Robot, abnormality notification method and program

Abstract

To provide a technique for making a robot appear to have better conversation capability.SOLUTION: A conversation output system 1000 includes: first information acquisition means for acquiring first information which is information of at least one of information related to a user of a robot 100 and situation information which is information of a situation around the robot 100; creation means for creating conversation data for making the user recognize that the robot 100 and a predetermined target have a conversation matching at least the first information, based on the acquired first information; and output control means for controlling an output unit to output information based on the created conversation data, thereby making the user recognize that the robot 100 and the predetermined target have a conversation matching at least the first information, where the robot 100 does not have a function of executing a conversation of a level equal to or higher than a level of the conversation based on the conversation data.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a conversation output system, a conversation output server, a conversation output method, and a program. [Background technology]

[0002] Robots that imitate animals are becoming popular. These robots are also called electronic pets, and have an appearance that is loved by users. Robots that recognize the user's voice and act according to the user's instructions, and robots that can converse with each other have also appeared. For example, Patent Document 1 discloses a robot system in which multiple robots converse with each other. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2003-205483 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventionally, a robot system capable of conversation between robots is disclosed in, for example, Patent Document 1. The content of the conversation between multiple robots described in Patent Document 1 is a script in which lines are written as a scenario, and is preset according to the number of conversations, so the conversation is a set one. Although a reasonably advanced conversation is possible by making full use of AI (Artificial Intelligence) technology using a supercomputer, it is not realistic to install it in consumer products for general users. Therefore, there is room for improvement in the conversation technology between robots. Such problems apply not only to conversation technology between multiple robots, but also to conversation technology between a robot and a specified target.

[0005] The present invention has been made to solve the above problems, and has an object to provide a technique for making a robot's conversational ability appear to be improved. [Means for solving the problem]

[0006] In order to achieve the above object, the conversation output system of the present invention comprises: A first information acquisition means for acquiring first information, which is at least one of information regarding a user of the robot and situation information, which is information regarding a situation around the robot; a creating means for creating conversation data for making the user recognize that the robot and a predetermined object are having a conversation that at least matches the first information, based on the acquired first information; an output control means for controlling an output unit to output information based on the created conversation data, thereby making the user recognize that the robot and the predetermined target are having a conversation that matches at least the first information; The robot does not have a function of executing a conversation at a level higher than the level of the conversation based on the conversation data. It is a conversation output system. Effect of the Invention

[0007] According to the present invention, a technique for making a robot's conversational ability appear to be improved can be provided. [Brief description of the drawings]

[0008] [Figure 1] 1 is a diagram showing a functional configuration of a conversation output system according to a first embodiment of the present invention. [Diagram 2] FIG. 1 is a diagram showing an example of the appearance of a robot according to a first embodiment. [Diagram 3] FIG. 2 is a diagram showing an example of data stored in a scenario storage unit according to the first embodiment. [Figure 4] FIG. 4 is a diagram showing an example of data stored in a user profile storage unit according to the first embodiment. [Diagram 5]FIG. 4 is a diagram showing an example of data stored in a user situation storage unit according to the first embodiment. [Figure 6] 13 is a flowchart of a thread group for collecting status information in the conversation processing according to the first embodiment. [Figure 7] 13 is a flowchart of a thread group for conversation request collection in the conversation processing according to the first embodiment. [Figure 8] 13 is a flowchart of a thread group for outputting conversation content in the conversation process according to the first embodiment. [Figure 9] 4 is a flowchart of a scenario selection process according to the first embodiment. [Figure 10] FIG. 2 is a diagram showing an example of conversation content output to one of the conversation output terminals in the conversation output system according to the first embodiment. [Figure 11] FIG. 4 is a diagram showing an example of conversation content output to another conversation output terminal in the conversation output system according to the first embodiment. [Figure 12] FIG. 13 is a diagram showing an example of data stored in a scenario storage unit according to the third modification of the first embodiment of the present invention. [Figure 13] FIG. 11 is a diagram showing a functional configuration of a conversation output system according to a second embodiment of the present invention. [Figure 14] FIG. 11 is a diagram showing a functional configuration of a conversation output system according to a third embodiment of the present invention. [Figure 15] FIG. 11 is a diagram showing a functional configuration of a conversation output system according to a fourth embodiment of the present invention. [Figure 16] FIG. 11 is a diagram showing a functional configuration of a conversation output system according to a fifth embodiment of the present invention. [Figure 17] FIG. 13 is a diagram showing a functional configuration of a conversation output system according to a sixth embodiment of the present invention. [Figure 18] 23 is a flowchart of a thread group for a pseudo chat according to the sixth embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, a conversation output system according to an embodiment of the present invention will be described with reference to diagrams. In the drawings, the same or corresponding parts are given the same reference numerals.

[0010] (Embodiment 1) The conversation output system according to the first embodiment of the present invention is a system that allows a robot that is unable to converse in a natural language by voice to appear to a user as if it is conversing with another robot in a natural language.

[0011] As shown in FIG. 1, a conversation output system 1000 according to the first embodiment of the present invention includes a robot 100, a conversation output terminal 200, and a conversation output server 300. The robot 100 and the conversation output terminal 200 are wirelessly connected to each other via short-range wireless communication to form a pair. The conversation output system 1000 may include a plurality of pairs of the robot 100 and the conversation output terminal 200 (for example, the robot 100 and the conversation output terminal 200, the robot 100' and the conversation output terminal 200', the robot 100'' and the conversation output terminal 200'', etc.). The robot 100 can appear to a user as if it is conversing with another robot 100 in a natural language via the conversation output terminal 200 and the conversation output server 300.

[0012] The robot 100 is a pet-type robot with a cute shape, and includes, as its functional components, a situation acquisition unit 110 and a short-distance communication unit 120. These functional components will be described later. Although not shown, the robot 100 may also include a clock that can acquire the current date and time.

[0013] As shown in Fig. 2, the robot 100 is provided with a human sensor 131 at the position of the eyes, a camera 132 at the position of the nose, a microphone 133 at the position of the ears, and a speaker 134 at the position of the mouth. The robot 100 can express emotions by moving its legs 135 and tail 136. For example, flapping its legs 135 back and forth and side to side, or wagging its tail 136, indicates that it is happy. Although not shown, the robot 100 is provided with an acceleration sensor, a tactile sensor, and the like, so that it can detect that it is being held by a user. Although not shown, the robot 100 is provided with a temperature sensor, a humidity sensor, and the like, so that it can obtain information about the surrounding environment.

[0014] The functional configuration of the robot 100 will be described. The situation acquisition unit 110 includes a human sensor 131, a camera 132, a microphone 133, an acceleration sensor, a tactile sensor, a temperature sensor, a humidity sensor, and the like, and acquires situation information, which is information on the situation around the robot 100, by using these sensors. The situation information includes information on the user of the robot 100 and information on the robot 100. For example, the information on the user of the robot 100 includes information obtained from the human sensor 131 that "the user approached the robot 100," information obtained from the camera 132 that "the user looked at the robot 100," information obtained from the microphone 133 that "the user spoke to the robot 100," information obtained from the acceleration sensor or the tactile sensor, and the like. The information on the robot 100 includes information such as "the current temperature around the robot 100" obtained from the temperature sensor, "the current humidity around the robot 100" obtained from the humidity sensor, and "the current date and time in the area where the robot 100 exists" obtained from the clock. Regarding the information about the user, information on the frequency (number of times) may be included in the situation information. Here, the various sensors provided in the situation acquisition unit 110 are collectively referred to as a first sensor.

[0015] The situation information may include only one of the information about the user of the robot 100 and the information about the robot 100. For example, in a scenario selection process described later, when the information about the robot 100 is not used and only the information about the user of the robot 100 is used, the situation information may include only the information about the user of the robot 100 and may not include the information about the robot 100.

[0016] The short-distance communication unit 120 includes a short-distance wireless communication device (for example, a Bluetooth (registered trademark) communication device) and transmits the situation information acquired by the situation acquisition unit 110 to the conversation output terminal 200. Therefore, the short-distance communication unit 120 functions as a situation transmission unit.

[0017] Although the robot 100 has a speaker 134, it does not have a function of speaking natural language. The robot 100 can output electronic sounds or sounds that imitate animal cries from the speaker 134. Therefore, as long as the user hears the sounds output by the robot 100, it cannot be assumed that the robot 100 can understand human speech. Here, the robot 100 may have a conversational ability like a baby or a small child, but does not have a function of carrying out a conversation at a level higher than the level of a conversation based on conversation data described later.

[0018] Next, the conversation output terminal 200 will be described. The conversation output terminal 200 is a smartphone equipped with a display 270, and includes, as functional components, a short-range communication unit 210, an LTE (Long Term Evolution) communication unit 220, and a conversation output unit 231 (terminal control unit 230). Although not shown, the terminal control unit 230 has a clock function and can acquire the current date and time. The display 270 is configured, for example, with an LCD (Liquid Crystal Display), an EL (Electroluminescence) display, or the like, and displays the contents instructed by the conversation output unit 231 (terminal control unit 230). The display 270 functions as an output unit.

[0019] The short-range communication unit 210 includes a short-range wireless communication device capable of communicating in accordance with the same communication standard as the short-range communication unit 120, and receives the situation information transmitted from the robot 100. Therefore, the short-range communication unit 210 functions as a situation receiving unit.

[0020] The LTE communication unit 220 includes a device that communicates according to the LTE communication standard, and communicates with the conversation output server 300. For example, the LTE communication unit 220 transmits status information to the conversation output server 300. The LTE communication unit 220 also receives data of a scenario (to be described later) transmitted by the conversation output server 300. The LTE communication unit 220 communicates with the conversation output server 300, and therefore functions as a server-to-server communication unit.

[0021] Depending on the robot 100 (e.g., because it does not have a clock or a temperature sensor), the situation information transmitted to the conversation output terminal 200 may not include information on the current date and time, weather, temperature, news, etc. of the area where the robot 100 exists. In this case, the conversation output terminal 200 adds information on the current date and time, weather, temperature, news, etc. of the area where the robot 100 exists to the situation information, and transmits the situation information with this information added to the conversation output server 300 via the LTE communication unit 220. The conversation output terminal 200 can obtain the current date and time from a clock provided in the terminal control unit 230. Also, the conversation output terminal 200 can access the Internet via the LTE communication unit 220 to obtain information on the weather, temperature, news, etc.

[0022] The terminal control unit 230 is composed of a CPU (Central Processing Unit) and the like, and executes a program stored in a storage unit (not shown) to realize the function of the conversation output unit 231. For example, after purchasing the robot 100, the user can install the robot application in the conversation output terminal 200 (smartphone) by accessing the URL (Uniform Resource Locator) of the robot application, and the function of the conversation output unit 231 is realized by this robot application. The URL of the robot application will be described in, for example, an instruction manual for the robot 100.

[0023] The conversation output unit 231 controls the display 270 to display on the display 270 conversation contents that appear as if the robot 100' is conversing in a natural language with another robot 100', based on scenario data (described later) received from the conversation output server 300 via the LTE communication unit 220. The conversation output unit 231 can be realized as SNS (Social Networking Service) client software that accesses an SNS provided by the conversation output server 300. The conversation output unit 231 functions as an output control means.

