JP6699010B2 - Dialogue method, dialogue system, dialogue device, and program - Google Patents

Description

  The present invention relates to a technique applicable to a robot or the like that communicates with a person, in which a computer interacts with a person using natural language.

  In recent years, research and development of robots that communicate with humans have progressed, and have been put to practical use in various fields. For example, in the field of communication therapy, there is a usage pattern in which a robot is a talking partner of a person who has a feeling of loneliness. Specifically, in a nursing home for the elderly, the robot plays a role of listening to the resident so that it can play a role of healing the loneliness of the resident and at the same time show the conversation with the robot and You can create opportunities for conversation with people around you, such as the family and caregivers. Further, for example, there is a usage mode in which a robot is a practicing partner in the field of communication training. Specifically, in a foreign language learning facility, the robot can be a foreign language learner's practice partner, so that the foreign language learning can be efficiently advanced. In addition, for example, in the application as an information presentation system, while basically speaking the dialogue between robots, by occasionally speaking to people, people can participate in the dialogue without getting bored and information can be accepted in a form that is easy for people to accept. Can be presented. Specifically, when people have too much time at a meeting place in the city, at a bus stop, at a platform at a station, or when they can afford to participate in a dialogue at home or in a classroom, news, product introduction, savings, knowledge, etc. Efficient information presentation, such as introduction and education (for example, childcare/education, general education professor for adults, moral enlightenment) can be expected. Furthermore, for example, in an application as an information collecting system, there is a usage form in which a robot collects information while talking to a person. Since it is possible to maintain a sense of dialogue through communication with the robot, it is possible to collect information without giving the sense of pressure that a person is listening. Specifically, it is expected to be applied to personal information research, market research, product evaluation, preference research for recommended products, and the like. In this way, various applications are envisioned for human-robot communication, and it is expected that a robot that more naturally interacts with the user will be realized. In addition, with the spread of smartphones, services such as LINE (registered trademark) that allows a plurality of users to chat in real time to enjoy conversations with people have been implemented. By applying the technology of conversation with a robot to this chat service, it becomes possible to realize a chat service that allows a user to more naturally interact with each other even if there is no chat partner.

  In this specification, the hardware used as a conversation partner with a user such as a robot or a chat partner used in these services, and computer software for causing a computer to function as hardware to be a conversation partner with a user are collectively referred to. I will call it an agent. Since the agent is a person who interacts with the user, the agent may be an anthropomorphic person, personified, or have a personality or individuality like a robot or a chat partner.

  The key to the realization of these services is the technology by which agents implemented by hardware and computer software can naturally interact with humans.

  As an example of the above-mentioned agent, there is a scenario dialogue system that interacts with a user about a specific topic according to a predetermined scenario. In the scenario dialogue system, it is possible to continue the dialogue as long as the dialogue develops according to the scenario. For example, the dialogue system described in Non-Patent Document 1 is a system for dialogue between a user and a plurality of agents, including interruptions by the agents and exchanges between the agents. For example, the agent functions to utter a question prepared in the scenario to the user and, if the utterance of the user's answer to the question corresponds to the option prepared in the scenario, utters the option. .. That is, the scenario dialogue system is a dialogue system in which an agent speaks based on a scenario stored in advance in the system. In this dialogue system, when the agent asks the user and receives a response from the user, he or she can play with a humorous "whispering" regardless of the content of the user's utterance, or change the topic by interrupting the agent, Even if the user's utterance deviates from the original topic, it is possible to respond so that the user does not feel the story collapse.

  In addition, as an example of the above-mentioned agent, there is a chat dialogue system in which the user and the agent have a natural dialogue when the agent speaks according to the content of the user's speech. For example, in the dialogue system described in Non-Patent Document 2, words included in the utterance of the user or the agent are more emphasized in a multi-turn dialogue performed between the user and the agent while giving more importance to the one specific to the context. It is a system that realizes chat conversation between the user and the system by using the trigger as a trigger and the system speaks according to the rules described in advance. The rules used by the chat dialogue system are not limited to those described in advance, but may be automatically generated based on the content of the user's utterance, or the user's or agent's last utterance or its utterance It may be automatically generated based on the utterance, or may be automatically generated based on the utterance including at least the utterance immediately before the user or the agent or the utterance uttered in the vicinity thereof. . Non-Patent Document 2 describes a technique of automatically generating a rule based on a word having a cooccurrence relationship or a dependency relationship with a word included in a user's utterance. Further, for example, the dialogue system described in Non-Patent Document 3 is a system in which the rule generation cost is reduced by fusing the rules manually described and the rules described by the statistical utterance generation method. Unlike the scenario dialogue system, the chat dialogue system does not allow the agent to speak in accordance with a prepared scenario. Therefore, depending on the user's speech, the agent's speech may not correspond to the user's speech. At least the content of the user's utterance, or the utterance of the user's or agent's last utterance or its vicinity, or the user's or agent's last utterance or its vicinity Agents can make utterances based on utterances. That is, the chat dialogue system includes at least the utterance content of the user, the utterance immediately before or by the user or the agent, or the utterance including at least the last utterance by the user or agent or the utterance near the utterance. It is a dialogue system in which an agent speaks based on. In these chat dialogue systems, it is possible to explicitly respond to the user's utterance.

