step S401.

[0088] (Step S403) The operation acquisition unit 132 determines whether or not to acquire operation information related to the user operation accepted in step S401. If operation information is to be acquired, the process proceeds to step S404, and if not, the process returns to step S401.

[0089] Here, the operation acquisition unit 132 normally determines whether or not the operation matches an acquisition condition, which may be, for example, that the performed operation is a specific operation (e.g., a screen transition, a menu transition, etc.).

[0090] (Step S404) The operation acquisition unit 132 acquires operation information related to the user operation accepted in step S401.

[0091] (Step S405) The operation acquisition unit 132 temporarily stores the operation information acquired in step S404 in a buffer (not shown).

[0092] (Step S406) Selection receiving unit 122 determines whether or not the selection of a UI widget performed by the user has been received. If the selection of a UI widget has been received, the process proceeds to step S407; if not, the process proceeds to step S409.

[0093] (Step S407) The screen acquisition unit 133 performs a question screen acquisition process. An example of the question screen acquisition process will be described with reference to the flowchart in FIG.

[0094] (Step S408) The screen output unit 141 outputs the question screen information acquired in step S407. The process returns to step S401.

[0095] The screen output unit 141 transmits, for example, question screen information to the terminal device 2. Note that the screen output unit 141 may configure a question screen from the question screen information acquired in step S407 and output the question screen. The output of such a question screen may be interpreted as an output of question screen information.

[0096] (Step S409) Question receiving unit 123 determines whether question information has been received from the user. If question information has been received, the process proceeds to step S410, and if not, the process proceeds to step S415.

[0097] (Step S410) The prompt construction unit 134 constructs a prompt using the question information received in step S409. An example of such a prompt construction process will be described with reference to the flowchart of FIG.

[0098] (Step S411) The answer acquisition unit 135 passes the prompt acquired in step S410 to the generation AI.

[0099] (Step S412) The answer acquisition unit 135 determines whether or not an answer has been acquired from the generation AI. If an answer has been acquired, the process proceeds to step S413, and if an answer has not been acquired, the process returns to step S412.

[0100] (Step S413) The output response acquisition unit 136 acquires an output response based on the response acquired in step S412.

[0101] (Step S414) The answer output unit 142 outputs the output answer acquired in step S413. The process returns to step S401.

[0102] The response output unit 142 transmits the output response to the terminal device 2, for example.

[0103] (Step S415) The learning unit 131 determines whether or not to perform the learning process. If the learning process is to be performed, the process proceeds to step S416, and if the learning process is not to be performed, the process returns to step S401.

[0104] (Step S416) The learning unit 131 assigns 1 to the counter i. Note that the learning process is performed, for example, when an instruction is received from the administrator or when a predetermined time comes.

[0105] (Step S417) The learning unit 131 determines whether or not the i-th data set exists in the data set management unit 111. If the i-th data set exists, the process proceeds to step S418, and if not, the process returns to step S401.

[0106] (Step S418) The learning unit 131 acquires the i-th data set from the data set management unit 111.

[0107] (Step S419) The learning unit 131 passes the data set acquired in step S418 to the generating AI.

[0108] (Step S420) The learning unit 131 increments the counter i by 1. The process returns to step S417.

[0109] In the flowchart of FIG. 4, the process ends when the power is turned off or an interrupt occurs to end the process.

[0110] Next, an example of the question screen acquisition process in step S407 will be described with reference to the flowchart in FIG.

[0111] (Step S501) The screen acquisition unit 133 acquires screen information that is the source of the question screen information from the storage unit 11. The screen information that is the source of the question screen information is called source information.

[0112] (Step S502) The screen acquisition unit 133 acquires two or more data set symbols from the storage unit 11.

[0113] (Step S503) The screen acquisition unit 133 places the two or more data set symbols acquired in step S502 at predetermined positions in the original information.

[0114] (Step S504) The screen acquisition unit 133 acquires operation information temporarily stored in a buffer (not shown). Note that here, the screen acquisition unit 133 normally acquires only operation information used to create a question guide or title information.

[0115] (Step S505) The screen acquisition unit 133 acquires a question guide including the operation information acquired in step S504. The screen acquisition unit 133, for example, assigns the operation information to a variable of a template of the question guide. The template of the question guide is stored, for example, in the template management unit 112.

[0116] (Step S506) The screen acquisition unit 133 places the question guide acquired in step S505 at a predetermined location in the original information.