[0024] For example, assume that a screen is output that shows the robot 100 (wirelessly connected to the conversation output terminal 200) and the robot 100' (wirelessly connected to the conversation output terminal 200') having a conversation. In this case, the conversation output unit 231 receives only the utterance content of the robot 100 as scenario data from the conversation output server 300, and transmits the received scenario data as a posting content to the SNS provided by the conversation output server 300. Then, the conversation output unit 231 of the conversation output terminal 200' that is wirelessly connected to the conversation partner (robot 100') also receives only the reply content of the robot 100' as scenario data from the conversation output server 300, and transmits the received scenario data as a posting content to the SNS provided by the conversation output server 300.

[0025] Then, the conversation output unit 231 serving as SNS client software will output the utterance content of the robot 100 and the reply content of the robot 100 ′ to the display 270 of the conversation output terminal 200 by the SNS function of the conversation output server 300 .

[0026] Next, the conversation output server 300 will be described. The conversation output server 300 is a cloud server existing on the Internet, and provides an SNS for the robots 100 to communicate with each other. When the conversation output terminal 200 wirelessly connected to the robot 100 accesses the SNS provided by the conversation output server 300, the robot 100 can appear to the user as if it is having a conversation (chat) with another robot 100.

[0027] The conversation output server 300 has, as its functional configuration, an LTE communication unit 310, a scenario selection unit 321 (control unit 320), a scenario memory unit 331 (memory unit 330), a user profile memory unit 332 (memory unit 330), and a user situation memory unit 333 (memory unit 330).

[0028] The LTE communication unit 310 includes a device that communicates according to the LTE communication standard, and communicates with the conversation output terminal 200. For example, the LTE communication unit 310 receives situation information transmitted by the conversation output terminal 200. The LTE communication unit 310 also transmits scenario data to the conversation output terminal 200. In this way, the LTE communication unit 310 communicates with the conversation output terminal 200, and therefore functions as a terminal communication unit.

[0029] The control unit 320 is composed of a CPU and the like, and realizes the functions of a scenario selection unit 321 by executing a program stored in the storage unit 330. The control unit 320 also includes a clock (not shown) and can obtain the current date and time of the area where the robot 100 is located.

[0030] The scenario selection unit 321 selects scenario data stored in the scenario storage unit 331 based on the situation information received by the LTE communication unit 310. When selecting scenario data for making it appear as if the robot 100 and the robot 100' are conversing, the scenario selection unit 321 uses not only the situation information of the robot 100 but also the situation information of the robot 100', as described below. Although both of these are situation information, when it is desired to distinguish between them, the situation information of the robot 100 will be called the first situation information and the situation information of the robot 100' will be called the second situation information.

[0031] The storage unit 330 is composed of a ROM (Read Only Memory), a RAM (Random Access Memory), etc., and functionally includes a scenario storage unit 331, a user profile storage unit 332, and a user situation storage unit 333. The ROM stores programs executed by the CPU of the control unit 320 and data required in advance to execute the programs. The RAM stores data that is created or changed during program execution.

[0032] 3, the scenario storage unit 331 stores, for each conversation topic, the contents of what the robot 100 will say and the contents of the reply from the conversation partner (here, robot 100') based on situation information, etc. A pair of the contents of what the robot 100 and its conversation partner will say, respectively, is called a scenario here.

[0033] For example, the top table in Fig. 3 is an example of scenario data when the topic is the intimacy of communication with the master (the user of each of the robots 100 and 100'). In Fig. 3, scenario data (the remarks made by the robot 100 and the replies made by the robot 100') are defined according to the intimacy level of the robot 100 and the intimacy level of the robot 100'. The intimacy level represents the degree of the user's involvement with the robot 100 (defined by comprehensively taking into consideration the number of times the robot 100 has spoken to the robot, the number of times the robot has looked at the robot's face, the number of times the robot has been held, etc.).

[0034] For example, the intimacy level is 1 if the user has no interaction at all (the user has never spoken to the robot 100 or held the robot 100), and 5 if the user has frequent interaction (for example, the number of times the user has spoken to the robot 100, the number of times the user has looked at the robot's face, and the number of times the user has held the robot 100 is 10 or more). In addition, the part marked "[I]" in FIG. 3 indicates that a phrase expressing a personal pronoun is to be inserted. In a country where personal pronouns change depending on gender, this part changes depending on the gender of the robot 100. For example, if the country of residence is Japan, "[I]" becomes "boku" if the (user of) the robot 100 is male, and becomes "watashi" if the (user of) the robot 100 is female. Also, the name of a pet may be inserted here. For example, if the pet's name is "GladDog", the message may read, "That's nice. GladDog's owner never plays with him."

[0035] 3 is an example of scenario data when the topic is the weather. In this example, when the weather included in the situation information of the robot 100 (first situation information) is sunny and the weather included in the situation information of the robot 100' (second situation information) is rainy, the utterance of the robot 100 is defined as "It's sunny and nice today," and the reply of the robot 100' is defined as "That's nice. It's raining over here and it's boring."

[0036] Moreover, the table at the bottom of FIG. 3 is an example of scenario data when the topic is an anniversary. The current date and time of robot 100 and the current date and time of robot 100' differ only due to the time difference between their respective places of residence, so the difference in dates is at most one day. Therefore, in this example, the scenario data is defined ignoring the date and time information included in the status information of robot 100'. Of course, taking the time difference into consideration, scenario data may be defined for each case in which the date and time included in the status information of robot 100' is one day before or one day after the date and time included in the status information of robot 100.

[0037] As shown in Fig. 4, the user profile storage unit 332 stores the ID and icon of the robot 100 on the SNS provided by the conversation output server 300, the country of residence, gender, birthday, hobbies, etc. of the user of the robot 100, and the profile of the robot 100 and its user. Note that in Fig. 4, only the gender, birthday, etc. of the user are stored, so the gender, birthday, etc. of the robot 100 are treated as being the same as the gender, birthday, etc. of the user. However, it is also possible to provide separate items for the gender, birthday, etc. of the robot 100 in the user profile storage unit 332 and set a gender and birthday separate from the user.

[0038] 5, the user situation storage unit 333 stores situation information transmitted from each robot 100 (each conversation output terminal 200). The user situation storage unit 333 is updated every time situation information is received from each conversation output terminal 200. In addition, the numbers of times "the user was spoken to" and "the user was looked at" are reset to 0 at regular intervals (for example, at midnight every day).

[0039] The control unit 320 creates conversation data for making the user recognize that the robot 100 is having a conversation that matches the first information by selecting scenario data stored in the scenario storage unit 331 based on the information about the user stored in the user profile storage unit 332 and the situation information stored in the user situation storage unit 333. The control unit 320 may select scenario data stored in the scenario storage unit 331 based on only one of the information about the user stored in the user profile storage unit 332 and the situation information stored in the user situation storage unit 333. At least one of the information about the user stored in the user profile storage unit 332 and the situation information stored in the user situation storage unit 333 is called first information. The control unit 320 functions as a first information acquisition means when acquiring the first information.

[0040] In the conversation data created by the control unit 320, status information of the conversation partner of the robot 100 (assumed to be the robot 100') and information on the user of the robot 100' are also stored in the user status storage unit 333 and the user profile storage unit 332, respectively. At least one of the information on the user of the robot 100' and the status information of the robot 100' can also be called the first information, but when it is desired to distinguish from at least one of the information on the user of the robot 100 and the status information of the robot 100 (the first information), at least one of the information on the user of the robot 100' and the status information of the robot 100' is called the second information. The control unit 320 functions as a second information acquisition means when acquiring the second information.

[0041] Next, a conversation process in which the robot 100 converses with another robot 100 via the conversation output terminal 200 and the conversation output server 300 will be described. This conversation process is composed of three thread groups, namely, a thread group for collecting situation information, a thread group for collecting conversation requests, and a thread group for outputting conversation content. These three thread groups are not executed sequentially, but are executed simultaneously in parallel. The thread group for outputting conversation content transmits scenario data stored in the scenario storage unit 331 (after being modified as necessary) to the conversation output terminal 200 wirelessly connected to the robot 100. Then, based on this scenario data, a screen in which the robot 100 appears to be conversing (chatting) with a conversation partner (for example, the robot 100') on the SNS provided by the conversation output server 300 is output from the conversation output terminal 200. First, the thread group for collecting situation information will be described with reference to FIG. 6.

[0042] When the robot 100 is powered on, a status transmission thread shown in the flowchart on the left side of Fig. 6 is started. When the conversation output terminal 200 is powered on, a status relay thread shown in the flowchart in the center of Fig. 6 is started. When the conversation output server 300 is powered on, a status update thread shown in the flowchart on the right side of Fig. 6 is started. In Fig. 6, dotted arrows indicate data being sent and received between each thread.

[0043] In the status transmission thread, the robot 100 acquires status information by the status acquisition unit 110 (step S101). Then, the robot 100 transmits the acquired status information to the conversation output terminal 200 via the short-range communication unit 120 (step S102), and returns to step S101. Note that in step S101, the robot 100 may constantly record (audio or video) the acquired status information and execute step S102 as appropriate, or may transmit the recorded (audio or video) data in its entirety to the conversation output terminal 200 and analyze it there.

[0044] In the status relay thread, the conversation output terminal 200 continues to wait until status information is sent from the robot 100, and when it is sent, receives the status information via the short-range communication unit 210 (step S111). Then, the conversation output terminal 200 adds information such as the current date and time and weather to the received status information as necessary, and transmits the information to the conversation output server 300 via the LTE communication unit 220 (step S112), and returns to step S111.

[0045] In the status update thread, the conversation output server 300 continues to wait until status information is sent from the conversation output terminal 200, and when the status information is sent, receives the status information via the LTE communication unit 310 (step S121). Then, using the received status information, the conversation output server 300 updates the status information stored in the user status storage unit 333 (step S122), and returns to step S121.

[0046] When there are multiple pairs of the robot 100 and the conversation output terminal 200, the above process is performed in each robot 100 and each conversation output terminal 200 that is communicatively connected to the robot 100. Therefore, the user situation storage unit 333 of the conversation output server 300 accumulates situation information on the user of each robot 100.

[0047] The thread group for collecting status information has been described above. Next, the thread group for collecting conversation requests will be described with reference to FIG.

[0048] When the robot 100 is powered on, a request sending thread shown in the flowchart on the left side of Fig. 7 is started. When the conversation output terminal 200 is powered on, a request relay thread shown in the flowchart in the center of Fig. 7 is started. When the conversation output server 300 is powered on, a request updating thread shown in the flowchart on the right side of Fig. 7 is started. In Fig. 7, dotted arrows indicate data being sent and received between each thread.

