Information processing apparatus, information processing method, and information processing program

Abstract

To present information so as to appropriately adapt to interaction with voice and interaction through screens.SOLUTION: An information processing apparatus configured to present information on a recommendation to a user on the basis of interaction with the user, includes a mode selection unit, a generation unit, and a presentation control unit. The mode selection unit selects one of a first interaction mode for voice interaction and a second interaction mode for screen interaction. The generation unit generates question request information for requesting an external device to output a question to narrow down recommendations, the question request information including form designation information that designates the form of a question. For example, when the first interaction mode is selected, the generation unit generates first-form designation information for designating a first form, as the form of the question, and generates, when the second interaction mode is selected, second-form designation information for designating a second form, which is different from the first form, as the form of the question.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The present invention relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] Some recent AI chatbots have advanced text interpretation and generation capabilities that can search for information on the web in response to user questions or requests and provide a summary of the search results. Such AI chatbots can also listen to user requests and make suggestions about related information and services. For this reason, for example, by linking with AI chatbots via an API (Application Programming Interface), it is possible to create applications that provide recommendation functions.

[0003] Incidentally, Patent Document 1 discloses a technology in which a chatbot is used for repeated question and answer exchanges with a user through voice dialogue (conversational input) to present recommendation information suited to the user. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2018-92585 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, the above-mentioned conventional technologies are not necessarily capable of realizing information presentation that can appropriately accommodate both dialogue via voice (conversational input) and dialogue via a screen (screen selection input).

[0006] For example, a user may find it difficult to speak depending on the situation, such as the presence of people around. For example, after a user starts conversational input to obtain recommendation information, it may become difficult for the user to speak. In such a case, it is desirable to be able to switch to screen selection input even midway through, and it is also required that the dialogue progress appropriately according to the screen selection input. The above-mentioned conventional technology does not disclose a method for meeting these needs.

[0007] For this reason, it can be said that there is room for improvement in the above-mentioned conventional technology in terms of realizing information presentation that can appropriately accommodate both dialogue via voice and dialogue via a screen.

[0008] The present invention has been made in consideration of the above, and proposes an information processing device, an information processing method, and an information processing program that can realize information presentation that can appropriately respond to both dialogue via voice and dialogue via a screen. [Means for solving the problem]

[0009] The information processing device described in claim 1 is an information processing device that presents information regarding a recommendation target to a user based on a dialogue with the user, and includes a mode selection unit that selects one of a first dialogue mode in which dialogue is conducted via voice and a second dialogue mode in which dialogue is conducted via a screen, a generation unit that generates question request information that requests an external device to output a question for narrowing down the recommendation targets, the question request information including format designation information that designates a format of the question, and a presentation control unit that causes the question output from the external device in response to the question request information to be presented to the user in a format corresponding to the dialogue mode selected by the mode selection unit, wherein when the first dialogue mode is selected, the generation unit generates first format designation information that designates a first format as the format of the question, and when the second dialogue mode is selected, generates second format designation information that designates a second format different from the first format as the format of the question.

[0010] The information processing method described in claim 13 is an information processing method executed by an information processing device that presents information regarding a recommendation target to a user based on a dialogue with the user, and includes a mode selection step of selecting one of a first dialogue mode in which dialogue is conducted via voice and a second dialogue mode in which dialogue is conducted via a screen, a generation step of generating question request information that requests an external device to output a question for narrowing down the recommendation targets, the question request information including format designation information that designates a format of the question, and a presentation control step of presenting the question output from the external device in accordance with the question request information to the user in a format corresponding to the dialogue mode selected by the mode selection step, wherein the generation step generates first format designation information that designates a first format as the format of the question when the first dialogue mode is selected, and generates second format designation information that designates a second format different from the first format as the format of the question when the second dialogue mode is selected.

[0011] The information processing program described in claim 14 is an information processing program executed by an information processing device that presents information regarding a recommendation target to a user based on a dialogue with the user, and causes the information processing device to execute a mode selection step of selecting one of a first dialogue mode in which dialogue is conducted via voice and a second dialogue mode in which dialogue is conducted via a screen, a generation step of generating question request information that requests an external device to output a question for narrowing down the recommendation targets, the question request information including format designation information that designates a format of the question, and a presentation control step of presenting the question output from the external device in response to the question request information to the user in a manner corresponding to the dialogue mode selected by the mode selection step, wherein the generation step generates first format designation information that designates a first format as the format of the question when the first dialogue mode is selected, and generates second format designation information that designates a second format different from the first format as the format of the question when the second dialogue mode is selected. [Brief description of the drawings]

[0012] [Figure 1] FIG. 1 is a diagram illustrating an example of a system according to an embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of dialogue control according to the embodiment. [Diagram 3] FIG. 3 shows a specific example of a dialogue proceeding in a voice dialogue mode and a specific example of a dialogue proceeding in a screen selection mode. [Figure 4] FIG. 4 is a diagram illustrating an example of the configuration of a terminal device according to the embodiment. [Diagram 5] FIG. 5 is a diagram (1) showing the processing procedure in the voice dialogue mode. [Figure 6] FIG. 6 is a diagram (2) showing the processing procedure in the voice dialogue mode. [Figure 7] FIG. 7 is a diagram showing a processing procedure in the screen selection mode. [Figure 8] FIG. 8 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the terminal device according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] [Embodiment] Hereinafter, an embodiment of the present invention will be described in detail with reference to the accompanying drawings. In this specification and the drawings, components having substantially the same functional configurations are denoted by the same reference numerals, and duplicated explanations will be omitted.

[0014] One or more embodiments (including examples, modifications, and application examples) described below can be implemented independently. Meanwhile, at least a part of the embodiments described below may be implemented in appropriate combination with at least a part of another embodiment. These embodiments may include novel features different from each other. Thus, these embodiments may contribute to solving different purposes or problems and may provide different effects.

[0015] [1. System Configuration] First, the configuration of a system according to an embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of a system according to an embodiment. Fig. 1 shows system 1 as an example of a system according to an embodiment. Information processing according to the proposed technology of the present invention (hereinafter abbreviated as "information processing according to an embodiment") is realized in system 1.

