Information processing system, information processing method, and program

Abstract

We provide information processing systems that can enhance the presence of conversational AI. According to one aspect of the present invention, there is provided an information processing system including at least one processor. In this information processing system, in an acquisition step, the processor acquires information indicating the presence or absence of an approach of a second user terminal functioning as a UI from a first user terminal functioning as a UI of an interactive artificial intelligence module. In a behavior control step, the processor controls the behavior of the UI, and when information indicating the approach of the second user terminal is acquired from the first user terminal, the processor changes the behavior of the UI of the first user terminal.

Description

[Technical field]

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

[0002] Patent Document 1 discloses an AI chatbot technology that receives a question message from a user's communication terminal, sends an answer message to the question to the user's communication terminal, and stores knowledge information that combines questions and answers in a first database, analyzes the received question message, searches the first database for knowledge information corresponding to the question message, and generates an answer message using the knowledge information obtained by the message analysis unit. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-131755 Summary of the Invention [Problem to be solved by the invention]

[0004] In a service that enables dialogue with an AI (artificial intelligence module) such as that in Patent Document 1, it is important to increase user awareness of the existence of dialogue-based AI in order to increase the number of users.

[0005] In view of the above circumstances, the present invention provides an information processing system etc. that can enhance the presence of conversational AI. [Means for solving the problem]

[0006] According to one aspect of the present invention, there is provided an information processing system including at least one processor. In this information processing system, the processor acquires, from a first user terminal functioning as a UI (User Interface) of an interactive artificial intelligence module, information indicating whether or not a second user terminal functioning as a UI is approaching, from the first user terminal functioning as a UI. In a behavior control step, the processor controls the behavior of the UI, and when information indicating the approach of the second user terminal is acquired from the first user terminal, changes the behavior of the UI of the first user terminal.

[0007] According to this embodiment, the presence of the dialogue-based AI can be enhanced. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram showing an example of the overall configuration of an automated dialogue system 1. [Diagram 2] 2 is a diagram illustrating an example of a hardware configuration of a server device 10. FIG. [Diagram 3] FIG. 2 is a diagram illustrating an example of a hardware configuration of a user terminal 20. [Figure 4] FIG. 2 is an activity diagram illustrating an example of an automated dialogue process. [Diagram 5] FIG. 13 is a diagram illustrating an example of a displayed login screen. [Figure 6] FIG. 13 is a diagram showing an example of an interactive AI screen. [Figure 7] FIG. 1 is a diagram showing an example of a dialogue with a dialogue-type AI. [Figure 8] FIG. 11 is a diagram showing an example of an accumulated dialogue history. [Figure 9] FIG. 11 is a diagram illustrating an example of a specific sound. [Figure 10] FIG. 13 is a diagram illustrating an example of a case where a specific sound is detected. [Figure 11] FIG. 13 is a diagram showing an example of a dialogue during approach. [Figure 12] FIG. 13 is a diagram showing another example of interaction upon approach. [Figure 13] FIG. 13 is a diagram showing another example of interaction upon approach. [Figure 14]FIG. 13 is a diagram showing another example of interaction upon approach. [Figure 15] FIG. 13 is a diagram showing another example of interaction upon approach. [Figure 16] FIG. 13 is a diagram illustrating an example of a location notification. [Figure 17] FIG. 13 is a diagram showing another example of interaction upon approach. [Figure 18] FIG. 13 is a diagram showing an example of a dialogue material registration screen. [Figure 19] FIG. 13 is a diagram showing another example of interaction upon approach. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described with reference to the drawings. Various characteristic features shown in the following embodiments can be combined with each other.

[0010] Incidentally, a program for realizing the software appearing in one embodiment may be provided as a non-transitory computer-readable recording medium, or may be provided so as to be downloadable from an external server, or may be provided so that the program is launched on an external computer and its functions are realized on a client terminal (so-called cloud computing).

[0011] In addition, in various information processing according to an embodiment, an input and an output according to the input can be realized. Here, as long as an output is obtained as a result of the input, the form of information referenced in such information processing (hereinafter referred to as reference information) is not limited. The reference information may be, for example, rule-based information such as a database, a lookup table, or a predetermined function (including a judgment formula such as a regression formula constructed by a statistical method), or may be a trained model that has previously trained the correlation between the input and the output, or may be a large-scale language model that can output a desired result by inputting a prompt.

[0012] In one embodiment, the term "unit" may include, for example, a combination of hardware resources implemented by a circuit in the broad sense and software information processing that can be specifically realized by these hardware resources. In one embodiment, various information is handled, and this information is represented by, for example, physical values ​​of signal values ​​representing voltage and current, high and low signal values ​​as a binary bit collection consisting of 0 or 1, or quantum superposition (so-called quantum bits), and communication and calculation can be performed on the circuit in the broad sense.

[0013] Furthermore, a circuit in the broad sense is a circuit realized by at least appropriately combining a circuit, circuitry, a processor, and a memory. The processor may be a general-purpose processor or a dedicated circuit. In other words, it includes an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)), etc.

[0014] <Embodiment 1> A first embodiment of an automatic dialogue system for realizing dialogue between a machine and a user will be described below. 1. System Configuration Fig. 1 is a diagram showing an example of the overall configuration of an automated dialogue system 1. Fig. 1 shows an overview of each device included in the automated dialogue system 1 and a user who uses those devices. The automated dialogue system 1 is an information processing system that executes automated dialogue processing to realize a dialogue between a machine and a user.

[0015] The automated dialogue system 1 includes a communication line 2, a server device 10, and a plurality of user terminals 20. The communication line 2 is not particularly limited, but may be configured, for example, by the Internet network. The communication line 2 may also include a local area network, a mobile communication network, and a VPN (Virtual Private Network), etc. The communication line 2 mediates data exchange between devices connected to the line. In the example of FIG. 1, the server device 10 is connected to the communication line 2 by wire, and a plurality of user terminals 20 are connected to the communication line 2 by wireless. The connection of each device to the communication line 2 may be wired or wireless.

[0016] The server device 10 is an information processing device that executes automatic dialogue processing. The server device 10 includes an AI module 3 and a dialogue history database 4. The AI ​​module 3 is a module that is adjusted (tuned) using AI (Artificial Intelligence) technology to realize a dialogue function that, for example, when a statement is input from a person, outputs a reply corresponding to the statement. A virtual person with which a user dialogues using the dialogue function realized by the AI ​​module 3 is hereinafter referred to as a "dialogue AI."

[0017] The AI ​​module 3 has a natural language processing model whose accuracy has been improved by machine learning using a large-scale data set called LLM (Large Language Models). By performing machine learning with LLM, the AI ​​module 3 can realize a variety of dialogues. The dialogue function realized by the AI ​​module 3 is not only able to answer questions from the user, but also, for example, to provide backchanneling to the user's remarks, develop the current topic, change the topic, provide a new topic, and touch on past topics.

[0018] In addition to the dialogue function, the AI ​​module 3 is also adjusted to realize a task execution function for executing a specific task instructed by a user in dialogue, as is realized in a smart speaker, etc. The specific task is, for example, searching the Internet, writing a document, sending an email, and using a service (such as a reservation service) provided on a specific site. The AI ​​module 3 can be adjusted to realize functions other than the dialogue function and the task execution function.

[0019] The dialogue history database 4 is a database that stores the history of dialogue between the user and the dialogue AI (AI module 3). For example, the dialogue history database 4 stores the user's utterances and the dialogue AI's utterances in association with the time information at which the utterances were made. In addition, the dialogue history database 4 also stores information (location information, weather information, etc.) that the user terminal 20 can acquire when a dialogue is made in association with the dialogue history.

[0020] The user terminal 20 is a portable terminal used by a user, such as a smartphone or a tablet terminal. The user terminal 20 functions as a UI (User Interface) of the dialogue AI. The UI of the dialogue AI is an interface that allows the user to recognize the appearance and behavior of the dialogue AI, which is a pseudo dialogue partner, and is specifically realized by a display function that displays images (including text images), a pronunciation function that outputs sounds (including voice), a vibration function that vibrates the housing of the user terminal 20, and a light emission function that turns on a light source. The behavior of these UIs of the dialogue AI is controlled by the server device 10.