[0049] In the request transmission thread, the robot 100 determines whether or not a user has approached using the human presence sensor 131 or the like provided in the situation acquisition unit 110 (step S201). If the user has not approached (step S201; No), the process returns to step S201. If the user has approached (step S201; Yes), the robot 100 transmits a conversation request packet to the conversation output terminal 200 via the short-range communication unit 120 (step S202). The conversation request packet is a packet indicating that the robot 100 is requesting to have a conversation with another robot 100′, and includes information on the ID of the robot 100.

[0050] Then, the robot 100 judges whether or not the user is still nearby using the human presence sensor 131 or the like provided in the situation acquisition unit 110 (step S203). If the user is still nearby (step S203; Yes), the process returns to step S203. If the user is no longer nearby (step S203; No), the robot 100 transmits a conversation cancellation request packet to the conversation output terminal 200 via the short-range communication unit 120 (step S204). The conversation cancellation request packet is a packet transmitted by the robot 100 to cancel a conversation request packet transmitted previously, and includes the ID of the robot 100. Then, the process returns to step S201.

[0051] Also, in the request relay thread, the conversation output terminal 200 continues to wait until a conversation request packet is sent from the robot 100, and when it is sent, receives the conversation request packet at the short-range communication unit 210 (step S211). Then, the conversation request packet is transmitted to the conversation output server 300 via the LTE communication unit 220 (step S212). Then, the conversation output terminal 200 continues to wait until a conversation cancellation request packet is sent from the robot 100, and when it is sent, receives the conversation cancellation request packet at the short-range communication unit 210 (step S213). Then, the conversation cancellation request packet is transmitted to the conversation output server 300 via the LTE communication unit 220 (step S214), and the process returns to step S211.

[0052] In the request update thread, the conversation output server 300 continues to wait until a conversation request packet or a conversation cancellation request packet (hereinafter referred to as a "request packet") is sent from the conversation output terminal 200, and when it is sent, receives the request packet at the LTE communication unit 310 (step S221). Then, using the received request packet, the server 300 updates the information of members available for conversation (step S222), and returns to step S221.

[0053] The information on available members for conversation is a collection of IDs of the robots 100 that have sent a conversation request packet (i.e., the robots 100 that are close to the user). When the conversation output server 300 receives a conversation request packet, it adds the IDs included in the conversation request packet to the information on available members for conversation, and when it receives a conversation cancel request packet, it deletes the IDs included in the conversation cancel request packet from the information on available members for conversation.

[0054] When there are multiple pairs of robots 100 and conversation output terminals 200, the above process is performed by each robot 100 and the conversation output terminal 200 that is communicatively connected to the robot 100. Therefore, the conversation output server 300 has the IDs of all robots 100 that are nearby the user at that time as information on possible conversation members.

[0055] The thread group for collecting conversation requests has been described above. However, the above process is merely an example, and the robot 100 may transmit a conversation request packet (for example, periodically) regardless of the approach of the user. Next, the thread group for outputting conversation contents will be described with reference to FIG. 8.

[0056] When the conversation output terminal 200 is powered on, a conversation output thread shown in the flowchart on the left side of Fig. 8 is started. When the conversation output server 300 is powered on, a scenario transmission thread shown in the flowchart in the middle of Fig. 8 is started. The conversation output thread shown in the flowchart on the right side of Fig. 8 is the same as the flowchart on the left side. It is assumed that the flowchart on the right side is executed by a conversation output terminal 200' that is wirelessly connected to another robot 100' that is a conversation partner of the robot 100 that is wirelessly connected to the conversation output terminal 200. Also, in Fig. 8, dotted arrows indicate that data is transmitted and received between each thread.

[0057] First, in the scenario transmission thread, the conversation output server 300 selects a conversation partner by arbitrarily selecting two IDs of the robots 100 included in the information of conversationable members updated in the request update thread (step S311). If there is only one ID of the robot 100 in the information of conversationable members, a conversation between that robot 100 and a virtual (non-existent) robot 100 may be provided. In addition, although only scenario data assuming a conversation between two robots 100 is stored in the scenario storage unit 331 shown in FIG. 3, if scenario data assuming a conversation between three or more robots 100 is also stored, three or more IDs may be selected in step S311 and selected as conversation partners.

[0058] The conversation partner may be selected appropriately depending on the recent conversation history. For example, the user may register in advance in the user profile storage unit 332 a conversation partner selection preference (whether the user wants his / her robot 100 to converse with a robot 100' of a person he / she knows, or a robot 100'' of a person he / she does not know). The conversation output server 300 may select a conversation partner so that robots of users with the same conversation partner selection preference become conversation partners. The virtual (non-existent) robot 100 may be a conversation engine based on AI on an SNS. This conversation engine may be provided in the conversation output server 300, or may be realized on another computer connected via a network.

[0059] Next, the control unit 320 of the conversation output server 300 transmits a conversation start notification packet to the conversation output terminals 200 connected to each robot 100 selected in step S311 via the LTE communication unit 310 (step S312). The conversation start notification packet includes the ID of each robot 100 that will be a conversation partner, and notifies each conversation output terminal 200 that scenario data indicating the conversation content will be transmitted from now on. Then, the conversation output server 300 uses the SNS function it provides to start a conversation (chat) between the robots 100 corresponding to the IDs included in the conversation start notification packet.

[0060] Next, the scenario selection unit 321 performs a scenario selection process to select scenario data from the scenario storage unit 331 (step S313). Details of this scenario selection process will be described later with reference to Fig. 9. Next, the control unit 320 transmits the scenario data to each conversation output terminal 200 via the LTE communication unit 310 (step S314). At this time, the control unit 320 functions as a transmission means.

[0061] The scenario data transmitted here differs depending on the destination conversation output terminal 200. Scenario data corresponding to the "statement content" in the scenario storage unit 331 (Fig. 3) is transmitted to the conversation output terminal 200 that speaks first. Then, scenario data corresponding to the "reply content" in the scenario storage unit 331 (Fig. 3) is transmitted to the conversation output terminal 200' that responds to that.

[0062] Next, the control unit 320 judges whether or not to end the conversation (step S315). Usually, the control unit 320 ends the conversation after selecting and transmitting two scenario data from the scenario storage unit 331. If the conversation is not to be ended (step S315; No), the control unit 320 returns to step S313.

[0063] If the conversation is to be ended (step S315; Yes), a conversation end notification packet is transmitted to each conversation output terminal 200 via the LTE communication unit 310 (step S316), and the process returns to step S311. The conversation end notification packet is a packet that includes the ID of the robot 100 that was the conversation partner, and notifies that the transmission of scenario data that has been performed up until now will be ended.

[0064] The operation of the scenario transmission thread has been explained above, but the following explains the conversation content output thread (left flow chart in FIG. 8), which is the corresponding operation of the conversation output terminal 200. The operation of the conversation output terminal 200' (right flow chart in FIG. 8) is also similar.

[0065] First, the terminal control unit 230 of the conversation output terminal 200 judges whether or not a conversation start notification packet has been received via the LTE communication unit 220 (step S301). If the conversation start notification packet has not been received (step S301; No), the process returns to step S301. If the conversation start notification packet has been received (step S301; Yes), the terminal control unit 230 prepares to have a conversation (chat) with the ID included in the conversation notification packet, and receives the scenario data transmitted by the conversation output server 300 via the LTE communication unit 220 (step S302).

[0066] Then, the conversation output unit 231 transmits the scenario data to the SNS of the conversation output server 300 via the LTE communication unit 220. Then, the conversation output unit 231, which serves as client software for the SNS, outputs the data returned from the SNS on the display 270 of the conversation output terminal 200, so that the conversation content on the SNS is output (step S303). Note that the SNS provided by the conversation output server 300 may have a function of translating data returned to the client software based on information on the country of residence of the accessing user. If the SNS has this translation function, the conversation content in the natural language used by the user will be output on the display 270 of each conversation output terminal 200.

[0067] After outputting the conversation contents, the terminal control unit 230 may notify the robot 100 of whose statement the contents have been outputted via the short-range communication unit 210. When the robot 100 receives a notification via the short-range communication unit 120 that the contents of the conversation partner's statement have been outputted, the robot 100 may, for example, wag its tail 136. Then, the robot 100 wags its tail 136 every time a message arrives from the conversation partner, so that the user sees the robot 100 as if it is reading a message from the conversation partner. In this case, the short-range communication unit 120 functions as a receiving means.

[0068] Then, the terminal control unit 230 determines whether or not a conversation end notification packet has been received via the LTE communication unit 220 (step S304). If the conversation end notification packet has not been received (step S304; No), the process returns to step S302. If the conversation end notification packet has been received (step S304; Yes), the conversation is ended and the process returns to step S301.

[0069] The thread group for outputting conversation contents has been described above. Through the above process, the conversation contents with the conversation partner are output to the display 270 of all the conversation output terminals 200 (the conversation output terminals 200 to which the robot 100 indicated by the ID selected in step S311 of the scenario transmission thread is wirelessly connected) that are selected by the conversation output server 300 in step S311 of the scenario transmission thread.

[0070] Next, details of the scenario selection process in step S313 of the scenario transmission thread of the conversation output server 300 will be described with reference to FIG.

[0071] First, the scenario selection unit 321 selects a conversation topic (step S321). This selection method is arbitrary, but for example, it may be selected randomly from the topics stored in the scenario storage unit 331. However, recently selected topics (for example, the most recent five topics) are excluded from the selection targets to prevent the same scenario data from being selected.

[0072] Next, the scenario selection unit 321 refers to the user situation storage unit 333 to acquire situation information transmitted from each robot 100 (step S322). For example, the scenario selection unit 321 acquires situation information (first situation information) of the robot 100 and situation information (second situation information) of the robot 100'. Then, based on the selected topic and the acquired situation information (first situation information and second situation information), the scenario selection unit 321 acquires scenario data (step S323). Note that, if a virtual (non-existent) robot 100 is set as the conversation partner in the conversation partner selection (step S311), the situation information of the conversation partner may be set randomly in step S322.

[0073] Furthermore, in step S322, the scenario selection unit 321 may acquire information on the user of each robot 100 by referring to the user profile storage unit 332 in addition to or instead of the situation information. In this case, in step S323, the scenario selection unit 321 acquires scenario data by referring to the scenario storage unit 331 based on at least one of the acquired situation information and information on the user and the topic selected in step S321. For example, in step S322, the scenario selection unit 321 acquires at least one of the situation information of the robot 100 and information on the user of the robot 100 (first information) and at least one of the situation information of the robot 100' and information on the user of the robot 100' (second information). Then, based on the selected topic and the acquired first information and second information, the scenario selection unit 321 acquires scenario data by referring to the scenario storage unit 331 (step S323).

