JP4370410B2 - Dialog system, dialog robot, program, and recording medium - Google Patents

Description

  The present invention relates to a dialogue robot that performs voice conversation with a user in cooperation with a life support robot system that autonomously controls an appliance to support the life of the user, and the life support robot system and the dialogue robot It is related with the dialogue system provided with.

With a ubiquitous environment as a background, a life support robot system that is installed in a user's living space or the like and autonomously supports the user's life has been realized. A life support robot system based on a ubiquitous environment is often an unconscious system that does not require a user to be particularly aware of the operation.
The unconscious lifestyle support robot system infers the environment and user behavior based on various sensor information to maintain a comfortable environment and support user activities, and connects the appliances (communication functions with communication functions). It provides services by controlling home appliances), information terminal devices, and the like.
For example, if the life support robot system infers that the user is in a relaxed state by analyzing the motion / posture of the user and the situation of the room based on the sensor information, the audio system that is one of the appliances will make the user's preference. The user can enjoy a comfortable living environment without having to consciously operate these appliances by playing music suitable for music or maintaining indoor temperature and humidity with an air conditioner.
The unconscious life support robot system is convenient in that the user does not need to consciously operate the appliance. However, it is expected that the service provided by the life support robot system by autonomous control may not always be accepted by the user.
The life support robot system is expected to support the whole of life, and the provided service will become more sophisticated and multifunctional, and the operation principle of the appliance will be complicated. Therefore, there is a possibility that it may not be possible to respond to individual user requests only by autonomous control of the life support robot system.
In addition, the mechanism of the life support robot system that is unconscious, that is, does not require a conscious operation from the user, makes it difficult to recognize the existence of the system, which may cause the user to feel weird. sell.
For example, even if the service that the life support robot system autonomously executes is comfortable for one user, the situation in which it becomes uncomfortable for another user, or the service that is executed is annoying for the user. It is expected that a situation will occur. In such a case, the life support robot system needs to resolve such dissatisfaction and questions because there is a request that the user wants to execute a different service or knows the reason for the service execution. There is.
Furthermore, there are cases where the user wants to know about matters other than the information stored in the life support robot system. For example, when the user himself / herself wants to operate the appliance, a situation may occur in which the user cannot operate the appliance so that the advanced functions of the appliance can be fully used. In such a case, since the user wants to know detailed information that is not covered by the life support robot system, it is necessary to provide such information in the dialog robot.
In this way, the unconscious life support robot system has a high level of situation handling capability as a universal user interface that can flexibly deal with various situations, and the user's familiarity. It is necessary to provide a simple dialogue system.
The present invention has been made in view of such a need. The purpose of the present invention is to more accurately receive a user's ambiguous request as a user interface of a life support robot system and reflect it in the control of the system. An interactive robot capable of providing services and information useful to the user and an interactive system using the interactive robot so that the control situation can be understood more accurately.

In order to achieve the above object, the present invention realizes an interactive system having a high situation response capability in which a life support robot system and an interactive robot cooperate. In addition, the user interface of the interactive system is realized by a visible interactive robot that can be recognized as an entity by the user, thereby realizing a user-friendly interface.
The present invention provides a life support robot system that autonomously controls an appliance that executes a service to support a user's life, and a dialog system that interacts with the user by the voice of a dialog robot in cooperation with the life support robot system. It is.
The life support robot system constituting the dialogue system includes: 1) an inference system that controls an appliance by inferring an environment in the space and a user's action based on sensor information measured in a predetermined space; 2) A distributed environment behavior database for accumulating environment information and behavior information as inference results by the inference system.
The dialogue robot 1) dialogue strategy database that stores associative information describing the degree of association between concepts; and 2) the robot utterance data generated in the dialogue robot is converted into voice data and uttered. Speech synthesis means, 3) speech recognition means for recognizing the contents of the user's voice data and converting it into user utterance data, and 4) obtaining the environment information and behavior information from the distributed environment behavior database and storing them in the situation storage means 5) Analyzing a user situation from the environment information and behavior information, selecting a service to be provided to the user based on the situation, and relating to the situation based on the association information A process of identifying a concept and generating robot utterance data using a linguistic expression indicating the concept, and a user for the robot utterance data Dialogue control means for inferring a context of utterance data and performing a process of determining whether or not the context of the user utterance data is conceptually related to the context of the robot utterance data with reference to the association information; 6) Execution requesting means for transmitting an execution request for the service to the life support robot system or the appliance when the dialog control means determines that the context of the user utterance data is related to the context of the robot utterance data. Is provided.
Dialogue robots store associative information used to generate dialogues based on the “associative interaction” behavioral hypothesis, in order for the dialogue robots to participate in and ask questions of users and to draw users into their own dialogues. A dialogue strategy database is provided. Further, the dialogue robot acquires the environment information and the action information from the distributed environment action database of the life support robot system by the situation information acquisition means, and stores it in the situation storage means.
The dialog control means of the dialog robot analyzes the user's situation from the environment information and the behavior information, and selects a service to be provided to the user based on the situation. In addition, a concept related to the situation is specified based on association information in the dialogue strategy database, and robot utterance data is generated using a language expression indicating the concept. Then, the speech synthesizer converts the generated robot utterance data into speech data and utters the speech.
Thereafter, the voice recognition means recognizes the content of the user's voice data and converts it into user utterance data. The dialogue control means infers the context of the user utterance data with respect to the robot utterance data, and refers to the association information to determine whether the context of the user utterance data is conceptually related to the context of the robot utterance data. judge. When it is determined that the context of the user utterance data is related to the context of the robot utterance data, the service execution request is transmitted to the life support robot system or the appliance.