[0021] The server device 10 executes an authentication process to authenticate a user who uses the user terminal 20. The server device 10 stores authentication information (such as a user ID and a password) for authenticating a user who uses the automated dialogue system 1, and authenticates a user who inputs the authentication information. By authenticating a user, the server device 10 can restrict access to data or add identification information to data input by the user to make the data identifiable.

[0022] 2. Hardware Configuration The hardware configuration according to the first embodiment will be described below. 2 is a diagram showing an example of a hardware configuration of server device 10. Server device 10 includes a control unit 11, a storage unit 12, a communication unit 13, and a bus 14. Bus 14 electrically connects each unit included in server device 10.

[0023] (Control unit 11) The control unit 11 has at least one processor. The at least one processor may be configured, for example, by a central processing unit (CPU), a micro processing unit (MPU), a graphics processing unit (GPU), one or more integrated circuits, one or more discrete circuits, or a combination of these (not shown).

[0024] The control unit 11 is a computer that realizes various functions related to the automated dialogue system 1 by reading out a predetermined program stored in the storage unit 12. That is, information processing by software stored in the storage unit 12 is specifically realized by the control unit 11, which is an example of hardware, and can be executed as each functional unit included in the control unit 11. Note that the control unit 11 is not limited to being single, and may be implemented with multiple control units 11 for each function. Also, a combination of these may be used.

[0025] (Storage unit 12) The storage unit 12 stores various pieces of information defined by the above description. This can be implemented, for example, as a storage device such as a solid state drive (SSD) or a hard disk drive (HDD) that stores various programs and the like related to the automated dialogue system 1 executed by the control unit 11, or as a memory such as a random access memory (RAM) that stores temporarily required information (arguments, arrays, etc.) related to the program calculations. The storage unit 12 stores various programs, variables, etc. related to the automated dialogue system 1 executed by the control unit 11.

[0026] (Communications Department 13) The communication unit 13 is configured by a communication module. The communication module may be a wireless communication module conforming to standards such as IEEE802.11a / b / g / n / ac / ax, LTE, 5G, and 6G, or may be a wired communication module conforming to standards such as IEEE802.3. The communication unit 13 is configured to be capable of transmitting various electrical signals from the server device 10 to external components. The communication unit 13 is also configured to be capable of receiving various electrical signals from the external components to the server device 10. More preferably, the communication unit 13 has a network communication function, and may be implemented so that various information can be communicated between the server device 10 and an external device via the communication line 2.

[0027] Fig. 3 is a diagram showing an example of a hardware configuration of the user terminal 20. The user terminal 20 includes a control unit 21, a storage unit 22, a communication unit 23, an input unit 24, an output unit 25, and a bus 26. The bus 26 electrically connects the various units included in the user terminal 20. The control unit 21, the storage unit 22, and the communication unit 23 are similar hardware to the control unit 11, the storage unit 12, and the communication unit 13 shown in Fig. 2, although the specifications, model, etc. may be different.

[0028] (Input section 24) The input unit 24 has keys, buttons, a touch screen, a mouse, etc., and accepts input from the user. The input unit 24 also has a microphone which is a sensor that detects sound, and outputs sound data indicating a sound detected by the microphone to the control unit 21. The input unit 24 accepts input such as, for example, a voice uttered by the user or a sound generated around the user terminal 20, by using the function of the microphone (sound detection function).

[0029] (Output section 25) The output unit 25 has a display and a speaker, and outputs visual information generated in a manner that is visible to the user, such as a screen, an image, an icon, and text, on the display surface of the display (display function), and outputs sounds representing human voices, etc., through the speaker (sound generation function). The output unit 25 also has a vibration means for outputting vibrations, and is controlled by the control unit 21 to vibrate the housing of the user terminal 20 (vibration function). The output unit 25 also has a light source such as an LED (Light Emitting Diode), and is controlled by the control unit 21 to output light (light emission function). The output unit 25 also has a positioning means such as a GPS (Global Positioning System), and outputs position information indicating the position of the terminal itself (positioning function).

[0030] 3. Information Processing The above-mentioned automatic dialogue processing will be described below as the information processing according to the embodiment. In the following description, the server device 10 and the user terminal 20 are described as the subjects of each automatic dialogue processing, but the information processing is executed by a processor included in the control unit of each device.

[0031] Fig. 4 is an activity diagram showing an example of automatic dialogue processing. Although one user terminal 20 is shown in Fig. 4, it is assumed that a plurality of user terminals 20 simultaneously log in and use the automatic dialogue system 1. The automatic dialogue processing shown in Fig. 4 is started when a login screen for the automatic dialogue service is displayed on the user terminal 20.

[0032] Fig. 5 is a diagram showing an example of a displayed login screen. A character string "Talk to a conversational AI!", a user ID input field D11, a password input field D12, and a login button B11 are displayed on the login screen C1 shown in Fig. 5. The user terminal 20 accepts input by the user into the input fields D11 and D12 and an operation on the login button B11 as a login operation by the user (activity A11). The user terminal 20 transmits the user ID and password input by the login operation to the server device 10 as authentication information.

[0033] The server device 10 authenticates the user based on the transmitted authentication information (activity A12). Next, the server device 10 transmits instruction data to the user terminal 20 to instruct the user terminal 20 to start dialogue-related processing (activity A13). The dialogue-related processing is processing related to dialogue with the dialogue AI, and includes dialogue processing and approach detection processing. The dialogue processing is processing performed when a user and the dialogue AI interact, and the approach detection processing is processing for detecting the approach of user terminals 20 that use the dialogue AI.

[0034] The user terminal 20 starts the dialogue process in accordance with the instruction of A13 (activity A21). The dialogue process includes a process of operating the UI of the dialogue AI of the user terminal 20, and specifically includes a process of displaying an avatar representing an image of the appearance of the dialogue AI (a process of operating a display function), a process of displaying an image such as a character string indicating a statement by the dialogue AI (a process of operating a display function), a process of outputting a sound indicating a statement by the dialogue AI (a process of operating a pronunciation function), a process of vibrating the housing of the user terminal 20 (a process of operating a vibration function), and a process of turning on a light source (a process of operating a light emission function).

[0035] In addition, the dialogue processing includes a process of accepting dialogue input from the user, and specifically includes a process of acquiring the user's voice and transmitting sound data representing the voice to the server device 10, and a process of accepting a user's operation and transmitting operation data representing the operation content to the server device 10.

[0036] The server device 10 executes a dialogue control process (activity A22) that controls the dialogue between the user and the dialogue AI in conjunction with the user terminal 20. The dialogue control process includes a process that controls the behavior of the UI of the dialogue AI, and specifically includes an avatar process that instructs the user terminal 20 to display and move an avatar, a display process that displays a character string indicating the content of the dialogue AI's statement, a voice process that outputs a voice indicating the content of the dialogue AI's statement, a vibration process that vibrates the housing of the user terminal 20, a lighting process that lights up a light source, a statement process that determines the content of the statement of the dialogue AI based on the voice or operation data transmitted from the user terminal 20, and a behavior process that determines the behavior of the UI of the dialogue AI.

[0037] The above avatar processing and display processing, etc. are all executed, for example, by the functions of the AI ​​module 3. In this case, the functions are realized by performing machine learning using the user's utterance as input and the processing to be performed by the dialogue AI as correct answer information. Note that some of the processing may be executed by functions other than the AI ​​module 3. In this case, the server device 10 executes the dialogue control processing, for example, by using reference information that associates the situation, including the user's utterance, with the processing to be performed by the dialogue AI.

[0038] The dialogue control process by the server device 10 includes normal dialogue control process and approach process. Approach refers to a period when the user terminals 20 using dialogue AI are close to each other. Normal refers to a period when the user terminals 20 using dialogue AI are not close to each other, that is, a period other than approach. In the example of FIG. 4, the server device 10 first executes normal dialogue control process.

