Conversation control device

Abstract

To improve confidence of a user in a robot that talks with the user.SOLUTION: A conversation control device 40 that controls a robot that talks with a conversation target person includes a setting unit 411, a determination unit 412, a voice control unit 413, a calculation unit 414, and an update unit 415. The setting unit 411 sets second personality information indicating personality of the robot according to first personality information indicating personality of the conversation target person. The determination unit 412 determines the way of talking of the robot and a topic based on the second personality information. The voice control unit 413 causes the robot to output a voice in which the determined topic is uttered in the determined way of talking. The calculation unit 414 calculates the degree of confidence indicating the strength of confidence in the robot based on a voice replied by the conversation target person. The update unit 415 updates the second personality information according to the degree of confidence calculated by the calculation unit 414.SELECTED DRAWING: Figure 7

Description

Technical Field

[0001] The present invention relates to a conversation control device.

Background Art

[0002] Patent Document 1 describes a pet robot having an autonomous function that can be easily grown into a desired personality. Patent Document 2 describes a conversation control system that causes an interaction device to behave in accordance with the emotions of a user.

Prior Art Documents

Non-Patent Documents

[0003]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, various robots that communicate with users have been proposed. Robots that communicate with users are expected to serve as, for example, teachers when users study on their own, friends, siblings or sisters of users. Regarding robots that serve as conversation partners for users, it may not be sufficient only to be able to grow personalities or to be able to behave in accordance with the emotions of users. If the user's trust in the robot is low, the frequency of the user speaking to the robot and the frequency of the user responding to inquiries from the robot decrease, etc., and the conversation itself between the robot and the user decreases, and the role as a conversation partner cannot be fulfilled.

Means for Solving the Problems

[0005] In order to solve the above problems, a conversation control device according to a preferred aspect of the present disclosure includes a setting unit, a determination unit, a voice control unit, a calculation unit, and an update unit. The setting unit sets second personality information indicating the personality of the robot according to first personality information indicating the personality of a user who converses with the robot. The determination unit determines the way of speaking and the topic of the robot based on the second personality information. The voice control unit causes the robot to output voice that speaks the determined topic in the determined way of speaking. The calculation unit calculates a reliability indicating the strength of the user's trust in the robot based on the voice of the user's response to the robot's utterance. The update unit updates the second personality information according to the reliability calculated by the calculation unit.

Effect of the Invention

[0006] According to the conversation control device of the present disclosure, since the personality of the robot that converses with the user can be updated according to the reliability of the user's trust in the robot estimated from the voice of the user's response, the user's trust in the robot can be enhanced through the conversation with the user.

Brief Description of the Drawings

[0007]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Embodiments for Carrying Out the Invention

[0008] (A. Embodiment) (A-1: Overall Configuration) FIG. 1 is a block diagram showing the configuration of a conversation system 1 according to an embodiment of the present disclosure. As shown in FIG. 1, the conversation system 1 includes a conversation control device 40, a user device 10, and a robot 30. The conversation partner U1 is a user who uses the robot 30. The robot 30 conducts a conversation with the conversation partner U1 under the control of the conversation control device 40. A typical example of the conversation partner U1 is a child such as an elementary school student. The robot 30 is purchased for the conversation partner U1 by the guardian U2 of the conversation partner U1. The robot 30 is arranged, for example, in the study room of the conversation partner U1.

[0009] The user device 10 communicates with the conversation control device 40 via the communication network NW. The user device 10 is used by the guardian U2. The guardian U2 stores, by operating on the user device 10, purpose information indicating the purpose of using the robot 30 and first personality information indicating the personality of the conversation partner U1 in the conversation control device 40. Specific examples of the purpose of using the robot 30 include playing the role of a friend with the conversation partner U1, playing the role of a brother or sister when the conversation partner U1 is an only child, or playing the role of a teacher when the conversation partner U1 is studying by oneself, etc.

[0010] FIG. 2 is a front view showing the appearance of the robot 30. The robot 30 has a head 31 and a body 32. The robot 30 operates on the power of a battery. A speaker 370 and a human sensor 350 are arranged on the body 32. A microphone 360 (not shown) is arranged inside the head 31. The robot 30 uses the human sensor 350 to detect that the conversation partner U1 has approached. The robot 30 switches the operation mode based on the detection result by the human sensor 350. The operation modes of the robot 30 include a conversation mode for conversing with the conversation partner U1 and a sleep mode for not conversing with the conversation partner U1. The power consumption of the robot 30 in the sleep mode is smaller than the power consumption of the robot 30 in the conversation mode. In the sleep mode, power is supplied to the human sensor 350 to detect that the conversation partner U1 has approached the robot 30, while the supply of power to other components is restricted. By providing the conversation mode and the sleep mode, the robot 30 can converse when the conversation partner U1 is nearby and can save power consumption when the conversation partner U1 is not nearby.

[0011] (A-2: User Device) FIG. 3 is a block diagram showing the configuration of the user device 10. Specific examples of the user device 10 include a smartphone or a tablet terminal. The user device 10 includes a processing device 110, a storage device 120, a display panel 130, a communication device 140, and an input device 150. Each element of the user device 10 is interconnected by one or more buses for communicating information. Note that the term "device" in this specification may be read as other terms such as a circuit, a device, or a unit. Each element of the user device 10 may be composed of one or more devices. Some elements of the user device 10 may be omitted.

[0012] The processing device 110 is a processor that controls the entire user device 10. The processing device 110 is composed of, for example, one or more chips. The processing device 110 is composed of, for example, a central processing unit (CPU) including an interface with peripheral devices, an arithmetic unit, registers, etc. Note that part or all of the functions of the processing device 110 may be realized by hardware such as a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), or an FPGA (Field Programmable Gate Array). The processing device 110 executes various processes in parallel or sequentially. By operating according to the program PR1 stored in the storage device 120, the processing device 110 functions as a control center of the user device 10.

[0013] The storage device 120 is a recording medium readable by the processing device 110. The storage device 120 stores a plurality of programs including the program PR1 and various information used by the processing device 110. The storage device 120 may be composed of, for example, at least one of a ROM (Read Only Memory), an EPROM (Erasable Programmable ROM), an EEPROM (Electrically Erasable Programmable ROM), a RAM (Random Access Memory), etc. The program PR1 may be transmitted from another device such as the conversation control device 40 via the communication network NW. Specific examples of the information stored in the storage device 120 and used by the processing device 110 include first identification information that uniquely identifies the robot 30 in the communication network NW and second identification information that uniquely identifies the conversation control device 40 in the communication network NW. Specific examples of the first identification information include a communication address assigned to the robot 30. Similarly, specific examples of the second identification information include a communication address assigned to the conversation control device 40.