As a result, in the interactive system, the interactive robot makes a voice inquiry to allow the user to recognize and provide the service selected based on the user's situation, and the user's response is drawn into the dialog with the robot. In this case, by transmitting a service execution request to the life support robot system or the appliance, the latent service can be provided to the user.
Alternatively, the interactive robot recognizes the contents of the user's voice data by voice recognition means and converts the contents into user utterance data. The dialog control means analyzes the context of the user utterance data, analyzes the situation from the environment information and behavior information, selects a service to be provided to the user based on the context and situation of the user utterance data, Based on association information, a concept related to the context of the user utterance data is specified, and robot utterance data is generated using a linguistic expression indicating the concept. Then, the speech synthesizer converts the generated robot utterance data into speech data and utters the speech.
Thereafter, the voice recognition means recognizes the contents of the user's voice data with respect to the robot utterance data and converts it into user utterance data. Then, the dialog control means infers the context of the new user utterance data with respect to the robot utterance data, and the context of the new user utterance data is conceptually related to the context of the robot utterance data with reference to the association information. It is determined whether or not. When it is determined that the context of the new user utterance data is conceptually related to the context of the robot utterance data, the service execution request is transmitted to the life support robot system or the appliance.
Thus, in the interactive system, in order to provide the user with a service selected based on the context of the user's conversation and the user's situation, the user's conversation is interrupted by voice, and the user's response is a dialogue with the robot. In the case of being drawn into the service, by sending a service execution request to the life support robot system or the appliance, the ambiguous service can be provided to the user.
Further, the interactive robot of the interactive system includes a knowledge database that accumulates knowledge information about the appliance or a service executed on the appliance when the above configuration is adopted, and the dialog control means has a context of the user utterance data. When it is determined that it is related to the context of the robot utterance data, knowledge information about the selected service is extracted from the knowledge database, and robot utterance data is generated using the extracted knowledge information.
Further, when the dialog robot of the dialog system has the above-described configuration, the knowledge robot acquires knowledge information about the selected service from another information providing server on the network using a predetermined communication protocol, and stores the knowledge information in the knowledge database. Information acquisition means is provided.
Thereby, in relation to the provision of the service, it becomes possible to provide the user with knowledge information about the service and the appliance that executes the service.
In addition, the dialog robot of the dialog system includes an inter-robot communication unit that transmits and receives information on the user's situation and the selected service with a predetermined communication protocol as a service selected by the dialog control unit. .
As a result, the dialogue robots can cooperate to provide a service to the user.
In this way, when there is a situation in which the user feels doubtful or dissatisfied with the autonomous control of the unconscious lifestyle support robot system, the visible interactive robot is By recognizing uncertain questions and dissatisfaction and asking the user, the reason for control can be obtained from the life support robot system and explained to the user. The user can eliminate the eerieness and dissatisfaction specific to the autonomous operation of the life support robot system.
In addition, when the user has an ambiguous request or a potential request, the interactive robot may advance the dialog with the user and notice that the life support robot system can respond to the potential request. it can. Furthermore, the user's ambiguous request can be materialized, and the life support robot system can be requested to execute the service. Thereby, the user life support robot system can realize more flexible and advanced service control.
In particular, according to the present invention, a natural interface that does not give the user a sense of incongruity is realized by conducting a conversation between the user and the unconscious life support robot system through a visible interactive robot that the user can recognize as an entity. can do.
Furthermore, according to the present invention, it is possible for a plurality of users such as family members who share a life support robot system to interact simultaneously with the conversation robot. Users share a topic with a visible interactive robot as a medium, which helps to resolve the individual user's sense of isolation with respect to the life support robot system.

FIG. 1 is a diagram showing a configuration in an embodiment of the dialogue system of the present invention.
FIG. 2 is a diagram showing a configuration example of a life support robot system and a dialogue robot.
FIG. 3 is a diagram showing a configuration example of a distributed environment behavior database.
FIG. 4 is a diagram showing an example of the processing flow of the interactive robot when a service is selected from the user's conversation.
FIG. 5 is a diagram showing an example of the processing flow of the interactive robot when a service is selected from the user's situation.
FIG. 6 is a diagram showing an example of the processing flow of the interactive robot when providing knowledge information related to a service from a user's conversation.

Examples of the present invention will be described below.
FIG. 1 is a diagram showing a configuration example of an interactive system according to the present invention. In this embodiment, the dialogue system is an unconscious life support robot system (hereinafter referred to as a robot system) applied to a family house (residential space) composed of a plurality of users 3 (3a, 3b, 3c). 1) and a visible interactive robot 2.
The robot system 1 uses the ubiquitous environment, monitors the entire living space, executes a service by the home appliance (appliance) 4 having a communication function, and autonomously supports the life of the user 3.
The dialogue robot 2 is installed in the living space of the user 3. The interactive robot 2 may be configured to be able to move freely in the living space of the user 3 with a function that can move autonomously.
In addition, the dialogue robot 2 has only one entity as a system, but may have a plurality of cases having processing units having the same configuration. The casing is set to a size that can be installed on a table, for example. When the interactive robot 2 has a plurality of housings, the processing means in the housing that detects the voice data among the interactive robots 2 installed in each room in the living space starts a processing operation as the interactive robot 2. . If the user who will interact with the user moves or needs to interact with a user at a distant location while the process continues, the chassis set closest to the partner The processing means takes over the processing so that the flow of one processing operation can be linked by a plurality of cases.
The dialogue system of the present invention is intended to achieve distributed cooperation between the unconscious lifestyle support robot system 1 and the visible dialogue robot 2. Such distributed collaboration can be compared to a metaphor of the relationship between mother and child.
