JP2007323233A - Method, device and program for processing reason explanation service using interactive robot - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a reason explanation service for clearly and briefly explaining reasons for executing a plurality of life support services to a user. <P>SOLUTION: When a trigger condition for reason explanation service execution is satisfied (S5) after the execution of life support services, services executed within a predetermined time period before detection are specified as reason explanation targets by reference to a service history database 17 (S6). The situations at the execution of the specified services are acquired (S7). Reason explanations are generated as robot speech information from the acquired information (S8). The generated reason explanations are voice-synthesized and the generated voice data are outputted to a user 3 (S9). Service history information about the executed reason explanation service is saved in the service history database 17 (S10). <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention is implemented in the life support robot system using a dialog robot that performs voice conversation with the user in cooperation with a life support robot system that autonomously controls the appliance to support the life of the user. The present invention relates to reason explanation service processing for explaining the reason for providing a service.

  More specifically, the present invention relates to a reason explanation service processing method for performing a reason explanation service for a plurality of services executed by the life support robot system, its apparatus, and its program.

  With the background of ubiquitous environment, a life support robot system that is installed in a user's living space and autonomously supports the user's life has been realized. Life support robot systems based on a ubiquitous environment are often unconscious systems that do not require users to be particularly aware of the operation.

In order to maintain a comfortable environment and support user activities, the unconscious lifestyle support robot system infers the environment and user behavior based on various sensor information, and uses an appliance (communication function with a communication function). It provides various services for supporting life by controlling home appliances) and information terminal devices. For example, a life support robot system analyzes the user's movement / posture and room conditions based on sensor information and infers that the user is in a relaxed state. By playing music that is suitable for the environment or by maintaining the indoor temperature and humidity with an air conditioner, users can realize a comfortable living environment without consciously operating these appliances (see, non- Patent Document 1).
Mino Tetsuhiko, “Purpose and Outline of the Yukari Project—UKARI Project Report No. 1”, IPSJ 66th National Convention, 2004

  The unconscious life support robot system is a universal user interface that can respond flexibly to various situations, and has an interactive system that has a high level of situational processing capability and makes the user feel familiar. is necessary. The inventor of the present invention can receive a user's ambiguous request more accurately and reflect it in the control of the system, and can help the user understand the control status of the system more accurately for life support. An interactive robot that can provide various services and information, and an interactive system using the interactive robot (see PCT / JP2004 / 002942).

  When various life support services can be provided by the above life support robot system, it is difficult for the user to grasp all the services to be executed. A mechanism is needed to explain to the user why.

  Therefore, the inventor of the present invention provides a reason explanation service processing method and a processing apparatus for explaining the reason for execution of the service provided by the life support robot system through the interactive robot when the user asks the reason for the execution. (See Japanese Patent Application No. 2005-191520).

  According to the reason explanation service processing method using the interactive robot described above, when the service is executed by the life support robot system, the user is asked the reason for executing the service as “why?” The reason is explained, and the user's evaluation of the executed service can be fed back based on the user's reaction to the explanation of the reason.

  However, in this processing method, when the user asks the reason for executing the service, the interactive robot explained the reason for one service that was executed most recently. In addition, if the reason for a plurality of services is explained, the only reason is to explain the reasons for all the services that have been executed until the user asks a question.

  When multiple services are executed at the same time for a single trigger, or when multiple services are executed within a short time, the user only needs to execute the service that was executed last. I couldn't know why. Further, if the explanation of the reasons for the execution of a plurality of services is given, all the reasons for the executed services will be covered, and the situation that the user will be told the explanation of the reasons for a long time has occurred.

  The present invention has been made in view of such problems, and an object of the present invention is to provide a processing method, apparatus, and program capable of providing a reason explanation service that easily and easily explains a plurality of service execution reasons to a user. It is to provide.

  In order to autonomously control a plurality of appliances that execute services, the present invention infers the environment in the space and the user's behavior based on sensor information measured in a predetermined space, and controls the appliance. Life support robot comprising a reasoning system to control, a distributed environment behavior database that accumulates environment information and behavior information as inference results by the reasoning system, and a service history information database that accumulates history information of services provided by the reasoning system In cooperation with the system and the life support robot system, inferring the context of the utterance based on the user utterance information generated by voice recognition processing of the user's voice data, and voice synthesis of the utterance information generated based on the inference A dialogue robot for outputting voice data generated by processing and having a voice dialogue with the user; Interactive system that is why explaining service processing method for describing the execution reason service the life support robot system is provided.

  The present invention provides: 1) When the service is executed based on the user's situation inferred from the environment information and the action information stored in the distributed environment action database, the execution time of the service and the situation at the time of service execution A process of storing service history information including information on the service history information database in the service history information database, and 2) when a predetermined situation for explaining the reason for execution of the service is detected, from the service history information database, A process of identifying a plurality of services executed within a predetermined period from the time of detection as the object of the reason explanation; and 3) a process of generating an execution notification for notifying the service execution for each of the specified services. 4) Determine the output order of the execution notifications based on the execution times of the specified services. 5) a process for synthesizing the execution notification according to the output order, and outputting the generated voice data from the interactive robot according to a predetermined response waiting period interval; 6) after the execution notification Service history of the service corresponding to the execution notification when it is inferred that the user's utterance is a request to explain the reason for service execution based on the context of the user's utterance information detected during the predetermined response waiting period A process for generating a reason explanation for executing the service based on the information; and 7) a process for synthesizing the reason explanation and outputting the generated voice data from the interactive robot.

  The present invention detects a predetermined situation for executing the reason explanation service (for example, a request for explanation of a reason such as “why?” From the user, a situation where the user is sitting on the sofa) or the like. When multiple services executed are identified, the voice data of the execution notification of each service generated based on the service history information (Television turned on, XX turned on, etc.) is taken for a predetermined waiting time. Output. Corresponds to an execution notification with a user's reaction when it is inferred that the user's utterance detected within the waiting time after a certain execution notification is a response indicating a reason explanation request (for example, “Why?”) The voice data explaining the reason for executing the service (“I'm sitting on the couch”) is output from the interactive robot.

  Since the dialogue robot utters the execution notification of the executed service with a certain interval, when the user is notified of the execution of the service for which the explanation of the reason is desired, it then utters "Why?" By interrupting the reason explanation request, it is possible to output only the explanation of the reason for executing the service that the user wants to know.

  In addition, the present invention provides: 1) the execution time of the service for a service inferred from the environment information and the action information stored in the distributed environment action database, and selected and executed based on the user condition; And a process of accumulating service history information including information related to service execution status in the service history information database, and 2) a request for explaining the reason for executing the service based on the context of the user's utterance information. A process of identifying a plurality of services executed within a predetermined period from the time of the user's utterance as the object of the reason explanation from the service history information when it is inferred, and 3) the specified For each service, a process for generating a description of the reason for executing the service, and 4) each identified service A process for determining the output order of the reason explanations based on the execution time of the task; and 5) a process for voice-synthesizing the reason explanations according to the output order and outputting the generated speech data from the interactive robot; Is provided.

  When there are multiple services that the life support robot system has executed within the predetermined time, if it is estimated that the user's utterance is a request for explanation of the reason, it was executed within the predetermined time until the user's utterance For a plurality of services (television control, program recommendation, lighting control, air conditioning control, etc.), audio data explaining the reason for executing each service is output. Therefore, it is possible to collectively explain the reasons for executing services executed within a predetermined period.

  When the present invention has the above-described configuration, in the process of storing the service history information, the service history information is stored as dependency information between executed services in the service history information database, and the output is performed. In the process of determining the order, when there is the dependency relationship between the identified services, the output order of the explanation of the reason for executing the service in the dependency relationship is determined based on the execution time order of the service. decide.

  When executed services have a dependency relationship that another service is executed by the execution of one service, they are in a dependency relationship when explaining the reason for the execution of multiple services retroactively. For services, explain the reasons in the order in which they were executed. For example, by explaining the reasons for executing dependent services in the order of execution, such as the “TV control” service and the “program recommendation” service, it is possible to explain the reason more easily to the user.

  In addition, the present invention provides: 1) the execution time of the service for a service inferred from the environment information and the action information stored in the distributed environment action database, and selected and executed based on the user condition; , Service history information including information regarding the status at the time of service execution, and information indicating whether or not the service has been selected as the reason for explanation, and a processing process stored in the service history information database, and 2) utterance information of the user If it is inferred that the user's utterance is a service execution reason explanation request based on the context of the service, the execution time closest to the user's utterance is determined from the service history information as the object of the reason explanation. A process of identifying one unselected service as the object of the reason explanation, and 3) before A process of generating a description of the reason for executing the specified service from service history information; and 4) performing a speech synthesis process on the reason for executing the specified service and outputting the generated voice data from the interactive robot. And a processing process.