Norihiro Arimoto, Yuichiro Yoshikawa, Hiroshi Ishiguro, “Impression Evaluation of Dialogue without Speech Recognition by Multiple Robots”, Academic Conference of the Robotics Society of Japan, 2016 Hiroaki Sugiyama, Toyomi Meguro, Ryuichiro Higashinaka, Yasuhiro Minami, “Dependency on User Utterance with Arbitrary Topic and Generation of Response Sentence Using Examples”, Journal of Japan Society for Artificial Intelligence, vol.30(1), pp. 183-194, 2015 Toyomi Meguro, Hiroaki Sugiyama, Ryuichiro Higashinaka, Yasuhiro Minami, “Construction of a dialogue system based on fusion of rule-based utterance generation and statistical utterance generation”, Proceedings of the Annual Conference of the Japan Society for Artificial Intelligence, vol. 28, pp. 1-4 ,2014

  In the conventional chat dialogue system, since it is basically one question and one answer, it is not possible to continue the dialogue in a consistent story. In the conventional scenario dialogue system, if the user's utterance is outside the range assumed in the scenario, it may not be possible to respond. Further, in the dialogue system of Non-Patent Document 1, the user may feel that his/her utterance is being swept.

  In view of the above points, an object of the present invention is to provide a dialogue technique capable of improving the responsiveness to a user's utterance and continuing the dialogue for a long time.

  In order to solve the above-mentioned problems, a dialogue method according to a first aspect of the present invention is referred to as a first dialogue system, which is a dialogue system for determining a utterance based on a pre-stored scenario. When the dialogue system that determines the utterance based on the utterance is referred to as a second dialogue system, the presentation unit presents a first presentation step of presenting an open utterance, and the input unit accepts the user's utterance for the open utterance. And a second presentation step in which the presentation unit presents the utterance determined by the second dialogue system based on the utterance of the user, and the presentation unit presents the utterance decided by the first dialogue system after the second presentation step. And a third presenting step of presenting.

  A dialogue system according to a second aspect of the present invention is a dialogue system that determines an utterance based on a pre-stored scenario is referred to as a first dialogue system, and a dialogue system that determines an utterance based on at least a utterance content of a user. When called the second dialogue system, open utterance is decided, after the open utterance, the utterance is decided by the second dialogue system based on the user's utterance for the open utterance, and after the utterance decided by the second dialogue system. The utterance determining unit that determines the utterance by the first dialogue system, the input unit that receives the utterance of the user for the open utterance, the open utterance determined by the utterance determining unit, and the utterance determining unit determines the second utterance by the second dialogue system. The presenting utterance is presented after the user's utterance, and the utterance determining unit presents the utterance determined by the first dialogue system after the utterance determined by the second dialogue system.

  A dialog device according to a third aspect of the present invention is a dialog device that determines an utterance presented by an interactive system including at least an input unit that receives an utterance of a user and a presentation unit that presents the utterance, and is stored in advance. The dialogue system that determines the utterance based on the scenario is called the first dialogue system, and the dialogue system that determines the utterance based on at least the utterance content of the user is called the second dialogue system. A utterance determination unit that determines an utterance by the second dialogue system based on the user's utterance with respect to the open utterance after the open utterance, and determines the utterance by the first dialogue system after the utterance decided by the second dialogue system.

  According to this invention, an appropriate response can be made to a user's utterance by at least a dialogue system based on the contents of the user's utterance, and thereafter, a dialogue system based on a scenario stored in advance is determined. It is possible to realize a dialogue system and a dialogue device that can give a high responsiveness to a user while giving them a sense of story, and can continue a dialogue with the user for a long time because the user can make a utterance. Becomes

FIG. 1 is a diagram illustrating a functional configuration of a dialogue system using a humanoid robot according to the first embodiment. FIG. 2 is a diagram illustrating a processing procedure of the interaction method according to the first embodiment. FIG. 3 is a diagram illustrating a functional configuration of a dialogue system using a humanoid robot according to the second embodiment. FIG. 4 is a diagram illustrating a processing procedure of the dialogue method of the second embodiment. FIG. 5 is a diagram exemplifying a functional configuration of a dialogue system using group chat according to the first embodiment.

  Hereinafter, embodiments of the present invention will be described in detail. In the drawings, components having the same function are designated by the same reference numeral, and duplicate description will be omitted.

<First embodiment>
The dialogue system of the first embodiment is a system in which a plurality of humanoid robots cooperate with each other to have a dialogue with a user. That is, the dialogue system of the first embodiment is an example in which the agent is a humanoid robot. As shown in FIG. 1, the dialogue system 10 includes an input unit 1, a voice recognition unit 2, a speech determination unit 3, a voice synthesis unit 4, and a presentation unit 5. The dialogue method of the first embodiment is realized by the dialogue system 10 performing the processing of each step described later. Note that, as shown in FIG. 1, a portion including the voice recognition unit 2, the speech determination unit 3, and the voice synthesis unit 4 of the dialogue system 10 is the dialogue device 11 of the first embodiment. The speech determination unit 3 includes an interface capable of communicating with the chat dialogue system 6 and the scenario dialogue system 7 existing outside. The chat dialogue system 6 and the scenario dialogue system 7 may be configured in the dialogue device 11 as processing units having similar functions. Note that the chat dialogue system 6 is an example of a dialogue system in which the agent utters at least based on the utterance content of the user, and the scenario dialogue system 7 is an example of a dialogue system in which the agent utters based on a scenario stored in advance. is there.