[0117] (Step S507) Screen acquisition unit 133 acquires title information including the operation information acquired in step S504. Note that screen acquisition unit 133, for example, assigns the operation information to a variable of a template of the title information. The template of the title information is stored, for example, in template management unit 112.

[0118] (Step S508) The screen acquisition unit 133 places the title information acquired in step S505 at a predetermined location in the original information, and then returns to the upper-level processing.

[0119] Next, an example of the prompt configuration process in step S410 will be described with reference to the flowchart in FIG.

[0120] (Step S601) The prompt construction unit 134 acquires a prompt template from the template management unit 112.

[0121] (Step S602) The prompt construction unit 134 acquires the question information received in step S409.

[0122] (Step S603) The prompt construction unit 134 assigns the question information acquired in step S602 to the first variable of the prompt template acquired in step S601. The first variable is a variable into which the question information is assigned.

[0123] (Step S604) Prompt composition unit 134 acquires operation information from a buffer (not shown). This operation information is used to create a prompt.

[0124] (Step S605) Prompt construction unit 134 assigns the operation information acquired in step S604 to the second variable of the prompt template acquired in step S601. The process returns to the upper-level process. Note that the second variable is a variable into which the operation information is assigned.

[0125] Next, an example of the operation of the terminal device 2 will be described with reference to the flowchart of FIG.

[0126] (Step S701) The terminal reception unit 22 determines whether or not an operation performed by the user has been received. If the operation has been received, the process proceeds to step S702, and if the operation has not been received, the process proceeds to step S705.

[0127] (Step S702) The device processing unit 23 acquires the user identifier from the device storage unit 21 and configures an operation paired with the user identifier. The terminal transmission unit 24 transmits the operation paired with the user identifier to the information processing device 1.

[0128] (Step S703) The terminal receiving unit 25 determines whether or not an operation result has been received from the information processing device 1. If an operation result has been received, the process proceeds to step S704, and if not, the process returns to step S703. The operation result may be, for example, transitioned screen information or transitioned menu.

[0129] (Step S704) The device processing unit 23 composes an operation result to be output. The terminal output unit 26 outputs the operation result. The process returns to step S701.

[0130] (Step S705) The terminal acceptance unit 22 determines whether or not the selection of a UI widget made by the user has been accepted. If the selection of a UI widget has been accepted, the process proceeds to step S706, and if the selection of a UI widget has not been accepted, the process proceeds to step S709.

[0131] (Step S706) The device processing unit 23 acquires the user identifier from the device storage unit 21 and configures a selection paired with the user identifier. The terminal transmission unit 24 transmits the selection paired with the user identifier to the information processing device 1.

[0132] (Step S707) The terminal receiving unit 25 determines whether or not question screen information has been received from the information processing device 1. If question screen information has been received, the process proceeds to step S708, and if not, the process returns to step S707.

[0133] (Step S708) The device processing unit 23 composes a question screen to be output from the question screen information. The device output unit 26 outputs the question screen. The process returns to step S701.

[0134] (Step S709) The terminal reception unit 22 determines whether or not question information has been received from the user. If question information has been received, the process proceeds to step S710, and if question information has not been received, the process returns to step S701.

[0135] (Step S710) The device processing unit 23 acquires the user identifier from the device storage unit 21 and configures question information paired with the user identifier. The device transmission unit 24 transmits the question information paired with the user identifier to the information processing device 1.

[0136] (Step S711) The terminal receiving unit 25 determines whether or not an output response has been received from the information processing device 1. If an output response has been received, the process proceeds to step S712, and if not, the process returns to step S711.

[0137] (Step S712) The device processing unit 23 composes an output response to be output. The terminal output unit 26 outputs the output response. The process returns to step S701.

[0138] In the flowchart of FIG. 7, the process ends when the power is turned off or an interrupt occurs to end the process.

[0139] A specific example of the operation of the information system A in this embodiment will be described below.

[0140] Assume that the data set management unit 111 of the information processing device 1 currently stores the data set "Year-end tax adjustment guide, frequently asked questions, help center, Bugyo Net service, Q&A, operation guide, manual, development specification, development inquiry history."

[0141] Then, it is assumed that the learning unit 131 of the information processing device 1 has caused the generation AI to learn all of the datasets in the dataset management unit 111.

[0142] The dataset management unit 111 also stores a dataset management table shown in FIG. 8. The dataset management table is a table for identifying datasets to be used to obtain answers by the generation AI. The dataset management table manages records having "ID," "operation information condition," and "data set." The "operation information condition" is a condition related to the obtained operation information. The "data set" is a dataset identifier. The operation information condition of "ID=1" is a condition that is met if "year-end tax adjustment" or the like is present in the obtained operation information. The operation information condition of "ID=2" is a condition that is met if the operation information condition of "ID=1" is not met.