[0039] The user terminal 20 starts the approach detection process in parallel with A21 (activity A31). Specifically, the user terminal 20 executes the approach detection process by outputting a specific sound (hereinafter referred to as the "specific sound") that is determined to notify the approach of the user terminals 20 to each other. The specific sound will be explained in detail later. First, the following describes the self-introduction dialogue with the interactive AI that takes place when the user logs in for the first time. The user terminal 20 displays an interactive AI screen, which is a screen on which a dialogue between the user and the interactive AI takes place, through the dialogue process.

[0040] Fig. 6 is a diagram showing an example of an interactive AI screen. In the example of Fig. 6, the user terminal 20 displays the interactive AI screen C2. Since the display of the interactive AI screen by the user terminal 20 is performed under the control of the server device 10, it can be said that the server device 10 causes the user terminal 20 to display the interactive AI screen C2 (the same applies to the subsequent displays). The interactive AI screen C2 displays a specific sound icon E21, an AI appearance image F21, and an end dialogue button B21.

[0041] The specific sound icon E21 is an image indicating that the user's own terminal (user terminal 20) is outputting a specific sound. The AI ​​appearance image F21 is an image for imagining the appearance of the interactive AI, and is displayed during a conversation. Although the AI ​​appearance image F21 is an image that imitates a human face, an image of an animal or a figure may also be used as the AI ​​appearance image. The conversation end button B21 is an operation image that is operated when ending a conversation with the interactive AI.

[0042] When the conversational AI is having a conversation with a user for the first time, it makes a statement to introduce itself and ask the other person's name. In the example of FIG. 6, the user terminal 20 outputs a voice V21 saying, "Nice to meet you. I'm Alpha, the conversational AI. What's your name?" as a voice indicating the conversational AI's statement. Such a statement by the conversational AI is made under the control of the server device 10, so it can be said that the server device 10 is making the conversational AI make the statement (the same applies to subsequent statements). Upon hearing the voice V21, the user makes a self-introduction statement, including, for example, their own name, to the conversational AI. The conversational AI then replies to the user's statement.

[0043] FIG. 7 is a diagram showing an example of a dialogue with a dialogue type AI. In the example of FIG. 7, the user utters a voice V11 indicating a statement, "Nice to meet you. My name is Tom." In response to this, the dialogue type AI utters a voice V22 indicating a reply, "Then I'll call you Tom!" When such a dialogue between the user and the dialogue type AI takes place, the server device 10 accumulates the dialogue history in the dialogue history database 4 (activity A23).

[0044] Fig. 8 is a diagram showing an example of the accumulated dialogue history. Fig. 8 shows information stored in the dialogue history database 4. In the dialogue history database 4, "nickname", "AI name", "user attributes", "time information", "location information", "external information", "statement content", etc. are stored as dialogue history in association with authentication information such as a user ID and password. "Tom", who conversed with the dialogue-based AI in Fig. 7, is assumed to be a user with a user ID of "U0001".

[0045] The nickname is the name that the conversational AI calls the user, and in the example of Figure 8, the nickname "Tom" is stored. The AI ​​name is the name of the conversational AI. In the example of Figure 8, the name "Alpha" is stored as the initial value. The user attributes are attributes such as the user's age, gender, area of ​​residence, and occupation. The user attributes are stored when the user speaks during a dialogue. The time information is information indicating the date and time when the dialogue history was stored, and is stored in correspondence with each dialogue history. The location information is information indicating the location of the user terminal 20 when the dialogue took place.

[0046] The external information is information that can be acquired from an external system when a dialogue takes place, such as weather information. For example, when the AI ​​module 3 is asked about today's weather by a user, the AI ​​module 3 acquires weather information by searching the Internet or using a weather information service using the above-mentioned task execution function, and the server device 10 stores the acquired weather information as external information in the dialogue history database 4. The server device 10 also stores text data indicating the content of remarks made in the dialogue.

[0047] By repeatedly executing activities A21, A22, and A23, the dialogue between the user and the conversational AI is repeated, and the dialogue history is accumulated. The dialogue history is accumulated in association with the user ID of each user. In the example of Figure 8, in addition to the user who calls someone "Tom," the dialogue history of users who call someone "Emma," "Mike," and "Sophia" is accumulated in association with each user ID. Note that the name, AI name, and user attributes are stored when they are discussed in a dialogue with the conversational AI, but even after being stored once, they can be changed through dialogue (such as asking the user to change the name).

[0048] When the server device 10 has the conversational AI converse with the user, the server device 10 refers to the conversation history of the user. For example, when the user logs off once and logs in again, the server device 10 has the AI ​​converse with the user while calling the user by the name that was initially decided. In addition, the server device 10 may refer to user attributes heard from the user and may refer to utterances made in previous conversations at the same time or location as the current time or current location.

[0049] Next, the above-mentioned specific sound will be described. FIG. 9 is a diagram showing an example of a specific sound. In FIG. 9, a graph is shown in which the vertical axis indicates wavelength and the horizontal axis indicates time. In the example of FIG. 9, login is performed at time t0, and output of a specific sound S1 is started. The user terminal 20 outputs the specific sound S1 from time t0 to time t1, and outputs the specific sound S2 from time t1 to time t2. After that, the user terminal 20 alternately outputs the specific sounds S1 and S2 at regular intervals at times t3 and t4. Both the specific sounds S1 and S2 are sounds outside the audible range. The specific sound S1 is a sound with a wavelength lower than the audible range, and the specific sound S2 is a sound with a wavelength higher than the audible range.

[0050] While smartphones and the like often use speakers capable of outputting sounds within the audible range, the automatic dialogue system 1 uses speakers capable of outputting sounds outside the audible range as well. By outputting sounds outside the audible range, it is possible to prevent the specific sounds from being heard by the user and people in the vicinity. Even if the speaker is not capable of outputting sounds outside the audible range, sounds near the upper and lower limits of the audible range are difficult to hear, so the user terminal 20 can output these sounds as specific sounds to prevent the specific sounds from being noticed by the user and people in the vicinity.

[0051] While continuing to output the specific sound, the user terminal 20 simultaneously acquires ambient sounds (sounds around the user terminal 20) by a microphone and transmits sound data indicating the acquired ambient sounds to the server device 10 (activity A32). The server device 10 receives the transmitted sound data and performs a process of detecting the approach of terminals (user terminals 20) based on the received sound data (activity A33). In the example of FIG. 4, it is assumed that the other user terminals 20 are also outputting the specific sounds S1 and S2 shown in FIG. 9. A case where the approach of terminals is detected will be described with reference to FIG. 10.

[0052] Fig. 10 is a diagram showing an example of a case where a specific sound is detected. The diagram shows two user terminals 20-1 and 20-2 moving to pass each other. Assume that the user terminal 20-1 is a terminal used by Tom, and the user terminal 20-2 is a terminal used by Emma shown in Fig. 8. Fig. 10 shows an area R1 in which the specific sound output by the user terminal 20-1 can be acquired, and an area R2 in which the specific sound output by the user terminal 20-2 can be acquired.

[0053] In FIG. 10(a), each user terminal 20 is outside each other's range, but then, as user terminals 20-1 and 20-2 move so as to pass each other, each user terminal 20 is now within each other's range, as shown in FIG. 10(b).

[0054] In the state of Fig. 10(a), the specific sound S1 or S2 is not included in the ambient sound indicated by the sound data transmitted from the user terminals 20-1 and 20-2, so the server device 10 does not detect the proximity of these user terminals 20. In the state of Fig. 10(b), the specific sound S1 or S2 is included in the ambient sound indicated by the sound data transmitted from the user terminals 20-1 and 20-2, so the server device 10 detects the proximity of these user terminals 20.

[0055] Depending on the arrangement of the speaker and microphone of the user terminal 20, a specific sound output by the user terminal (hereinafter referred to as "local terminal sound") may be included in the ambient sound. In such a case, the server device 10 performs a process of removing the local terminal sound of the user terminal 20 that acquired the ambient sound from the ambient sound, for example. The server device 10 determines that a specific sound that is included in the ambient sound from the beginning and whose intensity does not change is the local terminal sound, removes the local terminal sound from the ambient sound, and then determines whether the sound after removal includes the specific sound.