[0014] The display panel 130 is a device for displaying images. Specific examples of the display panel 130 include a liquid crystal display panel and an organic EL (Electro Luminescence) display panel, etc.

[0015] The communication device 140 is hardware (a transmission / reception device) for communicating with other devices. The communication device 140 is also called, for example, a network device, a network controller, a network card, a communication module, etc.

[0016] The input device 150 is a device for receiving external input. Specific examples of the input device 150 include a touch panel provided integrally with the display panel 130. The input device 150 may include a plurality of operators operable by the user. The input device 150 outputs input information corresponding to the operation of the user, that is, the caregiver U2, to the processing device 110.

[0017] (A-3: Robot) FIG. 4 is a block diagram showing the configuration of the robot 30. The robot 30 includes a processing device 310, a storage device 320, a motor 330, a communication device 340, a human sensor 350, a microphone 360, and a speaker 370. Each element of the robot 30 is interconnected by a single or a plurality of buses for communicating information.

[0018] The processing device 310 is a processor that controls the entire robot 30. The processing device 310 is composed of one or a plurality of chips. The processing device 310 functions as a control center of the robot 30 by operating according to the program PR3 stored in the storage device 320.

[0019] The storage device 320 is a recording medium readable by the processing device 310. The storage device 320 stores a plurality of programs including the program PR3 and various information used by the processing device 310. The storage device 320 may be composed of at least one of, for example, ROM, EPROM, EEPROM, and RAM.

[0020] The motor 330 operates under the control of the processing device 310. By driving the motor 330, the head 31 or the arm of the robot 30 shown in FIG. 2 moves. The communication device 340 is hardware (a transmission / reception device) for communicating with other devices. The communication device 340 communicates with the conversation control device 40. The human sensor 350 detects that a person has approached and outputs a detection signal indicating the detection result to the processing device 310. When a detection signal is input from the human sensor 350, the processing device 310 switches the operation mode to the conversation mode and transmits a start signal indicating the start of operation in the conversation mode to the conversation control device 40. After switching the operation mode to the conversation mode, if no detection signal is input from the human sensor 350 for a predetermined period of time, the processing device 310 switches the operation mode from the conversation mode to the sleep mode. Further, when the processing device 310 switches the operation mode from the conversation mode to the sleep mode, it transmits an end signal indicating the end of operation in the conversation mode to the conversation control device 40.

[0021] The microphone 360 generates a first audio signal indicating the voice of the conversation partner U1 by converting sound into an electrical signal. The first audio signal is converted into first audio data by an AD converter (not shown). The first audio data is output to the processing device 310. The processing device 310 transmits the first audio data to the conversation control device 40 via the communication device 340.

[0022] The speaker 370 outputs the voice of the robot 30 to the conversation partner U1 under the control of the processing device 310. The speaker 370 includes a DA converter. Although details will be described later, in the present embodiment, second audio data representing the voice of the robot in the conversation with the conversation partner U1 is generated by the conversation control device 40 and transmitted from the conversation control device 40 to the robot 30 via the communication network NW. The processing device 310 outputs the second audio data received via the communication network NW to the speaker 370. The speaker 370 uses the DA converter to convert the second audio data into a second audio signal. The speaker 370 is driven by the second audio signal.

[0023] (A-4: Conversation Control Device) 5 is a block diagram showing the configuration of the conversation control device 40. The conversation control device 40 is, for example, a server. The conversation control device 40 includes a processing device 410, a storage device 420, a display panel 430, a communication device 440, and an input device 450. The elements of the conversation control device 40 are connected to each other by a single or multiple buses for communicating information. The hardware configuration of the conversation control device 40 is similar to that of the user device 10. However, it is preferable that the processing speed of the processing device 410 is faster than the processing speed of the processing device 110. In addition, it is preferable that the storage capacity of the storage device 420 is larger than the storage capacity of the storage device 120.

[0024] The processing device 410 operates according to the program PR4 to function as the control center of the conversation control device 40. The storage device 420 stores a plurality of programs including the program PR4, a log table TBL1, a management table TBL2, a conversation database DB1, various types of information used by the processing device 410, and the like.

[0025] The log table TBL1 stores a pair of a date and time of an utterance by the conversation target U1 in a conversation between the robot 30 and the conversation target U1 and a text indicating the content of the utterance by the conversation target U1, as well as a pair of a date and time of an utterance by the robot 30 in the conversation and a text indicating the content of the utterance by the robot 30.

[0026] In the management table TBL2, the purpose information, the first personality information, and the second personality information are stored in association with the first identification information that uniquely identifies the robot 30. When the purpose of using the robot 30 is "friend", a specific example of the purpose information is a character string such as "friend". When the purpose of using the robot 30 is "teacher", a specific example of the purpose information is a character string such as "teacher". When the purpose of using the robot 30 is "brother" or "sister", a specific example of the purpose information is a character string such as "older brother", "younger brother", "older sister", "younger sister", "brother" or "sister".

[0027] The second personality information is information indicating the personality to be set for the robot 30. In the present embodiment, the personality of the conversation partner U1 and the personality of the robot 30 are set from a first perspective of whether they are social or introverted, and a second perspective of whether they are talkative or taciturn. Specifically, the personality of the conversation partner U1 and the personality of the robot 30 are represented by a point in the two-dimensional coordinate plane shown in FIG. 6. The two-dimensional coordinate plane shown in FIG. 6 is defined by a first coordinate axis L1 corresponding to the first perspective and a second coordinate axis L2 corresponding to the second perspective. In the present embodiment, although the personality of the conversation partner U1 and the personality of the robot 30 are associated with points in the two-dimensional coordinate plane, they may be associated with points in an N-dimensional coordinate space defined by N coordinate axes corresponding to N different (N is an integer of 3 or more) perspectives.