The entire living space of the user in which the unconscious lifestyle support robot system 1 is incorporated is referred to as a “mother metaphor”. In other words, it's like being in the house, watching over your family, appearing out of nowhere when you need it, and casually supporting your family. The dialogue robot 2 that handles the dialogue with the user 3 is referred to as a “child metaphor”. Although the conversation robot 2 does not have general social common sense, it can understand to some extent the preferences of specific users who share a small living environment such as a home, and the relationship between users. It can be compared to a person who wants to be teased and who is interested in it.
The child metaphor interactive robot 2 works with the mother metaphor life support robot system 1 in order to facilitate the relationship between the user 3 and the life support robot system 1 that is like a mother to the user. It is thought that it will play the role of the “youngest child” so that the presence of the mother can be felt closely by participating actively.
The naturalness of the human interface by the voice of the dialogue robot 2 is based on the natural language processing ability in voice recognition. However, there are cases where the voice recognition capability is not sufficient to continue the conversation with the user 3 naturally. Therefore, it is necessary for the user 3 to be able to understand that the dialogue robot 2 has poor dialogue ability as a firm mental model. Therefore, giving the knowledge of the field of cognitive science, educational psychology and developmental psychology as a reference, an affordance of about the capacity of a three-year-old child is given to the dialogue ability of the dialogue robot 2. To that end, we adopted the “associative chatter” behavior hypothesis in dialogue control.
“Associative Shiritori” means responding by using a linguistic expression indicating another concept conceptually related to the context of the spoken sentence in conversation, and then conceptually with the context of the response sentence (uttered sentence) to this response sentence. It is a behavioral hypothesis that continues the act of responding using a linguistic expression indicating another related concept.
That is, the behavior of an infant who tries to interrupt a conversation by capturing a word that matches his knowledge from the conversation of an adult is routinely observed. At this time, the infant tries to attract adults to his / her topic by providing a topic from his / her knowledge while making full use of association and reasoning. And when the reaction of the adult is the content that received the topic that I provided, in other words, when it is a ritual in an associative sense, it is judged that the topic has been successfully drawn, and my knowledge Will continue to talk about it.
In this example, while the affordance of the dialogue robot 2 is positioned as being about 3 years old and dialogue control is performed, information provided to the user 3 includes specialized information such as manual information of the appliance 4 and detailed information on services, for example. Be able to provide information. The dialogue robot 2 accumulates situation information regarding the situation of the user's living space, knowledge information in a knowledge database, information acquired from an external information server, etc., and the user 3 was not aware of the subject according to the subject of the user's dialogue. It becomes possible to provide specialized knowledge about the situation and the appliance 4. As a result, a so-called “nerd” existence is formed as an affordance of the dialogue robot 2.
Thus, the dialogue robot 2 makes it easy to give the user 3 an image of being “friendly and useful”.
FIG. 2 is a diagram showing a configuration example of the life support robot system 1 and the dialogue robot 2.
The robot system 1 includes an inference system 11, a sensor 12, a distributed environment behavior database 13, an event detection device 15, a service history database 17, and the like.
The inference system 11 includes a knowledge database. When the event detection device 15 detects an event, the inference system 11 obtains a context from the distributed environment behavior database 13, and the environment in the living space, the operation of the user 3, and the interaction between the users 3 ( It is a processing system that analyzes the interaction between the user 3 and the object, infers the user's action from the analysis result, determines the service to be executed according to the conclusion, and controls the corresponding appliance 4. Analysis results and inference results in the inference system 11 are accumulated in the distributed environment behavior database 13 as needed.
The sensor 12 is a processing unit that has a communication function, measures and collects various data in the living space of the user 3, and transmits the collected sensor information to the distributed environment behavior database 13. The sensor 12 is, for example, a TV camera, a microphone, a floor sensor, an RFID tag monitor, an internal sensor of the appliance 4, or the like.
The sensor information is data such as image data, sound data, pressure transition data, ID tag data, and the like. Assume that an ID tag, for example, an RFID (Radio Frequency Identification) tag, in which identification information for non-contact radio wave system recognition is stored, is attached to an object owned by the user 3 or an object existing in the living space.
The distributed environment behavior database 13 is a database system that accumulates and manages sensor information acquired from the sensor 12 and results analyzed or inferred by the inference system 11.
FIG. 3 shows a configuration example of the distributed environment behavior database 13.
The distributed environment behavior database 13 includes a distributed sensor information database 131, a distributed environment information database 132, a distributed operation information database 133, a distributed behavior information database 134, a person-object interaction database 135, a person-person interaction database 136, a unique information database 137, and the like. Consists of a database system.
The distributed sensor information database 131 is a database that accumulates various types of sensor information transmitted from the sensor 12 at a predetermined time or opportunity.
The distributed environment information database 132 is a database that accumulates environment information such as the position, posture, temperature and humidity of the living space, and the internal state of the appliance 4.
For example, when the user 3x is reading a book toward the study desk, sensor information (time, ID data, position, image data, pressure data, internal sensor information of the service execution unit, etc.) measured by the sensor 12 is stored. Analyzed by the inference system 11, the following environmental information is generated and accumulated.
"Time, book ID data, position, state (state held in hand),
Time, study desk lamp ID data, position, status (lit),
Time, study desk chair ID data, position, status (in use), ... "
The distributed motion information database 133 is a database that accumulates motion information indicating the position, posture, etc. of the user 3. For example, in the case of the above example, sensor information is analyzed by the inference system 11 and the following operation information is accumulated.
“Time, user 3x ID data, position, posture (sitting),...”.