[0056] When the server device 10 detects the approach of the terminals, it executes an approach-time interaction control process for the user terminal 20 that detected the approach (activity A41). The user terminal 20 executes an interaction process in accordance with the approach-time interaction control process by the server device 10 (activity A42). The server device 10 accumulates a history of interactions performed in cooperation with the user terminal 20 (activity A43). The interaction when approaching will be described with reference to FIG. 11 onwards.

[0057] FIG. 11 is a diagram showing an example of dialogue during approach. In the example of FIG. 11, an approach detection icon E22 is displayed on the interactive AI screen C2. When the server device 10 detects approach to another user terminal 20, the server device 10 displays the approach detection icon E22 to visually notify the user that the other user terminal 20 is approaching. In addition, the server device 10 switches the AI ​​appearance image F21 to an image of a surprised expression, and causes the interactive AI to output a voice V23 indicating a statement such as "Hey. Emma and her fellow interactive AI friend Beta are nearby." In this way, the server device 10 changes the control of the UI of the interactive AI when the approach between the terminals is detected.

[0058] The server device 10 refers to the dialogue history stored in the dialogue history database 4 in association with the user ID of "Emma", the user of the user terminal 20-2 that detected the approach of the user terminal 20-1, and causes the dialogue AI to make a statement including information about Emma. In the example of Fig. 11, the server device 10 refers to the "name" and "AI name" in Emma's dialogue history, causing the dialogue AI to make a statement including the names "Emma" and "Beta".

[0059] Fig. 12 is a diagram showing another example of a dialogue during approach. In the example of Fig. 12, the server device 10 switches the AI ​​appearance image F21 to an image of a winking expression, and causes the dialogue AI to output a voice V24 indicating a statement, "It seems that Beta and his friends were talking about a new shop in front of the station!" By referring to the "statement content" in Emma's dialogue history, the server device 10 causes the dialogue AI to make a statement including the content of the conversation between Emma and the dialogue AI Beta.

[0060] FIG. 13 is a diagram showing another example of a dialogue during approach. In the example of FIG. 13, the server device 10 causes the dialogue AI to output a voice V25 indicating a statement, "We passed each other the day before yesterday, Beta. It was raining then." When the server device 10 detects that the terminals have approached each other, it accumulates the dialogue history during the approach after adding an approach flag indicating the approaching party. When the approach flag with Tom is added to Emma's dialogue history, the server device 10 determines the content of the statement by referring to the dialogue history to which the approach flag is added. In the example of FIG. 13, the server device 10 causes the dialogue AI to make a statement including the time of past approach and the weather at that time by referring to the "time information" and "external information" to which the approach flag is added.

[0061] Returning to Fig. 4, the server device 10 judges whether the approaching state has ended based on the ambient sound indicated by the sound data transmitted from the user terminal 20 performing the approaching dialogue control process (activity A44), and if it judges that the approaching state has not ended (NO), it repeats A41 (approaching dialogue control process) and A43 (accumulation of dialogue history). If the server device 10 judges that the approaching state has ended (YES), it returns to A22 and executes the normal dialogue control process.

[0062] The processes of activities A21 to A23, A31 to A33, and A41 to A44 are repeatedly executed until the dialogue end button B21 is operated on the interactive AI screen C2. When the user terminal 20 accepts the operation of the dialogue end button B21 (activity A51), it transmits end instruction data instructing the end of the dialogue to the server device 10. When the server device 10 receives the end instruction data, it ends the dialogue control process (activity A52).

[0063] As described above, each of the multiple user terminals 20 shown in Fig. 1 functions as a UI for the interactive AI module 3. The multiple user terminals 20 include a first user terminal used by a first user (e.g., user terminal 20-1 used by Tom) and a second user terminal used by a second user (e.g., user terminal 20-2 used by Emma). In addition, the server device 10 functions as an example of an acquisition unit that acquires information indicating whether or not the terminals are approaching each other (hereinafter referred to as "approach notification information").

[0064] The server device 10 (an example of an acquisition unit) acquires approach notification information about the second user terminal from the first user terminal. In the examples of Figs. 4 and 10, the server device 10 receives sound data transmitted from the user terminal 20-1 at A33. This sound data is data indicating ambient sounds of the user terminal 20-1, and whether or not the ambient sounds include a specific sound indicates whether or not the user terminal 20-2 is approaching the user terminal 20-1. In this way, the server device 10 acquires approach notification information indicating whether or not the second user terminal (user terminal 20-2 in the example of Fig. 10) is approaching from the first user terminal (user terminal 20-1 in the example of Fig. 10) by receiving the sound data.

[0065] The server device 10 also functions as an example of a behavior control unit that controls the behavior of the UI of the dialogue AI. The server device 10 controls the behavior of the UI of the dialogue AI in each of a plurality of user terminals 20 including a first user terminal and a second user terminal. When the server device 10 acquires information indicating the approach of the second user terminal from the first user terminal as approach notification information, the server device 10 changes the behavior of the UI of the first user terminal.

[0066] In the example of Fig. 7 showing a normal state, the server device 10 controls the behavior of the UI of the conversational AI in the first user terminal so that the user makes a statement based on the dialogue history of Tom, the user of the first user terminal, but in the example of Fig. 11 showing an approach state, the server device 10 changes the behavior so that the user makes a statement based on the dialogue history of Emma, ​​the user of the second user terminal. According to this embodiment, the change in behavior can make the user aware that another conversational AI other than the one he or she is interacting with is nearby, thereby enhancing the presence of the conversational AI compared to when the behavior does not change even when the terminals are close to each other.

[0067] Furthermore, the user terminal 20 (including the second user terminal) has a function of outputting a specific sound (a sound output function shown in FIG. 3). A specific sound is a sound for notifying other user terminals 20 of the approach of the user terminal, and the specific sounds S1 and S2 described in FIG. 9 are both examples of the specific sound. The server device 10 (an example of a detection unit) changes the behavior of the UI of the first user terminal when approach notification information is information indicating sounds around the first user terminal and indicates a sound including the specific sound.

[0068] The user terminal 20 may output radio waves such as Bluetooth (registered trademark) or WiFi instead of the specific sound, and the server device 10 may detect the approach of the terminals when the user terminal 20 detects radio waves output by another user terminal 20. However, in this case, depending on the surrounding environment, the communication situation may be poor (such as a situation where radio waves that interfere with communication are flying) and it may be difficult to detect the approach. In the example of FIG. 4, etc., by using the specific sound as described above, the approach can be detected without being affected by the communication situation.

[0069] The specific sound includes a plurality of types of sounds. In the example of FIG. 9, two types of specific sounds S1 and S2 with different frequencies are included in the specific sound. The plurality of types of sounds is not limited to this, and may include, for example, three or more types of specific sounds with different frequencies. The specific sound may be a sound with one or more different elements of sound elements such as frequency (pitch), tone, or volume. The server device 10 functions as an example of a sound control unit that causes the user terminal 20 (including the second user terminal) to output the specific sound while sequentially switching the type of sound. In the example of FIG. 4, the server device 10 controls the output of the specific sound by the user terminal 20 by instructing the start of the dialogue-related process at A13.

[0070] Depending on the type of sound output, it may become difficult to detect because it blends in with surrounding sounds; however, by switching between different types of specific sounds, the likelihood that the specific sound will be a type of sound that is less likely to blend in with surrounding sounds can be increased compared to when there is only one type of specific sound, making it easier to detect approaching objects even in the presence of surrounding sounds.

[0071] Furthermore, the server device 10 (an example of an acquisition unit) functions as an example of a history acquisition unit that acquires a dialogue history with the dialogue AI, that is, a dialogue history with the AI ​​module 3 via the user terminal 20 (including the second user terminal). Then, the server device 10 (an example of a behavior control unit) changes the behavior of the UI of the dialogue AI of the first user terminal according to the acquired dialogue history.