  Each time the user utters “why?” As a reason explanation request, the reason explanation is given one by one for services executed within a predetermined period. When the user has finished explaining the reason for the service he / she wants to know, he / she ceases to say “Why?”, So there is no need to explain the reason for the service for which the reason explanation is unnecessary.

  In addition, the present invention provides: 1) the execution time of the service for a service inferred from the environment information and the action information stored in the distributed environment action database, and selected and executed based on the user condition; A process of storing service history information in the service history information database, including information on the status of service execution, and standby information for specifying the service of the user's reason explanation request, and 2) the utterance information of the user When it is inferred that the user's utterance is a request to explain the reason for service execution based on the context, the information included in the user utterance information and the service history information are the execution time closest to the utterance Process of identifying one service with the same waiting information as the reason explanation target 3) a process for generating a description of the reason for executing the specified service from the service history information; and 4) a voice synthesis process for the description of the reason for executing the specified service. And a process of outputting from the dialogue robot.

  Explanation of the reason for executing the service required by the user among the multiple services executed by specifying the service that is the target of the reason explanation using the keyword included in the user's utterance inferred as the reason explanation request. Can only do it.

  In addition, the present invention provides: 1) the execution time of the service for a service inferred from the environment information and the action information stored in the distributed environment action database, and selected and executed based on the user condition; And a process of accumulating service history information including information related to service execution status in the service history information database, and 2) a request for explaining the reason for executing the service based on the context of the user's utterance information. A process of identifying a plurality of services executed within a predetermined period from the time of the user's utterance as the object of the reason explanation from the service history information when it is inferred, and 3) the specified A process of generating an object confirmation for confirming to the user whether or not the service is the object of reason explanation; 4) A process of synthesizing the object confirmation and outputting the generated speech data from the interactive robot; and 5) the user's utterance is positive for the object confirmation based on the context of the user's utterance information for the object confirmation. A process of generating a reason for executing the service corresponding to the positively acknowledged object confirmation from the service history information when it is inferred that the response is a dynamic response; And a process of outputting the generated voice data from the interactive robot.

  In response to a reason explanation request uttered by the user, by confirming the services to be explained one by one and explaining only the reason for execution of the confirmed service, the user can ensure the service for which the reason explanation is desired. The reason can be explained.

  Further, the present invention is a processing device for performing processing realized in each processing step of the reason explanation service processing method using the dialog robot, and a program for causing the dialog system to execute the processing method.

  In the dialogue system invented by the inventor of the present invention, when the user requests explanation of the reason for executing the service, the reason is explained only for the execution of one service executed immediately before by the life support robot system.

  According to the present invention, when there are a plurality of services executed simultaneously by one trigger and a plurality of services executed within a short time by the life support robot system, a plurality of services subject to explanation of reasons are specified. In addition, it is possible to provide a reason explanation service that can concisely explain the reason for executing each service and present it to the user in an easy-to-understand manner.

  FIG. 1 is a diagram showing a configuration example of a dialogue system in which the present invention is executed. In this embodiment, the dialogue system includes an unconscious life support robot system 1 applied to a family (residential space) composed of a plurality of users 3 (3a, 3b, 3c), a visible type Consists of a dialogue robot 2.

  The life support 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 have a function of moving autonomously and may be configured to freely move in the living space of the user 3. In the dialogue system of FIG. 1, processing is performed by distributed cooperation between the unconscious life support robot system 1 and the visible dialogue robot 2.

  FIG. 2 is a diagram illustrating a configuration example of the life support robot system 1 and the dialogue robot 2. The life support 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 for inference. When the event detection device 15 detects an event, the inference system 11 acquires a context from the distributed environment behavior database 13 to obtain the environment in the living space, the operation of the user 3, the user 3 Analyzing the interaction (interaction), the interaction between the user 3 and the object, etc., inferring the action of the user 3 from the analysis result, and determining the service to be executed from the life support services implemented according to the conclusion , A processing system for controlling 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 reasoning system 11 is implemented with a reason explanation service as well as various life support services. The reason explanation service explains to the user 3 through the interactive robot 2 the reason why the life support service provided by the life support robot system 1 is determined based on detection of a predetermined opportunity, such as when the user 3 asks a question. Service.

  In addition, the inference system 11 performs feedback of user evaluation for the provided life support service. The user evaluation feedback is based on the user 3's reaction to the reason for service execution indicated by the reason explanation service. This is a process of reflecting the information unique to the user 3 in the distributed environment behavior database 13.

  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, for example. 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 specific 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 environmental 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. It is analyzed by the inference system 11, and the following environmental information is generated and accumulated.
“Time, book ID data, position, status (held by 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, the sensor information is analyzed by the inference system 11 and the following operation information is accumulated.
"Time, user 3x ID data, position, posture (sitting position), ...".

The person-object interaction database 135 is a database for accumulating person-object interaction information. The person-object interaction information is information indicating a combination of the user 3 and the object in which the 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, book, study desk, study desk chair, lamp,…”
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 the users 3 in which the interaction occurs. For example, it is assumed that a user 3a (father) and a user 3b (daughter) are sitting on a sofa and watching TV together. The inference system 11 analyzes the interaction from the motion information (position, posture, etc.) of the two people, and the following person-person interaction information is accumulated.
“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 is information inferred by the inference system 11 in addition to the physical characteristics and sex of the user 3 (for example, information on the preference of the user 3 and information on the necessity of the life support service).

  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 service history database 17 is a database system that accumulates history information for each service executed by the inference system 11.

  In addition, the service history database 17 infers the situation of the user 3 from the environment information and the action information accumulated in the distributed environment action database 13, and about the life support service selected and executed based on the situation of the user 3, the service history database 17 Service history information including information on the execution time of the service, information on the status of service execution, etc. is stored.

  The inference system 11 also refers to the information in the service history database 17 in the inference process. The service history information stored in the service history database 17 includes the name of the executed service, the service execution status, the service execution start time and end time, and the like. The service execution status is a part of information stored in the distributed environment behavior database 13 and is information related to the determination of the execution of the service, for example, information such as the position, operation, and behavior of the user 3. is there.

  Also, as information related to the reason explanation service, information indicating whether or not the reason explanation service has been processed, utterance keyword information representing the service used to utter a service execution notification to the user 3 when the service is started When a request for explaining the reason of the user 3 is triggered, information such as a standby keyword for identifying a life support service from the utterance of the user 3 is accumulated.

  The reasoning system 11, the distributed environment behavior database 13, the event detection device 15, and the service history database 17 of the life support robot system 1 can be implemented using known processing means or devices.

  The appliance 4 is a home appliance that has a data transmission / reception function and executes a predetermined service by the control from the inference system 11 or the operation of the user 3 itself.

  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 database 27, an execution request unit 29, and the like. .

  The voice recognition unit 21 is processing means for inputting voice data uttered by the user 3, recognizing the content of the input voice data, and converting it into the utterance information of the user 3. The voice synthesizer 22 is processing means for converting the robot utterance information generated by the dialogue controller 23 into voice data and uttering. The robot utterance information is data such as response sentence data for the conversation of the user 3 and an utterance sentence for asking the user 3.

  The speech recognition unit 21 and the speech synthesis unit 22 perform speech synthesis processing on an execution notification, target confirmation, or reason explanation generated by the reason explanation service processing unit 100 described later according to a predetermined output order, and the generated speech data is processed. Processing to output is performed.

  The dialogue control unit 23 analyzes the environment around the user 3 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 dialogue strategy It is a processing means for performing a process of identifying a concept related to the situation of the user 3 based on the association information in the database 24 and generating robot utterance data using a language expression indicating the concept. The dialogue control unit 23 includes a reason explanation service processing unit 100. As a process for selecting a service, the dialogue control unit 23 performs a reason explanation service based on information in the distributed environment behavior database 13 and the service history database 17 stored in the situation storage unit 26. Decide on execution.

  The reason explanation service processing unit 100 executes a service (reason explanation service) for explaining to the user 3 the reason why the life support service is executed when the life support service provided by the life support robot system 1 is executed. It is.

  The reason explanation service processing unit 100 includes a service identification unit 101, a reason explanation generation unit 103, and an output order determination unit 105.

  The service specifying unit 101 refers to the service history database 17 when a predetermined situation that triggers execution of the reason explanation service is detected, and a plurality of processes executed within a predetermined period from the time when the situation is detected. It is a processing means for specifying a service as an object of reason explanation.

  In addition, when the service specifying unit 101 infers that the utterance of the user 3 is a request for explaining the reason for executing the service based on the context of the user utterance information, the service specifying unit 101 uses the service history information to execute the execution time closest to the utterance of the user 3 However, one service that is not selected as the reason explanation target is specified as the reason explanation target.