The person-object interaction database 135 is a database that accumulates person-object interaction information. The person-object interaction information is information indicating a combination of a user and an object in which an interaction occurs. For example, in the case of the above example, the inference system 11 analyzes the environment information and the operation information, and the following person-object interaction information is accumulated.
"People-things interaction 0001: user 3x, books, study desk, study desk chair, electric light ..."
The person-person interaction database 136 is a database that accumulates person-person interaction information. The person-person interaction information is information indicating a combination of users having interaction. For example, it is assumed that a user 3a (father) and a user 3b (daughter) are sitting on a sofa and watching television together. The inference system 11 analyzes the interaction from the motion information (position, posture, etc.) of the two people, and accumulates the following person-person interaction information.
“People-person interaction 0011: user 3a, user 3b”.
The distributed behavior information database 134 is a database that accumulates behavior information indicating the behavior of the user 3. For example, in the case of the above-described example of the user 3x, the inference system 11 infers behavior information from environment information, operation information, person-object interaction information, person-person interaction information, etc., and accumulates the following behavior information. The
"User 3x: reading, studying ...".
The unique information database 137 is a database that accumulates unique information indicating attributes for each user 3. The unique information includes information such as the characteristics inferred by the inference system 11 in addition to the physical characteristics and sex of the user 3. In the inference system 11, the tendency of the dialog of the user 3 is inferred from the voice data of the dialog between the dialog robot 2 and the user 3 acquired by the sensor 12, and the inference result is accumulated as specific information.
The event detection device 15 is a processing device that notifies the inference system 11 of event detection when an update of information in the distributed environment behavior database 13 or a service execution request from the interactive robot 2 is detected.
The appliance 4 is a home appliance that has a data transmission / reception function and executes a predetermined service by control from the inference system 11 or by the user's own operation.
The service history database 17 is a database that accumulates history information of services executed by the inference system 11. The inference system 11 also refers to information in the service history database 17 in the inference process.
The distributed environment behavior database 13, the service history database 17, the situation information acquisition unit 25, and the situation storage unit 26 may be collectively configured as the distributed environment behavior database 13-1.
The inference system 11, the distributed environment behavior database 13, the event detection device 15, and the service history database 17 of the robot system 1 can be implemented using known processing means or devices.
The dialogue robot 2 includes a voice recognition unit 21, a voice synthesis unit 22, a dialogue control unit 23, a dialogue strategy database 24, a situation information acquisition unit 25, a situation storage unit 26, a knowledge information acquisition unit 27, a knowledge database 28, and an execution request unit 29. The robot communication unit 210 and the like.
The voice recognition unit 21 is a processing unit that inputs voice data uttered by the user 3, recognizes the content of the input voice data, and converts it into user utterance data (uttered sentence data).
The speech synthesizer 22 is a processing unit that converts the robot utterance data (response sentence data for the user's conversation, utterance sentence data for inquiring the user, etc.) generated by the dialogue control unit 23 into voice data and utters it. is there.
The dialogue control unit 23 analyzes the environment and the situation of the user 3 from the information stored in the situation storage unit 26, selects a service to be provided to the user 3 based on the analyzed situation, and uses it as association information in the dialogue strategy database 24. Based on the concept related to the user's situation, a process for generating robot utterance data using a linguistic expression indicating the concept, and user utterance data (response sentence data) that the user responds to the generated robot utterance data. ) And referring to the associative information in the dialogue strategy database 24 to determine whether or not the context of the user utterance data is conceptually related to the context of the robot utterance data. .
Further, when it is determined that the context of the user utterance data and the context of the robot utterance data are related, the dialogue control unit 23 extracts knowledge information about the selected service from the knowledge database 28 and uses the extracted knowledge information. Generate robot utterance data.
The dialogue strategy database 24 is a database for accumulating association information for the dialogue robot 2 to infer a dialogue with the user 3 and generate a response for pulling the user 3 into the dialogue by “association interaction”.
The associative information is information describing the degree of association between the concepts as the subject extracted from the context of the dialogue. Associative information uses information indicating the degree of synonymity, synonymity, or co-occurrence between the concepts. The associative information is given in consideration of affordance set in the dialogue robot 2. For example, when an affordance of “3 years old” is set in the dialogue robot 2, the concept and association information are defined based on a conceptual model corresponding to the reasoning and association ability of the 3 years old.
The situation information acquisition unit 25 is a processing unit that acquires information such as environment information, operation information, action information, and unique information from the distributed environment action database 13 and stores the information in the situation storage unit 26.
The knowledge information acquisition unit 27 is a processing unit that acquires knowledge information about a service selected from the information server 9 on the network 8 by a predetermined communication protocol, for example, TCP / IP, and accumulates the knowledge information in the knowledge database 28. As a result, in addition to the information stored in the robot system 1, it is possible to access a large amount and various information existing on the network 8, and to provide the user 3 with specialized information and the latest information. it can. In the knowledge database 28, for example, information related to the appliance 4 or a service executed on the appliance 4 is accumulated.
The knowledge database 28 is a database that accumulates knowledge information related to the appliance 4 or a service executed on the appliance 4, for example, manual information of the appliance.
The execution request unit 29 is a processing unit that transmits the service execution request selected by the dialogue control unit 23 to the robot system 1. Further, the execution request unit 29 may transmit a service execution request directly to the appliance 4.
The robot-to-robot communication unit 210, as a service selected by the dialogue control unit 23, uses another dialogue robot 2 ′ cooperating with a robot system 1 ′ other than the robot system 1 and the situation of the user 3 according to a predetermined communication protocol. Processing means for transmitting and receiving information about a selected service.