  In order to improve the responsiveness, the dialogue system 10 of the present embodiment presents the utterance determined by the chat dialogue system 6 based on the user's utterance with respect to the open utterance, and then the utterance decided by the scenario dialogue system 7 is chatted. It is presented after the utterance determined by the dialogue system 6. Since the chat dialogue system 6 determines the utterance based on at least the content of the utterance of the user, it is possible to explicitly reply to the utterance of the user. Therefore, it is possible to avoid giving the user a feeling that his or her own utterance is being swept, as compared with the case of simply hitting a hammer such as "Soka". As a result, it is possible to give the user the impression that the dialogue system 10 is seriously responding, and it is possible to continue the dialogue for a long time even in the subsequent scenario dialogue.

  The dialogue device 11 is a special program configured by reading a special program into a known or dedicated computer having, for example, a central processing unit (CPU) or a main storage device (RAM: Random Access Memory). It is a device. The dialogue device 11 executes each process under the control of the central processing unit, for example. The data input to the dialogue device 11 and the data obtained in each process are stored in, for example, the main storage device, and the data stored in the main storage device is read out as needed and used for other processes. It Further, at least a part of each processing unit of the dialog device 11 may be configured by hardware such as an integrated circuit.

  The input unit 1 is an interface for the dialogue system 10 to acquire a user's utterance. In other words, the input unit 1 is an interface for the user to input an utterance into the dialogue system 10. For example, the input unit 1 is a microphone that picks up a user's uttered voice to generate a voice signal. The input unit 1 inputs the collected voice signal of the uttered voice of the user to the voice recognition unit 2.

  The voice recognition unit 2 converts the voice signal of the user's uttered voice picked up by the input unit 1 into text representing the utterance content of the user. The voice recognition unit 2 inputs text representing the user's utterance content to the utterance determination unit 3. As a voice recognition method, any existing voice recognition technique may be used, and an optimum one may be appropriately selected according to a usage environment and the like.

  The utterance determination unit 3 communicates with the chat dialogue system 6 or the scenario dialogue system 7, and determines the text representing the utterance content from the dialogue system 10 with respect to the utterance of the user based on the input text. The utterance determination unit 3 inputs the text representing the determined utterance content to the voice synthesis unit 4.

  The voice synthesis unit 4 converts the text representing the utterance content determined by the utterance determination unit 3 into a voice signal representing the utterance content. The voice synthesizing unit 4 inputs the voice signal representing the utterance content to the presenting unit 5. Any existing voice synthesizing technique may be used as a voice synthesizing method, and an optimum one may be appropriately selected in accordance with a use environment or the like.

  The presentation unit 5 is an interface for presenting the utterance content determined by the utterance determination unit 3 to the user. For example, the presentation unit 5 is a humanoid robot that imitates the shape of a human. In this humanoid robot, for example, a voice signal representing the utterance content obtained by converting the text representing the utterance content determined by the utterance determining unit 3 into a voice signal by the voice synthesizing unit 4 is output from a speaker mounted on the head, that is, Present the utterance. When the presentation unit 5 is a humanoid robot, one humanoid robot is prepared for each personality participating in the dialogue. In the following, it is assumed that two humanoid robots 5-1 and 5-2 exist as an example in which the two personalities participate in the dialogue.

  The input unit 1 may be integrated with the presentation unit 5. For example, when the presentation unit 5 is a humanoid robot, it is possible to mount a microphone on the head of the humanoid robot and use it as the input unit 1.

  Hereinafter, the processing procedure of the dialogue method according to the first embodiment will be described with reference to FIG.

  In step S11, the humanoid robot 5-1 or 5-2 outputs a voice representing the content of the open utterance selected by the scenario dialogue system 7 or the chat dialogue system 6 from the speaker. The open utterance is an utterance that the other party can freely respond to, and is an utterance including at least one of an open question and an open comment. The open question is the so-called 5W1H (When, Where, Who, Who, What, Why, How) Is a question that can be answered. Contrary to open questions, questions with a limited range of answers, such as "Yes/No" and "A or B or C", are called closed questions. An open comment is a comment that does not require an answer, such as a rambling impression on a topic, that is, an utterance that the other party can freely comment. The text representing the content of the open utterance is determined according to the scenario selected by the scenario dialogue system 7 in response to a request from the utterance determination unit 3. The scenario dialogue system 7 may randomly select a scenario from a plurality of prepared scenarios, or may select a scenario according to a predetermined rule based on the dialogue contents up to immediately before. As a method of selecting a scenario based on the contents of the dialogue up to immediately before, for example, for a dialogue including the last five utterances, words included in each utterance, focus words forming each utterance, words included in each scenario, There is a method of selecting a scenario in which the distance between words and the focus word is shorter than a predetermined distance.

  In step S12, the microphone 1 receives the user's utterance for the open utterance. The voice recognition unit 2 performs voice recognition on the voice signal of the user's uttered voice picked up by the microphone 1, and inputs the text obtained as the voice recognition result to the utterance determination unit 3 as the text indicating the utterance content of the user.

  In step S13, the humanoid robot 5-1 outputs a voice representing the content of the chat utterance determined by the chat dialogue system 6 based on the text representing the utterance content of the user from the speaker. The text indicating the content of the chat utterance is determined by the utterance determining unit 3 using the chat dialogue system 6 based on the text indicating the utterance content of the user, which is the voice recognition result of the utterance of the user. The humanoid robot that outputs the voice that indicates the content of the chat utterance may be a humanoid robot that outputs the voice that indicates the content of the open utterance, or the humanoid robot that outputs the voice that indicates the content of the open utterance. It may be a different humanoid robot.