  Further, when service history information including a standby keyword is stored in the service history database 17, the service specifying unit 101 has an execution time that is closest to the time when the user 3 speaks and is included in the user utterance information. One service for which the received information matches the standby information of the service history information is identified as the reason explanation target.

  The reason explanation generation unit 103 acquires the status at the time of execution of each service from the service history information of the service history database 17 for each of the plurality of identified life support services, and generates a reason explanation for the execution of this life support service. Processing means. In addition, the reason explanation generation unit 103 generates an execution notification for notifying service execution for each service specified as the reason explanation target. Alternatively, an object confirmation for confirming to the user 3 whether or not the service specified as the object of the reason explanation is the object of the reason explanation is generated.

  The reason explanation generation unit 103 may generate the reason explanation at the same time when generating the life support service execution notification or target confirmation specified by the service specification unit 101.

  The output order determination unit 105 is a processing unit that determines the output order of the generated reason explanation based on the execution time of the life support service specified as the reason explanation target. In addition, when there is a dependency relationship between the services specified as the reason explanation target, the output order determination unit 105 sets the output order of the reason explanation of the execution of the service having the dependency relationship to the execution time of these services. Decide based on order.

  The dialogue strategy database 24 is a database in which the dialogue robot 2 infers a dialogue with the user 3 and accumulates information for generating a response for drawing the user 3 into his own dialogue or continuing.

  The situation information acquisition unit 25 acquires part of information such as environment information, operation information, action information, and unique information in the distributed environment action database 13 and part of service history information in the service history database 17 to obtain a situation storage unit 26. It is a processing means to store in.

  The knowledge database 27 is a database that accumulates knowledge information about the appliance 4 or a service executed on the appliance 4, for example, program information when the appliance 4 is a television, operation manual information when the appliance 4 is a microwave oven, and the like. is there.

  The execution request unit 29 is a processing unit that transmits the service execution request selected by the dialogue control unit 23 to the life support robot system 1. Further, the execution request unit 29 may transmit a service execution request directly to the appliance 4.

  In this example, the speech recognition unit 21, the speech synthesis unit 22, and the dialogue control unit 23 of the dialogue robot 2 are realized by an existing anthropomorphic spoken dialogue agent tool kit (Galatea Toolkit) (for example, http: //hil.tu -tokyo.ac.jp/~ galatea / galatea-jp.html, Prendinger, Helmut; Ishizuka, Mitsuru (Eds.); "Life-Like Characters Tools, Affective Functions, and Applications Series: Cognitive Technologies"; pp.187- 213; 2004; ISBN: 3-540-00867-5).

  Furthermore, the distributed environment behavior database 13 and the service history database 17 of the life support robot system 1 and the situation information acquisition unit 25 and the situation storage unit 26 of the dialogue robot 2 may be collectively configured as the distributed environment behavior database 13-1. it can.

  In addition, the reason explanation service processing unit 100 can be configured in the life support robot system 1. In addition, each processing unit of the reason explanation service processing unit 100 may be configured to be distributed in the life support robot system 1 and the dialogue robot 2 and perform the processing in cooperation.

  FIG. 4 is a diagram for explaining the outline of the processing of the present invention.

  Steps S1 to S4 show various life support service execution processes, Steps S5 to S10 show a reason explanation service execution process, and Step S11 shows a user evaluation feedback process.

Here, it is assumed that the following life support service is executed by satisfying the ignition condition (condition that enables inference).
"Service name = TV control; firing conditions = user 3 sat on sofa"
“Service name = Program recommendation; Firing condition = Program similar to the program I watched before is on air”
"Service name = lighting control; ignition condition = room is darker than the set illuminance"
"Service name = air conditioning control; ignition conditions = room is hotter than set temperature"
It is assumed that the reason explanation service is executed by satisfying firing conditions such as “user 3 is sitting on the couch” and “inferring that user 3's utterance is a request for explanation of reason”.

  The life support robot system 1 acquires a predetermined firing condition for executing the life support service based on the sensor information collected from the sensor 12 and the utterance information of the user 3 collected by the dialogue robot 2 (step S1). The inference system 11 determines the contents of the life support service provided to the user 3 according to the context of the user 3 acquired from the distributed environment behavior database 13 and the context such as dialogue (step S2). The corresponding appliance 4 is controlled to execute the determined life support service (step S3). Further, service execution history information on the determined service execution is stored in the service history database 17 (step S4).

  If the life support service determined by the life support robot system 1 is automatically executed, then the firing condition for executing the reason explanation service is satisfied (step S5). For example, by detecting that the user 3 is sitting on the sofa or inferring that the user 3's utterance “why?” Is a request for explaining the reason, the interactive robot 2 performs a predetermined reason execution service execution. Acquire the firing conditions.

  The reasoning system 11 of the life support robot system 1 refers to the service history information in the service history database 17 and identifies the life support service executed within a predetermined time before the detection of the firing condition as the object of reason explanation. (Step S6). The dialogue robot 2 acquires information such as the status of service history information for each identified life support service (step S7). A reason explanation is generated from the acquired service history information and is used as robot utterance information (step S8). Further, voice data generated by performing voice synthesis processing on the robot utterance information (reason explanation) is output to the user 3 (step S9).

  Thereafter, the life support robot system 1 stores the service history information of the executed reason explanation service in the service history database 17 (step S10).

  When the reason explanation service is executed in the process of step S9, if any response to the reason explanation can be obtained from the user 3, the inference system 11 provides feedback on the user evaluation using the information on the reaction of the user 3 as a firing condition. It performs (step S11).

  FIG. 5 is a diagram showing an example of the processing flow of the dialogue system.

  The life support robot system 1 and the dialog robot 2 of the dialog system cooperate with each other to repeatedly execute the life support service, the reason explanation service, and the user evaluation feedback.

Step S21: Speech data recognition processing The speech recognition unit 21 of the interactive robot 2 detects and inputs speech data uttered by the user 3, performs speech recognition processing on the speech data, and converts it into speech information.

Step S22: Status Information Acquisition Processing In parallel, the distributed environment behavior database 13 of the life support robot system 1 stores sensor information such as voice data and image data acquired from the sensor 12 in the distributed sensor information database 131, and sensor information Based on the information, the environment information in which the user 3 lives and the status information such as the state, operation, and behavior of the user 3 are acquired.

Step S23: Dialogue / situation inference / service selection processing When the voice data of the user 3 collected by the dialogue robot 2 and the sensor information collected by the sensor 12 are accumulated in the distributed environment behavior database 13, the event detection device 15 By referring to the distributed environment behavior database 13, an event such as addition or change of predetermined information is detected and notified to the inference system 11. The inference system 11 infers the situation of the user 3 using the utterance information and situation information of the user 3 related to the event detection as firing conditions, and selects an optimum service from the executable services.

  Alternatively, the dialogue control unit 23 of the dialogue robot 2 infers the context by analyzing the utterance information of the user 3, and infers the situation of the user 3 based on the inferred context and situation information. The optimum service may be selected from the above. In this case, the execution request unit 29 notifies the life support robot system 1 of the selected service execution request.

Step S24: Service Content Determination Process The inference system 11 determines the content of the selected life support service with reference to the information in the distributed environment behavior database 13.

Step S25: Execution Request Processing The inference system 11 generates control information for the appliance 4 to realize the selected service, and transmits it to the corresponding appliance 4.

Step S26: Speech synthesis processing When there is the robot utterance information of the interactive robot 2 as the control information of the service to be executed, the speech synthesizer 22 of the interactive robot 2 performs speech synthesis processing on the robot utterance information to obtain voice data. Is uttered to the user 3.

Step S27: Execution Content Storage Processing The inference system 11 stores the content of the executed service in the service history database 17 as service history information.

Step S28: Speech data recognition processing Thereafter, it is assumed that the user 3 utters “why?” To the service automatically executed by the life support robot system 1 and asks the reason for the service execution. The voice recognition unit 21 of the interactive robot 2 detects and inputs voice data uttered by the user 3, and performs voice recognition processing on the input voice data to acquire user utterance information.

Step S29: Dialogue / situation inference / service selection process The dialogue control unit 23 analyzes the utterance information of the user 3 to infer a context. Here, when the user utterance information includes a question expression such as “why, why” or an expression related to the execution of the service, the utterance information asks the reason for the service execution, that is, the “reason explanation” Inferring that it is a "request". If “acquisition of reason explanation request” is defined as the firing condition for executing the reason explanation service, the dialogue control unit 23 determines the execution of the reason explanation service. The execution request unit 29 notifies the life support robot system 1 of a request for executing the reason explanation service.

Step S30: Service identification process The reasoning system 11 refers to the service history information in the service history database 17 and determines the reason for the plurality of life support services executed within a certain period retroactive from the acquisition (detection) of the firing conditions. Identified as the target of the explanation service.