[0028] The personality corresponding to the point where the coordinate value of the first coordinate axis L1 component is 2 has a higher degree of sociability than the personality corresponding to the point where the coordinate value of the first coordinate axis L1 component is 1. The personality corresponding to the point where the coordinate value of the first coordinate axis L1 component is 3 has an even higher degree of sociability than the personality corresponding to the point where the coordinate value of the first coordinate axis L1 component is 1 or less. Similarly, the personality corresponding to the point where the coordinate value of the first coordinate axis L1 component is -2 has a higher degree of introversion than the personality corresponding to the point where the coordinate value of the first coordinate axis L1 component is -1. The personality corresponding to the point where the coordinate value of the first coordinate axis L1 component is -3 has an even higher degree of introversion than the personality corresponding to the point where the coordinate value of the first coordinate axis L1 component is -1 or more.

[0029] For example, the personality corresponding to the point where the coordinate value of the first coordinate axis L1 component is 3 is a "showy personality". The personality corresponding to the point where the coordinate value of the first coordinate axis L1 component is 2 is a "sociable personality". The personality corresponding to the point where the coordinate value of the first coordinate axis L1 component is 1 is a "somewhat sociable personality". The personality corresponding to the point where the coordinate value of the first coordinate axis L1 component is 0 is a "personality that is neither sociable nor introverted". The personality corresponding to the point where the coordinate value of the first coordinate axis L1 component is -1 is a "somewhat introverted personality". The personality corresponding to the point where the coordinate value of the first coordinate axis L1 component is -2 is an "introverted personality". And the personality corresponding to the point where the coordinate value of the first coordinate axis L1 component is -3 is a "shy personality".

[0030] The degree of talkativeness of the personality corresponding to the point where the coordinate value of the second coordinate axis L2 component is 2 is higher than that of the personality corresponding to the point where the coordinate value of the second coordinate axis L2 component is 1. The degree of talkativeness of the personality corresponding to the point where the coordinate value of the second coordinate axis L2 component is 3 is even higher than that of the personality corresponding to the point where the coordinate value of the second coordinate axis L2 component is 1 or less. Similarly, the degree of taciturnity of the personality corresponding to the point where the coordinate value of the second coordinate axis L2 component is -2 is higher than that of the personality corresponding to the point where the coordinate value of the second coordinate axis L2 component is -1. The degree of taciturnity of the personality corresponding to the point where the coordinate value of the second coordinate axis L2 component is -3 is even higher than that of the personality corresponding to the point where the coordinate value of the second coordinate axis L2 component is -1 or more.

[0031] For example, the personality corresponding to the point where the coordinate value of the second coordinate axis L2 component is 3 is a "noisy personality". The personality corresponding to the point where the coordinate value of the second coordinate axis L2 component is 2 is a "talkative personality". The personality corresponding to the point where the coordinate value of the second coordinate axis L2 component is 1 is a "somewhat talkative personality". The personality corresponding to the point where the coordinate value of the second coordinate axis L2 component is 0 is a "personality that is neither talkative nor taciturn". The personality corresponding to the point where the coordinate value of the second coordinate axis L2 component is -1 is a "somewhat taciturn personality". The personality corresponding to the point where the coordinate value of the second coordinate axis L2 component is -2 is a "taciturn personality". And the personality corresponding to the point where the coordinate value of the second coordinate axis L2 component is -3 is a "silent personality".

[0032] When the personality of the conversation target U1 is "sociable and noisy", the first personality information indicating the point P1 in FIG. 6 is stored in the management table TBL2 in association with the first identification information of the robot 30. When the personality of the conversation target U1 is "introverted and quiet", the first personality information indicating the point P2 in FIG. 6 is stored in association with the first identification information of the robot 30 in the management table TBL2. In this embodiment, the objective information and the first personality information are input to the user device 10 by operating the user device 10. The user device 10 transmits the objective information and the first personality information input by the guardian U2 together with the first identification information stored in the storage device 120 to the device indicated by the second identification information (i.e., the conversation control device 40). The processing device 410 generates the second personality information upon receiving the first identification information, the objective information, and the first personality information from the user device 10. Then, the processor 410 writes the received first identification information, purpose information, and first personality information in association with the generated second personality information in the management table TBL2.

[0033] The conversation database DB1 stores speech templates that indicate speech styles corresponding to each personality that can be set for the robot 30. Specific examples of speech templates include information that indicates the speech rate, volume, and intonation of the voice uttered by the robot 30. For example, the speech rate indicated by a speech template corresponding to a sociable personality is faster than the speech rate indicated by a speech template corresponding to an introverted personality. Also, the volume indicated by a speech template corresponding to a sociable personality is louder than the volume indicated by a speech template corresponding to an introverted personality. Also, the intonation indicated by a speech template corresponding to a sociable personality is louder than the intonation indicated by a speech template corresponding to an introverted personality.

[0034] In addition, in the conversation database DB1, one or more pieces of topic data indicating inquiry sentences in conversations related to topics corresponding to the purpose of the robot 30 are stored for each purpose of the robot 30. For example, as a specific example of the topic data when the purpose of use is a teacher, string data representing inquiry sentences related to study, inquiry sentences related to favorite things, or inquiry sentences related to consultations, etc. can be cited. Also, as a specific example of the topic data when the purpose of use is a friend, string data representing inquiry sentences related to play, inquiry sentences related to favorite things, or inquiry sentences related to consultations, etc. can be cited. Note that even for topic data related to the same topic, the topic data when the purpose of use is a teacher and the topic data when the purpose of use is a friend may represent sentences in different tones. For example, the former may represent a polite sentence in the "desu. masu." style, and the latter may represent a casual sentence such as "right?" This is to avoid a discrepancy between the tone of the voice output from the robot 30 and the role played by the robot 30, as it is common for the tone to be different between a teacher and a friend.

[0035] FIG. 7 is a block diagram showing the functions realized by the processing device 410 according to the program PR4. The processing device 410 functions as a setting unit 411, a determination unit 412, an audio control unit 413, a calculation unit 414, an update unit 415, and a log generation unit 416 by reading and executing the program PR4 from the storage device 420.

[0036] When the setting unit 411 receives the first identification information DI, the purpose information Dm, and the first personality information DC1, it sets the personality of the robot 30 according to the received purpose information Dm and the first personality information DC1. More specifically, the setting unit 411 sets, as a candidate personality that is a candidate for setting the personality of the robot 30, a personality that is the opposite of the personality indicated by the first personality information DC1. The personality that is the opposite of the personality indicated by the first personality information DC1 refers to the personality corresponding to the point that is point-symmetrical to the point indicated by the first personality information DC1 with respect to the origin of the two-dimensional coordinate plane shown in FIG. 6.