  In step S14, the humanoid robot 5-2 outputs a voice representing the content of the scenario utterance determined by the scenario dialogue system 7 from the speaker. Step S14 is performed after step S13. That is, the dialogue system outputs a voice indicating the content of the chat utterance determined by the chat dialogue system 6 based on the utterance of the user from the speaker, and then outputs a voice indicating the content of the scenario utterance determined by the scenario dialogue system 7 from the speaker. Output. The text representing the content of the scenario utterance is determined by the utterance determining unit 3 according to the scenario selected by the scenario dialogue system 7 in response to a request from the utterance determining unit 3. The humanoid robot that outputs the voice that indicates the content of the scenario utterance may be a humanoid robot that outputs the voice that indicates the content of the open utterance, or the humanoid robot that outputs the voice that indicates the content of the open utterance. It may be a different humanoid robot. After that, for example, the dialogue system outputs a voice representing the utterance content of the scenario utterance determined by the scenario dialogue system 7 from the speaker so that the dialogue according to the scenario is executed between the user and the dialogue system. The humanoid robot performing the following utterances may be any one humanoid robot or a plurality of humanoid robots.

  Hereinafter, a specific example of the dialogue content of the first embodiment will be shown. Here, R represents a humanoid robot, and H represents a user. The number in parentheses after R is the humanoid robot identifier. “R(1→H)” indicates that the humanoid robot 5-1 speaks with the intention of speaking to the user, and “R(1→2)” indicates that the humanoid robot 5-1 is the humanoid robot 5-. Indicates that you are speaking with the intention of speaking to 2. It should be noted that the intention of the humanoid robot to talk to may be expressed by, for example, the movement of the head or the line of sight of the humanoid robot, but may not be expressed.

R (1 → H): "What do you like about food?" (*2)
H: "I like ramen!"
R (1 → H): "I like pork bones." (*1)
R(2→1): “Because we are robots, we can't eat anything.” (*2)
R(1→2): “It can't be helped.” (*2)
R (2→1): “Soroka.” (*2)

  Here, *1 is the utterance content determined by the chat dialogue system 6. *2 is the utterance content determined by the scenario dialogue system 7. In addition, the utterance of the humanoid robot after *1 may be reversed from the uttering humanoid robot, or the person talking to may be a human being, another humanoid robot, or both a human being and another humanoid robot.

  With the above configuration, according to the dialogue technology of the present embodiment, even if the user's utterance to the open utterance is outside the scenario, the chat dialogue system can provide a response suitable for the user's utterance. , The responsiveness felt by the user is improved. This motivates the user to continue the dialogue with the system and allows the dialogue to be continued for a long time.

<Modification 1 of the first embodiment>
In the first embodiment, an example has been described in which the open utterance selected by the scenario dialogue system 7 is output from the speaker in step S11, but the open utterance output from the speaker in step S11 may be generated in any way.

  For example, the input unit 1 picks up the user's utterance performed before step S11 as a voice signal, the voice recognition unit 2 obtains text representing the user's utterance content, and the utterance determination unit 3 utters the user's utterance. Even if the chat dialogue system 6 determines the text indicating the utterance content of the open utterance based on at least the text indicating the content and the voice signal indicating the utterance content of the open utterance determined by the chat dialogue dialog system 6 is output from the speaker. Good.

<Modification 2 of the first embodiment>
In the first embodiment, an example in which a voice indicating the content of the chat conversation utterance determined by the chat dialogue system 6 based on the user's utterance in step S13 is output from the speaker, that is, one chat conversation system 6 determined in step S13 is output. Although the example of outputting the voice indicating the content of the chat utterance from the speaker has been described, the voice indicating the content of the plurality of chat utterances determined by the chat dialogue system 6 in step S13 may be output from the speaker.

  For example, in step S13, first, the humanoid robot 5-1 outputs a voice representing the content of the chat utterance determined by the chat dialogue system 6 based on the utterance of the user from the speaker, and then, the humanoid robot 5-. 2 may output from the speaker a voice representing the content of the chat utterance determined by the chat dialogue system 6 based on the utterance of the humanoid robot 5-1 output from the speaker.

<Modification 3 of the first embodiment>
Although the dialogue system 10 of the first embodiment is a system in which a plurality of humanoid robots collaborate to have a dialogue with the user, one humanoid robot performs all or part of the dialogue with the user. It may be a system. For example, the same single humanoid robot performs the open utterance in step S11, the chat utterance determined by the chat dialogue system 6 based on the user utterance in step S13, and the scenario utterance determined by the scenario dialogue system 7 in step S14. You may do it. In this case, for example, the interaction with the user after step S14 may be performed in cooperation with a plurality of humanoid robots, or may be performed by the same one humanoid robot up to step S14.

<Second embodiment>
In the second embodiment, in order to improve the user's feeling of participation in the topic, the scenario dialogue shifts to the chat dialogue, and then the chat dialogue shifts to the scenario dialogue again. By inserting the chat dialogue between the scenario dialogues, the flow of the dialogue becomes natural, and the user can be given the feeling that he or she also participates in the decision of the topic. This allows the user to continue the dialogue for a long time even in the subsequent scenario dialogue.