Step S31: Reason Explanation Text Generation Processing The status information acquisition unit 25 acquires information such as the status at the time of service execution of the service history information for each identified life support service. Further, if necessary, the unique information of the user 3 is acquired from the distributed environment behavior database 13. The dialogue control unit 23 extracts an expression that is a key to explain the reason from the service execution status, generates a reason explanation (reason explanation), and uses it as robot utterance information.

Step S32: Speech Synthesis Processing The speech synthesis unit 22 performs speech synthesis processing on the reason explanation and utters the generated speech data to the user 3.

Step S33: Execution Content Storage Process The inference system 11 stores the reason execution service execution content in the service history database 17 as service history information.

Step S34: Speech data recognition processing After that, when the dialogue robot 2 utters an explanation of the reason, it is assumed that the user 3 responds such as "I understand", "Thank you", or "I don't need it".

  The voice recognition unit 21 detects and inputs the voice data “I understand” of the user 3, performs voice identification processing, and converts it into speech information.

Step S35: Dialogue / Situation Reasoning / Service Selection Process The dialogue control unit 23 analyzes the utterance information of the user 3 and infers the context. When the utterance information includes a positive expression such as “I understand”, it is inferred that the utterance information is a positive response sentence. Then, the user evaluation feedback process is selected. The execution request unit 29 notifies the life support robot system 1 of a user evaluation feedback request.

Step S36: Feedback Process The inference system 11 regards the response sentence of the user 3 to the reason explanation as user evaluation information for the service for which the reason explanation is requested, and learns the user evaluation for the service concerning the reason explanation. Then, based on the learning result, related information such as preference information in the unique information database 137 of the distributed environment behavior database 13 is corrected, or new information indicating the necessity of the service is added.

  For example, it learns from a positive response sentence such as “I understand” that the service for which the reason was explained was necessary and appropriate for the user 3. On the other hand, from the negative response sentence such as “I don't need it”, it is learned that the service whose reason has been explained is unnecessary or inappropriate for the user 3. Based on the learning result, the preference information of the user 3 in the unique information database 137 and the evaluation information about this service are corrected.

  A specific example of the reason explanation service execution process will be described below.

[First Example]
FIG. 6 is a diagram showing a data configuration example of the service history database 17 in the first specific example. The service history database 17 includes information such as the execution time indicating the time when the service was executed, the name of the service (service), the firing condition of the service execution, and the information (content) such as the status at the time of service execution. Is accumulated.

  FIG. 7 is a diagram for explaining the reason explanation service process in the first specific example. In this example, the firing condition of the reason explanation service is “detection of a situation where a plurality of life support services are running in a short time (for example, within a few minutes) and the user 3 is sitting on the sofa”.

  When the firing condition of the reason explanation service is acquired, the service specifying unit 101 specifies a plurality of life support services executed within a predetermined time from the time when the firing condition is detected from the execution time of the service history information. .

  Further, the reason explanation generation unit 103 extracts information used for explanation of the reason from the contents of the service history information for each service, and executes for notifying the user 3 of the life support service being executed as a reason for explaining the reason. Generate a notification. For example, it is assumed that four life support services of television control, program recommendation, lighting control, and air conditioning control are specified from the service history information shown in FIG. In order to notify the user 3 of the execution of these services, there are four types: “I turned on the TV”, “I turned on the XX program”, “I turned on the lights”, and “I turned on the air conditioner”. An execution notification is generated.

  Further, the output order determination unit 105 determines the output order of the execution notifications based on the execution time of the service history information shown in FIG. Here, the output order is determined using the execution time order.

  The voice synthesizer 22 outputs the voice data of the generated execution notification at intervals of a predetermined waiting time (for example, 5 seconds to 10 seconds) so that the user 3 can respond to the execution notification. Output according to order. It is assumed that the user 3's utterance “Why?” Is detected during the standby time after the program recommendation service execution notification “I added a program” has been uttered. When the “request for reason explanation” is inferred from this utterance, the reason explanation generating unit 103 generates the reason explanation “because it is similar to ΔΔ seen before” from the contents of the program recommendation service. The generated voice data is output via the voice synthesizer 22. When the predetermined waiting time elapses, the next service execution notification is output at predetermined intervals in the output order (in this example, "I turned on the lights", "I turned on the air conditioners"). .

  FIG. 8 is a diagram showing a flow of processing of the reason explanation service in the first specific example. When the firing condition of the reason explanation service can be acquired from the sensor information acquired from the sensor 12 (step S110), the preset timing control of the service execution is started (step S111). When the service to be explained is identified based on the service history information (step S112), information such as the status at the time of execution is acquired for each service (step S113).

  Then, at the controlled timing, an execution notification (execution notification sentence) is generated and output as a sound (step S114). If there is a response from the user 3 to the output utterance of the interactive robot 2 (YES in step S115), an explanation (reason explanation) of the execution of the service corresponding to the execution notification output immediately before is generated, and the voice Is output (step S116). If there is no response from the user 3 to the output utterance of the interactive robot 2 (NO in step S115), the process proceeds to step S117.

  If there is a reason explanation target service remaining (YES in step S117), the process returns to step S114. If there is no reason explanation target service remaining (NO in step S117), the contents of the reason explanation service are returned. Is stored in the service history database 17 (step S118).

[Second specific example]
FIG. 9 is a diagram showing a data configuration example of the service history database 17 in the second specific example. The service history database 17 in FIG. 9 has the same configuration as the service history database 17 shown in FIG.

  FIG. 10 is a diagram for explaining the reason explanation service process in the second specific example. In this example, it is assumed that “request for reason explanation” is acquired by inference of the utterance of the user 3 as the firing condition of the reason explanation service.

  When the reason explanation service firing condition is acquired by inferring “reason request” from the user 3 utterance “why?”, The service specifying unit 101 determines the firing condition from the execution time of the service history information. A life support service executed within a predetermined time traced back from the detection time is specified. Here, four life support services similar to those in the first specific example are specified as the reasons for explanation.

The reason explanation generation unit 103 extracts information used for the reason explanation from the contents of the service history information for each service, and generates the following reason explanation.
“I sat on the couch and turned on the TV.” “Similar to the △△ I saw before, I turned on the XX program.” “The room was dark, so the lights were turned on.” “The room was hot. I turned on the air conditioner. "
The output order determination unit 105 determines the output order using the order of execution times of the life support services. The explanation of the reason is output following the oldest (in reverse order) execution time of the life support service. As shown in FIG. 10A, the speech synthesizer 22 generates and outputs the following speech data.
“I sat down on the couch and turned on the TV. It was similar to the △△ I saw before, so I turned on the XX program. The room was dark, so I turned on the lights. The room was hot, so I turned on the air conditioner. "
Further, the output order determination unit 105 determines the output order using the reverse order of the execution times of the life support services. The reason explanation is output in the order of the execution time of the life support service, and as shown in FIG. 10B, the speech synthesizer 22 generates and outputs the following speech data.
"I turned on the air conditioner because the room was hot. I turned on the light because the room was dark. It was similar to the △△ I saw earlier, so I turned on the XX program. I sat on the couch and turned on the TV. "
FIG. 11 is a diagram showing another data configuration example of the service history database 17 in the second specific example. In the service history database 17 of FIG. 11, information (dependency relationship) indicating whether or not there is a dependency relationship is added to the configuration of the service history database 17 shown in FIG. The case where there is a dependency relationship in the life support service is a case where execution of the life support service is selected due to the situation such as execution or contents of another life support service. The service history database 17 of FIG. 11 indicates that the program recommendation service has been selected to be executed according to the contents of the TV control service executed immediately before (the TV is turned on).

The output order determining unit 105 checks the dependency relationship of the service history information, arranges life support services having no dependency relationship in reverse order of execution times, and outputs life support services having dependency relationships in the order of execution time. Order. FIG. 12 is a diagram for explaining the processing of the reason explanation service in the second specific example. As shown in FIG. 12, the speech synthesizer 22 generates and outputs the following speech data.
“I turned on the air conditioner because the room was hot. I turned on the light because the room was dark. I sat on the couch and turned on the TV. It was similar to the △△ I saw earlier, so I turned on the XX program. "
FIG. 13 is a diagram showing a flow of processing of the reason explanation service in the second specific example. When the firing condition of the reason explanation service is acquired from the sensor information acquired from the sensor 12 (step S120), the service is executed within a predetermined period retroactive from the detection of the situation that becomes the firing condition. A life support service other than the explanation service is specified as the reason explanation target (step S121). Information such as the status at the time of execution is acquired for each identified service (step S122). A reason explanation (reason explanation) is generated and output as a voice in a predetermined output order (step S123). The contents of the reason explanation service are stored in the service history database 17 (step S124).