In this example, the voice recognition unit 21, the voice synthesis unit 22, and the dialogue control unit 23 of the dialogue robot 2 are realized by an anthropomorphic voice dialogue agent tool kit (Galatea TOOLkit) (for example, http: //hil.tu). -Tokyo.ac.jp/-galatea/galatea-jp.html, Pendinginger, Helmut; Ishizuka, Mitsuru (Eds.); "Life-Like Characters Tools, AffectsTip. 213; 2004; ISBN: 3-540-00867-5).
Hereinafter, the processing flow of the present invention will be described in several cases.
[When proposing services from user conversations]
FIG. 4 is a diagram illustrating a processing flow of the interactive robot when a service is selected from a user conversation. When the conversation robot 2 detects a conversation between the users 3 and proposes an appropriate service, the conversation robot 2 performs the following processing.
Step S1: Voice data recognition processing
The speech recognition unit 21 of the interactive robot 2 detects the conversation between the users 3 and inputs the user's speech, recognizes the speech data, and converts it into user speech data.
Step S2: Status information acquisition process
In parallel, the situation information acquisition unit 25 acquires predetermined situation information from the distributed environment behavior database 13 and stores it in the situation storage unit 26.
Step S3: Dialogue / situation inference processing
The dialog control unit 23 analyzes user utterance data (user conversation) and infers a context. Then, the user's situation is inferred based on the context and situation information of the user utterance data, and the optimum service is selected from the executable services. Furthermore, referring to the associative information in the dialogue strategy database 24, a concept associated with the context of the user utterance data is extracted, and robot utterance data (response of the dialogue robot) is created using a language expression indicating this concept.
Step S4: Speech synthesis process
Then, the speech synthesizer 22 synthesizes the speech data of the robot and responds to the user 3.
Step S5: voice data recognition processing
When the voice recognition unit 21 inputs the voice data of the user 3 with respect to the response uttered in step S4, the voice data is voice-recognized and converted into new user utterance data (new utterance of the user).
Step S6: Dialog pull-in determination process
The dialogue control unit 23 infers the context of new user utterance data and determines whether or not the user 3 has been drawn into the dialogue. In the determination of the dialog pull-in, it is determined that the dialog pull-in is successful when the context of the new user utterance data is within the range of the associative information of the extracted concept or the consent to the robot utterance data (response). . If the service to be executed is specified, the process proceeds to step S7. If the service to be executed is not specified, response sentence data is created (step S6-2), and the process proceeds to step S4.
In addition, when the context of the new user utterance data is outside the range of the extracted associative information of the concept, or when it is disapproval with respect to the robot utterance data (response), it is determined that the dialog pull-in has failed. In this case, another concept is extracted with reference to the association information, the topic is corrected by the new association (step S6-1), and response sentence data is generated using the language expression indicating the corrected topic (step S6-). 2) The process proceeds to step S4.
The dialogue control unit 23 determines that the dialogue pull-in has failed when the response sentence data is not received from the voice recognition unit 21 within a predetermined time.
Step S7: Service execution processing
The execution request unit 29 transmits an execution request for the selected service to the robot system 1. Alternatively, the data is transmitted directly to the corresponding appliance 4.
[When proposing services based on user conditions]
FIG. 5 is a diagram showing the flow of processing of the interactive robot when selecting a service from the user's situation. The dialogue robot 2 performs the following processing when selecting an appropriate service based on the situation of the user 3 acquired from the robot system 1.
Step S <b> 11: The situation information acquisition unit 25 of the interactive robot 2 acquires predetermined situation information from the distributed environment behavior database 13 and stores it in the situation storage unit 26.
Step S12: The dialogue control unit 23 analyzes the situation of the user 3 from the situation information in the situation storage unit 26, and selects an optimum service from the executable services. Furthermore, referring to the associative information in the dialog strategy database 24, the concept associated with the situation of the user 3 is extracted, and robot utterance data (interrogation of the dialog robot) is created using a language expression indicating this concept.
Step S13: Then, the speech synthesizer 22 synthesizes the speech data of the robot and utters it to the user 3.
Step S14: The voice recognition unit 21 inputs voice data of the response of the user 3 to the robot utterance data, recognizes the voice data, and converts it into user utterance data (user response).
Step S15: The dialogue control unit 23 infers the context of the user's response, and determines whether or not the user 3 has successfully drawn in the dialogue. If it is determined that the dialogue has been successfully drawn, if the service to be executed is specified, the process proceeds to step S16. If the service to be executed is not specified, response sentence data is created (step S15-2). The process proceeds to step S13. On the other hand, if the dialog pull-in fails, the topic is corrected with a new association (step S15-1), response sentence data is created (step S15-2), and the process proceeds to step S13.
Step S16: If the dialog pull-in is successful, the execution request unit 29 transmits an execution request for the selected service to the robot system 1 or the corresponding appliance 4.
[When providing information from user conversations]
FIG. 6 is a diagram showing a processing flow of the interactive robot when providing knowledge information related to a service from a user's conversation.
Step S21: The dialogue robot 2 detects the conversation between the users 3 by the voice recognition unit 21, inputs the voice data of the user's utterance, recognizes the voice data, and converts it into user utterance data (user's conversation). To do.
Step S22: In parallel, the situation information acquisition unit 25 acquires predetermined situation information from the distributed environment behavior database 13 and stores it in the situation storage unit 26.
Step S23: The dialogue control unit 23 analyzes the situation of the user 3 and the context of the conversation of the user 3 from the situation information. Then, an optimal service is selected from services that can be executed based on the context and situation of the conversation of the user 3. Further, the concept associated with the conversation context of the user 3 is extracted with reference to the associative information in the dialogue strategy database 24, and robot utterance data (robot response) is created using a language expression indicating this concept.