[0037] For example, when the personality indicated by the first personality information DC1 corresponds to the point PP in FIG. 8, that is, a "somewhat introverted and somewhat taciturn personality", the setting unit 411 sets, as a candidate personality, the personality corresponding to the point PV in FIG. 8, that is, a "somewhat sociable and somewhat talkative personality". The reason for setting a personality opposite to the personality indicated by the first personality information DC1 as the candidate personality is that it is known that when the conversation partner of the conversation target person U1 has a personality opposite to that of the conversation target person U1, the conversation between the two proceeds smoothly.

[0038] Next, the setting unit 411 sets, as the personality to be set for the robot 30, the personality obtained by correcting the candidate personality according to the usage purpose indicated by the target information Dm, and generates second personality information DC2 indicating the corrected personality. Various modes can be considered as the correction mode of the candidate personality according to the usage purpose indicated by the target information Dm. For example, according to the usage purpose indicated by the target information Dm, a correction for emphasizing the characteristics of the candidate personality or a correction for weakening the characteristics of the personality can be considered. A specific example of the correction for emphasizing the characteristics of the candidate personality is a correction for increasing the absolute value of the coordinate value of the point corresponding to the candidate personality without changing the sign. Similarly, a specific example of the correction for weakening the characteristics is a correction for decreasing the absolute value of the coordinate value of the point corresponding to the candidate personality without changing the sign.

[0039] In the present embodiment, when the usage purpose indicated by the target information Dm is "friend", the setting unit 411 performs a correction for emphasizing the characteristics on the candidate personality to generate the second personality information DC2. This is because when the characteristics of the personality are prominent regarding a friend, the interestingness is improved. On the other hand, when the usage purpose indicated by the target information Dm is "teacher", the setting unit 411 performs a correction for weakening the characteristics of the personality on the candidate personality to generate the second personality information DC2. This is because it is not preferable for the characteristics of the personality to be too prominent regarding a teacher.

[0040] For example, when the usage purpose indicated by the purpose information Dm is "friend" and the personality corresponding to the point PV in FIG. 8 (a somewhat social and somewhat talkative personality) is the candidate personality, the setting unit 411 generates second personality information DC2 representing the personality corresponding to the point PR1 in FIG. 8 (a social and talkative personality). Then, the setting unit 411 associates the received first identification information DI, purpose information Dm, and first personality information DC1 with the second personality information DC2 and writes them into the management table TBL2 to set the personality of the robot 30.

[0041] When the determination unit 412 receives the start signal SS, it reads out the purpose information Dm and the second personality information DC2 stored in the management table TBL2 in association with the first identification information DI of the robot 30 that is the transmission source of the start signal SS from the management table TBL2. Then, the determination unit 412 determines the speaking style and topic of the robot 30 based on the read purpose information Dm and second personality information DC2. The determination unit 412 determines the speaking style of the robot 30 by reading out the speaking style template DS1 stored in the conversation database DB1 in association with the personality indicated by the second personality information DC2. Also, the determination unit 412 determines the topic in the conversation with the conversation partner U1 by reading out any one of the topic data Dt2 stored in the conversation database DB1 in association with the purpose information Dm.

[0042] The voice control unit 413 causes the robot 30 to output a voice that speaks the topic determined by the determination unit 412 in the speaking style determined by the determination unit 412. The voice control unit 413 generates second voice data Dv2 representing a voice that reads out the topic data Dt2 in the speaking style indicated by the speaking style template DS1. Then, the voice control unit 413 transmits the second voice data Dv2 to the robot 30 via the communication network NW. The voice control unit 413 repeatedly executes the determination of the topic by the determination unit 412 and the generation of the second voice data Dv2 until it receives the end signal SE.

[0043] The robot 30 causes the speaker 370 to output the voice represented by the received second voice data Dv2. The robot 30 transmits the first voice data Dv1 representing the voice of the response of the conversation partner U1 to the conversation control device 40 via the communication network NW. Until the voice control unit 413 receives the end signal SE, every time the first voice data Dv1 is received, the voice control unit 413 performs voice recognition on the received first voice data Dv1 and generates response data Dt1 representing the words of the response of the conversation partner U1. The voice control unit 413 stores the received first voice data Dv1 and the response data Dt1 generated based on the first voice data Dv1 in the storage device 420 as a pair. When a conversation is made between the robot 30 and the conversation partner U1 between receiving the start signal SS and receiving the end signal SE, one or more pairs of the first voice data Dv1 and the response data Dt1 are stored in the storage device 420. The time from receiving the start signal SS to receiving the end signal SE corresponds to the conversation time of the conversation conducted between the conversation partner U1 and the robot 30.

[0044] The calculation unit 414 calculates a reliability indicating the degree of trust of the conversation partner U1 in the robot 30 based on one or more pairs of the first voice data Dv1 and the response data Dt1 stored in the storage device 420 and the conversation time of the conversation conducted between the robot 30 and the conversation partner U1.

[0045] In the present embodiment, the calculation unit 414 first calculates a first evaluation value regarding the content of the conversation estimated from the words indicated by each of the one or more pieces of response data Dt1 stored in the storage device 420. Further, the calculation unit 414 calculates a second evaluation value regarding the emotion incorporated in the voice represented by each of the one or more pieces of first voice data Dv1 stored in the storage device 420. Further, the calculation unit 414 calculates a third evaluation value and a fourth evaluation value regarding the conversation time between the robot 30 and the conversation partner U1. Then, the calculation unit 414 calculates a value V representing a reliability indicating the degree of trust of the conversation partner U1 in the robot 30 based on the first evaluation value, the second evaluation value, the third evaluation value, and the fourth evaluation value.

[0046] In this embodiment, the calculation unit 414 calculates an integer value between 1 and 5 as the first evaluation value. In this embodiment, when it is estimated that the trust of the conversation partner with respect to the robot 30 is high, the calculation unit 414 calculates a first evaluation value with a larger value compared to the case where it is estimated that the trust of the conversation partner with respect to the robot 30 is low.