[0143] The template management unit 112 also stores a prompt template in FIG. 9(a), a question guide template in FIG. 9(b), and a title information template in FIG. 9(c).

[0144] Furthermore, it is assumed that the storage unit 11 stores screen information that is the basis of the question screen information for constructing the screen shown in FIG.

[0145] The operation of the information processing device 1 under the above circumstances will be described with reference to the conceptual diagram of FIG.

[0146] Assume that the user selects the menu item "Year-end adjustment" on the top menu 1101 of the program of the information processing device 1, then selects the menu item "Year-end adjustment processing" on the menu 1102, and then selects the menu item "Year-end adjustment processing" on the menu 1103.

[0147] Next, it is assumed that the information processing device 1 accepts the selection and outputs a screen 1104.

[0148] In this flow of operations, the operation acquisition unit 132 of the information processing device 1 acquires the operation information "year-end adjustment," which is a character string of the menu item, through the above-described processing, and temporarily stores it in a buffer not shown.

[0149] Next, the user encounters a question about the year-end tax adjustment and selects the AI ​​chat button 1105 on the screen 1104. The AI ​​chat button 1105 is a UI component for calling up a question screen.

[0150] Then, the selection receiving unit 122 of the information processing device 1 receives the selection made by the user, ie, the selection of a specific UI widget (here, the AI ​​chat button 1105).

[0151] Next, the screen acquisition unit 133 performs a question screen acquisition process as follows. That is, the screen acquisition unit 133 acquires screen information that is the source of the question screen information from the storage unit 11. Note that this screen information is screen information for configuring FIG. 10.

[0152] Next, the screen acquisition unit 133 acquires the operation information "Year-end Adjustment" from a buffer (not shown). Next, the screen acquisition unit 133 determines that the operation information "Year-end Adjustment" satisfies the operation information condition of "ID=1". Next, the screen acquisition unit 133 acquires the data set identifier "Year-end Adjustment Guide, Frequently Asked Questions, Help Center, Bugyo Net Service" of "ID=1". Then, the screen acquisition unit 133 acquires the data set symbol paired with each of the data set identifiers from the storage unit 11. Next, the screen acquisition unit 133 places (replaces) each of the four acquired data set symbols "Year-end Adjustment Guide, Frequently Asked Questions, Help Center, Bugyo Net Service" in a predetermined position in the original information. Each of these data set symbols is 1201 in FIG. 12.

[0153] Furthermore, the screen acquisition unit 133 substitutes the operation information "year-end tax adjustment" into the variable <operation information> of the question guide template (FIG. 9(b)) and acquires the question guide "Please enter a question about "year-end tax adjustment" in short sentences. Example: I want to enter XX, XX is not displayed, etc." Next, the screen acquisition unit 133 places the question guide in a predetermined location in the original information. This question guide is 1202 in FIG. 12.

[0154] Furthermore, the screen acquisition unit 133 substitutes the acquired operation information "Year-end tax adjustment" into the variable <operation information> of the template of title information (FIG. 9(c)) to acquire title information. Next, the screen acquisition unit 133 places the title information in a predetermined position of the original information. This title information is 1203 in FIG. 12.

[0155] Next, the screen output unit 141 outputs the acquired question screen information. Note that an example of a question screen based on the question screen information is shown in FIG.

[0156] Next, the user inputs the question information "I would like to redo the year-end tax adjustment for just one person" into the question field 1203 shown in FIG.

[0157] Next, the question receiving unit 123 receives question information from the user, "I would like to redo the year-end tax adjustment for just one person."

[0158] Next, the prompt composition unit 134 composes a prompt using the question information as follows. That is, the prompt composition unit 134 obtains a prompt template (FIG. 9(a)) from the template management unit 112. The prompt composition unit 134 also obtains the accepted question information and assigns it to the variable <question information> of the prompt template. The prompt composition unit 134 also obtains the operation information "year-end tax adjustment" from a buffer (not shown) and assigns it to the variable <operation information> of the prompt template. The prompt composition unit 134 also obtains the data set identifier "year-end tax adjustment guide, frequently asked questions, help center, Bugyo Net service" that matches the operation information condition and assigns this data set identifier to the variable <data set>. Through the above processing, the prompt composition unit 134 obtains the prompt shown in FIG. 13. The underlined part in FIG. 13 is the character string in which the variables have been replaced.