[0072] 11 and 12, the server device 10 acquires a dialogue history with the dialogue AI via the second user terminal (user terminal 20-2), i.e., a dialogue history between Emma and the dialogue AI Beta, and causes the dialogue AI Alpha of the first user terminal (user terminal 20-1) to make a statement according to the acquired dialogue history. According to this embodiment, Tom, the user of the first user terminal, can be made to feel the atmosphere of the approaching partner by being informed of the type of dialogue that Emma, ​​the user of the second user terminal, the approaching partner, is having with the dialogue AI.

[0073] The server device 10 also functions as an example of a storage unit that stores a history of approach with other user terminals 20. As described in the description of FIG. 13, the server device 10 stores the approach history by adding an approach flag to the dialogue history. Then, the server device 10 (an example of a behavior control unit) changes the behavior of the UI of the dialogue AI according to the stored approach history. In the example of FIG. 13, the server device 10 causes Alpha of the dialogue AI to make a statement conveying that the first user terminal (user terminal 20-1) has come close to the second user terminal (user terminal 20-2) in the past and the external information at that time.

[0074] Note that the behavior of the UI of the dialogue AI according to the approach history is not limited to this. For example, the server device 10 may cause the UI to make a statement about the time period, location, or content of a previous approach. The server device 10 may also change the behavior of the UI according to the number of past approaches. For example, the server device 10 may increase the number of dialogue histories of the approaching user that can be referred to for behavior control as the number of approaches increases.

[0075] Specifically, the server device 10 allows reference to only external information when the number of approaches is equal to or less than a first threshold, allows reference to additional time information and location information when the number of approaches is equal to or more than the first threshold and less than a second threshold, and allows reference to additional user attributes and comment content when the number of approaches is equal to or more than the second threshold. According to such an embodiment, it is possible to increase the amount of information disclosed to a person who has been in close contact many times, thereby creating a sense of intimacy.

[0076] In addition, as information that the conversational AI can refer to, not only the dialogue history but also registered information registered in advance by the user may be used. The registered information may include the user's profile and a message to the approaching person. According to this embodiment, the user can convey specific information only to the person who approaches repeatedly. As described above, by performing behavior control based on the approach history, it is possible to increase the variety of UI behavior compared to when the approach history is not used.

[0077] <Variation: Interaction between UIs> The behavior control of the UI when approaching is not limited to the above. For example, the server device 10 (an example of a behavior control unit) may control the behavior of the UI of the first user terminal so that the AI ​​module 3 that interacts through the first user terminal and the AI ​​module 3 that interacts through the second user terminal interact with each other.

[0078] Fig. 14 is a diagram showing another example of dialogue during approach. In the example of Fig. 14, the server device 10 displays both an AI appearance image F21 of Tom's dialogue AI and an AI appearance image F31 of Emma, ​​the user of the second user terminal (user terminal 20-2), on the dialogue AI screen C2 of the first user terminal (user terminal 20-1). Then, the server device 10 causes the dialogue AI shown in the AI ​​appearance image F31 to output a voice V31 indicating a statement such as "Hello, Alpha. This is Beta. Are you shopping today?"

[0079] In response, the server device 10 causes the conversational AI shown in the AI ​​appearance image F21 to output a voice V26 indicating a statement, "Hello, Beta. I came to see a movie with Tom today." The server device 10 causes the conversational AI to make such a statement based on the content of the conversation between the conversational AI Alpha and Tom up to this point and the external information that Tom has looked up about movies. The server device 10 further refers to Emma's conversation history, determines a response from the conversational AI Beta, and causes the user terminal 20-1 to output the voice.

[0080] The server device 10, for example, makes it possible to know which conversational AI is speaking by moving or blinking the mouth of the AI ​​appearance image of the conversational AI that is speaking. The server device 10 also makes it possible to distinguish which conversational AI is speaking by outputting different voices depending on the conversational AI.

[0081] As described above, in the example of Fig. 14, the UI of the first user terminal is controlled so that the interactive AIs Alpha and Beta are interacting with each other. According to this embodiment, the presence of the interactive AI of the second user terminal can be more strongly felt than when the interactive AI of the second user terminal does not appear on the first user terminal.

[0082] The server device 10 may control the UI of the first user terminal so that the amount of dialogue between the interactive AIs increases as the number of past contacts with the approaching user terminal 20 increases. The amount of dialogue may be represented, for example, by the duration of the dialogue or the number of types of dialogue history used in the dialogue. According to this embodiment, the user can feel that the more the number of contacts increases, the more friendly the interactive AIs become.

[0083] <Modification: Notifying the other party's location> The user of the user terminal 20 may notify the approaching other party of his / her own location. In this case, for example, when the server device 10 acquires approach notification information indicating the approach of a second user terminal from a first user terminal, the server device 10 functions as an example of a request unit that requests permission to notify the second user terminal of the location via the first user terminal. For example, the server device 10 causes the first user terminal to display an image requesting permission.

[0084] Fig. 15 is a diagram showing another example of a dialogue during approach. In the example of Fig. 15, the server device 10 displays an OK button B22 and an NG button B23 on the dialogue AI screen C2 of the first user terminal (user terminal 20-1). The server device 10 then causes the dialogue AI to output a voice V27 indicating a statement saying, "Emma and fellow dialogue AI member Beta are nearby. May I let them know where you are?"

[0085] The server device 10 determines that the notification of the location is not permitted when the NG button B23 is operated, and determines that the notification of the location is permitted when the OK button B22 is operated. When the notification of the location is permitted, the server device 10 functions as an example of a first notification unit that notifies the user of the location of the first user terminal via the second user terminal. The server device 10 notifies the user of the location of the first user terminal by causing the second user terminal to display an image indicating the location of the first user terminal.

[0086] Fig. 16 is a diagram showing an example of a location notification. Fig. 16 shows an interactive AI screen C3 of a second user terminal (user terminal 20-2). The server device 10 displays an AI appearance image F31, an AI appearance image F32, and a location notification image E31. The AI ​​appearance image F31 is an image that evokes the interactive AI of the second user terminal, and the AI ​​appearance image F32 is an image that evokes the interactive AI of the first user terminal.

[0087] The position notification image E31 indicates the direction (north, south, east, west) in which the first user terminal (user terminal 20-1) is located (northwest in the example of FIG. 16) and the distance to the first user terminal (10 m in the example of FIG. 16). When the server device 10 determines that notification of the position is permitted, it acquires position information from both the first user terminal and the second user terminal, calculates the direction and distance, and generates and displays the position notification image E31.

[0088] The server device 10 causes the interactive AI to output a voice V31 indicating a statement such as "Alpha and his friends seem to be in this direction." By looking at the position notification image E31, Emma, ​​the user of the second user terminal, can grasp the positions of the other interactive AIs and the first user terminal functioning as their UI, and can identify the approaching party (Tom in the example of FIG. 16). If Emma is interested, she can then talk to the party in the displayed direction.

[0089] The method of notifying the location is not limited to the above method. For example, the server device 10 may notify the location by displaying an image showing a map of the surrounding area and the location of the first user terminal. The server device 10 may also display the direction of the first user terminal on the second user terminal and blink the light source of the first user terminal to make the first user terminal more easily noticeable. The user of the first user terminal may register his / her own characteristics (appearance, age, sex, height, etc.) in advance, and the server device 10 may display these characteristics on the second user terminal to make the user of the first user terminal more easily noticeable.

[0090] Furthermore, the server device 10 may determine whether or not to notify the location of the first user terminal according to the location of the first user terminal. For example, when the address of the user of the first user terminal is registered, the server device 10 does not notify the location of the first user terminal in a range close to the address, but notifies the location of the first user terminal in a range away from the address. According to this embodiment, the location is not notified when it is inconvenient for the user, and the location is notified only when it is convenient.

[0091] <Modification: 2-stage behavior> The server device 10 may control the behavior of the UI of the dialogue AI by dividing the state in which the user terminals 20 are close to each other into two stages. In this case, the server device 10 (an example of an acquisition unit) repeatedly acquires approach notification information at a predetermined time interval. Then, the server device 10 (an example of a behavior control unit) changes the behavior of the UI during a period in which approach notification information indicating the approach of the second user terminal continues to be acquired from the first user terminal and during a predetermined period after the end of that period.