[0016] 1, the system 1 includes a terminal device 10 and an external device 100. The terminal device 10 and the external device 100 are connected to each other via a network N so as to be able to communicate with each other via a wired or wireless connection. The system 1 may include any number of terminal devices 10 and any number of external devices 100.

[0017] The terminal device 10 may be an information processing terminal used by a user U who wishes to receive various pieces of recommended information in a dialogue through a recommendation service realized between the terminal device 10 and the external device 100. In other words, the terminal device 10 is an information processing device that presents information related to a recommendation target to the user U based on a dialogue with the user U.

[0018] For example, the terminal device 10 is a smartphone, a wearable device, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), or the like.

[0019] As another example, the terminal device 10 may be implemented as a navigation device built into or mounted on a vehicle, i.e., an in-vehicle device. The terminal device 10 as an in-vehicle device may have not only a navigation function but also a recording function (drive recorder function).

[0020] The external device 100 may be any server device as long as it is a device capable of realizing a dialogue with the user U. In this embodiment, the external device 100 is a chatbot device that operates as a general-purpose chatbot. The external device 100 may be equipped with a so-called generative AI (artificial intelligence that can create various contents and ideas such as conversations, stories, images, videos, and music). In addition, a machine learning model is used in the generative AI, and for example, repeated learning is performed so that a highly accurate dialogue can be realized with the user U.

[0021] The information processing according to the embodiment is characterized in that the terminal device 10 customizes the chatbot device by sending various commands to the chatbot device so that the general-purpose chatbot device (external device 100) can be used more appropriately in accordance with a first dialogue mode (conversational input) in which dialogue is performed via voice and a second dialogue mode (screen selection input) in which dialogue is performed via a screen. The terminal device 10 operates according to the information processing program according to the embodiment.

[0022] [2. Dialogue control example] An example of dialogue control realized by the terminal device 10 according to the embodiment will be described. As described above, the external device 100 operates as a general-purpose chatbot. Therefore, when the user U switches from a first dialogue mode to a second dialogue mode, or when the user U switches from the second dialogue mode to the first dialogue mode, the terminal device 10 controls the dialogue by giving various instructions to the external device 100 so that the external device 100 can realize an optimal dialogue according to the current dialogue mode. FIG. 2 is a diagram showing an example of dialogue control according to the embodiment.

[0023] In the following embodiment, the first dialogue mode in which dialogue is conducted via voice is referred to as the "voice dialogue mode," and the second dialogue mode in which dialogue is conducted via a screen is referred to as the "screen selection mode." In the "voice dialogue mode," the user U inputs information to the terminal device 10 by voice. On the other hand, in the "screen selection mode," the user U inputs information by performing a touch operation on the display screen of the terminal device 10.

[0024] First, a description will be given of an example of dialogue control in the case where the user U selects the voice dialogue mode. When the terminal device 10 accepts the selection of the voice dialogue mode, it generates various information corresponding to the voice dialogue mode based on the first template information TP1 (step S11).

[0025] The first template information TP1 is preconditioned to generate “question request information” that requests the external device 100 to output a question for narrowing down the recommendation targets (e.g., recommended visiting spots) of the type indicated by the “type designation information.” The type of the recommendation target may be recognized based on an input by the user U.

[0026] For example, when a user U inputs an utterance such as "Please tell me some recommended weekend spots," the terminal device 10 generates type designation information indicating recommended visiting spots as the type of recommendation target, and generates question request information that requests the external device 100 to output a question to narrow down the recommended visiting spots.

[0027] In addition, the first template information TP1 is pre-conditioned to generate "first format designation information" that includes information specifying the output format (first format) of the questions, which specifies that N open-ended questions are to be output one by one in sequence according to the answers of the user U.

[0028] Here, N, which is a value indicating the number of questions to be presented (the number of questions presented to the user U), may be changed arbitrarily. For example, when "N=2" is given in advance as a fixed value, the terminal device 10 generates "first format designation information" that designates two open-ended questions to be output one by one in sequence according to the answers of the user U. As another example, when "N=3" is set by the user U, the terminal device 10 may generate "first format designation information" that designates three open-ended questions to be output one by one in sequence according to the answers of the user U.

[0029] Next, the terminal device 10 uses the information generated according to the first template information TP1 to control the output of the external device 100 as a chatbot (step S12). For example, the terminal device 10 controls the output of the external device 100 by transmitting question request information and first format designation information to the external device 100.

[0030] Here, for example, if the question request information and the first format designation information are generated in response to a request from the user U to know recommended weekend outing destinations, the external device 100 generates a question (question sentence) such as "What is your budget for going out?" and outputs the generated question to the terminal device 10. Then, the external device 100 sequentially outputs the next question to the terminal device 10 according to the answer of the user U (step S13). At this time, the terminal device 10 presents the question output by the external device 100 in a presentation method according to the voice dialogue mode. More specifically, the terminal device 10 synthesizes a question voice in a voice format from the question output by the external device 100 and outputs this from the speaker of the terminal device. The user U inputs a spoken voice of the answer according to the output voice to the microphone of the terminal device 10.

[0031] As a result, a dialogue DL1 via voice is established between the user U and the external device 100, and the external device 100 can obtain various answers from the user U via the terminal device 10. Note that the question voices synthesized from the question of the external device 100 are presented one by one in sequence according to the answers of the user U in order to ensure the convenience of the user U in the voice dialogue. For example, if multiple question voices are output simultaneously, it may be difficult to understand the contents of each question voice, but the first format designation information can prevent such a situation.

[0032] The external device 100 searches for recommended visiting spots based on the answer of the user U obtained in the dialogue DL1 through voice, and outputs information about the recommended visiting spots to the terminal device 10 (step S14). The terminal device 10 outputs the information about the recommended visiting spots (information about the recommended target) output by the external device 100 from a speaker.

[0033] Next, a description will be given of an example of dialogue control in the case where the user U selects the screen selection mode. When the terminal device 10 receives the selection of the screen selection mode, the terminal device 10 generates various information corresponding to the voice dialogue mode based on the second template information TP2 (step S21).