[0047] It is considered that the conversation partner U1 will only have a greeting-level conversation if the trust in the conversation partner is low, and will start a conversation about study or play when the trust in the conversation partner increases. Then, as the trust of the conversation partner U1 in the conversation partner further increases, it is considered that the conversation partner U1 will start a conversation about favorite things, and as the trust in the conversation partner further increases, the conversation partner U1 will start a conversation about consultation matters. Therefore, when the content of the conversation estimated from the text of the response indicated by the response data Dt1 is "greeting", the calculation unit 414 calculates 1 as the first evaluation value. Regarding the estimation of the content of the conversation from the text of the response indicated by the response data Dt1, existing technologies may be appropriately adopted. In addition, when the content of the conversation estimated from the text indicated by the response data Dt1 is "study talk" or "play talk", the calculation unit 414 calculates "3" as the first evaluation value. Note that the evaluation values for "study talk" and "play talk" may vary depending on the purpose of use of the robot 30. For example, when the purpose of use of the robot 30 is a teacher, the evaluation value for "study talk" may be 4, and the evaluation value for "play talk" may be 3. On the other hand, when the purpose of use of the robot 30 is a friend, the evaluation value for "study talk" may be 3, and the evaluation value for "play talk" may be 4. Further, when the content of the conversation estimated from the text of the response indicated by the response data Dt1 is "talk about favorite things", the calculation unit 414 calculates "4" as the first evaluation value. Then, when the content of the conversation estimated from the text of the response indicated by the response data Dt1 is "consultation", the calculation unit 414 calculates "5" as the first evaluation value.

[0048] Similarly for the second evaluation value, the calculation unit 414 calculates an integer value of any one of 1 to 5. In the present embodiment, when it is estimated that the trust of the conversation partner with respect to the robot 30 is high, the calculation unit 414 calculates a second evaluation value with a larger value compared to the case where it is estimated that the trust of the conversation partner with respect to the robot 30 is low.

[0049] If the conversation partner U1 has low trust in the conversation partner, the reply to the conversation partner will contain the emotion of "anger" or "sadness". When the trust in the conversation partner increases, no special emotion is contained in the reply. In other words, it is considered that the emotion contained in the reply becomes "flat". And when the trust of the conversation partner U1 in the conversation partner further increases, the emotion of "happiness" is contained in the reply. When the trust of the conversation partner U1 in the conversation partner further increases, it is considered that the emotion of "joy" is contained in the reply. Therefore, when the emotion contained in the voice represented by the first voice data Dv1 is "joy", the calculation unit 414 calculates "5" as the second evaluation value. Regarding the estimation of the emotion contained in the voice represented by the first voice data Dv1, existing technologies may be appropriately used. Also, when the emotion contained in the voice represented by the first voice data Dv1 is "anger", the calculation unit 414 calculates "1" as the second evaluation value. When the emotion contained in the voice represented by the first voice data Dv1 is "sadness", the calculation unit 414 calculates "2" as the second evaluation value. When the emotion contained in the voice represented by the first voice data Dv1 is "happiness", the calculation unit 414 calculates "4" as the second evaluation value. And when the emotion contained in the voice represented by the first voice data Dv1 is "flat", that is, when no special emotion is contained, the calculation unit 414 calculates "3" as the second evaluation value. Note that the calculation unit 414 may calculate the second evaluation value in consideration of the content of the conversation represented by the reply data Dt1. As described above, the second evaluation value when the emotion contained in the voice represented by the first voice data Dv1 is "sadness" is "2". However, when the content of the conversation represented by the reply data Dt1 is "consultation", it is normal for the voice of "consultation" to contain the emotion of "sadness". Receiving "consultation" means being highly trusted by the conversation partner. Therefore, when the emotion contained in the voice represented by the first voice data Dv1 is "sadness" and the content of the conversation represented by the reply data Dt1 is "consultation", the calculation unit 414 may calculate a higher second evaluation value (for example, "4", etc.) than when the content of the conversation represented by the reply data Dt1 is other than "consultation".

[0050] The third evaluation value is an evaluation value regarding the length of the conversation time. Similarly for the third evaluation value, the calculation unit 414 calculates an integer value of any one of 1 to 5. In the present embodiment, when the conversation time is long, the calculation unit 414 calculates a third evaluation value with a larger value compared to the case where the conversation time is short. It is considered that if the trust of the conversation partner U1 in the conversation target is low, the conversation time is short, and as the trust in the conversation partner increases, the conversation time becomes long. For example, when the conversation time is less than 1 minute, the calculation unit 414 calculates 1 as the third evaluation value, and when the conversation time is 30 minutes or more, the calculation unit 414 calculates 5 as the third evaluation value.

[0051] The fourth evaluation value is an evaluation value regarding the change in the length of the conversation time from the previous conversation. Similarly for the fourth evaluation value, the calculation unit 414 calculates an integer value of any one of 1 to 5. In the present embodiment, when the conversation time is longer than that at the previous conversation, the calculation unit 414 calculates a fourth evaluation value with a larger value compared to the case where the conversation time is shorter than that at the previous conversation. For example, when the conversation time becomes less than half as short as that at the previous conversation, the calculation unit 414 calculates 1 as the fourth evaluation value, and when the conversation time becomes two times or more as long as that at the previous conversation, the calculation unit 414 calculates 5 as the fourth evaluation value.

[0052] Then, the calculation unit 414 calculates a value V representing the reliability by weighted addition of the first evaluation value, the second evaluation value, the third evaluation value, and the fourth evaluation value. The value V in the present embodiment is a value representing the reliability as a percentage with 100% when the reliability is maximum. In the present embodiment, the value V becomes 100 when each of the first evaluation value, the second evaluation value, the third evaluation value, and the fourth evaluation value is maximum. Note that the calculation unit 414 may change the weight of each of the first evaluation value, the second evaluation value, the third evaluation value, and the fourth evaluation value according to the elapsed time since the conversation partner U1 started using the robot 30. For example, until a predetermined period has elapsed since the conversation partner U1 started using the robot 30, the weight of the third evaluation value may be made larger than the weight of the fourth evaluation value, and after the elapse of the predetermined period, the weight of the fourth evaluation value may be made larger than the weight of the third evaluation value. This is because until a predetermined period has elapsed since the conversation partner U1 started using the robot 30, the conversation partner U1 is not yet accustomed to the conversation with the robot 30, and the conversation time is considered to be shorter regardless of the level of trust in the robot 30.