[0092] Fig. 17 is a diagram showing another example of dialogue during approach. In the example of Fig. 17(a), the server device 10 displays an approach detection icon E22 on the interactive AI screen C2 of the first user terminal (user terminal 20-1) and causes the interactive AI to output a voice V28 indicating a statement such as "Beta and the others also came to shop at the same store." In Fig. 17(a), the approach detection icon E22 is displayed to show a state in which approach notification information has been acquired (hereinafter referred to as a "first approach state").

[0093] When the approach notification information is no longer acquired from the first approach state, the server device 10 assumes that the second user terminal has not yet gone far for a certain period of time (hereinafter referred to as the "second approach state"), and causes the UI to behave according to the second approach state. In the example of Fig. 17(b), the server device 10 ends the display of the approach detection icon E22, and causes the interactive AI to output a voice V29 indicating a statement that "Beta and his friends have moved away a little, but it looks like they are still in the department store."

[0094] Since the approach detection icon E22 is not displayed, it is indicated that the ambient sound of the first user terminal does not include a specific sound, that is, the first approach state is not being reached. Meanwhile, the server device 10 continues to control the behavior of the UI of the dialogue-type AI from the first approach state by referring to the dialogue history of the user of the second user terminal (Emma in the example of FIG. 17). That is, the server device 10 executes the dialogue control process (A41 shown in FIG. 7) during approach in both the first approach state and the second approach state.

[0095] When a predetermined period of time has elapsed since the second approach state was entered, the server device 10 determines that the approach state has ended (A44=YES in FIG. 7), and returns to the normal dialogue control process (A22 in FIG. 7). Since the range in which the specific sound can reach (areas R1 and R2 in FIG. 10) is not very wide, the approach state may end quickly if the user continues to move. In contrast, according to the example in FIG. 17, the period during which the dialogue control process during approach is performed is longer, allowing the user to experience a longer sense of approach with other dialogue-based AIs.

[0096] The predetermined period is not limited to a fixed period, and may be, for example, a period until a second user terminal approaching a first user terminal moves away from the first user terminal by a predetermined distance. Also, the predetermined period may be a period during which the first user terminal and the second user terminal are in the same area (such as the same station premises, the same department store, the same town, etc.).

[0097] Furthermore, the server device 10 may set the predetermined period to be longer as the approach history of the first user terminal and the second user terminal increases. According to such an embodiment, the interactive AI of the user terminal 20 that has more opportunities to approach each other can experience a state of approach (the first approach state and the second approach state) for a longer period. Furthermore, the server device 10 may vary the predetermined period depending on the time of the day or the current day of the week. For example, the server device 10 sets the predetermined period on holidays to be longer than the predetermined period on weekdays. According to such an embodiment, the state of approach (the first approach state and the second approach state) can be experienced for a longer period during a predetermined time (for example, a time when there is more time, such as a holiday).

[0098] Furthermore, the server device 10 may vary the predetermined period depending on the location of the first user terminal. For example, the server device 10 sets the predetermined period in a predetermined location such as a park or a department store to be longer than the predetermined period in other locations. According to this aspect, the user can experience the close proximity state (the first close proximity state and the second close proximity state) for a longer period in a predetermined location (for example, a park, a department store, or other locations that the user visits when he or she has time).

[0099] <Variation: Registration of dialogue materials> In the dialogue control process at the time of approach, information other than the dialogue history may be used. In that case, for example, the server device 10 functions as an example of a registration receiving unit that receives registration of dialogue materials associated with the first user terminal. For example, the server device 10 displays a screen for registering dialogue materials.

[0100] FIG. 18 is a diagram showing an example of a dialogue material registration screen. In the example of FIG. 18, the server device 10 displays dialogue material registration buttons B24, B25, and B26 on the dialogue AI screen C2 of the first user terminal (user terminal 20-1). The registration buttons B24, B25, and B26 are operation images for registering "talking about a store you often go to," "talking about hobbies," and "talking about a movie you recently saw" as dialogue materials, respectively. The server device 10 causes the dialogue AI shown in the AI ​​appearance image F21 to output a voice V41 indicating a statement saying, "Please pick a topic to talk about when you meet with your dialogue AI friends!"

[0101] When the registration button is operated, the server device 10 registers the dialogue material indicated by the operated registration button by storing the dialogue material in the dialogue history database 4 in association with Tom, the user of the first user terminal. Note that the dialogue material to be registered may be information indicating only the theme as shown in FIG. 18, or may include more detailed content (for example, the name of a "frequently visited store" and products). More detailed content can be registered by further interacting with the dialogue AI.

[0102] Then, when the server device 10 (an example of a behavior control unit) acquires information indicating the approach of the second user terminal from the first user terminal as approach notification information, the server device 10 controls the behavior of the UI of the first user terminal based on the registered dialogue material. For example, when "talking about hobbies" is registered, the server device 10 determines the utterance by referring to the hobbies part of the user attributes included in the dialogue history. Depending on the registered topic, the server device 10 searches for the topic from external information using the task execution function of the AI ​​module 3 and determines the utterance. According to this embodiment, it is possible to select the dialogue content to be given to the dialogue-based AI of the approaching partner.

[0103] The server device 10 may, for example, register dialogue materials in association with a location, and control the behavior of the UI using the dialogue materials associated with the location where the approach state has occurred. The server device 10 may also register dialogue materials in association with a time period, such as a time of day or a day of the week, and control the behavior of the UI using the dialogue materials associated with the time period when the approach state has occurred. The server device 10 may also register dialogue materials in association with the number of past approaches, and control the behavior of the UI using the dialogue materials associated with the number of past approaches with the second user terminal that has become in a close state. According to these aspects, it is possible to have a dialogue whose content matches the situation in which the approach between the terminals is detected.

[0104] <Variation: Behavior Record> The behavior of the UI of the interactive AI when approaching may be reused. For example, when approach notification information indicating the approach of the second user terminal is acquired from the first user terminal, the server device 10 functions as an example of a storage control unit that stores the behavior of the UI of the first user terminal in association with the combination of both terminals (the first user terminal and the second user terminal). The behavior of the UI here is the behavior when approaching.

[0105] 12, the conversational AI of the first user terminal makes a statement based on the conversation history of the conversational AI of the second user terminal, and the server device 10 stores the content of the statement (an example of the UI behavior of the first user terminal) in association with the combination of the first user terminal and the second user terminal. Then, when the server device 10 acquires approach notification information for the combination again, the server device 10 functions as an example of a second notification unit that notifies the user via the first user terminal of the UI behavior stored in association with the combination.

[0106] FIG. 19 is a diagram showing another example of a dialogue during approach. In the example of FIG. 19, the server device 10 causes the conversational AI of the first user terminal (user terminal 20-1) to output a voice V42 indicating a statement such as "When we passed each other last time, I told you that you were talking about a new shop in front of the station!" In the example of FIG. 19, the server device 10 explains the behavior of the UI stored in the example of FIG. 12, thereby notifying the user of the first user terminal of the behavior. According to this aspect, it is possible to remind the user of the previous time they passed each other.

[0107] The method of notifying the behavior of the UI is not limited to this. For example, the server device 10 may notify by displaying an explanation of the behavior of the UI or by making the interactive AI perform the same behavior. Also, the server device 10 may store only when the UI of the interactive AI performs a predetermined behavior when approaching. The predetermined behavior is, for example, a behavior in which the interactive AIs of the approaching user terminals 20 converse with each other as in the example of FIG. 14, or a behavior in which the position of the first user terminal is notified as in the example of FIG. 16. According to this embodiment, it is possible to remember only the times when a specific behavior was performed when passing each other.

[0108] Furthermore, the server device 10 may store the UI behavior only when the time of the approaching state is equal to or longer than a threshold value. According to such an embodiment, the UI behavior when passing by another person in an instant is not notified, but the stored UI behavior is notified only when passing by another person who has been in close proximity for a certain period of time, so that the user can remember the previous time they passed by each other.