[0034] The second template information TP2 is preconditioned to generate "question request information" that requests the external device 100 to output a question for narrowing down the recommendation targets (e.g., recommended visiting spots) of the type indicated by the "type designation information." The type of the recommendation target may be recognized based on an input by the user U. This is similar to the first template information TP1.

[0035] In addition, the second template information TP2 is pre-conditioned to generate "second format designation information" that includes information specifying that N multiple-choice questions should be output as a list separated by commas, as format designation information that specifies the output format (second format) of the questions.

[0036] Here, N, which is a value indicating the number of questions to be presented (the number of questions to be presented to the user U), may be changed arbitrarily. For example, when "N=2" is given in advance as a fixed value, the terminal device 10 generates "second format designation information" that designates outputting a list of two multiple-choice questions separated by a comma. As another example, when "N=3" is given by the user U, the terminal device 10 may generate "second format designation information" that designates outputting a list of three multiple-choice questions separated by a comma.

[0037] Next, the terminal device 10 uses the information generated according to the second template information TP2 to control the output of the external device 100 as a chatbot (step S22). For example, the terminal device 10 controls the output of the external device 100 by transmitting question request information and second format designation information to the external device 100.

[0038] Here, for example, if the question request information and the second format designation information are generated in response to a request from the user U to know recommended weekend destinations, the external device 100 generates a question (question sentence) such as "Do you want to take a walk in the mountains or forests?" and outputs a list of the generated questions separated by commas to the terminal device 10 (step S23). Then, the terminal device 10 presents the question output by the external device 100 to the user U. Specifically, the terminal device 10 presents the question in a presentation format according to the screen selection mode.

[0039] For example, the terminal device 10 generates question images in an image format from the list of questions output by the external device 100, and displays the images on the display screen of the terminal device 10. For example, the terminal device 10 generates a dialogue screen that allows a user to answer yes / no to each question included in the list, and displays the generated dialogue screen on the display screen. At this time, the terminal device 10 may simultaneously display a number of N questions grouped together in a state separated by commas on the display screen of the terminal device 10. As a result, a dialogue DL2 via the screen is established between the user U and the external device 100, and the external device 100 can obtain various answers from the user U via the terminal device 10. The questions are separated by commas so that the terminal device 10 can distinguish the questions when generating the dialogue screen.

[0040] The external device 100 searches for recommended visiting spots based on the answer of the user U obtained in the dialogue DL2 via the screen, and outputs information about the recommended visiting spots to the terminal device 10 (step S24). The terminal device 10 displays the information about the recommended visiting spots (information about the recommended target) output by the external device 100 on the display screen.

[0041] [3. Specific examples of dialogue progression] 3 is a diagram showing a specific example of a dialogue proceeding in a voice dialogue mode and a specific example of a dialogue proceeding in a screen selection mode. FIG. 3 shows a scene in which a dialogue takes place between a user U who wants to know recommended weekend destinations and the external device 100.

[0042] First, a specific example of a dialogue proceeding in a voice dialogue mode, that is, a dialogue DL1 mediated through voice, will be described.

[0043] First, when the external device 100 generates a question QT11 such as "How much is your budget for going out?", the terminal device 10 outputs a question voice QS11 synthesized from the question QT11 from the speaker.

[0044] In response to the question voice QS11, the user U inputs a response AN11, "Please keep it to 10,000 yen or less," into the microphone by speech. In this case, the external device 100 then generates a question QT12, "What kind of genre are the spots you are interested in?" The terminal device 10 outputs the question voice QS12 synthesized from the question QT12 from the speaker.

[0045] In response to the question voice QS12, it is assumed that the user U inputs an answer AN12, "I want to go to the zoo," into the microphone by speech. In this case, it is assumed that the external device 100 then generates a question sentence QT13, "What is the acceptable range of travel time?" The terminal device 10 outputs the question voice QS13 synthesized from the question sentence QT13 from the speaker.

[0046] In response to the question voice QS13, it is assumed that the user U speaks an answer AN13, "Within one hour one way." into the microphone.

[0047] In this way, when question voices corresponding to a prescribed number of three question sentences (N=3) are presented one by one in sequence according to the answers of the user U, the external device 100 searches for recommended visiting spots based on the answers AN11 to AN13, and outputs information on the search results to the terminal device 10. At this time, the external device 100 may also search for a route to the recommended visiting spots, and output information indicating the route to the terminal device 10.

[0048] Then, the terminal device 10 presents the information of the search result to the user U as recommendation information RC1 regarding recommended visiting spots. For example, the terminal device 10 synthesizes a voice to read out the recommendation information RC1, and outputs the synthesized voice from a speaker. FIG. 3 shows an example in which recommendation information RC1 such as "XX zoo and amusement park is recommended" is output from a speaker.

[0049] Next, a specific example of a dialogue that proceeds in the screen selection mode, that is, a dialogue DL2 via a screen, will be described.

[0050] First, the external device 100 generates a specified number of three questions (N=3), namely, question QT21, "Would you like to take a walk in the mountains or forest?", question QT22, "Would you like to take a bath in a hot spring?", and question QT23, "Would you like to interact with animals?", and outputs a list of these to the terminal device 10.

[0051] In this case, the terminal device 10 generates a dialogue screen G2 in which a "Yes" button and a "No" button are associated with each of the questions QT21, QT22, and QT23, as shown in FIG. 3. The user U can answer "Yes" or "No" to each question by a screen selection operation (for example, a touch operation). The answer is transmitted from the terminal device 10 to the external device 100, and the external device 100 searches for recommended visiting spots based on the answer "Yes" or "No" to each question, and outputs information on the search results to the terminal device 10. At this time, the external device 100 may also search for a route to the recommended visiting spot and output information indicating the route to the terminal device 10.

[0052] Then, the terminal device 10 presents the information of the search result to the user U as recommendation information RC2 related to recommended visiting spots. For example, as shown in Fig. 3, the terminal device 10 generates a recommendation screen G21 on which the recommendation information RC2 is displayed, and displays the generated recommendation screen G21. Fig. 3 shows an example in which the recommendation screen G21 corresponding to the recommendation information RC2 "We recommend △△ Zoo and Nature Park" is displayed on the display screen.