Step S24: The speech synthesizer 22 synthesizes the speech data of the robot and responds to the user 3.
Step S25: The voice recognition unit 21 inputs the voice data of the user 3 for the response uttered in step S24, recognizes the voice data, and converts it into new user utterance data (user response).
Step S26: The dialogue control unit 23 infers the context of the new user response, and determines whether or not the user 3 has successfully drawn in the dialogue. If it is determined that the dialogue has been successfully drawn, if the service to be executed is specified, the process proceeds to step S27. If the service to be executed is not specified, response sentence data is created (step S26-2). The process proceeds to step S24. On the other hand, if the dialog pull-in fails, the topic is corrected with a new association (step S26-1), response sentence data is created (step S26-2), and the process proceeds to step S24.
Step S27: If the dialog pull-in is successful, the dialog control unit 23 extracts knowledge information related to the selected service from the knowledge database 28.
Step S28: Furthermore, the dialogue control unit 23 generates robot utterance data (providing knowledge information) using the extracted knowledge information.
Step S29: The speech synthesizer 22 synthesizes speech by synthesizing the robot utterance data. Note that the speech synthesizer 22 may directly convert the extracted knowledge information into speech data and speak.
The processing examples described above may be processed by combining any of the processing. Further, in each processing example, before the execution request unit 29 transmits a service execution request, the dialogue control unit 23 may generate robot utterance data for inquiring whether or not the service to be executed is permitted, and may inquire the user. .
Further, when cooperation with a dialogue robot 2 ′ cooperating with another robot system 1 ′ is necessary in executing services or providing knowledge information, the inter-robot communication unit 210 determines the situation of the user 3 Send and receive information about the selected service.
Hereinafter, specific examples of the present invention will be described.
In the first specific example, as shown in FIG. 1, it is assumed that the user 3a (father) and the user 3b (daughter) have a conversation in the living room (room 1).
In the voice recognition unit 21 of the interactive robot 2, users (father and daughter) in the living room input voices having conversations as described below, and the voice data is voice-recognized and converted into speech sentence data.
Father's utterance: "Kotoshino Hanshinha ..."
Daughter's utterance: "... Katsu ..."
In addition, the situation information acquisition unit 25 acquires predetermined information such as unique information, environment information, and behavior information from the distributed environment action database 13 and stores it in the situation storage unit 26.
With this information, the dialog control unit 23 is in a situation where the user 3a (father) and the user 3b (daughter) are talking in the living room (room 1) and the user 3c (mother) is cleaning up in the kitchen (room 2). I understand a certain situation.
Further, the dialogue control unit 23 infers the context of the speech sentence data of the user whose voice has been recognized. Analyzes that <hanshin, cutlet> included in the utterance text data is <Hanshin, win>, and infers that the concept of the subject of conversation is <baseball>. Then, with reference to the associative information in the dialogue strategy database 24, the concept <baseball> and the concept <professional baseball> having a strong degree of association are specified. Then, based on the context and situation of the user's 3 conversation, services such as <extract baseball relay program from electronic TV program guide> and <turn on TV if there is a baseball relay program> are selected.
Further, the robot utterance data “baseball story?” Is generated using a linguistic expression (for example, baseball) representing the identified concept. The speech synthesizer 22 synthesizes this data by speech synthesis and speaks. As a result, the dialogue robot 2 asks “the story of baseball?” And participates in the conversation between the father and the daughter.
The voice recognition unit 21 detects whether or not there is a user utterance for the robot utterance data. If the user is speaking, the voice data is recognized and converted into new user speaking data. For example, if the new user's utterance is “Professional baseball”, the dialog control unit 23 determines that the user 3 has been successfully drawn into the dialog, assuming that the context is within the range to be associated. If the new user's utterance is “Yes”, it is determined that the conversation has been successfully drawn, assuming that the context is a positive reply.
On the other hand, if the utterance of the new user is “Department Store”, the context is not within the reminiscent range and is not a positive reply, so it is determined that the conversation has failed to be drawn. If the dialogue control unit 23 determines that the dialogue has been successfully drawn, the dialogue control unit 23 executes the selected service. Here, the electronic television program guide is searched from the knowledge database 28.
Here, if the electronic television program guide is not stored in the knowledge database 28, the knowledge information acquisition unit 27 acquires the URL of the information server 9 that provides the electronic television program guide from the knowledge database 28, and transmits the information server through the network 8. The electronic TV program guide is acquired from 9 and stored in the knowledge database 28.
The dialogue control unit 23 extracts baseball relay program information from the TV program guide stored in the knowledge database 28, and for example, it is assumed that the relay program of the “Hanshin-Chunichi War” game is currently being broadcast. . The dialogue control unit 23 generates new robot utterance data “I am playing a game between Hanshin and Chunichi” from the information (knowledge information) of this baseball broadcast program.
Further, the dialogue control unit 23 extracts unique information that the user 3c (mother) is a Hanshin fan from the information stored in the situation storage unit 26. From this unique information (situation information), new robot utterance data “I also like mom” is generated.
Further, the execution request unit 29 transmits an execution request for the selected service to the robot system 1. The event detection device 15 of the robot system 1 detects a service execution request from the interactive robot 2 and notifies the reasoning system 11 of the request.
In the second specific example, it is assumed that the user 3c (mother) is in a situation where the dishwasher that is one of the appliances 4 does not operate during cleaning after meals.
The situation information acquisition unit 25 of the interactive robot 2 in the kitchen (room 2) acquires predetermined information from the distributed environment behavior database 13 and stores it in the situation storage unit 26.