[Third example]
FIG. 14 is a diagram showing a data configuration example of the service history database 17 in the third specific example. The service history database 17 in FIG. 14 is added with flag information (executed flag) indicating that the life support service has been the object of the reason explanation in the configuration of the service history database 17 shown in FIG. Here, it is shown that the reason explanation service for which the air conditioning control service is the subject of explanation is “executed”.

  FIG. 15 is a diagram for explaining the reason explanation service process in the third specific example. In this example, the reasoning service firing conditions are the same as in the second specific example. Each time the user 3 speaks “Why?”, The reason for execution of one life support service is explained.

  When the user's 3 utterance “why?” Is detected and the reasoning service firing condition is acquired, the service specifying unit 101 is closest to the time when the condition that caused the firing condition is detected from the execution time of the service history information. A service that is a life support service other than the reason explanation service executed at the execution time and for which the executed flag is not set is identified as the reason explanation target, and the executed flag is set for the identified service.

  In the service history information shown in FIG. 14, the life support service at the most recent execution time at the time of detecting the situation that has become the firing condition is “air conditioning control”. However, an “executed” flag is set in “air conditioning control”, and the reason has already been explained. Therefore, the “lighting control” at the next execution time is specified as the object of the reason explanation.

As shown in FIG. 16, the reason explanation generation unit 103 extracts information used for the reason explanation from the contents of the service history information for the specified lighting control service, and generates the following reason explanation.
“I turned on the lights because the room was dark.”
Further, when the user 3 detects the utterance “why?” Of the user 3 and the execution of the reason explanation service is started, the service specifying unit 101 similarly explains “program recommendation” from the service history information. Identified as an explanation target.

As illustrated in FIG. 16, the reason explanation generation unit 103 extracts information used for the reason explanation from the contents of the service history information for the identified “program recommendation”, and generates the following reason explanation.
“Since it looks like the △△ I saw before, I put on a XX program.”
FIG. 16 is a diagram showing a flow of processing of the reason explanation service in the third specific example. When the firing condition of the reason explanation service is acquired from the sensor information obtained from the sensor 12 (step S130), the service executed at the most recent execution time is obtained when the situation that becomes the firing condition is detected (step S130). S131), the type of service is determined (step S132). If the service is a life support service (YES in step S132), the process proceeds to step S133. If the service is not a life support service (NO in step S132), the process returns to step S131, and the next closest service is acquired.

  In step S133, it is checked whether or not the executed flag is set. If the executed flag is set (YES in step S133), the process returns to step S131. If the executed flag is not set (NO in step S133), it is specified as the reason for explanation and the executed flag is set for the service (step S134). Information such as the status at the time of execution is acquired for each identified service (step S135). A reason explanation (reason explanation) is generated and output as a voice (step S136). The contents of the reason explanation service are stored in the service history database 17 (step S137).

[Fourth example]
FIG. 17 is a diagram illustrating a data configuration example of the service history database 17 in the fourth specific example. In the service history database 17 of FIG. 17, standby keywords such as words and phrases that may be used in the explanation of the reason to the life support service are added to the configuration of the service history database 17 shown in FIG. Yes. For example, standby keywords such as “TV” are set for the television control service, “program” for the program recommendation service, “lighting and lighting” for the lighting control service, and “air conditioner and air conditioning” for the air conditioning control service.

  FIG. 18 is a diagram for explaining the reason explanation service process in the fourth specific example. In this example, the reasoning service firing conditions are the same as in the second specific example. When the user 3 points out a specific service requesting the reason explanation and requests the reason explanation by the utterance “Why the lighting was turned on”, the reason for executing the indicated life support service is explained.

  Here, as the sensor information, the user 3's utterance "Why did you recommend this program?" It is inferred that this is a request and that the target of the request is a service for “program recommendation”.

The service specifying unit 101 specifies a life support service in which the standby keyword of the service history information matches the word / phrase obtained from the user utterance information as a target for explaining the reason. As illustrated in FIG. 18, the reason explanation generation unit 103 extracts information used for the reason explanation from the contents of the service history information for the specified program recommendation service, and generates the following reason explanation.
“Because it looks like the △△ I saw before.”
FIG. 19 is a diagram illustrating a flow of processing of the reason explanation service in the fourth specific example. When the firing condition of the reason explanation service is acquired by the sensor information obtained from the sensor 12 (step S140), the word that is the key of the utterance content from the utterance (user utterance information) of the user 3 that has become the firing condition, A word is extracted (step S141). Furthermore, the standby keyword of the service executed before the detection of the situation that is the firing condition is matched with the word or phrase extracted in step S141, and the standby keyword matches the extracted word or phrase. Alternatively, a similar service is extracted and specified as a reason explanation target (step S142). Information such as the status at the time of execution is acquired for each identified service (step S143). A reason explanation (reason explanation) is generated and output in a predetermined output order (step S144). The contents of the reason explanation service are stored in the service history database 17 (step S145).

[Fifth Example]
FIG. 20 is a diagram illustrating a data configuration example of the service history database 17 in the fifth specific example. The service history database 17 shown in FIG. 20 includes the contents of the service support database 17 shown in FIG. 6 and the contents of the life support service used by the interactive robot 2 for utterances for confirming the reason for explanation to the user 3. Utterance keywords such as words and phrases are added. For example, an utterance keyword such as “TV” is set for the television control service, “program recommendation” for the program recommendation service, “lighting” for the lighting control service, and “air conditioning” for the air conditioning control service.

  FIG. 21 is a diagram for explaining the reason explanation service process in the fifth specific example. In this example, the reasoning service firing conditions are the same as in the second specific example. When the utterance “why?” Of the user 3 is detected and the firing condition of the reason explanation service is acquired, a plurality of life support services executed within a predetermined period retroactive from the detection time are specified. Then, whether or not the identified service is the target of reason explanation is sequentially confirmed by the user 3, and the reason for the execution of the life support service confirmed by the user 3 is explained.

The service specifying unit 101 specifies, from the execution time of the service history information, the life support service executed at the execution time closest to the detection of the situation that is the firing condition, as the reason explanation target. As shown in FIG. 21, the reason explanation generation unit 103 uses the utterance keyword of each life support service in the service history information for the specified life support service to perform object confirmation (object confirmation text). ) Is generated.
“Air conditioning?” “Lighting?” “Program recommendation?” “TV?”
The voice synthesizer 22 outputs the voice data of the target confirmation sentence one by one from the life support service with a new execution time according to the output order determined by the output order determiner 105.

  Based on the utterance of the user 3 with respect to the output target confirmation, the reason explanation generation unit 103 determines that the response to the target confirmation of the user 3 is a negative response such as “No.” Output confirmation. On the other hand, when the response of the user 3 is an affirmative response such as “Yes,” for example, an explanation (reason explanation) of the execution of the target confirmation service that prompted the affirmative response is generated. The voice synthesizer 22 outputs the voice data of the generated reason explanation text.

  In the example of FIG. 21, since it is inferred that user 3's utterance “I'm different” is a negative response to the output of the target confirmation “Is air conditioning?”, The next target confirmation “Is lighting? Is output. If it is inferred that the utterance of the user 3 in response to this is also a negative response, the next target confirmation “program recommendation?” Is output in the same manner. If it is inferred that user 3's utterance “Yes” is an affirmative response to the target confirmation “Is program recommendation?” Is generated and output.

  Although not shown in FIG. 21, it is also possible to output the next target confirmation “TV?” And perform the same processing as described above.

  FIG. 22 is a diagram showing the flow of processing of the reason explanation service in the fifth specific example. When the firing condition of the reason explanation service is acquired from the sensor information acquired from the sensor 12 (step S150), the reason explanation service other than the reason explanation service executed within a predetermined period is detected retroactively from the detection of the situation that becomes the firing condition. The life support service is specified as the reason explanation target (step S151). An utterance keyword of service history information is acquired for each identified service (step S152). Based on the utterance keyword of each service, a target confirmation (target confirmation sentence) is generated and output as a voice (step S153). It is inferred whether or not the utterance of the user 3 with respect to the output target confirmation is an affirmative response (step S154). If the utterance of the user 3 is an affirmative response (YES in step S154), a reason explanation (reason explanation) of execution of the service related to the target confirmation sentence is generated and outputted as a voice (step S155). If there is a next service to be checked (YES in step S156), the process returns to step S153 to check the target of the next specified life support service. If there is no next service to be checked (NO in step S156), the contents of the reason explanation service are stored in the service history database 17 (step S157). If the utterance of the user 3 is not a positive response (NO in step S154), the contents of the reason explanation service are stored in the service history database 17 (step S157).