[0053] The update unit 415 updates the second personality information DC2 stored in the management table TBL2 in association with the first identification information DI according to the value V calculated by the calculation unit 414. Specifically, when the value V calculated by the calculation unit 414 is smaller than a predetermined threshold value, the update unit 415 updates the second personality information DC2 by performing a correction to emphasize the personality characteristics or a correction to weaken the personality characteristics.

[0054] Various modes of correction of the second personality information DC2 are conceivable. For example, a mode in which a predetermined one of the correction to emphasize the personality characteristics and the correction to weaken the personality characteristics is applied to the second personality information DC2 regardless of the purpose of using the robot 30 is conceivable. Also conceivable is a mode in which the correction corresponding to the purpose of using the robot 30 among the correction to emphasize the personality characteristics and the correction to weaken the personality characteristics is applied to the second personality information DC2. In the present embodiment, the latter mode is adopted.

[0055] For example, when the usage purpose indicated by the target information Dm is "friend", and the personality indicated by the second personality information corresponds to the point PR1 in FIG. 9 (a social and talkative personality), the update unit 415 updates the second personality information DC2 to information indicating a personality (attention-seeking and noisy personality) corresponding to the point PR2 in FIG. 9 by performing correction to accentuate the characteristics of the personality.

[0056] The log generation unit 416 generates log data Dl in which the response data Dt1 or the topic data Dt2, the type data Dy, and the date and time data Dx are associated. The type data Dy indicates the type of text data included in the log data Dl, that is, whether it is the response data Dt1 or the topic data Dt2. When the data value of the type data Dy is "0", it indicates that the log data Dl includes the topic data Dt2. When the data value of the type data Dy is "1", it indicates that the log data Dl includes the response data Dt1. The date and time data Dx indicates the generation date and time of the text data whose type is indicated by the type data Dy. The log generation unit 416 writes the log data Dl into the log table TBL1.

[0057] Also, the processing device 410 executes the conversation control method of the present disclosure by executing the program PR4. FIG. 10 is a flowchart showing the flow of the conversation control method executed by the processing device 410 according to the program PR4. As shown in FIG. 10, this conversation control method includes each process from step SA110 to step SA180.

[0058] In step SA110, the processing device 410 functions as the setting unit 411. In step SA110, the processing device 410 determines whether the first identification information DI, the target information Dm, and the first personality information DC1 have been received. When it is determined that the first identification information DI, the target information Dm, and the first personality information DC1 have been received, the processing device 410 generates the second personality information DC2 based on the target information Dm and the first personality information DC1. Then, the processing device 410 associates the received first identification information DI, target information Dm, and first personality information DC1 with the generated second personality information DC2 and writes them into the management table TBL2.

[0059] In step SA120 following step SA110, the processing device 410 functions as a determination unit 412. In step SA120, the processing device 410 determines whether or not the start signal SS has been received. If it is determined that the start signal SS has been received, that is, if the determination result of step SA120 is “Yes”, the processing device 410 executes the processing of step SA130. If it is determined that the start signal SS has not been received, that is, if the determination result of step SA120 is “No”, the processing device 410 executes the processing of step SA120 again.

[0060] In step SA130, the processing device 410 determines the way of speaking and the topic of the robot 30 in the conversation between the robot 30 and the conversation partner U1 by reading out the speech template DS1 and the topic data Dt2 corresponding to the target information Dm and the second personality information DC2 stored in the management table TBL2 from the conversation database DB1.

[0061] In step SA140 following step SA130, the processing device 410 functions as an audio control unit 413 and a log generation unit 416. In step SA140, the processing device 410 generates second audio data Dv2 representing the voice read out in the way of speaking indicated by the speech template DS1 for the sentence represented by the topic data Dt2, and transmits the second audio data Dv2 to the robot 30. Also, in step SA140, when the processing device 410 receives the first audio data Dv1, the processing device 410 performs speech recognition on the first audio data Dv1 to generate response data Dt1. Also, in step SA140, the processing device 410 generates log data Dl and writes the generated log data Dl into the log table TBL1.

[0062] In step SA150 following step SA140, the processing device 410 functions as the voice control unit 413. In step SA150, the processing device 410 determines whether the end signal SE has been received. If the end signal SE has been received, the determination result of step SA150 is "Yes", and the processing device 410 executes the processing after step SA160. After receiving the start signal SS and until the end signal SE is received, the determination result of step SA150 is "No", and the processing device 410 executes the processing after step SA130. When the determination result of step SA150 is "No" and the processing of step SA130 is executed again, the processing device 410 omits the reading of the speaking style template DS1 and reads different topic data Dt2 from the conversation database DB1.

[0063] In step SA160, the processing device 410 functions as the calculation unit 414. In step SA160, the processing device 410 calculates a value V indicating the reliability of the conversation partner U1 for the robot 30 based on one or more sets of response data Dt1 and the first voice data Dv1 stored in the storage device 420.

[0064] In steps SA170 and SA180, the processing device 410 functions as the update unit 415. In step SA170, the processing device 410 determines whether the value V calculated in step SA160 is smaller than the threshold value. If the value V is smaller than the threshold value, the determination result of step SA170 is "Yes", and if the value V is greater than or equal to the threshold value, the determination result of step SA170 is "No". When the determination result of step SA170 is "Yes", the processing device 410 executes the processing of step SA180 and then executes the processing after step SA120 again. In step SA180, the processing device 410 updates the second personality information DC2 according to the usage purpose indicated by the target information Dm. When the determination result of step SA170 is "No", the processing device 410 executes the processing after step SA120 again without executing the processing of step SA180.

[0065] As described above, according to the conversation control device 40, the personality of the robot 30 that converses with the conversation partner U1 can be updated according to the reliability calculated from the response of the conversation partner U1 in the conversation with the robot 30. Therefore, by updating to a personality with increasing reliability, the reliability of the conversation partner U1 with respect to the robot 30 is improved.