[0074] Then, the scenario selection unit 321 corrects the acquired scenario data as necessary (step S324). For example, if the scenario data includes a character string "I" or "me", this part is replaced with "I" or "me" depending on the gender. If the language of the country of residence of the user to whom the scenario data is to be transmitted is different from the language of the scenario data, a translation process is also performed. The scenario selection unit 321 acquires information on the country of residence of the user from the user profile storage unit 332, and acquires the language of the scenario data from the scenario storage unit 331. This allows the scenario selection unit 321 to determine whether the language of the country of residence of the user is different from the language of the scenario data. At this time, the scenario selection unit 321 also functions as a country of residence acquisition means. In addition, in step S321, the scenario selection unit 321 adds an icon of the robot that makes the statement in order to distinguish which robot 100 made each statement. In this manner, the conversation data to be presented to the user is created. In addition, scenario data for each country may be stored in advance in the scenario memory unit 331, and when acquiring scenario data in step S323, scenario data written in the language of the country in which the user to whom the scenario data is to be sent resides may be acquired.

[0075] Then, the scenario selection process ends. Usually, the control unit 320 ends the conversation after selecting and transmitting two scenario data from the scenario storage unit 331, so the above scenario selection process is performed twice in one conversation. That is, a first topic is selected in step S321 for the first time, first scenario data is acquired in step S323 based on the first topic, and finally, first conversation data is created. Then, a second topic is selected in step S321 for the second time, second scenario data is acquired in step S323 based on the second topic, and finally, second conversation data is created. When performing the scenario selection process, the control unit 320 functions as a creation means.

[0076] By the above-mentioned scenario selection process, the conversation output server 300 becomes able to transmit to the conversation output terminal 200 scenario data capable of generating a conversation based on the selected topic and the acquired situation information.

[0077] Now, a specific example of processing by the thread group for conversation content output (FIG. 8) will be described. Here, it is assumed that a robot 100 exists near the conversation output terminal 200, and that the robot 100 has a user profile with an ID of GladDog as shown in FIG. 4. Also, it is assumed that a robot 100' exists near the conversation output terminal 200', and that the robot 100' has a user profile with an ID of HappyCat as shown in FIG. 4. It is also assumed that users are approaching each of the robots 100 and 100', and that the robots 100 and 100' have transmitted conversation request packets.

[0078] Then, in step S311, it is assumed that the robot 100 with the ID GladDog and the robot 100' with the ID HappyCat are selected as conversation partners. The situation information is assumed to be the content shown in Fig. 5. It is also assumed that in the first step S321, "communicative intimacy" is selected as the topic, and in the second step S321, "anniversaries" is selected as the topic.

[0079] Then, in the first step S322, the intimacy level of each is calculated from the situation information shown in Fig. 5. For example, if the intimacy level is expressed as "number of times spoken to" + "number of times looked at" + "number of times hugged" (however, if these exceed 5, it is set to 5, and if they are less than 1, it is set to 1), then GladDog's intimacy level will be 5 and HappyCat's intimacy level will be 1. Then, in step S323, referring to Fig. 3, GladDog's statement will be "I'm so happy that you played with me so much," and HappyCat's reply will be "That's great. My master never plays with me."

[0080] 4, HappyCat is a woman, so the scenario data "How nice. My master never plays with me" is modified in step S324 to "How nice. My master never plays with me." Also, according to the user profile storage unit 332 shown in FIG. 4, it is known that the user of the robot 100' with the ID HappyCat is American, so the scenario data to be transmitted to the conversation output terminal 200' connected to the robot 100' is translated into English.

[0081] Then, in the next step S322, it is found from the situation information shown in Fig. 5 that today is Christmas, so in step S323, referring to Fig. 3, GladDog's utterance becomes "Merry Christmas!" and a Christmas card is attached as an image file. Then, HappyCat's reply becomes "Christmas card? Thanks!" In this case, in step S324, no correction of the first person is necessary, but the scenario data to be sent to the conversation output terminal 200' is translated into English.

[0082] As a result of the above-mentioned processing, the screen displayed on the conversation output terminal 200 connected to the robot 100 is as shown in Fig. 10, and the screen displayed on the conversation output terminal 200' connected to the robot 100' is as shown in Fig. 11. In both figures, the conversation content is displayed together with an icon showing the robot 100 or the robot 100', so that it is possible to distinguish which is the utterance content of the robot 100 and which is the utterance content of the robot 100'. In addition, since the user of the robot 100 resides in Japan, the conversation content shown in Fig. 10 is displayed in Japanese, and since the user of the robot 100' resides in America, the conversation content shown in Fig. 11 is displayed in English.

[0083] As described above, in this embodiment, sentences are displayed on the display of the conversation output terminal 200, 200' of each user as if the robot 100 and the robot 100' were having a conversation. Therefore, it is possible to make the robot 100, 100' appear to the user as if it has high conversation ability.

[0084] (Modification 1 of the first embodiment) As in the above specific example, in a conversation on the first topic, if oneself (GladDog in the above example) is feeling happy but the other person (HappyCat in the above example) is feeling down, a "connecting sentence" such as "I see, then cheer up!" may be added to the beginning of one's remarks when moving on to the next topic. By inserting such connecting sentences that connect topics, the flow of the conversation can be made to look more natural. A first modification of the first embodiment that performs such processing will be described.

[0085] In the first modified example of the first embodiment, the functional configuration of the conversation output server 300 is such that the storage unit 330 is provided with a "connecting sentence storage unit" (not shown) that stores connecting sentences according to the moods of the user and the respondent, and each scenario data in the scenario storage unit 331 also stores "mood" information indicating the mood of the user and the respondent. Note that this "mood" information can be considered to be information similar to the level and the other person's level when the topic shown in Fig. 3 is communication intimacy.

[0086] Then, in scenario modification (step S324) of the scenario selection process for the second and subsequent topics, a transition sentence corresponding to the mood of the user and the respondent in the scenario data of the previous topic is obtained from the transition sentence storage unit, and the transition sentence is added to the beginning of the comment content. Note that, depending on the mood of the user and the respondent, a transition sentence may not be necessary, in which case no transition sentence is added.

[0087] By the above process, what GladDog said in the first embodiment, "Merry Christmas!", is corrected to "I see, then cheer up! Merry Christmas!" in the first variation of the first embodiment.

[0088] In this way, in the first modification of the first embodiment, the flow between topics can be made to look more natural, and therefore the robots 100 and 100' can be made to look to the user as if they have high conversational ability.

[0089] (Modification 2 of the first embodiment) In the first embodiment, the conversation output server 300 provides the function of an SNS, and the conversation output unit 231 of the conversation output terminal 200 operates as client software for this SNS, thereby outputting conversation contents in which the robot 100 appears to be conversing with another robot 100' in a natural language to the display of the conversation output terminal 200. However, it is not essential that the conversation output server 300 provides the function of an SNS. Here, a second modification of the first embodiment will be described, in which conversation contents in which the robot 100 appears to be conversing with another robot 100' in a natural language are output to the display of the conversation output terminal 200 even when the conversation output server 300 does not provide the function of an SNS.

[0090] In the second modification of the first embodiment, in the processing of the conversation content output thread group (FIG. 8), the contents transmitted as scenario data by the conversation output server 300 and the processing when the conversation output terminal 200 receives the scenario data are different from those in the first embodiment. Also, in the second modification, the conversation output server 300 does not need to provide an SNS function. In the following explanation, it is assumed that a screen is output in which the robot 100 (wirelessly connected to the conversation output terminal 200) and the robot 100' (wirelessly connected to the conversation output terminal 200') appear to be having a conversation.

[0091] The conversation output server 300 according to the second modification of the first embodiment transmits not only the utterance content of the robot 100 but also the reply content of the robot 100' as scenario data to each conversation output terminal 200 in scenario transmission (step S314) of the scenario transmission thread (middle flowchart in FIG. 8). At that time, the conversation output server 300 translates the utterance content and reply content in advance into the language of the country in which the user of the destination conversation output terminal 200 resides in scenario correction (step S324) of the scenario selection process (FIG. 9).

[0092] Furthermore, the conversation output unit 231 according to the second modification of the first embodiment receives not only the utterance content of the robot 100 but also the reply content of the robot 100' as scenario data from the conversation output server 300 in scenario reception (step S302) of the conversation output thread (left or right flowchart in FIG. 8). Then, in conversation content output (step S303), the utterance content of the robot 100 and the reply content of the robot 100' received in step S302 are output in order to the display of the conversation output terminal 200.

[0093] By such processing, in the second modification of the first embodiment, even if the conversation output server 300 does not provide a function of an SNS, text is displayed on the display of the conversation output terminal 200, 200' of each user as if the robot 100 and the robot 100' were having a conversation. Therefore, the robot 100, 100' can be made to appear to the user as if it has high conversational ability. Also, even if the SNS provided by the conversation output server 300 does not have a function of translating data returned to the client software based on information on the country of residence of the accessing user, according to the second modification, the conversation content in the natural language used by the user is output on the display of each conversation output terminal 200.

[0094] (Modification 3 of embodiment 1) A third modification of the first embodiment will be described, in which a conversation between the robot 100 and the robot 100' is guided between the user of the robot 100 and the user of the robot 100'.

[0095] In the third modification, as shown in Fig. 12, topics of information related to the user of the robot 100 (robot 100') such as "introducing the master's ID" and "master's hobbies" are also prepared as topics of scenarios stored in the scenario storage unit 331. The user profile storage unit 332 also stores the names of SNSs used by the user and their IDs in those SNSs.

[0096] 12, when the topic of the scenario is "Introducing the master's ID", the statement content is, for example, "My master is participating in an SNS called [SNS name] with the ID [ID on that SNS]," and the reply content is, "Oh, is that so? My master is participating in an SNS called [SNS name] with the ID [ID on that SNS]," and these are stored in the scenario storage unit 331. Here, the [SNS name] and [SNS ID] parts are replaced with the name of the SNS used by each user and the SNS ID stored in the user profile storage unit 332 in step S324 of the scenario selection process (FIG. 9).

[0097] Also, as shown in FIG. 12, when the topic of the scenario is "my husband's hobbies", for example, one of the husband's hobbies ("reading" in FIG. 12) is introduced as "One of my husband's hobbies is reading.", and the reply, if there is a common hobby ("reading" in FIG. 12), is "My husband's hobby is also reading. It might be interesting to introduce each other to your favorite authors and works.", and if there is no common hobby, the reply is "Oh, I see. My husband's hobby is tennis." about one of the other person's hobbies ("tennis" in FIG. 12), and this is stored in the scenario memory unit 331.

[0098] By adopting the above-described configuration, in this manner, in variant example 3 of embodiment 1, not only can the robots 100, 100' appear to the user as having high conversational ability, but also the conversation between the robots 100, 100' can lead to conversation between the users, thereby expanding the scope of interaction between users.

[0099] (Embodiment 2) In the first embodiment, the conversation output terminal 200 is a smartphone, and the conversation content is output as text. However, the output form of the conversation is not limited to text. A second embodiment in which the conversation content is output as audio will be described.

[0100] A conversation output system 1001 according to the second embodiment of the present invention includes a robot 100, a conversation output terminal 201, and a conversation output server 300, as shown in Fig. 13. The conversation output terminal 201 is a smart speaker (AI speaker) and outputs the conversation contents as voice. The functional configuration of the conversation output terminal 201 includes a speaker 280 instead of the display 270 of the conversation output terminal 200. The conversation output unit 231 synthesizes the conversation contents into voice and outputs it from the speaker 280. The speaker 280 functions as an output unit.