  In the first to fifth embodiments, while the reason explanation service is being executed, there is an utterance that is negatively answered by the user 3 such as "I don't need it" or "I'm fine". When a “request to cancel the reason explanation service” is inferred from the utterance information, the reason explanation service being executed is canceled.

  While the present invention has been described above with reference to the embodiments, it is obvious that the present invention can be variously modified within the scope of the gist thereof.

  In the present embodiment, for the sake of simplicity of explanation, the processing for a single user 3 has been described. However, the present invention can be implemented as processing for each user even in the case of a plurality of users. In this case, information indicating to which user the life support service is provided is accumulated in the service history information.

  In addition, the present invention can be implemented as a program that is read and executed by a computer. However, a program that realizes the present invention is an appropriate record such as portable medium memory, semiconductor memory, and hard disk that can be read by a computer. It can be stored in a medium, provided by being recorded on these recording media, or provided by transmission / reception using various communication networks via a communication interface.

It is a figure which shows the structural example in implementation of the dialogue system of this invention. It is a figure which shows the structural example of a life support robot system and a dialogue robot. It is a figure which shows the structural example of a distributed environment action database. It is a figure for demonstrating the outline | summary of the process of this invention. It is a figure which shows the example of the flow of a process of a dialogue system. It is a figure which shows the data structural example of the service history database in a 1st specific example. It is a figure for demonstrating the process of the reason explanation service in a 1st specific example. It is a figure which shows the flow of a process of the reason explanation service in a 1st specific example. It is a figure which shows the data structural example of the service history database in a 2nd specific example. It is a figure for demonstrating the process of the reason explanation service in a 2nd specific example. It is a figure which shows another data structural example of the service history database in a 2nd specific example. It is a figure for demonstrating the process of the reason explanation service in a 2nd specific example. It is a figure which shows the flow of a process of the reason explanation service in a 2nd specific example. It is a figure which shows the data structural example of the service history database in a 3rd specific example. It is a figure for demonstrating the process of the reason explanation service in a 3rd specific example. It is a figure which shows the flow of a process of the reason explanation service in a 3rd specific example. It is a figure which shows the example of a data structure of the service history database in a 4th specific example. It is a figure for demonstrating the process of the reason explanation service in a 4th specific example. It is a figure which shows the flow of a process of the reason explanation service in a 4th specific example. It is a figure which shows the example of a data structure of the service history database in a 5th specific example. It is a figure for demonstrating the process of the reason explanation service in a 5th example. It is a figure which shows the flow of a process of the reason explanation service in a 5th specific example.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Life support robot system 11 Reasoning system 12 Sensor 13 Distributed environment action database 15 Event detection apparatus 17 Service history database 2 Dialogue robot 100 Reason explanation service processing part 101 Service specification part 103 Reason explanation generation part 105 Output order determination part 21 Voice recognition part DESCRIPTION OF SYMBOLS 22 Speech synthesis part 23 Dialog control part 24 Dialog strategy database 25 Situation information acquisition part 26 Situation storage part 27 Knowledge database 29 Execution request part 3 User 4 Appliance

Claims (18)