[0066] (B: Modification Example) The present disclosure is not limited to the embodiments illustrated above. Specific modification modes are as follows. Two or more modes arbitrarily selected from the following examples may be combined. (B-1: Modification Example 1) In the setting unit 411 in the above embodiment, a candidate personality indicating a personality opposite to the personality represented by the first personality information DC1 was used. However, the candidate personality is not limited to a personality opposite to the personality represented by the first personality information DC1. For example, with respect to either the first coordinate axis L1 or the second coordinate axis L2, a personality corresponding to a point that is line-symmetric to the point corresponding to the first personality information DC1 may be used as the candidate personality. Also, in the above embodiment, the calculation unit 414 calculated a value indicating reliability by weighted addition of the first evaluation value, the second evaluation value, the third evaluation value, and the fourth evaluation value. However, a value indicating reliability may be calculated using an arbitrary function taking the first evaluation value, the second evaluation value, the third evaluation value, and the fourth evaluation value as arguments. Further, the calculation unit 414 may calculate a value indicating reliability using any one or more of the first evaluation value, the second evaluation value, the third evaluation value, and the fourth evaluation value.

[0067] (B-2: Modification Example 2) In the above embodiment, the robot 30 only detects the approach of a person in the sleep mode. However, in a conversation between the conversation partner U1 and another person, the robot 30 may also pick up the voice of the conversation partner U1 and transmit voice data representing the picked-up voice to the conversation control device 40. Note that a specific example of the other person is the caregiver U2. In a mode where the robot 30 transmits voice data representing the voice of the conversation partner U1 in a conversation between the conversation partner U1 and another person to the conversation control device 40, a generation unit that analyzes the voice data to diagnose the personality of the conversation partner U1 and generates first personality information DC1 according to the diagnosis result may be provided in the conversation control device 40. Note that existing technologies may be appropriately adopted for the personality diagnosis of the speaker based on voice. According to this aspect, since the first personality information DC1 is generated based on the voice of the conversation partner U1 in a conversation between the conversation partner U1 and another person, the trouble of the caregiver U2 inputting the first personality information DC1 is reduced. Further, according to this aspect, second personality information DC2 is generated based on the first personality information DC1 that is not affected by the subjectivity of the caregiver U2.

[0068] (B-3: Variant Example 3) In the above embodiment, the setting unit 411 generated the second personality information DC2 based on the target information Dm and the first personality information DC1. However, the setting unit 411 may generate the second personality information DC2 based only on the first personality information DC1. For example, the setting unit 411 may generate the second personality information DC2 that represents a personality opposite to the personality indicated by the first personality information DC1. In a mode where the setting unit 411 generates the second personality information DC2 based only on the first personality information DC1, it is not necessary for the caregiver U2 to input the target information Dm.

[0069] Further, the setting unit 411 may set the personality of the robot 30 in consideration of the expertise level indicating the height of the topic specialty in the conversation of the conversation partner U1 or the erudition degree indicating the degree of erudition set for the robot 30, instead of or together with the target information Dm. For example, when the personality of the conversation partner U1 is a "character with strong intellectual curiosity", it is considered that the trust of the conversation partner U1 in the robot 30 will be further enhanced by setting the personality of the robot 30 with a high expertise level or erudition degree.

[0070] (B-4: Modification Example 4) The log generation unit 416 in the above embodiment is not essential and may be omitted. In an aspect where the log generation unit 416 is omitted, the log table TBL1 can also be omitted. Further, in the above embodiment, the conversation control device 40 and the robot 30 are separate devices, but the conversation control device 40 may be included in the robot 30. Also, the program PR4 may be manufactured or sold alone.

[0071] (C: Others) (1) In the above-described embodiment, the storage devices 120, 320, and 420 are exemplified by ROM, RAM, etc., but flexible disks, magneto-optical disks (e.g., compact disks, digital versatile disks, Blu-ray (registered trademark) disks), smart cards, flash memory devices (e.g., cards, sticks, key drives), CD-ROM (Compact Disc-ROM), registers, removable disks, hard disks, floppy (registered trademark) disks, magnetic strips, databases, servers, and other appropriate storage media. Also, the program may be transmitted from a network via a telecommunication line. Also, the program may be transmitted from a communication network via a telecommunication line.

[0072] (2) In the above-described embodiments, the information, signals, etc. described may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0073] (3) In the above-described embodiments, the input / output information, etc. may be stored in a specific location (e.g., memory) or may be managed using a management table. The input / output information, etc. may be overwritten, updated, or appended. The output information, etc. may be deleted. The input information, etc. may be transmitted to other devices.

[0074] (4) In the above-described embodiments, the determination may be made based on a value represented by 1 bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0075] (5) The processing procedures, sequences, flowcharts, etc. illustrated in the above-described embodiments may be reordered as long as there is no contradiction. For example, for the methods described in the present disclosure, the elements of various steps are presented using an exemplary order and are not limited to the specific order presented.

[0076] (6) Each function illustrated in FIG. 7 is realized by any combination of at least one of hardware and software. Also, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one physically or logically combined device, or two or more physically or logically separated devices may be directly or indirectly (e.g., using wired, wireless, etc.) connected and realized using these multiple devices. The functional block may be realized by combining software with the above one device or the above multiple devices.

[0077] (7) The programs exemplified in the above-described embodiments should be broadly interpreted to mean instructions, instruction sets, code, code segments, program codes, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, etc., whether called software, firmware, middleware, microcode, a hardware description language, or by any other name.

[0078] Also, software, instructions, information, etc. may be transmitted and received via a transmission medium. For example, when software is transmitted from a website, server, or other remote source using at least one of wired technologies (such as coaxial cables, optical fiber cables, twisted pairs, digital subscriber lines (DSLs), etc.) and wireless technologies (such as infrared rays, microwaves, etc.), at least one of these wired and wireless technologies is included within the definition of the transmission medium.

[0079] (8) In each of the foregoing embodiments, the terms "system" and "network" are used interchangeably.

[0080] (9) The information, parameters, etc. described in the present disclosure may be represented using absolute values, relative values from a predetermined value, or corresponding other information.

[0081] (10) In the above-described embodiments, the user device 10 may include a case where it is a mobile station (MS: Mobile Station). A mobile station may be referred to by those skilled in the art as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other suitable terms. Also, in the present disclosure, terms such as "mobile station", "user terminal", "user equipment (UE: User Equipment)", "terminal", etc. may be used interchangeably.

[0082] (11) In the above-described embodiments, the terms "connected" and "coupled", or any variations thereof, mean any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements "connected" or "coupled" to each other. The coupling or connection between elements may be physical, logical, or a combination of these. For example, "connected" may be read as "accessed". As used in the present disclosure, two elements can be considered to be "connected" or "coupled" to each other using at least one of one or more wires, cables, and printed electrical connections, and, as some non-limiting and non-exhaustive examples, electromagnetic energy having wavelengths in the radio frequency region, microwave region, and optical (both visible and invisible) region, etc.