The dialogue control unit 23 analyzes the situation from the information stored in the situation storage unit 26 and selects a service of <investigating and notifying the cause of failure>.
Further, referring to the dialogue strategy database 24, the robot utterance data “Is the dishwasher strange?” Is generated using the language expression associated with the situation, and the speech synthesizer 22 synthesizes and asks.
Thereafter, when the voice recognition unit 21 of the dialog robot 2 inputs a response “why is it?” To the question with the robot, the dialog control unit 23 determines that the dialog has been successfully drawn from the context of the mother's response, Run the selected service.
That is, the dialogue control unit 23 acquires the state of the dishwasher from the environment information in the situation storage unit 26. The knowledge information acquisition unit 27 acquires the URL of the information server 9 of the manufacturer of the corresponding appliance (dishwasher) 4 from the knowledge database 28, and information on the cause of the failure from the information server 9 of the manufacturer using the state of the dishwasher as a key. To get. The dialogue control unit 23 creates robot utterance data “I know the cause of the failure ...” based on the information (knowledge information) about the cause of the failure, and utters the speech by speech synthesis in the speech synthesis unit 22.
In the third specific example, it is assumed that another life support robot system 1 ′ and a dialogue robot 2 ′ are set in another living space.
The dialogue robot 2 infers from the dialogue with the user 3x (married and independent daughter) that the daughter needs the advice of the user 3y (mother), and connects the service <mother's videophone to the daughter. Suppose that> is selected. When the dialog control unit 23 of the dialog robot 2 determines that the dialog pull-in is successful, the inter-robot communication unit 210 transmits a service execution request to the inter-robot communication unit 210 ′ of the dialog robot 2 ′.
The dialogue robot 2 ′ utters the robot utterance data “Mr. XX is waiting for contact” to the user 3 y (mother), and gives the telephone number and call instruction of the user 3 x to the appliance (videophone) 4. Send.
As described above, the present invention provides the robot system 1 in which the interactive robot 2 infers conversations between users and user situations based on the “associative interaction” behavior hypothesis and advances the conversation with the users. It is possible to provide services that are available and that the user has not noticed and related knowledge information according to the situation of the user.
The interactive robot 2 of the present invention can also be realized as a program that is read, installed, and executed by a computer. The program for realizing the present invention can be stored in a computer-readable recording medium, provided by being recorded on these recording media, or provided by transmission / reception using various communication networks via a communication interface. Is done.

  INDUSTRIAL APPLICABILITY The present invention is suitable for an interactive system that realizes a user interface function having a high level of situation response capability in a life support robot system that autonomously supports human life on the premise of a ubiquitous environment.

Claims (22)

A life support robot system that autonomously controls an appliance that performs a service to support a user's life, and a dialog system that interacts with the user by the voice of the dialog robot in cooperation with the life support robot system,
The life support robot system includes:
An inference system that controls the appliance by inferring the environment in the space and user behavior based on sensor information measured in a predetermined space;
A distributed environmental behavior database for accumulating environmental information and behavior information as inference results by the inference system;
The dialogue robot is
A dialogue strategy database that stores associative information describing the degree of association between concepts;
Speech synthesis means for converting the speech data generated in the dialogue robot into speech data and speaking;
Voice recognition means for recognizing the content of the user's voice data and converting it into user utterance data;
Situation information acquisition means for acquiring the environment information and action information from the distributed environment action database and storing them in a situation storage means;
A language indicating the concept by analyzing a situation of the user from the environment information and the behavior information, selecting a service to be provided to the user based on the situation, identifying a concept related to the situation based on the association information A process of generating robot utterance data using an expression, inferring a context of user utterance data with respect to the robot utterance data, and referring to the association information, the context of the user utterance data is conceptually related to the context of the robot utterance data A dialogue control means for performing a process of determining whether or not it is related to,
An execution requesting unit for transmitting an execution request for the service to the life support robot system or the appliance when the dialog control unit determines that the context of the user utterance data is related to the context of the robot utterance data; An interactive system characterized by that. The dialogue robot is
The dialogue system according to claim 1, wherein the dialogue system is configured as a substantial device independent of the life support robot system. The dialogue robot is
The inter-robot communication means for transmitting / receiving information on the user's situation or the selected service with a predetermined communication protocol as the selected service with a predetermined communication protocol. Dialog system described in the section. The dialogue robot is
A knowledge database for accumulating knowledge information about the appliance or services performed on the appliance;
When the conversation control means determines that the context of the user utterance data is related to the context of the robot utterance data, it extracts knowledge information about the selected service from the knowledge database, and uses the extracted knowledge information The dialog system according to claim 1, wherein robot utterance data is generated. The dialogue robot is
5. The knowledge information acquisition means for acquiring knowledge information about the selected service from another information providing server on the network by a predetermined communication protocol and storing the knowledge information in the knowledge database. The described dialogue system. A life support robot system that autonomously controls an appliance that performs a service to support a user's life, and a dialog system that interacts with the user by the voice of the dialog robot in cooperation with the life support robot system,
The life support robot system includes:
An inference system that controls the appliance by inferring the environment in the space and user behavior based on sensor information measured in a predetermined space;
A distributed environmental behavior database for accumulating environmental information and behavior information as inference results by the inference system;
The dialogue robot is
A dialogue strategy database that stores associative information describing the degree of association between concepts;
Speech synthesis means for converting the speech data generated in the dialogue robot into speech data and speaking;
Voice recognition means for recognizing the content of the user's voice data and converting it into user utterance data;
Situation information acquisition means for acquiring the environment information and action information from the distributed environment action database and storing them in a situation storage means;
Analyzing the context of the user utterance data, analyzing the situation from the environment information and behavior information, selecting a service to be provided to the user based on the context and situation of the user utterance data, and the user based on the association information Identifying a concept related to the context of the utterance data, generating robot utterance data using a linguistic expression indicating the concept, inferring a context of new user utterance data for the robot utterance data, and obtaining the association information Dialogue control means for performing a process of determining whether or not the context of the new user utterance data is conceptually related to the context of the robot utterance data with reference to;