[0159] Next, the answer acquisition unit 135 passes the prompt of Fig. 13 to the generation AI and acquires an answer from the generation AI. An example of such an answer is shown in Fig. 14.

[0160] Next, the output answer acquisition unit 136 acquires an output answer including the answer in Fig. 14. Next, the answer output unit 142 outputs the output answer. An example of such output is shown in Fig. 15. Here, the output answer includes the entire answer. However, the output answer may include only a part of the answer.

[0161] As described above, according to this embodiment, by providing the user's operation information to the generation AI and receiving a response from the generation AI, a response that can resolve the user's questions about the program can be easily obtained.

[0162] Furthermore, according to this embodiment, by providing operation information about screen transitions to the generation AI and receiving a response from the generation AI, it is possible to easily obtain an appropriate response that can resolve the user's questions about the program.

[0163] Furthermore, according to this embodiment, by providing operation information about menu transitions to the generation AI and obtaining an answer from the generation AI, it is possible to easily obtain an appropriate answer that can resolve the user's questions about the program.

[0164] Furthermore, according to this embodiment, by obtaining answers from a generation AI that has been trained on two or more types of data sets related to program explanations, appropriate answers that can resolve the user's questions about the program can be easily obtained.

[0165] Furthermore, according to this embodiment, the dataset used by the generation AI can be shown to the user, which can encourage the user to directly use the dataset.

[0166] Furthermore, according to this embodiment, by outputting to the user a screen including subject-related information that allows the user to grasp the subject of the question, it is possible to assist the user in inputting an appropriate question that can resolve the user's doubts.

[0167] Furthermore, according to this embodiment, by outputting to the user a question guide including a string of characters that enables the user to understand the subject of the question or a screen including title information of the screen, it is possible to assist the user in entering an appropriate question that can resolve the user's doubts.

[0168] The processing in this embodiment may be implemented by software. This software may be distributed by software download or the like. This software may also be recorded on a recording medium such as a CD-ROM and distributed. This also applies to other embodiments in this specification. The software implementing the information processing device 1 in this embodiment is the following program. That is, this program causes a computer to function as an operation acquisition unit that acquires operation information related to a user's operation, a question acceptance unit that accepts question information from the user, a prompt composition unit that constructs a prompt having the operation information acquired by the operation acquisition unit and the question information accepted by the question acceptance unit, an answer acquisition unit that passes the prompt to a generation AI and acquires an answer from the generation AI, an output answer acquisition unit that acquires an output answer based on the answer acquired by the answer acquisition unit, and an answer output unit that outputs the output answer acquired by the output answer acquisition unit.

[0169] FIG. 16 is a block diagram of a computer system 300 that executes the programs described in this specification to realize the information processing device 1 and the like according to the various embodiments described above.

[0170] In FIG. 16, a computer system 300 includes a computer 301 including a CD-ROM drive, a keyboard 302, a mouse 303, and a monitor 304.

[0171] 16, computer 301 includes, in addition to CD-ROM drive 3012, MPU 3013, bus 3014 connected to CD-ROM drive 3012 etc., ROM 3015 for storing programs such as a boot-up program, RAM 3016 connected to MPU 3013 for temporarily storing instructions of application programs and providing temporary storage space, and hard disk 3017 for storing application programs, system programs, and data. Although not shown here, computer 301 may further include a network card for providing connection to a LAN.

[0172] A program that causes computer system 300 to execute the functions of information processing device 1 and the like of the above-described embodiment may be stored on CD-ROM 3101, inserted into CD-ROM drive 3012, and then transferred to hard disk 3017. Alternatively, the program may be transmitted to computer 301 via a network (not shown) and stored on hard disk 3017. The program is loaded into RAM 3016 when executed. The program may also be loaded directly from CD-ROM 3101 or the network.

[0173] The program does not necessarily include an operating system (OS) or a third-party program that causes the computer 301 to execute the functions of the information processing device 1 of the above-described embodiment. The program only needs to include instructions that call appropriate functions (modules) in a controlled manner and achieve desired results. How the computer system 300 operates is well known, and a detailed description thereof will be omitted.

[0174] In addition, in the above program, the steps of transmitting information and receiving information do not include processing performed by hardware, such as processing performed by a modem or interface card in the transmission step (processing that can only be performed by hardware).

[0175] The computer that executes the program may be a single computer or a plurality of computers, that is, it may perform centralized processing or distributed processing.