[0053] [4. Functional Configuration] A configuration example of the terminal device 10 will be described with reference to Fig. 4. Fig. 4 is a diagram showing a configuration example of the terminal device 10 according to the embodiment. As shown in Fig. 4, the terminal device 10 has a communication unit 11, an input unit 12, an output unit 13, a storage unit 14, and a control unit 15.

[0054] (Communications Department 11) The communication unit 11 is realized by, for example, a network interface card (NIC) etc. The communication unit 11 is connected to a network N by wire or wirelessly, and transmits and receives information to and from the external device 100, for example.

[0055] (Input section 12) The input unit 12 is an input device that accepts various inputs from the outside. For example, the input unit 12 is an operation device such as a keyboard, a mouse, or operation keys that allows the user U to perform various operations. If a touch panel is adopted in the terminal device 10, the touch panel is also included in the input unit 12. In this case, the user U performs various operations by touching the touch panel. The input unit 12 also includes a microphone that accepts voice input by speaking.

[0056] (Output section 13) The output unit 13 is a device that outputs various types of information to the outside, such as sound, light, vibration, and image. The output unit 13 outputs various types of information to the user U under the control of the control unit 15. The output unit 13 includes a display device that displays various types of information. The display device is, for example, a liquid crystal display or an organic electroluminescence display (OLED). The output unit 13 may be a touch panel type display device. In this case, the input unit 12 and the output unit 13 may be regarded as an integrated configuration. The output unit 13 may be a speaker.

[0057] (Storage unit 14) The storage unit 14 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 14 may store, for example, data and programs related to the information processing according to the embodiment. According to the example of Fig. 4, the storage unit 14 may include a first template storage unit 14a, a second template storage unit 14b, a voice dialogue history storage unit 14c, and a screen dialogue history storage unit 14d.

[0058] The first template storage unit 14a stores first template information TP1. The second template storage unit 14b stores second template information TP2. The voice dialogue history storage unit 14c stores a dialogue log of a dialogue DL1 via voice. The screen dialogue history storage unit 14d stores a dialogue log of a dialogue DL2 via a screen. The dialogue log includes questions generated by the external device 100 and the user's answers to the questions in chronological order.

[0059] (Regarding the control unit 15) The control unit 15 is realized by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), etc., executing various programs (for example, the information processing program according to the embodiment) stored in a storage device inside the terminal device 10 using a RAM as a working area. The control unit 15 is also realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0060] As shown in Fig. 4, the control unit 15 has a reception unit 15a, a mode selection unit 15b, a generation unit 15c, a transmission / reception unit 15d, and a presentation control unit 15e, and realizes or executes the functions and actions of information processing described below. Note that the internal configuration of the control unit 15 is not limited to the configuration shown in Fig. 4, and may be other configurations as long as they perform information processing described below. Also, the connection relationship between the processing units of the control unit 15 is not limited to the connection relationship shown in Fig. 4, and may be other connection relationships.

[0061] (Reception section 15a) The reception unit 15a receives information input via the input unit 12. For example, the reception unit 15a receives voice input by speaking via a microphone or touch input via a touch panel. For example, the reception unit 15a receives information indicating an answer by the user U to a question.

[0062] (Mode selection unit 15b) The mode selection unit 15b selects one of the dialogue modes, a voice dialogue mode (first dialogue mode) and a screen selection mode (second dialogue mode). For example, the mode selection unit 15b accepts a selection of one of the dialogue modes, the voice dialogue mode and the screen selection mode, from the user U.

[0063] The user U may switch to the screen selection mode while engaging in a dialogue DL1 via voice in the voice dialogue mode. In such a case, the mode selection unit 15b accepts switching from the voice dialogue mode to the screen selection mode. The user U may switch to the voice dialogue mode while engaging in a dialogue DL2 via a screen in the screen selection mode. In such a case, the mode selection unit 15b accepts switching from the screen selection mode to the voice dialogue mode.

[0064] (Generation part 15c) The generating unit 15c generates question request information that requests the external device 100 to output a question for narrowing down the recommendation targets, and includes format designation information that designates the format of the question. For example, the generating unit 15c may generate question request information that further includes type designation information that designates the type of the recommendation target (the category to which the recommendation target belongs). The types of recommendation targets include, for example, "visiting spots," "cooking recipes," and "music content."

[0065] In this example, the user U can specify the type of recommendation target that the user wants to be proposed from among "visiting spots," "cooking recipes," "music content," and the like. The type specified by the user U may be accepted by the accepting unit 15a. The user U can specify the type by speech, or can specify the type by a touch operation on the touch panel.

[0066] Furthermore, when the voice dialogue mode is selected, the generating unit 15c generates first format designation information that designates a first format as the format of the question. For example, the generating unit 15c generates first format designation information including information that designates that an open-ended question is to be output as the first format. Note that the generating unit 15c may determine a value N indicating the number of questions, and include information that designates that N questions are to be output one by one in response to the answers of the user U in the first format designation information.

[0067] On the other hand, when the screen selection mode is selected, the generating unit 15c generates second format designation information that designates the second format as the question format. For example, the generating unit 15c generates second format designation information including information that designates outputting a multiple choice question as the second format. Note that the generating unit 15c may determine a value N indicating the number of questions, and include in the second format designation information information that designates outputting a list in which each question among the N questions is distinguished (for example, separated by a comma).

[0068] (Transmitter / receiver 15d) The transmission / reception unit 15d is a processing unit that manages transmission and reception of information with the external device 100. For example, the transmission / reception unit 15d controls the output of the external device 100 as a chatbot by transmitting question request information and format designation information to the external device 100. In addition, the transmission / reception unit 15d receives a question output by the external device in response to question request information including format designation information.

[0069] When an answer from the user U to a question is accepted, the transmitting / receiving unit 15d transmits information indicating the accepted answer to the external device 100. In addition, the transmitting / receiving unit 15d receives recommendation information output by the external device 100 based on the answer from the user U.