  As shown in FIG. 3, the dialogue system 12 of the second embodiment includes an input unit 1, a voice recognition unit 2, a speech determination unit 3, a voice synthesis unit 4, and a presentation unit 5 as in the first embodiment. Further, the dialogue control section 8 is provided. The dialogue method of the second embodiment is realized by the dialogue system 12 performing the processing of each step described later. As shown in FIG. 3, the speech recognition unit 2, the speech determination unit 3, the speech synthesis unit 4, and the dialogue control unit 8 of the dialogue system 12 are the dialogue device 13 of the second embodiment. The dialogue control unit 8 controls another processing unit included in the dialogue system 12 to execute a dialogue flow, which is a dialogue for receiving at least one utterance of the user and presenting the utterance to the user at least once.

  Hereinafter, the processing procedure of the dialogue method according to the second embodiment will be described with reference to FIG.

  In step S21, the humanoid robot 5-1 or 5-2 outputs a voice representing the content of the first scenario utterance included in the first scenario arbitrarily selected by the scenario dialogue system 7 from the speaker. The selection of the first scenario is triggered by a request from the utterance determination unit 3. The scenario dialogue system 7 may randomly select the first scenario from a plurality of prepared scenarios, or may select the first scenario according to a predetermined rule based on the contents of the previous dialogue. The method for the scenario dialogue system 7 to select the first scenario is the same as the method described in step S11 of the first embodiment.

  In step S22, the microphone 1 receives the first user utterance uttered by the user in response to the first scenario utterance. The voice recognition unit 2 voice-recognizes the voice signal of the user's utterance picked up by the microphone 1, and inputs the text obtained as the voice recognition result to the utterance determination unit 3 as the text representing the content of the first user utterance.

  In step S23, the dialogue system 12 determines whether or not the condition for switching from the scenario dialogue to the chat dialogue is satisfied. If it is determined that the conditions are satisfied, the process proceeds to step S24. If it is determined that the conditions are not satisfied, the process returns to step S21 and the processes of steps S21-S22 are executed again.

  The condition for switching from the scenario dialogue to the chat dialogue is, for example, A1. When all the dialogues according to the first scenario are completed, A2. For example, the case where the progress of the first scenario fails. The case where the scenario has failed is, for example, A2-1. When the utterance of the user after uttering to the user is not included in the expected range of the scenario dialogue system, A2-2. For example, it may be recognized that the behavior of the user with respect to the ongoing scenario has reduced the intention not to talk about the scenario or the user's willingness to interact with the scenario. In addition, a case in which the case of A2-1 and the case of A2-2 are combined and the reaction of the user is poor after the user speaks to the user is also included. When the utterance of the user is not included in the expected range of the scenario dialogue system, for example, the utterance of the user matches the utterance determined by the scenario dialogue system with respect to the utterance of the user based on the scenario stored in advance. If not. User behavior also includes non-verbal signals, paralinguistic signals (including information between them), and so on. The case where the user's reaction is not good includes the case where the user's behavior recognizes the intention not to speak, or the case where the user's motivation to interact is recognized. For example, if the user issues a certain predetermined phrase (for example, "This story, I just mentioned this."), you can talk about the topic. You can judge that it represents your unwillingness.

  In step S24, the humanoid robot 5-1 or 5-2 outputs a voice representing the content of the chat utterance determined by the chat dialogue system 6 based on the text representing the content of the first user utterance from the speaker. The humanoid robot that outputs the voice that represents the content of the chat utterance may be the humanoid robot that outputs the voice that represents the content of the last utterance among the one or more utterances based on the first scenario, or the last one. It may be a humanoid robot different from the humanoid robot that has output the voice indicating the content of the utterance.

  The text representing the content of the chat conversation is based on the text representing the content of the utterance sequence, which is the speech recognition result of the utterance sequence of the humanoid robot and the user during the dialogue in the first scenario by the utterance determining unit 3, based on the text indicating the chat conversation. It is determined using the system 6. The range of the utterance sequence input to the chat dialogue system 6 may be limited to the immediately preceding utterance, a part or all of the first scenario, or the chat dialogue or the scenario dialogue performed before the first scenario. All may be included. The first utterance when switching to the chat dialogue may be set in advance for each scenario. For example, it may be possible to prepare a question such as “what do you like other than eating?” after a scenario of talking about food.

  In step S25, the microphone 1 receives the second user utterance uttered by the user in response to the chat utterance. The voice recognition unit 2 voice-recognizes the voice signal of the second user's utterance picked up by the microphone 1, and inputs the text obtained as the voice recognition result to the utterance determination unit 3 as the text representing the content of the second user's utterance. .

  In step S26, the dialogue system 12 determines whether or not the condition for switching from the chat dialogue to the scenario dialogue is satisfied. If it is determined that the conditions are satisfied, the process proceeds to step S27. If it is determined that the conditions are not satisfied, the process returns to step S24, and the processes of steps S24-S25 are executed again.