[0101] It is preferable that the voice used when outputting the utterance contents of the robot 100 is different from the voice used when outputting the utterance contents of the conversation partner robot 100'. For this reason, the conversation output terminal 201 has a function of outputting a plurality of types of voices. The user profile storage unit 332 according to the second embodiment also stores information on the type of voice for each robot, and the conversation output server 300 transmits a conversation start notification packet including information on the type of voice corresponding to each robot 100. The conversation output terminal 201 then speaks the utterance contents corresponding to each robot 100 in the type of voice notified in the conversation start notification packet.

[0102] Then, the conversation output terminal 201 can use different voices to make speech as if a plurality of robots 100 were conversing with each other.

[0103] As described above, in this embodiment, the conversation output terminals 200 and 200' of the users output voices as if the robots 100 and 100' were having a conversation. Therefore, the robots 100 and 100' can be made to appear to the users as if they have high conversational ability.

[0104] Note that conversation output terminal 201 may include not only speaker 280 but also display 270. In this case, conversation output unit 231 may output the conversation content as sound from speaker 280 and also display it on display 270. Also, based on a user instruction or the like, the output unit may be switchable so that the conversation content is sometimes output as sound from speaker 280 and sometimes displayed on display 270.

[0105] (Modification of the second embodiment) In the above-mentioned second embodiment, even if the voices output by the conversation output terminal 201 are different for the contents of speech of different robots, it may be difficult for the user to distinguish which voice corresponds to the contents of speech of his / her robot 100. Therefore, in order to show the user what kind of voice his / her robot 100 has, when setting up the connection between the robot 100 and the conversation output terminal 201, the conversation output terminal 201 may be made to utter "I am ____" in the voice of the robot 100. In addition, when making this setting, the conversation output terminal 201 may be made to utter a voice of the user's preference (for example, a male voice, a female voice, a child's voice (both male and female), an elderly person's voice (both male and female), an announcer's voice, a voice actor's voice, etc.) as the voice of the robot 100.

[0106] Here, as for the voices of announcers, voice actors, etc., the voices of famous announcers, voice actors, etc. may be registered in advance in the conversation output terminal 201. Also, voice data may be made available for download so that the conversation output terminal 201 can output the voices of less famous announcers, voice actors, etc.

[0107] In addition, the conversation output terminal 201 may be configured to say, for example, "I am XX" in the voice of the robot 100 at any timing (for example, when the user instructs the robot 100 or the conversation output terminal 201 that he or she wishes to hear the voice (for example, by pressing a voice confirmation button (not shown) provided on the robot 100 or the conversation output terminal 201)) rather than just when making settings to connect the robot 100 to the conversation output terminal 201.

[0108] Furthermore, when setting up the robot 100 to be connected to the conversation output terminal 201, the conversation output terminal 201 does not need to speak in the voice of the robot 100, but in order to make the user recognize that the robot 100 and the robot 100' are actually conversing with each other, the conversation output terminal 201 may speak at the beginning of the conversation in a voice corresponding to each robot, such as "I am robot XX" in the voice of robot 100 and "I am robot △△" in the voice of robot 100'.

[0109] (Embodiment 3) In the first and second embodiments, the conversation output server 300 is a device separate from the conversation output terminals 200 and 201, but a specific conversation output terminal may have the functions of the conversation output server 300. Such a third embodiment will now be described.

[0110] A conversation output system 1002 according to the third embodiment of the present invention includes at least a robot 100 and a scenario conversation output terminal 250, as shown in Fig. 14. The conversation output system 1002 may include a plurality of pairs of a robot 100 and a conversation output terminal 200, as in the first embodiment. The robot 100 can appear to a user as if it is having a conversation with another robot 100 via the scenario conversation output terminal 250 and the conversation output terminal 200.

[0111] The third embodiment differs from the first embodiment in that there is no conversation output server 300, but instead there is a scenario conversation output terminal 250. Other than that, the configuration is the same as that of the first embodiment, so the following describes the scenario conversation output terminal 250.

[0112] Like the conversation output terminal 200, the scenario conversation output terminal 250 is a smartphone equipped with a display, but also has the functions of the conversation output server 300. As shown in Fig. 14, the scenario conversation output terminal 250 has, as its functional components, a short-range communication unit 210, an LTE communication unit 220, a terminal control unit 230, and a storage unit 240. The terminal control unit 230 functions as a conversation output unit 231 and a scenario selection unit 232. The storage unit 240 has, as its functional components, a scenario storage unit 241, a user profile storage unit 242, and a user situation storage unit 243.

[0113] The short-range communication unit 210, the LTE communication unit 220 and the conversation output unit 231 are similar to those provided in the conversation output terminal 200. However, the LTE communication unit 220 provided in the scenario conversation output terminal 250 communicates with the LTE communication unit 220 provided in the conversation output terminal 200. For example, the LTE communication unit 220 provided in the scenario conversation output terminal 250 receives situation information transmitted by the LTE communication unit 220 provided in the conversation output terminal 200. In addition, the LTE communication unit 220 provided in the scenario conversation output terminal 250 transmits scenario data to the conversation output terminal 200. In this way, the LTE communication unit 220 provided in the scenario conversation output terminal 250 communicates with the conversation output terminal 200, and therefore functions as a terminal communication unit.

[0114] The scenario selection unit 232 is similar to the scenario selection unit 321 included in the conversation output server 300 of embodiment 1. In addition, the scenario storage unit 241, the user profile storage unit 242, and the user situation storage unit 243 are similar to the scenario storage unit 331, the user profile storage unit 332, and the user situation storage unit 333 included in the conversation output server 300 of embodiment 1, respectively.

[0115] The same processing can be applied to the processing in which the robot 100 converses with another robot 100 via the scenario conversation output terminal 250 and the conversation output terminal 200, except for the following two points. The first point is that the scenario conversation output terminal 250 performs the processing of the conversation output server 300 instead. The second point is that when a robot 100 connected to the scenario conversation output terminal 250 is selected as a conversation partner, the scenario conversation output terminal 250 performs the processing of the conversation output terminal 200 and the conversation output server 300 in parallel in separate threads. In this case, communication between the status relay thread and the status update thread performed in the scenario conversation output terminal 250 is performed by inter-thread communication (the LTE communication unit 220 is not used). Similarly, communication between the request relay thread and the request update thread, and communication between the conversation output thread and the scenario transmission thread performed in the scenario conversation output terminal 250 are also performed by inter-thread communication (the LTE communication unit 220 is not used).

[0116] With the above configuration and processing contents, in the third embodiment, the scenario conversation output terminal 250 can transmit scenario data based on the situation information received from each robot 100 to each conversation output terminal 200, even if the conversation output server 300 is not provided. Therefore, in this embodiment, even if the conversation output server 300 is not provided, text is displayed on the display of each user's scenario conversation output terminal 250 and conversation output terminal 200 as if the robot 100 and the robot 100' were having a conversation. Therefore, it is possible to make the robot 100, 100' appear to the user as if it has high conversational ability.

[0117] (Embodiment 4) In the above embodiment, the SNS function is mainly used to enable communication between the robot and other robots. When the user sees his / her robot engaging in a fluent conversation as shown in Fig. 10 or 11, he / she is impressed that "this robot can have such a fluent conversation even though it has no voice conversation function or has an insufficient voice conversation function", and can enjoy watching the conversation. Since each robot has its own user, it is considered that the user of the robot 100 becomes interested in what kind of user the user of the robot 100', etc., with whom the robot 100 is conversing, is.

[0118] In such a case, in order to enable users to communicate with each other, in the third modification of the first embodiment, "introduction of the master's ID" and "master's hobbies" of each user of the robot 100 and the robot 100' are prepared as topics of the scenario stored in the scenario storage unit 331, and the name of the SNS used by the user and the ID in that SNS are also stored in the user profile storage unit 332. This enables communication between the user of the robot 100 and another user who is a user of the robot 100'.

[0119] However, in the third modification of the first embodiment, the conversation output server 300 selects the topic of the scenario by itself, so the conversation does not necessarily have the content that the user wants to know when he or she wants to know it. Also, some users may not want their personal information to be known to others. Therefore, the fourth embodiment will be described, which allows the user to make personal information public only when he or she wants to interact with other users.

[0120] As shown in FIG. 15, the conversation output system 1003 according to the fourth embodiment of the present invention includes a robot 101, a conversation output terminal 202, and a conversation output server 301. The robot 101 includes a user intention acquisition unit 130. The user intention acquisition unit 130 acquires information (user intention information) indicating whether or not the user wants to make his / her personal information (SNSs and IDs in which the user participates, his / her hobbies, etc.) public. The user intention acquisition unit 130 may be, for example, a simple switch (set to ON if the user wants to make his / her personal information public, and set to OFF if the user does not want to make his / her personal information public). The user intention acquisition unit 130 functions as a user intention information acquisition means. The robot 101 may also acquire user intention information by voice recognition. In this case, the user intention acquisition unit 130 is configured with a microphone 133 and a voice recognition unit (not shown).

[0121] The robot 101 transmits the user intention information acquired by the user intention acquisition unit 130 to the conversation output terminal 202 via the short-range communication unit 120. Then, the conversation output terminal 202 transmits the user intention information received from the robot 101 to the conversation output server 301. Then, the conversation output server 301 selects a scenario based on the received user intention information.

[0122] For example, consider a case where robot 101 and robot 101' have been selected as conversation partners. If the user intention information transmitted from robot 101 and the user intention information transmitted from robot 101' are both "personal information not to be disclosed", then when selecting a scenario, the robot will avoid selecting a scenario with a topic that would result in the disclosure of personal information, such as "introducing master's ID" or "master's hobbies". Conversely, when the user intention information is both "personal information can be disclosed", the robot will frequently select scenarios with a topic that would result in the disclosure of personal information, such as "introducing master's ID" or "master's hobbies".

[0123] Furthermore, if the user intention information of only one of the robots 101 engaged in a conversation is "personal information cannot be made public," the conversation output server 301 gives the user who has set "personal information cannot be made public" an opportunity to permit the disclosure of personal information by transmitting a statement such as "My master wants to exchange personal information, is that okay?" to the conversation output terminal 202. Note that the conversation output server 301 may select a scenario in which only the personal information of the user who has set "personal information can be made public" (the user intention information acquired by the user intention acquisition unit 130 of the robot 101 is "I do not want to make personal information public") is made public, without giving the user who has set "personal information cannot be made public" (the user intention information acquired by the user intention acquisition unit 130 of the robot 101 is "I want to make personal information public") an opportunity to permit the disclosure of personal information.

[0124] The conversation output terminal 202 also includes a user input unit 260. The user input unit 260 accepts utterances (text) input by the user, and the conversation output terminal 202 posts them to an SNS provided by the conversation output server 301. This allows the user of the robot 101 to enter the SNS in which the robot 101 and another robot 101' are conversing, and to converse with the user of the other robot 101'.