[0070] (Presentation control unit 15e) The presentation control unit 15e presents the question output from the external device 100 in response to the question request information including the format designation information to the user U in a format corresponding to the dialogue mode selected by the mode selection unit 15b.

[0071] For example, when the voice dialogue mode is selected, the presentation control unit 15e synthesizes a voice-format question voice from the question output by the external device 100, and outputs the synthesized question voice from the speaker.

[0072] For example, when the screen selection mode is selected, the presentation control unit 15e generates a question image in an image format from the list of questions output by the external device 100, and displays the generated question image on the display screen. For example, the presentation control unit 15e may generate a dialogue screen that allows a user to answer yes / no for each question included in the list, and display the generated dialogue screen on the display screen.

[0073] [5. Processing procedure in voice dialogue mode] The procedure of information processing realized between the terminal device 10 and the external device 100 in the voice dialogue mode will be described with reference to Fig. 5 and Fig. 6. The scene illustrated in Fig. 5 and Fig. 6 corresponds to a detailed example of the voice dialogue mode described in Fig. 2.

[0074] Fig. 5 is a diagram (1) showing a processing procedure in the voice dialogue mode. In the example of Fig. 5, it is assumed that the user U selects the voice dialogue mode and inputs a voice message such as "Tell me some recommended weekend getaways" into the microphone of the terminal device 10.

[0075] The generating unit 15c of the terminal device 10 generates information (control information for controlling the external device 100) according to the voice dialogue mode based on the first template information TP1, and transmits the generated information to the external device (step S51). For example, the generating unit 15c recognizes "recommended visiting spots" as the type of recommendation target based on the content indicated by the input voice, and generates a prompt main sentence TP11 such as "You are a travel planner. You are consulting with someone looking for a weekend outing spot." The prompt main sentence TP11 corresponds to type designation information.

[0076] Moreover, the generating unit 15c generates question request information TP12, which reads "To search for possible destinations, please output a question sentence according to the following conditions." based on the first template information TP1.

[0077] The generating unit 15c generates first format designation information TP13 that defines the output format of the questions as follows: starting point [Kawagoe City, Saitama Prefecture], questions in a format that allows free response, the number of questions [3], outputting the questions one by one in sequence according to the response, etc. The generating unit 15c may determine the starting point according to the current location of the terminal device 10 or the contents of the user U's presettings, and may determine the number N of questions according to the contents of the user U's presettings.

[0078] Then, the transmitting / receiving unit 15d transmits to the external device 100 the prompt main text TP11 (type designation information), the question request information TP12, and the first format designation information TP13.

[0079] The external device 100 generates a first question QT11 according to generation information corresponding to the voice dialogue mode (e.g., question request information TP12 and first format designation information TP13) (step S52). Then, the external device 100 transmits the first question QT11 to the terminal device 10 (step S53). FIG. 5 shows an example in which the external device 100 transmits the question QT11, "How much do you plan to spend on your trip?" to the terminal device 10.

[0080] When the transmission / reception unit 15d receives the first question QT11, the presentation control unit 15e of the terminal device 10 synthesizes a voice-format question QS11 from the question QT11 and outputs the voice question QS11 from the speaker (step S54).

[0081] In response to the question voice QS11, the user U inputs an answer AN11, "Please keep it to 10,000 yen or less," into the microphone. In this case, in response to the answer AN11 being accepted by the accepting unit 15a, the transmitting / receiving unit 15d transmits information indicating the answer AN11 to the external device 100 (step S55).

[0082] The external device 100 then generates a second question QT12 in response to the generation information according to the voice dialogue mode (step S56). Then, the external device 100 transmits the second question QT12 to the terminal device 10 (step S57). Fig. 5 shows an example in which the external device 100 transmits the question QT12, "What type of spots are you interested in?" to the terminal device 10.

[0083] When the second question QT12 is received by the transmitting / receiving unit 15d, the presentation control unit 15e synthesizes a voice-format question QS12 from the question QT12, and outputs the voice question QS12 from the speaker (step S58).

[0084] In response to the question voice QS12, it is assumed that the user U inputs an answer AN12, "I want to go to the zoo," into the microphone. In this case, in response to the answer AN12 being accepted by the accepting unit 15a, the transmitting / receiving unit 15d transmits information indicating the answer AN12 to the external device 100 (step S59).

[0085] The external device 100 then generates a third question QT13 in accordance with the generation information corresponding to the voice dialogue mode (step S60). Then, the external device 100 transmits the third question QT13 to the terminal device 10 (step S61). Fig. 5 shows an example in which the external device 100 transmits the question QT13 "How much travel time is acceptable?" to the terminal device 10.

[0086] When the third question QT13 is received by the transmitting / receiving unit 15d, the presentation control unit 15e synthesizes a voice-format question QS13 from the question QT13, and outputs the voice question QS13 from the speaker (step S62).

[0087] We now move on to the explanation of Fig. 6. Fig. 6 is a diagram (2) showing the processing procedure in the voice dialogue mode. As shown in Fig. 6, it is assumed that the user U inputs an answer AN13, "Within one hour one way," into the microphone in response to the question voice QS13. In this case, in response to the answer AN13 being accepted by the accepting unit 15a, the transmitting / receiving unit 15d transmits information indicating the answer AN13 to the external device 100 (step S63).

[0088] Furthermore, at the time of step S63, question voices corresponding to a prescribed number of three question sentences (N=3) have been presented one by one in sequence in response to the answers of the user U, and answers to each question voice have been acquired. Therefore, the generation unit 15c may generate recommendation request information TP14 requesting output of recommendation information based on the answers of the user U obtained so far. Furthermore, the transmission / reception unit 15d may transmit the recommendation request information TP14 to the external device 100 together with information indicating the answer AN13, as shown in FIG. 6. FIG. 6 shows an example in which the transmission / reception unit 15d transmits recommendation request information TP14 stating, "Based on the above answers, please output one place to go and a guide to that spot."

[0089] When the external device 100 receives the recommendation request information TP14, it searches for recommended visiting spots based on the replies AN11 to AN13, and generates recommendation information RC1 according to the search results (step S64).