  The condition for switching from the chat dialogue to the scenario dialogue is, for example, B1. When it becomes difficult to continue the chat dialogue, B2. This may be the case when it becomes possible to select the next scenario with sufficient confidence through chat conversation. When it is difficult to continue the chat dialogue, for example, B1-1. When the utterance of the user after uttering the user is not included in the expected range of the chat dialogue system, B1-2. If it is recognized that the behavior of the user with respect to the ongoing chat dialogue has reduced the intention not to talk about the scenario or the user's motivation for dialogue, B1-3. There is a case where the following scenario cannot be selected with sufficient reliability and the chat conversation is repeated a predetermined number of times. In addition, a case in which the case of B1-1 and the case of B1-2 are combined and the reaction of the user is not favorable after speaking to the user is also included. The case of B1-3 can be combined with the case of B1-1 and/or the case of B1-2, for example, when the utterance of the user is not included in the expected range of the chat dialogue system and/or from the behavior of the user. It may be configured such that it is determined that it is difficult to continue the chat dialogue when the intention to not talk is recognized repeatedly a predetermined number of times. The case where the user's utterance is not included in the expected range of the chat dialogue system is, for example, a case where the user's utterance does not match the utterance determined by the chat dialogue system at least based on the user's utterance. User behavior also includes non-verbal signals, paralinguistic signals (including information between them), and so on. The case where the user's reaction is not good includes the case where the user's behavior recognizes the intention not to speak, or the case where the user's motivation to interact is recognized. The recognition of the intention not to speak and the decline in the willingness to talk can be cited, for example, when the user issues a predetermined specific phrase (for example, "This story, I just spoke.").

  When switching to the scenario dialogue, while accepting the utterance of the user immediately before with a sledgehammer such as "Sokka", insert a space immediately before the first utterance and change the topic such as "By the way", "Yes so", "Hey" It is recommended that the utterance indicating that the user is trying to do so is uttered by a humanoid robot different from the humanoid robot uttered at the end of the chat dialogue. As a result, it is possible to reduce the discomfort caused by the discontinuity of topics. At this time, the uttered content may be changed according to the reliability when the next scenario is selected. Here, the reliability of selection is an index indicating the degree of similarity between the content of the chat conversation and the selected scenario. For example, if the reliability of the selection is relatively high, a short utterance such as “Yes,...” is inserted, and if the reliability of the selection is relatively low, “By the way, it may not be relevant at all. It is conceivable to utter content that explicitly indicates that the topic will change, such as "No, but...". As a specific example when the reliability of the selection is low, for example, after uttering “eating ramen” in the chat dialogue, talking about “management of restaurant” in the scenario dialogue This may be the case when the similarity between terms is low. In addition, for example, after talking about “I don't like sports” in the chat dialog, and then talking about “skiing” in the scenario dialog, although the topic similarity is high, the user rejects the topic. There are cases where it is target. Furthermore, for example, when there is an utterance about "drug" in a chat dialogue and it is not possible to distinguish whether it is a topic of mouse drag or a topic of drug drag, the topic word is a polysemous word and was uttered in any sense. There are cases where it is not possible to determine whether or not.

  In step S27, the humanoid robot 5-1 or 5-2 outputs a voice representing the content of the second scenario utterance included in the second scenario selected by the scenario dialogue system 7 from the speaker. The selection of the second scenario is triggered by a request from the speech determination unit 3. If the scenario dialogue is switched to the chat dialogue before the completion of the first scenario in step S23, the remaining part of the first scenario may be the second scenario. After that, the dialogue according to the second scenario is executed between the user and the dialogue device.

  The scenario dialogue system 7 selects the second scenario in accordance with a predetermined rule based on the content of the chat dialogue conducted in steps S24 and S25. Since it is considered that the utterance during the chat dialogue includes words and phrases that represent topics that the user may be interested in, a scenario regarding an appropriate topic can be selected as the second scenario by using these as clues. For example, a keyword representing a topic is set in each scenario, and the scenario is selected according to the similarity between the keyword and one or both of the utterance of the humanoid robot and the user's utterance during chat conversation. Further, for example, when the sentence generated by the chat dialogue system 6 for the user's utterance is similar to the head sentence of any scenario, that scenario is selected.

  If the utterance during the chat dialogue cannot be used as a clue and it is determined that it is difficult to continue the dialogue, the second scenario is randomly selected from a plurality of scenarios prepared in advance. In this case, the selection probability may be set for each scenario when preparing the scenario in advance. That is, it is not always necessary to perform uniform random selection. Further, the selection probability may be weighted based on the degree of similarity calculated from the observation information so far.

  Each step in the dialogue method of the second embodiment is executed under the control of the dialogue control unit 8. The dialogue control unit 8 presents the content of the first scenario utterance based on the first scenario determined by the scenario dialogue system 7 and the step S22 of accepting the first user utterance uttered by the user in response to the first scenario utterance. And a step S24 of presenting the contents of the chat utterance determined by the chat dialogue system 6 based on the user's utterance, and the second user utterance made by the user in response to the chat utterance. By executing the control for executing the step S25 of accepting the step S25 and the second dialog flow for executing the step S25 one or more times, the dialog method of the second embodiment is realized.

  Hereinafter, a specific example of the dialogue content of the second embodiment will be shown. Here, R represents a humanoid robot, and H represents a user. The number in parentheses after R is the humanoid robot identifier. Similar to the first embodiment, the intention of the humanoid robot to talk to may be expressed by, for example, the movement of the head or the line of sight of the humanoid robot, but it is not necessary to express it. Good.