An inference system that controls the appliance by inferring the environment in the space and the user's behavior based on sensor information measured in a predetermined space in order to autonomously control a plurality of appliances that execute services A life support robot system comprising a distributed environmental behavior database for accumulating environmental information and behavior information as inference results by the inference system, and a service history information database for accumulating history information of services provided by the inference system; Collaborate with the life support robot system, infer the utterance context based on the user utterance information generated by voice recognition processing of the user's voice data, and synthesize the utterance information generated based on the inference A dialogue robot comprising a dialogue robot for outputting the voice data and having a voice dialogue with the user. Temu runs, a processing method for describing the execution reason service the life support robot system is provided,
A service history including information on the execution time of the service and the status at the time of service execution when the service is executed based on the status of the user inferred from the environmental information and the behavior information stored in the distributed environment behavior database A process of storing information in the service history information database;
When a predetermined situation for explaining the reason why the service is executed is detected, a plurality of services executed within a predetermined period from the time of detection are selected as the object of the reason explanation from the service history information database. Process to identify,
A process of generating an execution notification for notifying the execution of the service for each identified service;
A process of determining the output order of the execution notifications based on the execution time of each identified service;
A process of synthesizing the execution notification according to the output order and outputting the generated voice data from the interactive robot according to a predetermined response waiting period interval;
Corresponds to the execution notification when it is inferred that the user's utterance is a service execution reason explanation request based on the context of the user's utterance information detected during a predetermined response waiting period after the execution notification. Based on the service history information of the service, a process for generating a description of the reason for executing the service,
A reason explanation service processing method using a dialog robot, comprising: a process of performing voice synthesis processing on the reason explanation and outputting the generated voice data from the dialog robot. An inference system that controls the appliance by inferring the environment in the space and the user's behavior based on sensor information measured in a predetermined space in order to autonomously control a plurality of appliances that execute services A life support robot system comprising a distributed environmental behavior database for accumulating environmental information and behavior information as inference results by the inference system, and a service history information database for accumulating history information of services provided by the inference system; Collaborate with the life support robot system, infer the utterance context based on the user utterance information generated by voice recognition processing of the user's voice data, and synthesize the utterance information generated based on the inference A dialogue robot comprising a dialogue robot for outputting the voice data and having a voice dialogue with the user. Temu runs, a processing method for describing the execution reason service the life support robot system is provided,
Information about the execution time of the service and the status at the time of service execution for the service inferred from the environment information and behavior information accumulated in the distributed environment behavior database and selected and executed based on the user status A process of storing service history information including the service history information in the service history information database;
When it is inferred that the user's utterance is a request for explaining the reason for service execution based on the context of the user's utterance information, a plurality of items executed within a predetermined period from the time of the user's utterance are determined from the service history information. The process of identifying the service of the subject as the subject of the reason explanation,
For each identified service, a process of generating a description of the reason for executing the service;
A process of determining an output order of the explanation of reasons based on an execution time of each identified service;
A reason explanation service processing method using a dialog robot, comprising: a process of performing voice synthesis processing on the reason explanation according to the output order, and outputting the generated voice data from the dialog robot. In the process of storing the service history information, as the service history information, dependency relationships between executed services are stored in the service history information database;
In the process of determining the output order, when there is the dependency relationship between the identified services, the output order of the explanation of the reason for executing the service having the dependency relationship is set to the execution time order of the service. The reason explanation service processing method using the dialogue robot according to claim 2, wherein the reason explanation service processing method is used. An inference system that controls the appliance by inferring the environment in the space and the user's behavior based on sensor information measured in a predetermined space in order to autonomously control a plurality of appliances that execute services A life support robot system comprising a distributed environmental behavior database for accumulating environmental information and behavior information as inference results by the inference system, and a service history information database for accumulating history information of services provided by the inference system; Collaborate with the life support robot system, infer the utterance context based on the user utterance information generated by voice recognition processing of the user's voice data, and synthesize the utterance information generated based on the inference A dialogue robot comprising a dialogue robot for outputting the voice data and having a voice dialogue with the user. Temu runs, a processing method for describing the execution reason service the life support robot system is provided,
Information about the execution time of the service and the status at the time of service execution for the service inferred from the environment information and the behavior information stored in the distributed environment behavior database and selected and executed based on the user status , And service history information including information indicating whether or not the service has been selected as a reason explanation target, and a process of storing in the service history information database;
When it is inferred that the user's utterance is a request for explaining the reason for service execution based on the context of the user's utterance information, the execution time closest to the user's utterance is obtained from the service history information, and A process of identifying one service not selected as the reason for explanation as a reason for explanation;
A process of generating a description of the reason for execution of the identified service from the service history information;
A reason explanation service processing method using a dialog robot, comprising: a voice synthesis process for explaining the reason for execution of the specified service and outputting the generated voice data from the dialog robot. An inference system that controls the appliance by inferring the environment in the space and the user's behavior based on sensor information measured in a predetermined space in order to autonomously control a plurality of appliances that execute services A life support robot system comprising a distributed environmental behavior database for accumulating environmental information and behavior information as inference results by the inference system, and a service history information database for accumulating history information of services provided by the inference system; Collaborate with the life support robot system, infer the utterance context based on the user utterance information generated by voice recognition processing of the user's voice data, and synthesize the utterance information generated based on the inference A dialogue robot comprising a dialogue robot for outputting the voice data and having a voice dialogue with the user. Temu runs, a processing method for describing the execution reason service the life support robot system is provided,
Information about the execution time of the service and the status at the time of service execution for the service inferred from the environment information and the behavior information stored in the distributed environment behavior database and selected and executed based on the user status And a process of storing service history information including standby information for specifying the service of the user's reason explanation request in the service history information database;
When it is inferred that the user's utterance is a request for explaining the reason for service execution based on the context of the user's utterance information, the execution time closest to the user's utterance and the user's utterance information A process of identifying, as the object of the reason explanation, one service in which the information included in the service information and the standby information of the service history information match,
A process of generating a description of the reason for execution of the identified service from the service history information;
A reason explanation service processing method using a dialog robot, comprising: a voice synthesis process for explaining the reason for execution of the specified service and outputting the generated voice data from the dialog robot. An inference system that controls the appliance by inferring the environment in the space and the user's behavior based on sensor information measured in a predetermined space in order to autonomously control a plurality of appliances that execute services A life support robot system comprising a distributed environmental behavior database for accumulating environmental information and behavior information as inference results by the inference system, and a service history information database for accumulating history information of services provided by the inference system; Collaborate with the life support robot system, infer the utterance context based on the user utterance information generated by voice recognition processing of the user's voice data, and synthesize the utterance information generated based on the inference A dialogue robot comprising a dialogue robot for outputting the voice data and having a voice dialogue with the user. Temu runs, a processing method for describing the execution reason service the life support robot system is provided,
Information about the execution time of the service and the status at the time of service execution for the service inferred from the environment information and behavior information accumulated in the distributed environment behavior database and selected and executed based on the user status A process of storing service history information including the service history information in the service history information database;
When it is inferred that the user's utterance is a request for explaining the reason for service execution based on the context of the user's utterance information, a plurality of items executed within a predetermined period from the time of the user's utterance are determined from the service history information. The process of identifying the service of the subject as the subject of the reason explanation,
A process of generating an object confirmation for confirming to the user whether the identified service is an object of reason explanation;
A process of synthesizing the target confirmation and outputting the generated voice data from the interactive robot;
When it is inferred that the user's utterance is an affirmative response to the target confirmation based on the context of the user's utterance information for the target confirmation, the service confirmation information is used for the positively confirmed target confirmation. A process of generating a description of the reason for executing the corresponding service;
A reason explanation service processing method using a dialog robot, comprising: a process of performing voice synthesis processing on the reason explanation and outputting the generated voice data from the dialog robot. An inference system that controls the appliance by inferring the environment in the space and the user's behavior based on sensor information measured in a predetermined space in order to autonomously control a plurality of appliances that execute services A life support robot system comprising a distributed environmental behavior database for accumulating environmental information and behavior information as inference results by the inference system, and a service history information database for accumulating history information of services provided by the inference system; Collaborate with the life support robot system, infer the utterance context based on the user utterance information generated by voice recognition processing of the user's voice data, and synthesize the utterance information generated based on the inference A dialogue robot comprising a dialogue robot for outputting the voice data and having a voice dialogue with the user. Temu comprises, a processing apparatus for explaining the execution reason service the life support robot system is provided,
A service history including information on the execution time of the service and the status at the time of service execution when the service is executed based on the status of the user inferred from the environmental information and the behavior information stored in the distributed environment behavior database Processing means for storing information in the service history information database;
When a predetermined situation for explaining the reason why the service is executed is detected, a plurality of services executed within a predetermined period from the time of detection are selected as the object of the reason explanation from the service history information database. Processing means to identify;
For each identified service, an execution notification for notifying the execution of the service is generated, and the user's utterance is a service based on the context of the user's utterance information detected during a predetermined response waiting period after the execution notification. Processing means for generating a reason for executing the service based on service history information of the service corresponding to the execution notification when it is inferred that the request is an explanation of the reason for execution;
Processing means for determining the output order of the execution notifications based on the execution time of each identified service;
From the interactive robot, the execution notification is subjected to speech synthesis processing according to the output order, the generated speech data is output according to a predetermined response waiting period interval, the reason explanation is speech synthesized, and the generated speech data is A reason explanation service processing apparatus using a dialogue robot, characterized by comprising: a processing means for outputting. An inference system that controls the appliance by inferring the environment in the space and the user's behavior based on sensor information measured in a predetermined space in order to autonomously control a plurality of appliances that execute services A life support robot system comprising a distributed environmental behavior database for accumulating environmental information and behavior information as inference results by the inference system, and a service history information database for accumulating history information of services provided by the inference system; Collaborate with the life support robot system, infer the utterance context based on the user utterance information generated by voice recognition processing of the user's voice data, and synthesize the utterance information generated based on the inference A dialogue robot comprising a dialogue robot for outputting the voice data and having a voice dialogue with the user. Temu comprises, a processing apparatus for explaining the execution reason service the life support robot system is provided,
Information about the execution time of the service and the status at the time of service execution for the service inferred from the environment information and behavior information accumulated in the distributed environment behavior database and selected and executed based on the user status Processing means for storing service history information including the service history information in the service history information database;
When it is inferred that the user's utterance is a request for explaining the reason for service execution based on the context of the user's utterance information, a plurality of items executed within a predetermined period from the time of the user's utterance are determined from the service history information. A processing means for identifying the service as the object of the reason explanation,
Processing means for generating an explanation of the reason for executing the service for each identified service;
Processing means for determining an output order of the explanation of reasons based on execution times of the specified services;
A reason explanation service processing apparatus using a dialogue robot, comprising: processing means for performing voice synthesis processing on the reason explanation according to the output order and outputting the generated voice data from the dialogue robot. The processing means for accumulating the service history information accumulates dependencies between executed services in the service history information database as the service history information.
The processing means for determining the output order includes the output order of the explanation of the reason for executing the service having the dependency relation, and the execution time order of the service when the specified service has the dependency relation. The reason explanation service processing apparatus using the dialog robot according to claim 8, wherein the reason explanation service processing apparatus is used. An inference system that controls the appliance by inferring the environment in the space and the user's behavior based on sensor information measured in a predetermined space in order to autonomously control a plurality of appliances that execute services A life support robot system comprising a distributed environmental behavior database for accumulating environmental information and behavior information as inference results by the inference system, and a service history information database for accumulating history information of services provided by the inference system; Collaborate with the life support robot system, infer the utterance context based on the user utterance information generated by voice recognition processing of the user's voice data, and synthesize the utterance information generated based on the inference A dialogue robot comprising a dialogue robot for outputting the voice data and having a voice dialogue with the user. Temu comprises, a processing apparatus for explaining the execution reason service the life support robot system is provided,