[0090] Then, the external device 100 transmits the recommendation information RC1 to the terminal device 10 (step S65). Fig. 6 shows an example in which the external device 100 transmits the recommendation information RC1 to the terminal device 10, saying "We recommend XX Zoo Amusement Park. It is a theme park that combines an amusement park and a zoo, located 50 minutes by car from Kawagoe City. The average budget is about 5,000 yen per adult."

[0091] When the transmission / reception unit 15d receives the recommendation information RC1, the presentation control unit 15e synthesizes a voice that reads out the recommendation information RC1, and outputs the synthesized voice from the speaker (step S66).

[0092] The processing procedure in the voice dialogue mode has been described above with reference to Fig. 5 and Fig. 6. In the example of Fig. 5 and Fig. 6, the external device 100 generates one question sentence every time it acquires an answer from the user U from the terminal device 10, and transmits the generated question sentence to the terminal device 10. However, the external device 100 may generate all three questions QT11 to QT13 at the timing of step S52 when it receives generation information according to the voice dialogue mode (e.g., question request information TP12 and first format designation information TP13) from the terminal device 10. Then, the external device 100 may output the questions QT11 to QT13 to the terminal device 10 one by one.

[0093] 6, the generating unit 15c generates the recommendation request information TP14 requesting one recommended visiting spot, but may generate the recommendation request information TP14 requesting multiple recommended visiting spots. The requested number of recommended visiting spots may be included in the pre-set contents of the user U.

[0094] [6. Processing procedure in screen selection mode] A procedure of information processing implemented between the terminal device 10 and the external device 100 in the screen selection mode will be described with reference to Fig. 7. The scene illustrated in Fig. 7 corresponds to a detailed example of the screen selection mode described with reference to Fig. 2.

[0095] Fig. 7 is a diagram showing a processing procedure in the screen selection mode. In the example of Fig. 7, it is assumed that a user U selects the screen selection mode and inputs a user request on the screen, such as "Tell me some recommended weekend getaways."

[0096] In addition, in the screen selection mode, the terminal device 10 may display types of recommendation targets such as “visiting spots,” “cooking recipes,” and “music content” on the display screen, and allow the user U to select one type from these options.

[0097] The generating unit 15c of the terminal device 10 generates information (control information for controlling the external device 100) according to the screen selection mode based on the second template information TP2, and transmits the generated information to the external device (step S71). For example, the generating unit 15c recognizes "recommended visiting spots" as a type of recommendation target based on a user request, and generates a prompt main sentence TP21 such as "You are a travel planner. You are consulting with people who are looking for weekend outing spots." The prompt main sentence TP21 corresponds to type designation information.

[0098] Moreover, the generating unit 15c generates question request information TP22, which reads "To search for possible destinations, please output a question sentence according to the following conditions." based on the second template information TP2.

[0099] The generating unit 15c also generates second format designation information TP23 that defines the output format of the questions, such as the starting point [Kawagoe City, Saitama Prefecture], the questions being in a format that can be answered with "yes" or "no," the number of questions being [3], and the questions being output in a list separated by commas. Note that the generating unit 15c may determine the starting point according to the current location of the terminal device 10 or the contents of the user U's presettings, and may determine the number N of questions according to the contents of the user U's presettings.

[0100] Then, the transmitting / receiving unit 15d transmits to the external device 100 the prompt main text TP21 (type designation information), the question request information TP22, and the second format designation information TP23.

[0101] The external device 100 generates three questions, QT21, QT22, and QT23, in accordance with generation information corresponding to the screen selection mode (for example, question request information TP22 and second format designation information TP23) (step S72).

[0102] Then, the external device 100 transmits the questions QT21 to QT23 to the terminal device 10 (step S73). Fig. 7 shows an example in which the external device 100 transmits a list of the questions QT21, "Do you want to take a walk in the mountains or forest?", QT22, "Do you want to take a bath in a hot spring?", and QT23, "Do you want to interact with animals?" to the terminal device 10. As shown in Fig. 7, the questions QT21, QT22, and QT23 are separated by commas.

[0103] When the list of questions QT21 to QT23 is received by the transmitting / receiving unit 15d, the presentation control unit 15e generates a dialogue screen G2 in which a "Yes" button and a "No" button are associated with each of the questions QT21, QT22, and QT23, and displays the dialogue screen G2 on the display screen (step S74). The dialogue screen G2 can be said to be a multiple choice question image.

[0104] The user U can answer "yes" or "no" to the questions QT21 to QT23 by a screen selection operation (for example, a touch operation). For example, assume that the user U selects and inputs the answer AN21 of "yes" to the question QT21, selects and inputs the answer AN22 of "no" to the question QT22, and selects and inputs the answer AN23 of "yes" to the question QT23. In this case, in response to the answers AN21 to AN23 being accepted by the acceptance unit 15a, the transmission / reception unit 15d transmits information indicating the answer AN21, information indicating the answer AN22, and information indicating the answer AN23 to the external device 100 (step S75).

[0105] Furthermore, at the time of step S74, questions corresponding to the prescribed number of three questions (N=3) have been presented together, and answers to each question have been acquired. Therefore, the generation unit 15c may generate recommendation request information TP24 that requests output of recommendation information based on the answers of the user U obtained up to that point. Furthermore, the transmission / reception unit 15d may transmit the recommendation request information TP24 to the external device 100 together with information indicating the answers AN21 to AN23, as shown in FIG. 7. FIG. 7 shows an example in which the transmission / reception unit 15d transmits recommendation request information TP24 stating, "Based on the above answers, please output one place to go and a guide to that spot."

[0106] When the external device 100 receives the recommendation request information TP24, it searches for recommended visiting spots based on the replies AN21 to AN23, and generates recommendation information RC2 according to the search results (step S76).

[0107] Then, the external device 100 transmits the recommendation information RC2 to the terminal device 10 (step S77). Fig. 7 shows an example in which the external device 100 transmits the recommendation information RC2 to the terminal device 10, stating "We recommend △△ Zoo and Nature Park. It is a zoo located 40 minutes by car from Kawagoe City. You can interact with and feed about 120 kinds of animals. If you want to take a walk, you can learn about nature on the nature observation trails and forest classrooms in the park."