R(1→2): “What do you like for food?” (*1: The utterance content decided based on the first scenario selected by the scenario dialogue system 7)
R (2→1): “I like sushi.” (*1: The utterance content determined based on the first scenario selected by the scenario dialogue system 7)
H: "This story was done a while ago." (* A2-2. A specific example of "A2-2. When the user's behavior with respect to a scenario in progress recognizes the intention not to talk about the scenario".)
R (1→H): “What do you like other than eating?” (*1: Specific utterances included in the first scenario selected by the scenario dialogue system 7 based on the previous dialogue content “food”. This is an example.)
H: "Is it a book?"
R (1→H): “What is your favorite book genre?” (*2: This is a specific example of the utterance determined by the chat dialogue system 6 based on the “reading” of the user utterance.)
H: “I like sports manga”
R(2→H): “Do you do sports well?” (*2: This is a specific example of repeating chat dialogue multiple times. Here, chat dialogue system 6 determines the utterance content based on the user's utterance “sport”. is doing.)
H: "I don't really like sports."
R(2→H): “Soka” (*3: “B1-2. When the user's behavior with respect to ongoing chat dialogue recognizes the intention not to talk about the scenario”, it is difficult to continue the chat dialogue. It is a specific example of the case where it is judged that it is difficult for the user to continue the chat dialogue because the user denied the topic "I don't like much." .)
R (1→2): “By the way, I've skied the other day” (*3: First, I utter “Say,” which means that I'm trying to change the topic, and then in the chat dialogue The utterance included in the second scenario selected by the scenario dialogue system 7 is based on the content "sports".)
R (2→1): "Isn't it difficult to ski with that body?" (*3: The utterance included in the second scenario selected by the scenario dialogue system 7 based on "sports" that was the content of the chat dialogue. This is a specific example.)

  With the above configuration, according to the dialogue technology of the present embodiment, after a certain scenario dialogue is finished, the topic of the next scenario dialogue is determined according to the content of the chat dialogue, so that the user can participate in the dialogue. Feeling improves. This motivates the user to continue the dialogue with the dialogue system and allows the dialogue to be continued for a long time.

<Modification>
In the above-described embodiment, an example in which a robot is used as an agent to perform a dialogue by voice has been described. However, even if the robot of the above-described embodiment is a humanoid robot having a body or the like, it is a robot having no body or the like. It may be. Further, the dialogue technology of the present invention is not limited to these, and it is also possible to adopt a form in which dialogue is performed using an agent that does not have a physical body such as a humanoid robot and does not have a vocalization mechanism. As such a form, for example, a form in which an agent displayed on the screen of a computer is used for dialogue is mentioned. More specifically, in a group chat, such as "LINE" (registered trademark) and "2 channel" (registered trademark), in which a plurality of accounts interact by text messages, the user's account and the dialog device account interact with each other. It is also possible to apply to the form which performs. In this form, the computer having the screen displaying the agent needs to be in the vicinity of a person, but the computer and the dialogue device may be connected via a network such as the Internet. That is, the present dialogue system is applicable not only to a dialogue in which a speaker such as a human and a robot actually face each other but also to a conversation in which the speakers communicate with each other via a network.

  As shown in FIG. 5, the dialogue system 20 of the modified example includes an input unit 1, a speech determination unit 3, and a presentation unit 5. In the example of FIG. 5, the dialogue system 20 of the modification includes one dialogue device 21, and the dialogue device 21 of the modification includes the input unit 1, the speech determination unit 3, and the presentation unit 5. The utterance determination unit 3 includes an interface capable of communicating with the chat dialogue system 6 and the scenario dialogue system 7 existing outside. The chat dialogue system 6 and the scenario dialogue system 7 may be configured in the dialogue device as processing units having similar functions.

  The interaction device of the modification is, for example, a mobile terminal such as a smartphone or a tablet, or an information processing device such as a desktop or laptop personal computer. Hereinafter, it is assumed that the interactive device is a smartphone. The presentation unit 5 is a liquid crystal display included in the smartphone. A window of the chat application is displayed on the liquid crystal display, and the conversation contents of the group chat are displayed in time series in the window. Group chat is a function in which a plurality of accounts in a chat post text messages with each other to develop a dialogue. It is assumed that a plurality of virtual accounts corresponding to the virtual personality controlled by the dialogue device and the user's account participate in this group chat. That is, the present modification is an example of a case where the agent is a virtual account displayed on the liquid crystal display of the smartphone which is the interactive device. The user can input the utterance content to the input unit 1 using the software keyboard and post it to the group chat through his/her own account. The utterance determining unit 3 inputs the posting from the user's account into the chat dialogue system 6 or the scenario dialogue system 7, and posts the utterance content obtained from each dialogue system to the group chat through each virtual account. It is also possible to adopt a configuration in which the user inputs the utterance content to the input unit 1 by uttering, using a microphone and a voice recognition function mounted on the smartphone. Further, the speaker and the voice synthesizing function mounted on the smartphone may be used to output the utterance content obtained from each dialogue system from the speaker as a voice corresponding to each virtual account.

  When the utterances of the agent are simultaneously displayed on the presentation unit 5 (display), it may be possible to feel that the conversation is active or lively, but the user cannot read it all at once. When a large amount of text is presented, it may be difficult for the user to continue the dialogue, so depending on the usage situation, such as a situation where the user does not impose a cognitive load or a situation where a calm atmosphere is required. Utterances may be sequentially displayed. In addition, when displaying sequentially, you may open and display a predetermined time interval. The time interval may be fixed or variable.

  Although the embodiments of the present invention have been described above, the specific configuration is not limited to these embodiments, and even if the design is appropriately changed without departing from the spirit of the present invention, Needless to say, it is included in the present invention. The various kinds of processing described in the embodiments may be executed not only in time series according to the order described, but also in parallel or individually according to the processing capability of the device that executes the processing or the need.