[0109] <Variation: Method for outputting specific sound> The method of outputting the specific sound is not limited to the above-mentioned method. For example, a sound corresponding to an ambient sound may be the specific sound. In this case, the server device 10 functions as an example of an ambient sound acquisition unit that acquires the ambient sound of the user terminal 20 (including the second user terminal). The server device 10 acquires the sound indicated by the sound data transmitted from the user terminal 20 as the ambient sound of the user terminal 20.

[0110] Then, the server device 10 (an example of a sound control unit) outputs a sound corresponding to the acquired ambient sound as a specific sound (an example of a specific sound) to the user terminal 20 (including the second user terminal). For example, the server device 10 analyzes the distribution of frequencies of sounds contained in the ambient sound, and outputs a sound of a frequency that is contained in the ambient sound at a low ratio as the specific sound. In this case, the specific sound may be limited to sounds outside the audible range, or may include sounds in the audible range.

[0111] For example, when the specific sound contains many high-frequency sounds, the server device 10 outputs a low-frequency sound as the specific sound, and when the specific sound contains many low-frequency sounds, the server device 10 outputs a high-frequency sound as the specific sound. According to this embodiment, compared to when the specific sound is a uniform sound, it is easier to separate the specific sound from ambient sounds, even if there are ambient sounds, so that it is easier to detect the proximity of terminals to each other.

[0112] Conversely, the server device 10 may output a sound of a frequency that is contained in a large proportion of the ambient sound as the specific sound. In particular, when a sound in the audible range is output as the specific sound, this method makes it easier for the specific sound to blend in with the ambient sound compared to when a sound of a frequency that is contained in a small proportion of the ambient sound is output, so that when the specific sound reaches the human ear, it is difficult for the person to notice that the specific sound is a specific sound.

[0113] Furthermore, a sound corresponding to the position of the user terminal 20 may be the specific sound. In this case, the server device 10 functions as an example of a position acquisition unit that acquires position information indicating the position of the user terminal 20. The server device 10 periodically requests the user terminal 20 for position information, and repeatedly acquires the position information of the user terminal 20. Then, the server device 10 (an example of a sound control unit) causes the user terminal 20 to output a sound corresponding to the position indicated by the acquired position information as a specific sound.

[0114] For example, when the server device 10 acquires location information of a place where there is a high possibility of many people, such as a station, a department store, or a downtown area, the server device 10 outputs a sound that is difficult to blend in with the sounds of the crowd and has a high volume as the specific sound. Also, when the server device 10 acquires location information of a relatively quiet place, such as a hospital, a library, or a residential area, the server device 10 outputs a sound with a low volume as the specific sound (especially in the case of a sound in the audible range). According to this embodiment, it is possible to make it easier to detect the approach of a person while making it difficult for people in the vicinity to notice the specific sound, compared to when the specific sound is a uniform sound.

[0115] <Other examples> In the example of FIG. 4, the server device 10 performs a detection process to detect the approach of the terminals at A33, but this detection process may be performed by the user terminal 20. In this case, the user terminal 20 acquires an ambient sound at A32 and determines whether or not the acquired ambient sound includes a specific sound. If the specific sound is included, the user terminal 20 transmits detection data indicating that the terminals have been approached to the server device 10. Upon receiving the detection data, the server device 10 acquires the detection result indicated by the detection data as approach notification information and starts a dialogue control process at the time of approach at A41. According to this embodiment, the communication load between the user terminal 20 and the server device 10 can be reduced compared to the case of communicating sound data.

[0116] In the example of Fig. 4 etc., the approach between terminals is detected using a specific sound output by a speaker and a sound detected by a microphone serving as a sound sensor, but the method of detecting the approach between terminals is not limited to this. For example, the server device 10 may detect the approach between terminals when the communication unit 23 serving as a communication sensor receives radio waves (radio waves such as Bluetooth (registered trademark) or WiFi) output by the communication unit 23 of the user terminal 20. In this case, since radio waves are less likely to be blocked by obstacles than sounds, it is possible to more easily detect the approach even in places with many obstacles compared to the case of using a specific sound.

[0117] Furthermore, the server device 10 may detect the approach based on the position information output by a positioning sensor of the user terminal 20. For example, the server device 10 periodically acquires position information from each user terminal 20, and detects that the terminals have approached each other when the distance between them becomes less than a threshold. As described above, the server device 10 or the user terminal 20 may detect the approach of the terminals by acquiring information output by a sensor included in the user terminal 20 as approach notification information.

[0118] In the example of FIG. 4, the user terminal 20 starts and ends the dialogue process and the approach detection process at the same time, but this is not limited thereto. For example, the approach detection process may be continued regardless of whether the dialogue process is being executed. The user terminal 20 continues to execute the approach detection process, for example, by having a program for the approach detection process resident and executing it in the background. In this case, when the server device 10 detects the approach of the terminals based on the sound data transmitted by the approach detection process, it instructs the user terminal 20 to start the dialogue process. According to this embodiment, even when the user is not interacting with the dialogue AI, the interaction can be started when the user approaches another dialogue AI.

[0119] Also, the AI ​​module 3 may be installed in the user terminal 20 so that the conversational AI operates offline. In this case, the conversation history of other conversational AIs cannot be used, but it is possible to change the behavior of the UI in response to the proximity of another user terminal 20, so that the presence of the conversational AI can be enhanced by making the user aware of the presence of other conversational AIs, as in the above example. In this way, the processor that realizes the above-mentioned acquisition unit and behavior control unit, etc., is not limited to the processor of the server device 10, but may be the processor of the user terminal 20 alone, or may be both the processor of the server device 10 and the processor of the user terminal 20.

[0120] <Configuration variations> The configuration (overall configuration, hardware configuration, functional configuration, etc.) shown in FIG. 1 and the like is an example, and other configurations may be used as long as there is no inconvenience in implementation. For example, the server device 10 may be distributed across two or more devices, and may be provided in the form of SaaS (Software as a Service) or a cloud computing system. Furthermore, the information processing performed by the server device 10 may be collectively executed by the user terminal 20. In short, as long as the necessary information processing is executed in the entire automated dialogue system 1, the devices that execute the information processing may have any configuration.

[0121] Furthermore, the artificial intelligence module (AI module 3) may be an internal or external component of the server device 10, or may be an internal or external component of the automated dialogue system 1. Furthermore, the function realized by one artificial intelligence module may be distributed and realized by two or more artificial intelligence modules, or the function realized by two or more artificial intelligence modules may be integrated and realized by one artificial intelligence module.

[0122] The output destination of information or data (hereinafter referred to as "information, etc.") may be another device, a display, a memory unit (including a built-in memory unit and an external memory unit), etc. Acquisition of information, etc. includes acquiring information, etc. generated by the device itself, in addition to acquiring information, etc. transmitted from another device. Tables, etc. (tables, databases, etc.) that associate parameters are not limited to the tables, etc. shown in the figures, and the number of parameters may be reduced or increased. Furthermore, information, etc. corresponding to parameters may be obtained by a formula, a conditional formula, etc., without using a table, etc.

[0123] The above-described aspects of the embodiment are information processing devices such as the server device 10 and the user terminal 20, and information processing systems such as the automated dialogue system 1 including the server device 10 and the user terminal 20, but may also be information processing methods. The information processing methods include the same steps as those executed by the information processing system. The above-described aspects of the embodiment may also be programs. The programs cause a computer to execute the same steps as those executed by the information processing system.

[0124] <Additional Notes> Furthermore, it may be provided in the following aspects:

[0125] (1) An information processing system having at least one processor, wherein in an acquisition step, the processor acquires information from a first user terminal functioning as a UI (User Interface) of an interactive artificial intelligence module, indicating whether or not a second user terminal functioning as the UI is approaching, and in a behavior control step, controls the behavior of the UI, and when the information indicating the approach of the second user terminal is acquired from the first user terminal, changes the behavior of the UI of the first user terminal.

[0126] According to this embodiment, the presence of the dialogue-based AI can be enhanced.

[0127] (2) In the information processing system described in (1) above, the second user terminal has a function of outputting a specific sound, the information is information indicating sounds around the first user terminal, and the processor, in the behavior control step, changes the behavior when the information indicating a sound including the specific sound is acquired.