[0108] When the recommendation information RC2 is received by the transmitting / receiving unit 15d, the presentation control unit 15e generates a recommendation screen G21 showing the recommendation information RC2 as shown in FIG. 7, and displays the generated recommendation screen G21 (step S78).

[0109] The processing procedure in the screen selection mode has been described above with reference to Fig. 7. In the example of Fig. 7, the generating unit 15c generates recommendation request information TP24 requesting one recommended visiting spot, but recommendation request information TP24 requesting multiple recommended visiting spots may be generated. In addition, the requested number of recommended visiting spots may be included in the pre-set contents of the user U.

[0110] 7. Modifications Modifications of the above embodiment will be described. For example, the terminal device 10 may be implemented in various different forms other than the above embodiment. Therefore, other embodiments of the terminal device 10 will be described below.

[0111] [7-1. Switching from voice dialogue mode to screen selection mode] When a switching operation for switching from a currently selected dialogue mode to another dialogue mode is performed by the user U, the generation unit 15c may generate format designation information corresponding to the switched dialogue mode based on the dialogue history in the dialogue mode before the switching. Furthermore, the presentation control unit 15e may present to the user U a question output from the external device 100 in accordance with the format designation information corresponding to the switched dialogue mode in a manner corresponding to the switched dialogue mode.

[0112] For example, assume that the user U performs a switching operation to switch to the screen selection mode while a dialogue is proceeding in the voice dialogue mode. The switching operation may be accepted by the mode selection unit 15b. In this case, the generation unit 15c identifies the number of questions that the user U currently has not answered based on the dialogue history (voice dialogue history storage unit 14c) of the dialogue between the user U and the external device 100 in the voice dialogue mode. Then, the generation unit 15c generates question request information that requests the external device 100 to output the remaining questions that can narrow down the recommendation targets within the identified number. The presentation control unit 15e causes the remaining questions output from the external device 100 in response to the question request information to be presented as question images in an image format. This point will be described using examples in Figs. 5 to 7.

[0113] For example, assume that a question voice QS11 corresponding to a first question sentence QT11 "How much do you plan to spend on going out?" is output from the speaker, and the user U performs a switching operation to switch to the screen selection mode at the timing when the user U answers this. In this case, the generation unit 15c can identify the number of questions "2" that the user U has not currently answered among the specified number of three questions, based on the dialogue history (voice dialogue history storage unit 14c) of the dialogue conducted between the user U and the external device 100 in the voice dialogue mode.

[0114] Then, the generating unit 15c generates question request information that requests the external device 100 to output the remaining questions that can narrow down the recommended visiting spots within the number of unanswered questions, "2". For example, the generating unit 15c generates question request information TP221 that reads, "I have already obtained the answer "Within 10,000 yen, please" to the question "What is your budget for going out?", but please make it possible to narrow down the recommended visiting spots with the remaining [2] questions". In addition, the generating unit 15c generates second format designation information TP231 that reads, "Please output a list in which the [2] questions are separated by commas".

[0115] Then, the transmitting / receiving section 15d transmits the question request information TP221 and the second format designation information TP231 to the external device 100.

[0116] The external device 100 generates two questions, questions QT24 and QT25, in accordance with generation information corresponding to the screen selection mode (for example, question request information TP221 and second format designation information TP231), and transmits them to the terminal device 10.

[0117] As a result, when the list of questions QT24 and QT25 is received by the transmission / reception unit 15d, the presentation control unit 15e generates a dialogue screen G2 in which a "Yes" button and a "No" button are associated with each of the questions QT24 and QT25, and displays the dialogue screen G2 on the display screen.

[0118] [7-2. Switching from screen selection mode to voice dialogue mode] On the other hand, suppose that the user U performs a switching operation to switch to the voice dialogue mode while the dialogue is proceeding in the screen selection mode. The switching operation may be accepted by the mode selection unit 15b. In this case, the generation unit 15c identifies a question that is currently unanswered by the user U based on the dialogue history (screen dialogue history storage unit 14d) of the dialogue between the user U and the external device 100 in the screen selection mode. The presentation control unit 15e causes the identified unanswered question to be presented as a question voice in the form of voice. This point will be described using the examples of Figs. 5 to 7.

[0119] For example, it is assumed that the user U performs a switching operation to switch to the voice dialogue mode at the timing when the user selects and inputs an answer only to the question QT21 among the questions QT21 to QT23 included in the dialogue screen G2. In this case, the generation unit 15c can identify the questions QT22 and QT23 as unanswered questions among the questions QT21 to QT23 based on the dialogue history (screen dialogue history storage unit 14d) of the dialogue conducted between the user U and the external device 100 in the screen selection mode.

[0120] The presentation control unit 15e synthesizes a question voice QS22 in the form of a voice from the question sentence QT22, and outputs the question voice QS22 from the speaker. When the answer of the user U to the question voice QS22 is accepted by the accepting unit 15a and the information of the answer is transmitted to the external device 100 by the transmitting / receiving unit 15d, the presentation control unit 15e synthesizes a question voice QS23 in the form of a voice from the question sentence QT23. Then, the presentation control unit 15e outputs the question voice QS23 from the speaker. That is, the content of the question sentence that was not answered in the screen selection mode before the mode switching operation is output from the speaker as a question voice. Note that instead of outputting the content of the question sentence that was not answered as a question voice, the presentation control unit 15e may output a question voice of a new question content from the speaker. In this case, the generation unit 15c generates question request information that requests the external device 100 to output an open-ended question that can narrow down the recommendation targets, and the presentation control unit 15e causes the question output from the external device 100 in response to this question request information to be output as a question voice from the speaker.

[0121] [8. Hardware Configuration] The above-described terminal device 10 may be realized, for example, by a computer 1000 having a configuration as shown in Fig. 8. Fig. 8 is a hardware configuration diagram showing an example of a computer that realizes the functions of the terminal device 10 according to the embodiment. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, a HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0122] The CPU 1100 operates and controls each unit based on a program stored in the ROM 1300 or the HDD 1400. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, programs that depend on the hardware of the computer 1000, and the like.