[Program, recording medium]
When various processing functions of the dialog device described in the above embodiment are realized by a computer, processing contents of functions that the dialog device should have are described by a program. Further, when various processing functions in the dialog system described in the above modification are realized by a computer, processing contents of functions that the dialog system should have are described by a program. By executing this program on a computer, various processing functions of the dialog device and dialog system are realized on the computer.

  The program describing the processing contents can be recorded in a computer-readable recording medium. The computer-readable recording medium may be, for example, a magnetic recording device, an optical disc, a magneto-optical recording medium, a semiconductor memory, or the like.

  The distribution of this program is performed by, for example, selling, transferring, or lending a portable recording medium such as a DVD or a CD-ROM in which the program is recorded. Further, the program may be stored in a storage device of a server computer and transferred from the server computer to another computer via a network to distribute the program.

  A computer that executes such a program first stores, for example, the program recorded on a portable recording medium or the program transferred from the server computer in its own storage device. Then, when executing the process, this computer reads the program stored in its own storage device and executes the process according to the read program. As another execution form of this program, a computer may directly read the program from a portable recording medium and execute processing according to the program, and the program is transferred from the server computer to this computer. Each time, the processing according to the received program may be sequentially executed. In addition, the above-described processing is executed by a so-called ASP (Application Service Provider) type service that does not transfer the program from the server computer to this computer but realizes the processing function only by executing the instruction and obtaining the result. May be Note that the program in this embodiment includes information that is used for processing by an electronic computer and that conforms to the program (such as data that is not a direct command to a computer but has the property of defining computer processing).

  Further, in this embodiment, the present apparatus is configured by executing a predetermined program on the computer, but at least a part of the processing content may be implemented by hardware.

Claims (5)

A method of interaction with a user using a plurality of virtually set personalities,
When a dialogue system that determines an utterance based on a pre-stored scenario is called a first dialogue system, and a dialogue system that determines an utterance based on at least a user's utterance content is called a second dialogue system,
The presenting unit presents an open utterance in a first presenting step,
An utterance receiving step in which the input unit receives a user's utterance for the open utterance,
A second presentation step in which the presentation unit presents the utterance determined by the second dialogue system based on the utterance of the user,
A third presentation step in which the presentation unit presents the utterance determined by the first dialogue system after the second presentation step,
Only including,
The first presentation step is to present the open utterance with a first personality of the plurality of personalities,
The utterance determined by the second dialogue system is a plurality of utterances,
The second presentation step is to present the plurality of utterances determined by the second dialogue system by a personality including at least a second personality different from the first personality among the plurality of personalities. ,
The utterance determined by the first dialogue system is a plurality of utterances,
In the third presentation step, a plurality of utterances determined by the first dialogue system are presented by the first personality and the second personality of the plurality of personalities in cooperation with each other.
How to interact. An interactive system for interacting with a user using a plurality of virtually set personalities,
When a dialogue system that determines an utterance based on a pre-stored scenario is called a first dialogue system, and a dialogue system that determines an utterance based on at least a user's utterance content is called a second dialogue system,
The open utterance is determined, the utterance is determined by the second dialogue system based on the user's utterance for the open utterance after the open utterance, and the utterance is determined by the first dialogue system after the utterance decided by the second dialogue system. An utterance decision unit that decides,
An input unit that receives a user's utterance for the open utterance,
The utterance determination unit presents the open utterance determined, the utterance determination unit presents the utterance determined by the second dialogue system after the utterance of the user, and the utterance determination unit uses the first dialogue system. A presentation unit that presents the determined utterance after the utterance determined by the second dialogue system,
Only including,
The utterance determined by the utterance determination unit by the second dialogue system is a plurality of utterances,
The utterance determined by the utterance determination unit by the first dialogue system is a plurality of utterances,
The presenting unit presents the open utterance with a first personality of the plurality of personalities, and presents a plurality of utterances determined by the second dialogue system with the first personality of the plurality of personalities. Presented by a personality including at least a second personality different from the personality, a plurality of utterances determined by the first dialogue system, the first personality and the second personality of the plurality of personalities are It is a collaborative presentation.
Dialog system. An input unit for accepting a user's speech, at least seen including a presentation unit that presents the speech, in an interactive apparatus for determining utterance interactive system presents to perform a dialogue with the user by using a plurality of personality that is virtually set There
When a dialogue system that determines an utterance based on a pre-stored scenario is called a first dialogue system, and a dialogue system that determines an utterance based on at least a user's utterance content is called a second dialogue system,
The open utterance is determined, the utterance is determined by the second dialogue system based on the user's utterance for the open utterance after the open utterance, and the utterance is determined by the first dialogue system after the utterance decided by the second dialogue system. speech determining unit determining seen including,
The utterance determined by the utterance determination unit by the second dialogue system is a plurality of utterances,
The utterance determined by the utterance determination unit by the first dialogue system is a plurality of utterances,
The presenting unit presents the open utterance with a first personality of the plurality of personalities, and presents a plurality of utterances determined by the second dialogue system with the first personality of the plurality of personalities. Presented by a personality including at least a second personality different from the personality, a plurality of utterances determined by the first dialogue system, the first personality and the second personality of the plurality of personalities are It is a collaborative presentation.
Dialogue device. A program for causing a computer to execute each step of the interaction method according to claim 1 . A program for causing a computer to function as the dialog device according to claim 3 .

Images