Execution request means for transmitting an execution request for the service to the life support robot system or the appliance when the dialog control means determines that the context of the new user utterance data is related to the context of the robot utterance data; A dialogue system characterized by comprising: The dialogue robot is
The dialogue system according to claim 6, wherein the dialogue system is configured as a substantial device independent of the life support robot system. The dialogue robot is
The inter-robot communication means which transmits / receives information on the user's situation or the selected service with a predetermined communication protocol as the selected service with a predetermined communication protocol. Dialog system described in the section. The dialogue robot is
A knowledge database that stores information about the appliance or services performed on the appliance;
When the conversation control means determines that the context of the new user utterance data is related to the context of the robot utterance data, it extracts knowledge information about the selected service from the knowledge database, and extracts the extracted knowledge information. The dialog system according to claim 6, wherein the robot utterance data is generated by using. The dialogue robot is
10. The knowledge information acquisition means for acquiring knowledge information relating to the selected service from another information providing server on the network by a predetermined communication protocol and storing the knowledge information in the knowledge database. The described dialogue system. An interactive robot that interacts with a user by voice in cooperation with a life support robot system that autonomously controls an appliance that performs services to support the user's life,
A dialogue strategy database that stores associative information describing the degree of association between concepts;
Speech synthesis means for converting the speech data generated in the dialogue robot into speech data and speaking;
Voice recognition means for recognizing the content of the user's voice data and converting it into user utterance data;
A situation in which the environment information and action information is acquired from a distributed environment action database that accumulates environment information and action information inferred from sensor information measured in a predetermined space in the life support robot system and stored in the situation storage means Information acquisition means;
A language indicating the concept by analyzing a situation of the user from the environment information and the behavior information, selecting a service to be provided to the user based on the situation, identifying a concept related to the situation based on the association information A process of generating robot utterance data using an expression, inferring a context of user utterance data with respect to the robot utterance data, and referring to the association information, the context of the user utterance data is conceptually related to the context of the robot utterance data A dialogue control means for performing a process of determining whether or not it is related to,
An execution requesting unit for transmitting an execution request for the service to the life support robot system or the appliance when the dialog control unit determines that the context of the user utterance data is related to the context of the robot utterance data; A dialogue robot characterized by that. 12. The inter-robot communication means for transmitting / receiving information related to the user's situation or the selected service with a predetermined communication protocol as a selected service with another interactive robot. The interactive robot according to the item. A knowledge database for accumulating knowledge information about the appliance or services performed on the appliance;
When the conversation control means determines that the context of the user utterance data is related to the context of the robot utterance data, it extracts knowledge information about the selected service from the knowledge database, and uses the extracted knowledge information The interactive robot according to claim 11, wherein the robot utterance data is generated. 14. The knowledge information acquisition means for acquiring knowledge information related to the selected service from another information providing server on the network by a predetermined communication protocol and storing the knowledge information in the knowledge database. The described interactive robot. An interactive robot that interacts with a user by voice in cooperation with a life support robot system that autonomously controls an appliance that performs services to support the user's life,
A dialogue strategy database that stores associative information describing the degree of association between concepts;
Speech synthesis means for converting the speech data generated in the dialogue robot into speech data and speaking;
Voice recognition means for recognizing the content of the user's voice data and converting it into user utterance data;
A situation in which the environment information and action information is acquired from a distributed environment action database that accumulates environment information and action information inferred from sensor information measured in a predetermined space in the life support robot system and stored in the situation storage means Information acquisition means;
Analyzing the context of the user utterance data, analyzing the situation from the environment information and behavior information, selecting a service to be provided to the user based on the context and situation of the user utterance data, and the user based on the association information Identifying a concept related to the context of the utterance data, generating robot utterance data using a linguistic expression indicating the concept, inferring a context of new user utterance data for the robot utterance data, and obtaining the association information Dialogue control means for performing a process of determining whether or not the context of the new user utterance data is conceptually related to the context of the robot utterance data with reference to;
Execution request means for transmitting an execution request for the service to the life support robot system or the appliance when the dialog control means determines that the context of the new user utterance data is related to the context of the robot utterance data; A dialogue robot characterized by comprising: 16. The inter-robot communication means for transmitting / receiving information on the user's situation or the selected service with a predetermined communication protocol as a selected service with another interactive robot. The interactive robot according to the item. A knowledge database that stores information about the appliance or services performed on the appliance;
When the conversation control means determines that the context of the new user utterance data is related to the context of the robot utterance data, it extracts knowledge information about the selected service from the knowledge database, and extracts the extracted knowledge information. 16. The dialog robot according to claim 15, wherein the robot utterance data is generated by using the robot. 18. The knowledge information acquisition means for acquiring knowledge information about the selected service from another information providing server on the network by a predetermined communication protocol and storing the knowledge information in the knowledge database. The described interactive robot. An interactive robot program for causing a computer to function as the interactive robot according to claim 11. An interactive robot program for causing a computer to function as the interactive robot according to claim 15. A computer-readable recording medium storing the interactive robot program according to claim 19. A computer-readable recording medium storing the interactive robot program according to claim 20.

Images