[0123] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, etc. The communication interface 1500 receives data from other devices via a predetermined communication network and sends it to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the predetermined communication network.

[0124] The CPU 1100 controls an output device such as a display and an input device such as a keyboard via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. The CPU 1100 also outputs generated data to the output device via the input / output interface 1600.

[0125] The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0126] For example, when the computer 1000 functions as the terminal device 10 according to the embodiment, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to realize the functions of the control unit 15. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via a predetermined communication network.

[0127] [9. Others] Furthermore, among the processes described in each of the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by a known method. In addition, the information including the processing procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

[0128] In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads, usage conditions, etc.

[0129] Furthermore, the above-described embodiments can be appropriately combined as long as the processing contents are not contradictory.

[0130] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be implemented in other forms that incorporate various modifications and improvements based on the knowledge of those skilled in the art, including the aspects described in the present invention section. [Explanation of symbols]

[0131] 1 System 10 Terminal Equipment 12 Input section 13 Output section 14 Storage section 15 Control section 15a Reception 15b Mode selection section 15c Generator 15d Transmitter / receiver 15e Presentation control unit

Claims

1. An information processing device that presents information about a recommendation target to a user based on a dialogue with the user, a mode selection unit that selects one of a first dialogue mode in which dialogue is performed via voice and a second dialogue mode in which dialogue is performed via a screen; a generation unit that generates question request information that requests an external device to output a question for narrowing down the recommendation targets, the question request information including format designation information that designates a format of the question; a presentation control unit that presents the question output from the external device in response to the question request information to the user in a format corresponding to the dialogue mode selected by the mode selection unit; Equipped with The generation unit is generating first format designation information for designating a first format as the format of the question when the first dialogue mode is selected; When the second dialogue mode is selected, second format designation information is generated to designate a second format different from the first format as the format of the question.

23. An information processing apparatus comprising:

2. When the second dialogue mode is selected, the generation unit generates the second format designation information including information designating that a closed-ended question is to be output as the second format.

2. The information processing apparatus according to claim 1,

3. When the first dialogue mode is selected, the generating unit generates the first format designation information including information designating that an open-ended question is to be output as the first format.

3. The information processing apparatus according to claim 2.

4. The generating unit generates the question request information further including type designation information that designates a type of the recommendation target.

2. The information processing apparatus according to claim 1,

5. The generating unit generates the format designation information including information designating a number of questions as the format of the questions.

2. The information processing apparatus according to claim 1,

6. When the first dialogue mode is selected, the generation unit generates the first format designation information including information designating that questions corresponding to the number of questions are to be output one by one in sequence according to the user's answers as the first format.

6. The information processing apparatus according to claim 5,

7. When the second dialogue mode is selected, the generation unit generates the second format designation information including information designating that questions corresponding to the number of questions are to be output collectively as the second format.

6. The information processing apparatus according to claim 5,

8. The generating unit generates the second format designation information including information designating that questions corresponding to the number of questions are output together in a differentiated state as the second format.

8. The information processing apparatus according to claim 7,

9. when a switching operation for switching from a currently selected dialogue mode to another dialogue mode is performed by the user, the generation unit generates the format designation information corresponding to a dialogue mode after the switching based on a dialogue history in the dialogue mode before the switching; The presentation control unit causes the question output from the external device in accordance with the format designation information corresponding to the switched-to dialogue mode to be presented to the user in a format corresponding to the switched-to dialogue mode.

2. The information processing apparatus according to claim 1,

10. the generation unit, when a switching operation for switching to the second dialogue mode is performed while the dialogue is progressing in the first dialogue mode, identifies the number of questions currently unanswered by the user based on a dialogue history in the first dialogue mode, and generates the question request information that requests the external device to output remaining questions that can narrow down the recommendation targets within the identified number of questions; The presentation control unit causes the remaining questions output from the external device to be presented as question images in an image format.

10. The information processing apparatus according to claim 9,

11. The generation unit causes the external device to transmit the dialogue history, which includes a combination of a question output from the external device when the first dialogue mode is selected and an answer by the user to the question, together with the question request information, to the external device, thereby causing the external device to output the remaining question.

11. The information processing apparatus according to claim 10,

12. when a switching operation to switch to the first dialogue mode is performed while the dialogue is progressing in the second dialogue mode, the generation unit identifies, based on a dialogue history in the second dialogue mode, questions that have not yet been answered by the user among questions output from the external device when the second dialogue mode is selected; The presentation control unit presents the identified unanswered question in a voice format.

10. The information processing apparatus according to claim 9,

13. An information processing method executed by an information processing device that presents information about a recommendation target to a user based on a dialogue with the user, a mode selection step of selecting one of a first dialogue mode in which dialogue is performed via voice and a second dialogue mode in which dialogue is performed via a screen; a generating step of generating question request information for requesting an external device to output a question for narrowing down the recommendation targets, the question request information including format designation information for designating a format of the question; a presentation control step of presenting the question output from the external device in response to the question request information to the user in a format corresponding to the dialogue mode selected by the mode selection step; Including, The generating step includes: generating first format designation information for designating a first format as the format of the question when the first dialogue mode is selected; When the second dialogue mode is selected, second format designation information is generated to designate a second format different from the first format as the format of the question.

23. An information processing method comprising:

14. An information processing program executed by an information processing device that presents information about a recommendation target to a user based on a dialogue with the user, a mode selection step of selecting one of a first dialogue mode in which dialogue is performed via voice and a second dialogue mode in which dialogue is performed via a screen; a generating step of generating question request information for requesting an external device to output a question for narrowing down the recommendation targets, the question request information including format designation information for designating a format of the question; a presentation control step of presenting the question output from the external device in response to the question request information to the user in a format corresponding to the dialogue mode selected by the mode selection step; causing the information processing device to execute the above; The generating procedure includes: generating first format designation information for designating a first format as the format of the question when the first dialogue mode is selected; When the second dialogue mode is selected, second format designation information is generated to designate a second format different from the first format as the format of the question.

23. An information processing program comprising:

Images