Information about the execution time of the service and the status at the time of service execution for the service inferred from the environment information and the behavior information stored in the distributed environment behavior database and selected and executed based on the user status , And service history information including information indicating whether or not the service has been selected as a reason explanation target, and processing means for accumulating in the service history information database;
When it is inferred that the user's utterance is a request for explaining the reason for service execution based on the context of the user's utterance information, the execution time closest to the user's utterance is obtained from the service history information, and Processing means for identifying one service not selected as the reason explanation target as the reason explanation target;
Processing means for generating a description of the reason for execution of the identified service from the service history information;
A reason explanation service processing apparatus using a dialog robot, comprising: processing means for performing a speech synthesis process on the reason for executing the specified service and outputting the generated voice data from the dialog robot. An inference system that controls the appliance by inferring the environment in the space and the user's behavior based on sensor information measured in a predetermined space in order to autonomously control a plurality of appliances that execute services A life support robot system comprising a distributed environmental behavior database for accumulating environmental information and behavior information as inference results by the inference system, and a service history information database for accumulating history information of services provided by the inference system; Collaborate with the life support robot system, infer the utterance context based on the user utterance information generated by voice recognition processing of the user's voice data, and synthesize the utterance information generated based on the inference A dialogue robot comprising a dialogue robot for outputting the voice data and having a voice dialogue with the user. Temu comprises, a processing apparatus for explaining the execution reason service the life support robot system is provided,
Information about the execution time of the service and the status at the time of service execution for the service inferred from the environment information and the behavior information stored in the distributed environment behavior database and selected and executed based on the user status And processing means for storing in the service history information database service history information including standby information for service identification of the user's reason explanation request,
When it is inferred that the user's utterance is a request for explaining the reason for service execution based on the context of the user's utterance information, the execution time closest to the user's utterance and the user's utterance information Processing means for identifying, as the reason explanation target, one service in which the information included in the service information and the standby information of the service history information match,
Processing means for generating a description of the reason for execution of the identified service from the service history information;
A reason explanation service processing apparatus using a dialog robot, comprising: processing means for performing a speech synthesis process on the reason for executing the specified service and outputting the generated voice data from the dialog robot. An inference system that controls the appliance by inferring the environment in the space and the user's behavior based on sensor information measured in a predetermined space in order to autonomously control a plurality of appliances that execute services A life support robot system comprising a distributed environmental behavior database for accumulating environmental information and behavior information as inference results by the inference system, and a service history information database for accumulating history information of services provided by the inference system; Collaborate with the life support robot system, infer the utterance context based on the user utterance information generated by voice recognition processing of the user's voice data, and synthesize the utterance information generated based on the inference A dialogue robot comprising a dialogue robot for outputting the voice data and having a voice dialogue with the user. Temu comprises, a processing apparatus for explaining the execution reason service the life support robot system is provided,
Information about the execution time of the service and the status at the time of service execution for the service inferred from the environment information and behavior information accumulated in the distributed environment behavior database and selected and executed based on the user status Processing means for storing service history information including the service history information in the service history information database;
When it is inferred that the user's utterance is a request for explaining the reason for service execution based on the context of the user's utterance information, a plurality of items executed within a predetermined period from the time of the user's utterance are determined from the service history information. A processing means for identifying the service as the object of the reason explanation,
A target confirmation is generated to confirm to the user whether or not the identified service is a target of reason explanation, and the user's utterance is determined based on a context of the user's utterance information with respect to the target confirmation. Processing means for generating, from the service history information, a reason for executing the service corresponding to the positively confirmed target confirmation when it is inferred that the response is a positive response to
A dialogue robot comprising: processing means for performing voice synthesis processing on the target confirmation from the dialogue robot, outputting the generated voice data, performing voice synthesis processing on the explanation of the reason, and outputting the generated voice data. Reason explanation service processing device using An inference system that controls the appliance by inferring the environment in the space and the user's behavior based on sensor information measured in a predetermined space in order to autonomously control a plurality of appliances that execute services A life support robot system comprising a distributed environmental behavior database for accumulating environmental information and behavior information as inference results by the inference system, and a service history information database for accumulating history information of services provided by the inference system; Collaborate with the life support robot system, infer the utterance context based on the user utterance information generated by voice recognition processing of the user's voice data, and synthesize the utterance information generated based on the inference A dialogue robot comprising a dialogue robot for outputting the voice data and having a voice dialogue with the user. In Temu,
A service history including information on the execution time of the service and the status at the time of service execution when the service is executed based on the status of the user inferred from the environmental information and the behavior information stored in the distributed environment behavior database Storing information in the service history information database;
When a predetermined situation for explaining the reason why the service is executed is detected, a plurality of services executed within a predetermined period from the time of detection are selected as the object of the reason explanation from the service history information database. Processing to identify,
Processing for generating an execution notification for notifying the execution of the service for each identified service;
A process for determining the output order of the execution notifications based on the execution time of each identified service;
A process of performing speech synthesis processing on the execution notification according to the output order, and outputting the generated voice data from the interactive robot according to a predetermined response waiting period interval;
Corresponds to the execution notification when it is inferred that the user's utterance is a service execution reason explanation request based on the context of the user's utterance information detected during a predetermined response waiting period after the execution notification. A process for generating a description of the reason for executing the service based on the service history information of the service;
Processing the speech explanation for the reason explanation and outputting the generated speech data from the interactive robot;
Reason explanation service processing program using a dialogue robot for execution. An inference system that controls the appliance by inferring the environment in the space and the user's behavior based on sensor information measured in a predetermined space in order to autonomously control a plurality of appliances that execute services A life support robot system comprising a distributed environmental behavior database for accumulating environmental information and behavior information as inference results by the inference system, and a service history information database for accumulating history information of services provided by the inference system; Collaborate with the life support robot system, infer the utterance context based on the user utterance information generated by voice recognition processing of the user's voice data, and synthesize the utterance information generated based on the inference A dialogue robot comprising a dialogue robot for outputting the voice data and having a voice dialogue with the user. In Temu,
Information about the execution time of the service and the status at the time of service execution for the service inferred from the environment information and behavior information accumulated in the distributed environment behavior database and selected and executed based on the user status Storing service history information including the service history information in the service history information database;
When it is inferred that the user's utterance is a request for explaining the reason for service execution based on the context of the user's utterance information, a plurality of items executed within a predetermined period from the time of the user's utterance are determined from the service history information. The process of identifying the service of the subject as the object of the reason explanation,
For each identified service, a process for generating a description of the reason for executing the service;
A process for determining the output order of the explanation of reasons based on the execution time of each identified service;
A process of synthesizing the explanation of the reason according to the output order and outputting the generated voice data from the interactive robot;
Reason explanation service processing program using a dialogue robot for execution. In the process of storing the service history information, as the service history information, dependency relationships between executed services are stored in the service history information database;
In the process of determining the output order, when there is the dependency relationship between the identified services, the output order of the explanation of the reason for executing the service in the dependency relationship is determined based on the execution time order of the service. The process to determine
A reason explanation service processing program using the dialogue robot according to claim 14 for execution. An inference system that controls the appliance by inferring the environment in the space and the user's behavior based on sensor information measured in a predetermined space in order to autonomously control a plurality of appliances that execute services A life support robot system comprising a distributed environmental behavior database for accumulating environmental information and behavior information as inference results by the inference system, and a service history information database for accumulating history information of services provided by the inference system; Collaborate with the life support robot system, infer the utterance context based on the user utterance information generated by voice recognition processing of the user's voice data, and synthesize the utterance information generated based on the inference A dialogue robot comprising a dialogue robot for outputting the voice data and having a voice dialogue with the user. In Temu,
Information about the execution time of the service and the status at the time of service execution for the service inferred from the environment information and the behavior information stored in the distributed environment behavior database and selected and executed based on the user status , And service history information including information indicating whether or not the service has been selected as a reason explanation target, and a process of accumulating in the service history information database;
When it is inferred that the user's utterance is a request for explaining the reason for service execution based on the context of the user's utterance information, the execution time closest to the user's utterance is obtained from the service history information, and A process of identifying one service not selected as the reason explanation target as the reason explanation target;
Processing for generating an explanation of the reason for execution of the identified service from the service history information;
A process of performing a speech synthesis process on the reason for executing the identified service and outputting the generated voice data from the interactive robot;
Reason explanation service processing program using a dialogue robot for execution. An inference system that controls the appliance by inferring the environment in the space and the user's behavior based on sensor information measured in a predetermined space in order to autonomously control a plurality of appliances that execute services A life support robot system comprising a distributed environmental behavior database for accumulating environmental information and behavior information as inference results by the inference system, and a service history information database for accumulating history information of services provided by the inference system; Collaborate with the life support robot system, infer the utterance context based on the user utterance information generated by voice recognition processing of the user's voice data, and synthesize the utterance information generated based on the inference A dialogue robot comprising a dialogue robot for outputting the voice data and having a voice dialogue with the user. In Temu,
Information about the execution time of the service and the status at the time of service execution for the service inferred from the environment information and the behavior information stored in the distributed environment behavior database and selected and executed based on the user status , And a process of storing service history information including standby information for service identification of the user reason explanation request in the service history information database;
When it is inferred that the user's utterance is a request for explaining the reason for service execution based on the context of the user's utterance information, the execution time closest to the user's utterance and the user's utterance information A process for identifying, as the reason explanation target, one service in which the information included in the service information and the standby information of the service history information match,
Processing for generating an explanation of the reason for execution of the identified service from the service history information;
A process of performing a speech synthesis process on the reason for executing the identified service and outputting the generated voice data from the interactive robot;
Reason explanation service processing program using a dialogue robot for execution. An inference system that controls the appliance by inferring the environment in the space and the user's behavior based on sensor information measured in a predetermined space in order to autonomously control a plurality of appliances that execute services A life support robot system comprising a distributed environmental behavior database for accumulating environmental information and behavior information as inference results by the inference system, and a service history information database for accumulating history information of services provided by the inference system; Collaborate with the life support robot system, infer the utterance context based on the user utterance information generated by voice recognition processing of the user's voice data, and synthesize the utterance information generated based on the inference A dialogue robot comprising a dialogue robot for outputting the voice data and having a voice dialogue with the user. In Temu,
Information about the execution time of the service and the status at the time of service execution for the service inferred from the environment information and behavior information accumulated in the distributed environment behavior database and selected and executed based on the user status Storing service history information including the service history information in the service history information database;
When it is inferred that the user's utterance is a request for explaining the reason for service execution based on the context of the user's utterance information, a plurality of items executed within a predetermined period from the time of the user's utterance are determined from the service history information. The process of identifying the service of the subject as the object of the reason explanation,
Processing for generating an object confirmation for confirming to the user whether or not the identified service is an object of reason explanation;
Processing for synthesizing the target confirmation and outputting the generated speech data from the interactive robot;
When it is inferred that the user's utterance is an affirmative response to the target confirmation based on the context of the user's utterance information for the target confirmation, the service confirmation information is used for the positively confirmed target confirmation. Processing to generate a description of the reason for executing the corresponding service;
Processing the speech explanation for the reason explanation and outputting the generated speech data from the interactive robot;
Reason explanation service processing program using a dialogue robot for execution.

Images