[0128] According to this embodiment, it is possible to detect the approach without being affected by the communication state.

[0129] (3) In the information processing system described in (2) above, the specific sound includes multiple types of sound, and in the sound control step, the processor outputs the specific sound to the second user terminal while sequentially switching the type.

[0130] According to this embodiment, the approach can be easily detected even in the presence of ambient noise.

[0131] (4) In the information processing system described in (3) above, the processor acquires sounds around the second user terminal in the ambient sound acquisition step, and outputs a sound corresponding to the acquired ambient sound as the specific sound to the second user terminal in the sound control step.

[0132] According to this embodiment, the approach can be easily detected even in the presence of ambient noise.

[0133] (5) In the information processing system described in (3) or (4) above, in the position acquisition step, the processor acquires position information indicating the position of the second user terminal, and in the sound control step, causes the second user terminal to output a sound corresponding to the position indicated by the acquired position information as the specific sound.

[0134] According to this aspect, it is possible to make it easier to detect the approach of a specific sound while making it difficult for people in the vicinity to notice the specific sound.

[0135] (6) In the information processing system described in any one of (1) to (5) above, in the history acquisition step, the processor acquires an interaction history with the artificial intelligence module via the second user terminal, and in the behavior control step, changes the behavior of the UI of the first user terminal in accordance with the acquired interaction history.

[0136] According to this embodiment, it is possible to feel the atmosphere of the person approaching.

[0137] (7) In an information processing system described in any one of (1) to (6) above, in the behavior control step, the processor controls the behavior of the UI of the first user terminal so that the artificial intelligence module that interacts via the first user terminal and the artificial intelligence module that interacts via the second user terminal interact with each other.

[0138] According to this embodiment, the presence of the interactive AI can be more strongly felt.

[0139] (8) In the information processing system described in any one of (1) to (7) above, in a request step, when the information indicating the approach of the second user terminal is obtained from the first user terminal, the processor requests a user of the first user terminal for permission to notify the second user terminal of the location of the first user terminal, and in a first notification step, if the permission is granted, notifies the user of the second user terminal of the location of the first user terminal via the second user terminal.

[0140] According to this embodiment, it is possible to identify the person who has approached.

[0141] (9) In the information processing system described in any one of (1) to (8) above, in the storage step, the processor stores a history of the approach, and in the behavior control step, changes the behavior of the UI in accordance with the stored history.

[0142] According to this embodiment, it is possible to increase the variety of UI behavior.

[0143] (10) In the information processing system described in any one of (1) to (9) above, in the acquisition step, the processor repeatedly acquires the information, and in the behavior control step, changes the behavior of the UI during a period during which the information indicating the approach of the second user terminal continues to be acquired from the first user terminal and for a predetermined period after the end of that period.

[0144] According to this embodiment, it is possible to have a prolonged sense of closeness to other interactive AIs.

[0145] (11) In the information processing system described in any one of (1) to (10) above, in the registration reception step, the processor accepts registration of dialogue material associated with the first user terminal, and in the behavior control step, changes the behavior of the UI of the first user terminal in accordance with the registered dialogue material.

[0146] According to this embodiment, it is possible to select the content of the dialogue to be given to the interactive AI of the approaching partner.

[0147] (12) In the information processing system described in any one of (1) to (11) above, in a storage control step, when the information indicating the approach of the second user terminal is obtained from the first user terminal, the processor stores the UI behavior of the first user terminal in correspondence with a combination of both terminals, and in a second notification step, when the information of the combination is obtained again, notifies a user via the first user terminal of the UI behavior stored in correspondence with the combination.

[0148] According to this embodiment, the user can be reminded of the previous time they passed each other.

[0149] (13) An information processing method, in which a processor included in an information processing system executes each step of the information processing system according to any one of (1) to (12) above.

[0150] According to this embodiment, the presence of the dialogue-based AI can be enhanced.

[0151] (14) A program for causing a computer to execute each step of the information processing system according to any one of (1) to (12) above.

[0152] According to this embodiment, the presence of the dialogue-based AI can be enhanced. Of course, this is not the case. Furthermore, the above-described embodiments and modifications may be combined in any desired manner.

[0153] Finally, although various embodiments of the present invention have been described, these are presented as examples and are not intended to limit the scope of the invention. The new embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. The embodiments and their modifications are within the scope and spirit of the invention, and are included in the scope of the invention and its equivalents described in the claims. [Explanation of symbols]

[0154] 1: Automated dialogue system 2: Communication lines 3: AI module 4: Dialogue history database 10: Server device 11: Control section 20: User terminal 20-1: User terminal 20-2: User terminal 21: Control section

Claims

1. An information processing system including at least one processor, The processor, In the acquisition step, information is acquired from a first user terminal functioning as a UI (User Interface) of an interactive artificial intelligence module, the information indicating whether or not a second user terminal functioning as the UI is approaching; In the behavior control step, a behavior of the UI is controlled, and when the information indicating the approach of the second user terminal is acquired from the first user terminal, a behavior of the UI of the first user terminal is changed; The second user terminal has a function of outputting a specific sound, the information is information indicating a sound around the first user terminal, The processor, In the behavior control step, the behavior is changed when the information indicating a sound including the specific sound is acquired. Information processing system.

2. 2. The information processing system according to claim 1, The specific sound includes a plurality of types of sound, The processor, In the sound control step, the specific sound is output from the second user terminal while sequentially switching the type of the specific sound. Information processing system.

3. 3. The information processing system according to claim 2, The processor, In the ambient sound acquisition step, ambient sound of the second user terminal is acquired, In the sound control step, a sound corresponding to the acquired surrounding sound is output as the specific sound to the second user terminal. Information processing system.

4. 3. The information processing system according to claim 2, The processor, In the position acquisition step, position information indicating a position of the second user terminal is acquired; In the sound control step, a sound corresponding to a position indicated by the acquired position information is output to the second user terminal as the specific sound. Information processing system.

5. 2. The information processing system according to claim 1, The processor, In the history acquisition step, a dialogue history with the artificial intelligence module is acquired via the second user terminal; In the behavior control step, a behavior of the UI of the first user terminal is changed in accordance with the acquired dialogue history. Information processing system.

6. 2. The information processing system according to claim 1, The processor, In the behavior control step, the behavior of the UI of the first user terminal is controlled so that the artificial intelligence module that interacts through the first user terminal and the artificial intelligence module that interacts through the second user terminal interact with each other. Information processing system.

7. 2. The information processing system according to claim 1, The processor, In the request step, when the information indicating the approach of the second user terminal is acquired from the first user terminal, a user of the first user terminal is requested to give permission for a notification of the location of the first user terminal to the second user terminal; In the first notification step, if the permission is granted, the location of the first user terminal is notified to a user of the second user terminal via the second user terminal. Information processing system.

8. 2. The information processing system according to claim 1, The processor, In the storage step, the history of the approach is stored; In the behavior control step, a behavior of the UI is changed in accordance with the accumulated history. Information processing system.

9. 2. The information processing system according to claim 1, The processor, In the acquiring step, the information is acquired repeatedly; In the behavior control step, a behavior of the UI is changed during a period during which the information indicating the approach of the second user terminal continues to be acquired from the first user terminal and during a predetermined period after the end of the period. Information processing system.

10. 2. The information processing system according to claim 1, The processor, In the registration acceptance step, registration of dialogue material associated with the first user terminal is accepted, In the behavior control step, a behavior of the UI of the first user terminal is changed in accordance with the registered dialogue material. Information processing system.

11. 2. The information processing system according to claim 1, The processor, In the storage control step, when the information indicating the approach of the second user terminal is acquired from the first user terminal, a behavior of the UI of the first user terminal is stored in association with a combination of both terminals; In the second notification step, when the information on the combination is acquired again, a behavior of the UI stored in association with the combination is notified to a user via the first user terminal. Information processing system.

12. 1. An information processing method, comprising: A processor included in the information processing system Executing each step of the information processing system according to any one of claims 1 to 11. Information processing methods.

13. A program, A computer is caused to execute each step of the information processing system according to any one of claims 1 to 11. program.

Images