[0083] (12) In the above-described embodiments, the description "based on" does not mean "only based on" unless otherwise specified. In other words, the description "based on" means both "only based on" and "at least based on".

[0084] (13) The terms "determining" and "deciding" as used in this disclosure may encompass a wide variety of operations. "Determining" and "deciding" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching in a table, database, or another data structure), and considering something as having been "determined" or "decided" based on what has been ascertained. Also, "determining" and "deciding" may include considering something as having been "determined" or "decided" based on receiving (e.g., receiving information), transmitting (e.g., transmitting information), inputting, outputting, accessing (e.g., accessing data in memory), etc. Further, "determining" and "deciding" may include considering something as having been "determined" or "decided" based on resolving, selecting, choosing, establishing, comparing, etc. That is, "determining" and "deciding" may include considering that some operation has been "determined" or "decided". Also, "determining (deciding)" may be read as "assuming", "expecting", "considering", etc.

[0085] (14) In the above-described embodiments, when the terms "include", "including" and their variants are used, these terms are intended to be inclusive, similar to the term "comprising". Further, the term "or" as used in this disclosure is not intended to be an exclusive disjunction.

[0086] (15) In this disclosure, for example, when articles are added by translation, such as a, an, and the in English, this disclosure may include that the nouns following these articles are in the plural form.

[0087] (16) In the present disclosure, the term "A and B are different" may mean "A and B are different from each other". Note that the term may also mean "A and B are each different from C". Terms such as "separate" and "coupled" may also be interpreted in the same way as "different".

[0088] (17) Each aspect / embodiment described in the present disclosure may be used alone, in combination, or switched and used during execution. Also, the notification of predetermined information (for example, the notification of "being X") is not limited to being explicitly performed, and may be performed implicitly (for example, by not performing the notification of the predetermined information).

[0089] (D: Aspects grasped from the above-described forms or modified examples) As described above in detail, it is obvious to those skilled in the art that the present disclosure is not limited to the embodiments described in the present disclosure. The present disclosure can be implemented as modified and changed aspects without departing from the spirit and scope of the present disclosure determined by the description of the claims. Therefore, the description of the present disclosure is for the purpose of illustrative explanation and has no restrictive meaning for the present disclosure. At least one of the above-described embodiments or modified examples grasps the following aspects.

[0090] The conversation control device according to the first aspect includes a setting unit, a determination unit, a voice control unit, a calculation unit, and an update unit. The setting unit sets second personality information indicating the personality of the robot according to first personality information indicating the personality of the user who converses with the robot. The determination unit determines the way of speaking and the topic of the robot based on the second personality information. The voice control unit causes the robot to output a voice uttered in the way of speaking determined by the determination unit for the topic determined by the determination unit. The calculation unit calculates a reliability indicating the strength of the user's trust in the robot based on the voice replied by the user to the utterance of the robot. The update unit updates the second personality information according to the reliability calculated by the calculation unit. According to the conversation control device according to the first aspect, the second personality information indicating the personality of the robot that converses with the user is updated according to the reliability calculated from the voice replied by the user to the utterance of the robot. That is, the conversation control device according to the first aspect can update the personality of the robot that converses with the user according to the reliability of the user in the robot estimated from the voice of the user's reply.

[0091] In an example of the first aspect (second aspect), the calculation unit may calculate the reliability based on at least one of the utterance time of the voice replied by the user, the content replied by the user, and the emotion incorporated in the voice replied by the user. The conversation control device of the second aspect can calculate the reliability based on at least one of the utterance time of the voice replied by the user, the content replied by the user, and the emotion incorporated in the voice replied by the user.

[0092] The conversation control device in an example of the first aspect or the second aspect (third aspect) may further include a generation unit that generates the first personality information by analyzing the voice of the user in the conversation between the user and another person. In the third aspect, the setting unit may set the second personality information according to the first personality information generated by the generation unit. The conversation control device of the third aspect can set the first personality information based on the voice of the user in the conversation between the user and another person.

[0093] In an example of the first, second, or third aspect (the fourth aspect), the setting unit may set the second personality information according to at least one of the purpose of use of the robot and the degree of expertise of the topic in the conversation with the user and the first personality information. The conversation control device of the fourth aspect can set the personality of the robot that converses with the user according to at least one of the purpose of use of the robot and the degree of expertise of the topic in the conversation with the user and the personality of the user.

[0094] In an example of the first, second, third, or fourth aspect (the fifth aspect), the second personality information set by the setting unit may indicate a personality opposite to the personality indicated by the first personality information. The conversation control device of the fifth aspect can set the personality of the robot that converses with the user to a personality opposite to that of the user.

Explanation of Signs

[0095] 1…Conversation system, 10…User device, 30…Robot, 40…Conversation control device, 411…Setting unit, 412…Determination unit, 413…Voice control unit, 414…Calculation unit, 415…Update unit, 416…Log generation unit.

Claims

1. A setting unit that sets second personality information indicating the personality of the robot according to first personality information indicating the personality of a user who converses with the robot; A determination unit that determines the way of speaking and topics of the robot based on the second personality information; An audio control unit that outputs to the robot an audio for uttering the determined topic in the determined way of speaking; A calculation unit that calculates a reliability indicating the strength of the user's trust in the robot based on the audio of the user's response to the robot's utterance; An update unit that updates the second personality information according to the reliability calculated by the calculation unit; A conversation control device comprising the above.

2. The calculation unit calculates the reliability based on at least one of the utterance time of the audio of the user's response, the content of the user's response, and the emotion contained in the audio of the user's response. The conversation control device according to Claim 1.

3. Further comprising a generation unit that generates the first personality information by analyzing the audio of the user in a conversation between the user and another person, The setting unit sets the second personality information according to the first personality information generated by the generation unit. The conversation control device according to Claim 1 or Claim 2.

4. The setting unit sets the second personality information according to additional information indicating at least one of the purpose of using the robot and the degree of expertise of the topic in the conversation with the user and the first personality information. The conversation control device according to any one of Claims 1 to 3.

5. The second personality information set by the setting unit indicates a personality opposite to the personality indicated by the first personality information. The conversation control device according to any one of Claims 1 to 4.

Images