[0125] For example, the following conversation example (scenario example) can be considered. GladDog: I'm having a lot of fun because you've played with me a lot. HappyCat: I'm glad for you. Actually, my husband played with you a lot. GladDog:My husband's hobby is tennis. HappyCat: That's right. My husband also enjoys tennis. It might be fun to play tennis together sometime. Here, the scenario shown in FIG. 12 is prepared in advance assuming a combination of hobbies. However, the present invention is not limited to this. For example, in the scenario selection process (FIG. 9), a judgment step may be added to judge whether the conversation partners have the same hobbies, and if they do, a scenario may be generated in which the two parties tell each other that they do. In the case of the above conversation, the two parties share the same hobby of tennis, so for example, the following scenario may be generated. GladDog: We have the same hobbies! HappyCat: Yeah, it's the same.

[0126] If the user of the robot 101 who has seen this conversation wishes to have an exchange with the user of the other robot 101', the user notifies the user intention acquisition unit of the robot 101 that he wishes to make the personal information public (for example, by turning on a switch indicating that it is OK to make the personal information public). This user intention information is then transmitted to the conversation output server 301 via the conversation output terminal 202. If the user of the robot 101' who is the conversation partner of the robot 101 also wishes to make the personal information public, the user intention acquisition unit 130 of the robot 101' will acquire user intention information indicating that the user wishes to make the personal information public, and this user intention information is transmitted to the conversation output server 301.

[0127] Then, since both the user intention information and the conversation output server 301 are "personal information disclosure possible", when selecting a scenario, the conversation output server 301 will frequently select scenarios on topics where personal information is disclosed, such as "introducing the master's ID" and "master's hobbies". For example, when the topic "master's address" is selected, the following conversation will take place. GladDog:Where does your husband live? My husband lives in Tokyo. HappyCat:My husband lives in Seattle. Also, for example, when the topic "husband's email address" is selected, the following conversation takes place: GladDog:What is your master's email address? My master's email address is name@ne.jp. HappyCat: My husband's email address is name@net.

[0128] Here, user information is exchanged through conversations between robots, but when a user is watching a conversation between robots 101 and becomes interested in the user of the other robot 101', the user may have a conversation with the user of the other robot 101' via SNS from the conversation output terminal 202.

[0129] For example, the following conversation might take place: GladDog: I'm having a lot of fun because you've played with me a lot. HappyCat: I'm glad for you. Actually, my husband played with you a lot. GladDog:My husband's hobby is tennis. HappyCat: That's right. My husband also enjoys tennis. It might be fun to play tennis together sometime.

[0130] After such a conversation between the robots 101, the users can also directly talk to each other as follows. Tarou: Nice to meet you. My name is Tarou and I'm a GladDog user. Can I contact you directly? Lily: Nice to meet you. That's fine. Tarou: Thank you. So tennis is your hobby. I also like tennis. Lily: What a coincidence. In this way, users can communicate with each other through the conversation of the robot 101.

[0131] As a modification of the fourth embodiment, the user intention acquisition unit 130 may be provided in the conversation output terminal 202, instead of in the robot 101. In this case, the user can input whether or not to make personal information public by operating a touch panel or the like provided in the conversation output terminal 202, and the user intention acquisition unit 130 acquires user intention information from the touch panel or the like.

[0132] (Embodiment 5) In the above-mentioned embodiment 1, since the robot 100 does not have an LTE communication unit, the situation information acquired by the situation acquisition unit 110 is transmitted to the conversation output terminal 200 by the short-range communication unit 120, and the conversation output terminal 200 transmits the situation information to the conversation output server 300 by the LTE communication unit 220. However, if the robot has an LTE communication unit, it becomes possible to directly transmit the situation information to the conversation output server 300. Also, in the embodiment 1, the situation information is acquired by the situation acquisition unit 110 equipped in the robot 100, but if the situation information can be acquired by a sensor provided separately from the robot, it becomes possible to use the situation information from a sensor not equipped in the robot. Such an embodiment 5 will be described.

[0133] As shown in FIG. 16, a conversation output system 1004 according to the fifth embodiment of the present invention includes a robot 102, a conversation output terminal 200, a conversation output server 300, and a sensor device 400. The sensor device 400 is usually attached to the robot 102 and complements the function of the situation acquisition unit 110 of the robot 102. However, the sensor device 400 does not necessarily need to be attached to the robot 102 as long as it can acquire information on the situation around the robot 102. The robot 102, the conversation output terminal 200, and the sensor device 400 are wirelessly connected by short-range wireless communication to form a triad. The conversation output system 1004 may include a plurality of triads of the robot 102, the conversation output terminal 200, and the sensor device 400 (for example, the robot 102, the conversation output terminal 200, and the sensor device 400, the robot 102', the conversation output terminal 200', and the sensor device 400', etc.).

[0134] The sensor device 400 includes a situation acquisition unit 410 and a short-range communication unit 420, and transmits situation information acquired by the situation acquisition unit 410 to the robot 102.

[0135] The situation acquisition unit 410 acquires situation information, which is information on the situation around the robot 102, from various sensors (temperature sensor, humidity sensor, illuminance sensor, human presence sensor, etc.) included in the sensor device 400.

[0136] The short-distance communication unit 420 includes a short-distance wireless communication device (e.g., a Bluetooth (registered trademark) communication device) and transmits the situation information acquired by the situation acquisition unit 410 to the robot 102. Although not shown in Fig. 16, the short-distance communication unit 420 may communicate with the short-distance communication unit 210 of the conversation output terminal 200 to transmit the situation information acquired by the situation acquisition unit 410 to the conversation output terminal 200.

[0137] Although not shown, the sensor device 400 may include an LTE communication unit so that the situation information acquired by the situation acquisition unit 410 can be transmitted directly to the conversation output server 300 .

[0138] There may be a plurality of sensor devices 400. For example, a sensor device 400A having only a temperature sensor, a sensor device 400B having only a humidity sensor, and a sensor device 400C having only an illuminance sensor may be present as sensors, and each of the sensor devices 400A, 400B, and 400C may transmit situation information acquired by its own sensor to the robot 102.

[0139] The robot 102 includes an LTE communication unit 140 in addition to the configuration of the robot 100 according to the first embodiment. The LTE communication unit 140 includes a device that communicates according to the LTE communication standard, and communicates with the conversation output server 300. For example, the LTE communication unit 140 transmits situation information to the conversation output server 300.

[0140] In addition, the short-range communication unit 120 of the robot 102 communicates not only with the short-range communication unit 210 of the conversation output terminal 200 but also with the short-range communication unit 420 of the sensor device 400, and receives from the sensor device 400 situation information acquired by the sensor device 400.

[0141] It should be noted that the robot 102 does not need to include the situation acquisition unit 110. In this case, situation information, which is information on the situation around the robot 102, is acquired entirely by the sensor device 400.

[0142] The configurations of the conversation output terminal 200 and the conversation output server 300 are the same as those in the first embodiment, and therefore a description thereof will be omitted. In addition, the processing contents of the various threads executed by the robot 102, the conversation output terminal 200, and the conversation output server 300 also have much in common with the first embodiment, and therefore the following description will focus on the differences.

[0143] In step S101 of the status transmission thread (left side of Figure 6), the robot 102 of embodiment 5 acquires not only the status information acquired by the status acquisition unit 110, but also the status information acquired by the status acquisition unit 410 of the sensor device 400 via the short-range communication unit 120.

[0144] Furthermore, in step S102 of the status transmission thread (left side of FIG. 6), the robot 102 according to the fifth embodiment may transmit the status information acquired in step S101 to the conversation output server 300 via the LTE communication unit 140. In the case of performing such processing, the conversation output terminal 200 does not need to execute the status relay thread (middle of FIG. 6), and the conversation output server 300 continues to wait in step S121 of the status update thread (right side of FIG. 6) until the status information is transmitted from the robot 102, and receives the status information via the LTE communication unit 310 when it is transmitted.

[0145] In addition, when the sensor device 400 is attached to the robot 102 of embodiment 5, in steps S201 and S203 of the request sending thread (left side of Figure 7), the robot 102 may also use situation information obtained from the sensor device 400 to determine whether or not a user has approached or whether or not the user is still nearby.

[0146] The processes other than the above are the same as those in the first embodiment, and therefore the description thereof will be omitted. In the fifth embodiment, the robot 102 directly transmits the situation information to the conversation output server 300, so that the load on the conversation output terminal can be reduced.

[0147] In addition, in the fifth embodiment, the situation information acquired by the sensor device 400 can also be used, so the range of situation information that can be used in a scenario is broadened, and the variety of scenarios can be expanded. For example, the robot 102 may be equipped with only the minimum number of sensors to reduce costs, but even in this case, the user can purchase additional sensor devices 400 later to enjoy a wider variety of conversations.

[0148] In the fifth embodiment, when the robot 102 does not need to transmit the situation information directly to the conversation output server 300 (when transmitting the situation information via the conversation output terminal 200), the robot 102 does not need to include the LTE communication unit 140. In the fifth embodiment, when there is no need to expand the variation of the situation information, the conversation output system 1004 does not need to include the sensor device 400.

[0149] (Embodiment 6) In the above embodiment, the conversation output server 300 selected scenario data based on situation information, and the conversation output terminal 200 output the selected scenario data, making it possible for the robot 100 to appear to the user as if it had high conversational ability. However, it is also possible for the robot 100 to appear to the user as if it had high conversational ability without relying on scenario data. Such an embodiment 6 will now be described.

[0150] A conversation output system 1005 according to the sixth embodiment of the present invention includes a robot 103, a conversation output terminal 203, and a conversation output server 302, as shown in FIG.

[0151] The robot 103 includes a self-diagnosis unit 150 in addition to the configuration of the robot 100 of the first embodiment. The self-diagnosis unit 150 diagnoses the robot 103 itself, and if an abnormality is found, transmits information about the abnormality as situation information to the conversation output terminal 203 via the short-range communication unit 120. For example, if the robot 103 is unable to move the legs 135 or the tail 136, or if these movements become poor, information indicating this is transmitted to the conversation output terminal 203 as situation information.

[0152] In addition to the configuration of the conversation output terminal 202 of the fourth embodiment, the conversation output terminal 203 includes a terminal control unit 230 equipped with a status notification creation unit 233. The conversation output terminal 203 also stores contact information for a service center that undertakes repairs and the like for the robot 103, and can notify the service center of a message via the LTE communication unit 220.

[0153] In the conversation output terminal 203, when the short-distance communication unit 210 receives from the robot 103 status information related to an abnormality in the robot 103, the status notification creation unit 233 creates a message in natural language to notify the status information. For example, when status information is received indicating that the leg 135 cannot be moved, the status notification creation unit 233 creates a message such as "I am a robot with model number XX and serial number △△, and this morning I suddenly became unable to move my legs. What should I do?"

[0154] Then, the conversation output terminal 203 notifies the service center of the message created by the status notification creating section 233 via the LTE communication section 220, and outputs the exchange with the service center by the message at the conversation output section 231.