[0176] Furthermore, in each of the above embodiments, it goes without saying that two or more communication means present in one device may be physically realized by one medium.

[0177] Furthermore, in each of the above embodiments, each process may be realized by centralized processing in a single device, or may be realized by distributed processing in a plurality of devices.

[0178] The present invention is not limited to the above-described embodiment, and various modifications are possible, and it goes without saying that these modifications are also included within the scope of the present invention. [Industrial Applicability]

[0179] As described above, the information processing device 1 according to the present invention has the effect of easily obtaining answers that can resolve a user's questions about a program, and is useful as a server or the like that easily provides appropriate answers to a user's questions. [Explanation of symbols]

[0180] 1. Information processing equipment 2. Terminal Device 3 Generation AI device 11 Storage area 12 Reception 13 Processing section 14 Output section 21 Terminal storage section 22 Terminal Reception 23 Terminal processing section 24 Terminal transmitter 25 Terminal receiving section 26 Terminal Output Unit 111 Data Collection Management Unit 112 Template Management Department 121 Operation reception section 122 Selection Reception Department 123 Question Reception Department 131 Learning Department 132 Operation acquisition part 133 Screen acquisition section 134 Prompt Component 135 Answer acquisition part 136 Output answer acquisition part 141 Screen Output Section 142 Answer output section

Claims

1. Computer, an operation acquisition unit that acquires operation information related to a user's operation; a question receiving unit that receives question information from the user; a prompt composition unit that composes a prompt having the operation information acquired by the operation acquisition unit and the question information accepted by the question acceptance unit; an answer acquisition unit that passes the prompt to a generation AI and acquires an answer from the generation AI; an output answer acquisition unit that acquires an output answer based on the answer acquired by the answer acquisition unit; a program for causing the output response acquisition unit to function as an answer output unit that outputs the output response acquired by the output response acquisition unit;

2. The operation acquisition unit Obtain transition information, which is operation information regarding screen transitions, The prompt composition unit 2. The program of claim 1, causing the computer to function as a prompt having the transition information and the question information.

3. The operation acquisition unit 3. The program according to claim 2, for causing the computer to function as acquiring transition information relating to a menu transition of the user, the transition information including a character string of a menu item selected by the user.

4. The program of claim 1 , further causing the computer to function as a learning unit that causes the generating AI to learn two or more types of data sets related to the description of the program operated by the user.

5. a screen acquisition unit that acquires screen information of a screen for inputting the question information, the screen information including data set symbols indicating each of the two or more types of data sets; The program according to claim 4 , further causing the computer to function as a screen output unit that outputs the screen information acquired by the screen acquisition unit.

6. Each of the two or more screens operated by the user has a UI component that calls up a question screen for passing question information to the generation AI, a selection receiving unit that receives a selection of the UI component; a screen acquisition unit that, when the selection receiving unit receives the selection of the UI component, uses the operation information to generate question screen information, which is screen information of a screen including target-related information that can grasp the target of a question, and is screen information of a question screen for inputting the question information to be passed to the generation AI; The program according to claim 1 , further causing the computer to function as a screen output unit that outputs the question screen information.

7. The program according to claim 6, for causing the computer to function as the target-related information being a question guide including a character string that enables the user to understand the target of the question to be entered, or title information of the screen information.

8. an operation acquisition unit that acquires operation information related to a user's operation; a question receiving unit that receives question information from the user; a prompt composition unit that composes a prompt having the operation information acquired by the operation acquisition unit and the question information accepted by the question acceptance unit; an answer acquisition unit that passes the prompt to a generation AI and acquires an answer from the generation AI; an output answer acquisition unit that acquires an output answer based on the answer acquired by the answer acquisition unit; an answer output unit that outputs the output answer acquired by the output answer acquisition unit.

9. An information processing method implemented by an operation acquisition unit, a question reception unit, a prompt configuration unit, an answer acquisition unit, an output answer acquisition unit, and an answer output unit, an operation acquisition step in which the operation acquisition unit acquires operation information related to a user's operation; a question receiving step in which the question receiving unit receives question information from the user; a prompt construction step in which the prompt construction unit constructs a prompt having the operation information acquired by the operation acquisition unit and the question information accepted by the question acceptance unit; an answer acquisition step in which the answer acquisition unit passes the prompt to a generation AI and acquires an answer from the generation AI; an output answer acquisition step in which the output answer acquisition unit acquires an output answer based on the answer acquired by the answer acquisition unit; an answer output step in which the answer output unit outputs the output answer acquired by the output answer acquisition unit.

Images