[0155] By outputting such messages of exchange with the service center, the conversation output system 1005 can make the robot 103 appear to the user as if it were conversing with a person in charge at the service center. Note that since the conversation output terminal 203 can make the robot 103 appear to the user as if it were conversing with a person in charge at the service center without using the user input unit 260, the conversation output terminal 203 does not need to include the user input unit 260 if it is only to provide this function.

[0156] The conversation output server 302 includes a sentence creation unit 322 in addition to the configuration of the conversation output server 300 of embodiment 1. When the conversation output server 302 does not process the scenario transmission thread (FIG. 8), the conversation output server 302 does not need to include the scenario selection unit 321 or the scenario storage unit 331.

[0157] When a comment (a comment input by a user, etc.) is given to the comment creation unit 322, the comment creation unit 322 creates a reply comment that appears to be a reply to the comment. The method for creating the reply comment is arbitrary, but for example, the following process may be performed.

[0158] A large amount of conversations on SNS publicly available from the Internet or the like is acquired in advance via the LTE communication unit 310 and stored in the storage unit 330. Then, when a message is given, a message closest to the message is searched for among the conversations stored in the storage unit 330, and the message used as a reply to the message closest to the message in the given conversation is set as the reply message. In the process of searching for the message closest to the message, it is not necessary to search for the closest message strictly, and it is also possible to perform a process such as "search for a message containing a keyword contained in the message, and set as the reply message a message used as a reply to the message."

[0159] Then, the conversation output server 302 transmits the sentence created by the sentence creation unit 322 to the conversation output terminal 203 via the LTE communication unit 310, and the conversation output terminal 203 outputs the sentence at the conversation output unit 231. In this manner, the user can enjoy a simulated chat with the robot 103. The thread group for this simulated chat will be described with reference to FIG.

[0160] When the conversation output terminal 203 is powered on, a sentence input / output thread shown in the flowchart on the left side of Fig. 18 is started. When the conversation output server 302 is powered on, a sentence transmission thread shown in the flowchart in the middle of Fig. 18 is started. The sentence input / output thread shown in the flowchart on the right side of Fig. 18 is the same as that in the flowchart on the left side. It is assumed that the flowchart on the right side is executed in a conversation output terminal 203' that is wirelessly connected to another robot 103' that is a conversation partner of the robot 103 that is wirelessly connected to the conversation output terminal 203. Also, in Fig. 18, dotted arrows indicate that data is sent and received between each thread.

[0161] If the conversation output server 302 includes a scenario selection unit 321 and a scenario storage unit 331, the text input / output thread and the text transmission thread operate in parallel with the conversation content output thread group described with reference to Fig. 8. Even in this case, the process of determining whether a conversation start notification has been received (step S301) and whether a conversation end notification has been received (step S304) is common to the text input / output thread (Fig. 18) and the conversation output thread (Fig. 8). In addition, the process of selecting a conversation partner (step S311), sending a conversation start notification (step S312), determining whether a conversation has ended (step S315), and sending a conversation end notification (step S316) is common to the text input / output thread (Fig. 18) and the conversation output thread (Fig. 8).

[0162] Therefore, when the conversation output server 302 includes a scenario selection unit 321 and a scenario storage unit 331, steps S331 to S337 of the sentence input / output thread operate in parallel with scenario reception (step S302) and conversation content output (step S303), and steps S341 to S344 of the sentence transmission thread operate in parallel with the scenario selection process (step S313) and scenario transmission (step S314). Whether the conversation output server 302 includes the scenario selection unit 321 and the scenario storage unit 331 or not, the processing of the steps in Fig. 18 that share the same reference numerals as Fig. 8 is the same as the processing explained in Fig. 8, so that the processing of the parts that differ from the processing explained in Fig. 8 will be explained below.

[0163] First, in the input / output thread, when a conversation start notification packet is received (step S301; Yes), the terminal control unit 230 determines whether or not a message has been input from the user input unit 260 or whether a message has been received from the LTE communication unit 220 (step S331). If no message has been input or received (step S331; No), the process returns to step S331.

[0164] If a message has been input from the user input unit 260 or a message has been received from the LTE communication unit 220 (step S331; Yes), the terminal control unit 230 determines whether or not a message has been input from the user input unit 260 (step S332). If a message has not been input from the user input unit 260 (step S332; No), the process proceeds to step S334.

[0165] If a message has been input from the user input unit 260 (step S332; Yes), the terminal control unit 230 transmits the message input from the user input unit 260 to the conversation output server 302 via the LTE communication unit 220 (step S333). Then, in the message transmission thread of the conversation output server 302, the control unit 320 receives the message transmitted from the conversation output terminal 203 via the LTE communication unit 310 (step S341), and transmits the received message to all conversation output terminals 203 that are conversation partners, including the sender of the message (step S342).

[0166] Then, in the message sending thread, the message creating unit 322 creates a response message to the message (step S343), and transmits the created response message to all conversation output terminals 203 that are conversation partners (step S344).

[0167] On the other hand, in the sentence input / output thread, the terminal control unit 230 receives a message sent from the conversation output server 302 via the LTE communication unit 220 (step S334), and the conversation output unit 231 outputs the received message (step S335).

[0168] Then, the terminal control unit 230 receives the response message transmitted from the conversation output server 302 via the LTE communication unit 220 (step S336), and the conversation output unit 231 outputs the received response message (step S337). The other processes are the same as those of the steps (denoted by the same reference numerals) described with reference to Fig. 8, and therefore description thereof will be omitted.

[0169] By performing the processing shown in FIG. 18 as described above, the conversation output terminal 203 can output a reply to a statement input by a user, etc., based on a conversation that actually took place on, for example, an SNS. Therefore, the conversation output system 1005 can make the user recognize that the robot 103 is conversing in natural language.

[0170] In the above embodiment, the LTE communication units 140, 220, and 310 are described as being equipped with devices that communicate according to the LTE communication standard, but the LTE communication units 140, 220, and 310 are not limited to the LTE communication standard. Any device that can communicate between the LTE communication units 140, 220, and 310 can be used.

[0171] In addition, in the above-mentioned embodiment, the data communication is described as being performed wirelessly, but some or all of the data communication may be performed wired instead of wirelessly. In particular, in the third embodiment, as described above, the communication between the status relay thread and the status update thread, the communication between the request relay thread and the request update thread, and the communication between the conversation output thread and the scenario transmission thread performed in the scenario conversation output terminal 250 are performed by inter-thread communication, and the LTE communication unit 220 is not used in these communications.

[0172] (Effects of the embodiment) A user can see and hear the fluent conversation between his / her robot, which is displayed as text on the conversation output terminal and spoken as voice on the conversation output terminal, and feel as if the robot has excellent conversational ability, even if the robot does not have a voice conversation function or has an insufficient voice conversation function. Also, the user can enjoy watching the conversation between the robots. Furthermore, the user can communicate with other users through the conversation. And because the conversation is output as if the robots have become friends without the user's knowledge, the user can be inspired by the conversation between the robots and expand the circle of communication.

[0173] The functions of the conversation output terminals 200, 201, 202, the scenario conversation output terminal 250, and the conversation output servers 300, 301 can also be implemented by a computer such as a normal PC (Personal Computer). Specifically, in the above embodiment, the programs executed by the conversation output terminals 200, 201, 202, the terminal control unit 230 of the scenario conversation output terminal 250, and the control unit 320 of the conversation output servers 300, 301 have been described as being stored in advance in the ROM of the storage units 240, 330. However, the programs may be stored in a computer-readable recording medium such as a flexible disk, a CD-ROM (Compact Disc Read Only Memory), a DVD (Digital Versatile Disc), and an MO (Magneto-Optical Disc) and distributed, and the programs may be read and installed in a computer to configure a computer capable of implementing the above-mentioned functions. In the above embodiment, one-to-one conversation between the robots 100 and 100' has been described as an example, but multiple robots may converse with each other, such as with the group function of LINE (registered trademark). In this case, the scenario data becomes more complex and the volume increases, but basically, the number of patterns simply increases. In addition, although the scenario data has been described as being prepared in advance, it can also be updated or newly created on an ongoing basis using a learning function or AI. Furthermore, in the above embodiment, the information on both robot 100 and robot 100' is managed by the same conversation output server, so the conversation output server generates utterances for both robot 100 and robot 100', making it possible to create conversational sentences that are consistent with the scenario.

[0174] Although the preferred embodiment of the present invention has been described above, the present invention is not limited to the specific embodiment, and the present invention includes the inventions described in the claims and their equivalents. The inventions described in the original claims of this application are listed below.

[0175] (Appendix 1) A first information acquisition means for acquiring first information, which is at least one of information regarding a user of the robot and situation information, which is information regarding a situation around the robot; a creating means for creating conversation data for making the user recognize that the robot and a predetermined object are having a conversation that at least matches the first information, based on the acquired first information; an output control means for controlling an output unit to output information based on the created conversation data, thereby making the user recognize that the robot and the predetermined target are having a conversation that matches at least the first information; The robot does not have a function of executing a conversation at a level higher than the level of the conversation based on the conversation data. Speech output system.

[0176] (Appendix 2) The robot comprises: A first sensor that acquires the situation information as the first information; a situation transmission unit that transmits the situation information as the first information acquired by the first sensor to the conversation output system, The conversation output system includes a conversation output server and a conversation output terminal, The conversation output server includes a terminal communication unit, the first information acquisition means, and the creation means, the conversation output terminal includes the output control means, the output unit, a status receiving unit, and a server communication unit; the output control means of the conversation output terminal receives and acquires the status information as the first information transmitted by the status transmission unit of the robot via the status receiving unit, and transmits the received status information as the first information to the terminal communication unit of the conversation output server via the server communication unit; the first information acquisition means of the conversation output server acquires the transmitted first information by receiving it via the terminal communication unit, and transmits the conversation data created by the creation means to the server communication unit of the conversation output terminal via the terminal communication unit; the output control means of the conversation output terminal receives and acquires the conversation data transmitted by the conversation output server via the server communication unit, and controls the output unit to output information based on the acquired conversation data, thereby making the user recognize that the robot and the predetermined target are having a conversation that matches at least the first information; 2. A conversation output system as described in appended claim 1.

[0177] (Appendix 3) The conversation output server is configured to be able to provide a social networking service (SNS), The output control means of the conversation output terminal Functioning as an SNS client software for accessing the SNS provided by the conversation output server, The acquired conversation data is transmitted to the terminal communication unit of the conversation output server via the server communication unit as a posting content to the SNS; By controlling the output unit to output information based on the conversation data, the user is made to recognize that the robot and the predetermined target are having a conversation on the SNS that is at least consistent with the first information. 3. A conversation output system as described in appended claim 2.

[0178] (Appendix 4) The creating means includes: Choose a topic of conversation creating the conversation data based on at least the selected topic and the first information; 4. A conversation output system according to any one of claims 1 to 3.

[0179] (Appendix 5) The creating means includes: Select the first topic of conversation, creating first conversation data based on the selected first topic and the first information; After the output control means controls the output unit to output information based on the first conversation data, a second topic different from the selected first topic is selected; creating second conversation data based on the selected second topic and the first information; 5. A conversation output system as described in appended claim 4.

[0180] (Appendix 6) The creating means includes: acquiring a linking sentence that is a sentence linking the first conversation data and the second conversation data; adding the acquired transition sentence before the created second conversation data; 6. A conversation output system as described in appended claim 5.

[0181] (Appendix 7) The system further includes a country of residence acquisition means for acquiring a country of residence of the user, The creation means translates the conversation data into the language of the acquired country of residence. 7. A conversation output system according to any one of claims 1 to 6.

[0182] (Appendix 8) The predetermined target is the user, another robot other than the robot, or a person other than the user. 8. A conversation output system according to any one of claims 1 to 7.

[0183] (Appendix 9) the predetermined target is another robot that is provided separately from the robot and belongs to another user different from the user, a second information acquisition means for acquiring second information, which is at least one of information about the other user and situation information, which is information about a situation around the other robot; the creation means creates, as the conversation data, data for allowing the user to recognize that the robot and the other robot are having a conversation that matches the first information and the second information, based on the acquired first and second information; the output control means controls the output unit to output information based on the conversation data, thereby making the user recognize that the robot and the other robot are having a conversation that matches the first and second information; 8. A conversation output system according to any one of claims 1 to 7.

[0184] (Appendix 10) the predetermined object is a virtual robot, the creation means sets second information related to the virtual robot, and creates, as the conversation data, data for making the user recognize that the robot and the virtual robot are having a conversation that matches the first and second information, based on the first information and the set second information; the output control means controls the output unit to output information based on the conversation data, thereby making the user recognize that the robot and the virtual robot are having a conversation that matches the first and second information; 8. A conversation output system according to any one of claims 1 to 7.

[0185] (Appendix 11) The information processing device further includes a user intention information acquiring means for acquiring user intention information from the user, the user indicating whether the user intends to make the personal information public; the creation means creates the conversation data based on the first information including information about the user when the acquired user intention information indicates that the user wishes to make personal information public. 11. The conversation output system of claim 1.

[0186] (Appendix 12) The robot does not have a conversation function. 12. A conversation output system according to any one of claims 1 to 11.

[0187] (Appendix 13) A display is provided as the output unit, the output control means causes the user to recognize that the robot and the predetermined target are having a conversation that matches at least the first information by displaying the conversation data created by the creation means on the display; 13. The speech output system of any one of claims 1 to 12.

[0188] (Appendix 14) The output unit includes a speaker, the output control means synthesizes voice from the conversation data created by the creation means and outputs the voice from the speaker, thereby making the user recognize that the robot and the predetermined target are having a conversation that at least matches the first information. 14. The conversation output system of claim 1.

[0189] (Appendix 15) An information acquisition means for acquiring first information which is at least one of information on a user of the robot and situation information which is information on a situation around the robot; a creating means for creating conversation data for allowing a user of the robot to recognize that the robot and a predetermined object are having a conversation that at least matches the first information, based on the acquired first information; and a transmission means for transmitting the created conversation data to a conversation output terminal provided separately from the robot. Conversation output server.

[0190] (Appendix 16) A conversation output method executed by a conversation output system, comprising: acquiring first information, which is at least one of information about a user of the robot and situation information, which is information about a situation around the robot; creating conversation data for allowing the user to recognize that the robot and a predetermined target are having a conversation that matches at least the first information, based on the acquired first information; a step of causing the user to recognize that the robot and the predetermined target are having a conversation that matches at least the first information by controlling an output unit provided separately from the robot so as to output information based on the created conversation data; A conversation output method including:

[0191] (Appendix 17) On the conversation output server computer, A process of acquiring first information, which is at least one of information about a user of the robot and situation information, which is information about a situation around the robot; A process of creating conversation data for allowing a user of the robot to recognize that the robot and a predetermined target are having a conversation that at least matches the first information, based on the acquired first information; a process for making the user recognize that the robot and the predetermined target are having a conversation that matches at least the first information by controlling an output unit provided separately from the robot so as to output information based on the created conversation data; Execute the program. [Explanation of symbols]

[0192] 100,100',100'',101,101',101'',102,102',103,103',103''...robot, 110,410...situation acquisition unit, 120,210,420...short-range communication unit, 130...user intention acquisition unit, 131...human sensor, 132...camera, 133...microphone, 134,280...speaker, 135...legs, 136...tail, 140,220,310...LTE communication unit, 150...self-diagnosis unit, 200,200',200'',201,202,202',202'',203,203',203''...conversation output terminal, 230...terminal control control unit, 231...conversation output unit, 232, 321...scenario selection unit, 233...situation notification creation unit, 240, 330...storage unit, 241, 331...scenario storage unit, 242, 332...user profile storage unit, 243, 333...user situation storage unit, 250...scenario conversation output terminal, 260...user input unit, 270...display, 300, 301, 302...conversation output server, 320...control unit, 322...sentence creation unit, 400, 400A, 400B, 400C, 400'...sensor device, 1000, 1001, 1002, 1003, 1004, 1005...conversation output system

Claims

1. a first information acquiring means for acquiring first information, which is at least one of information regarding a user of the robot and situation information, which is information regarding a situation around the robot; a creating means for creating conversation data for making the user recognize that the robot and a predetermined target are having a conversation that matches at least the first information, based on the acquired first information; an output control means for controlling an output unit to output information based on the created conversation data, thereby making the user recognize that the robot and the predetermined target are having a conversation that matches at least the first information; The robot does not have a function of executing a conversation at a level higher than the level of the conversation based on the conversation data. Speech output system.

2. The robot comprises: A first sensor that acquires the situation information as the first information; a situation transmission unit that transmits the situation information as the first information acquired by the first sensor to the conversation output system, The conversation output system includes a conversation output server and a conversation output terminal, the conversation output server includes a terminal communication unit, the first information acquisition means, and the creation means; the conversation output terminal includes the output control means, the output unit, a status receiving unit, and a server communication unit; the output control means of the conversation output terminal receives and acquires the status information as the first information transmitted by the status transmission unit of the robot via the status receiving unit, and transmits the received status information as the first information to the terminal communication unit of the conversation output server via the server communication unit; the first information acquisition means of the conversation output server acquires the transmitted first information by receiving it via the terminal communication unit, and transmits the conversation data created by the creation means to the server communication unit of the conversation output terminal via the terminal communication unit; the output control means of the conversation output terminal receives and acquires the conversation data transmitted by the conversation output server via the server communication unit, and controls the output unit to output information based on the acquired conversation data, thereby making the user recognize that the robot and the predetermined target are having a conversation that matches at least the first information; 2. The speech output system according to claim 1.

3. The conversation output server is configured to be able to provide a social networking service (SNS), The output control means of the conversation output terminal Functioning as an SNS client software for accessing the SNS provided by the conversation output server, Transmitting the acquired conversation data as a posting content to the SNS via the server communication unit to the terminal communication unit of the conversation output server; By controlling the output unit to output information based on the conversation data, the user is made to recognize that the robot and the predetermined target are having a conversation on the SNS that is at least consistent with the first information. The speech output system according to claim 2 .

4. The creating means includes: Choose a topic of conversation creating the conversation data based on at least the selected topic and the first information; A conversation output system according to any one of claims 1 to 3.

5. The creating means includes: Select the first topic of conversation, creating first conversation data based on the selected first topic and the first information; After the output control means controls the output unit to output information based on the first conversation data, a second topic different from the selected first topic is selected; creating second conversation data based on the selected second topic and the first information; 5. The speech output system according to claim 4.

6. The creating means includes: acquiring a linking sentence which is a sentence linking the first conversation data and the second conversation data; adding the acquired transition sentence before the created second conversation data; 6. A speech output system according to claim 5.

7. The system further includes a country of residence acquisition means for acquiring a country of residence of the user, The creation means translates the conversation data into the language of the acquired country of residence. A conversation output system according to any one of claims 1 to 6.

8. The predetermined target is the user, another robot other than the robot, or a person other than the user. A conversation output system according to any one of claims 1 to 7.

9. the predetermined target is another robot that is provided separately from the robot and belongs to another user different from the user, a second information acquisition means for acquiring second information, which is at least one of information about the other user and situation information, which is information about a situation around the other robot; the creation means creates, as the conversation data, data for allowing the user to recognize that the robot and the other robot are having a conversation that matches the first information and the second information, based on the acquired first and second information; the output control means controls the output unit to output information based on the conversation data, thereby making the user recognize that the robot and the other robot are having a conversation that matches the first and second information; A conversation output system according to any one of claims 1 to 7.

10. the predetermined object is a virtual robot, the creation means sets second information related to the virtual robot, and creates, as the conversation data, data for allowing the user to recognize that the robot and the virtual robot are having a conversation that matches the first and second information, based on the first information and the set second information; the output control means controls the output unit to output information based on the conversation data, thereby making the user recognize that the robot and the virtual robot are having a conversation that matches the first and second information; A conversation output system according to any one of claims 1 to 7.

11. The information processing device further includes a user intention information acquiring means for acquiring user intention information from the user, the user indicating whether the user intends to make the personal information public; the creation means creates the conversation data based on the first information including information about the user when the acquired user intention information indicates that the user wishes to make personal information public. A conversation output system according to any one of claims 1 to 10.

12. The robot does not have a conversation function. A speech output system according to any one of claims 1 to 11.

13. A display is provided as the output unit, the output control means causes the user to recognize that the robot and the predetermined target are having a conversation that matches at least the first information by displaying the conversation data created by the creation means on the display; A speech output system according to any one of claims 1 to 12.

14. The output unit includes a speaker, the output control means synthesizes voice from the conversation data created by the creation means and outputs the voice from the speaker, thereby making the user recognize that the robot and the predetermined target are having a conversation that matches at least the first information; A speech output system according to any one of claims 1 to 13.

15. an information acquisition means for acquiring first information, which is at least one of information regarding a user of the robot and situation information, which is information regarding a situation surrounding the robot; a creating means for creating conversation data for allowing a user of the robot to recognize that the robot and a predetermined target are having a conversation that matches at least the first information, based on the acquired first information; and a transmission means for transmitting the created conversation data to a conversation output terminal provided separately from the robot. Conversation output server.

16. A conversation output method executed by a conversation output system, comprising: acquiring first information, which is at least one of information about a user of the robot and situation information, which is information about a situation around the robot; creating conversation data for making the user recognize that the robot and a predetermined target are having a conversation that matches at least the first information, based on the acquired first information; a step of causing the user to recognize that the robot and the predetermined target are having a conversation that matches at least the first information by controlling an output unit provided separately from the robot so as to output information based on the created conversation data; A conversation output method including:

17. On the conversation output server computer, A process of acquiring first information, which is at least one of information about a user of the robot and situation information, which is information about a situation around the robot; A process of creating conversation data for allowing a user of the robot to recognize that the robot and a predetermined target are having a conversation that at least matches the first information, based on the acquired first information; a process of causing the user to recognize that the robot and the predetermined target are having a conversation that matches at least the first information by controlling an output unit provided separately from the robot so as to output information based on the created conversation data; Execute the program.

Images