JP2018161713A - Dialog control device and robot control system - Google Patents

Abstract

An interactive control apparatus and a robot control system capable of performing a natural dialog with a customer are provided. A dialogue control apparatus includes an information acquisition unit, a scenario progress control unit, a scenario correction unit, and a corrected dialogue scenario utterance unit. The information acquisition unit acquires dialog scenario information for interacting with a customer who has visited a restaurant from a plurality of dialog scenario information. The scenario progress control unit controls the progress of the dialog scenario corresponding to the acquired dialog scenario information. The scenario correction unit corrects the dialogue scenario based on the stay state of the customer determined by the stay state determination unit. The corrected dialogue scenario utterance unit is a dialogue scenario in which the scenario correction unit corrects the dialogue scenario executed immediately before or the dialogue scenario to be executed immediately after when an instruction to return or advance the dialogue scenario is given. To speak. [Selection] Figure 1

Description

  The present invention relates to a dialog control device and a robot control system.

  In recent years, there have been cases where humanoid robots are used as a guide for visitors in restaurants and other public facilities (see Patent Document 1). A technology for performing communication (dialogue) with such robots using dedicated operation terminals is being studied. According to this technology, customers can enjoy dialogues with robots via operation terminals and provide guidance information. Can be obtained.

  Specifically, a service is conceivable in which the user can interact directly or indirectly with a robot installed at a table seat. In this case, customer satisfaction can be improved by presenting a recommended menu or chatting.

Japanese Patent Laying-Open No. 2015-66623

  However, various sounds (conversations, tableware sounds, people walking, clerk greetings, etc.) are mixed in the restaurant, and it is often impossible to hear the content of the robot's utterance. May occur. In this case, if the robot speaks the same content as once spoken, there is a problem that it makes the customer feel that they are “interacting with the robot”.

  Therefore, the problem to be solved by the present invention is to provide a dialog control device and a robot control system capable of performing a natural dialog with a customer.

  An interactive control device according to an embodiment includes an information acquisition unit that acquires interactive scenario information for interacting with a customer who has visited a restaurant from a plurality of interactive scenario information, and progress of the interactive scenario corresponding to the acquired interactive scenario information Based on the stay state of the customer determined by the stay state determination unit and the stay state determination unit that determines the stay state of the customer in the restaurant When the scenario correction unit and an instruction to return or advance the progress of the dialog scenario are given, the dialog scenario executed immediately before or the dialog scenario to be executed immediately after is replaced with the dialog scenario corrected by the scenario correction unit. And a corrected dialogue scenario utterance section that causes the user to utter.

  The corrected dialogue scenario utterance unit replaces the dialogue scenario executed immediately before or the dialogue scenario to be executed immediately after with the dialogue scenario corrected by the scenario correction unit and utters a predetermined predetermined word. You can also speak.

  The predetermined word may include a word informing that the utterance of the dialog scenario executed immediately before or the dialog scenario to be executed immediately after is started.

  The scenario correction unit may perform correction processing for summarizing the dialogue scenario based on the stay state of the customer determined by the stay state determination unit.

  The scenario correction unit may generate a summary scenario that summarizes the dialog scenario executed immediately before or the dialog scenario to be executed immediately after, and the correction dialog scenario utterance unit may utter the generated summary scenario.

  The corrected dialogue scenario utterance unit may acquire the dialogue scenario executed immediately before and the summary of the dialogue scenario to be executed immediately after, from the scenario summary accumulation unit that accumulated the utterance.

  A user interface unit that performs at least one of information input, information selection, and information operation for dialogue with the robot, and the correction dialogue scenario utterance unit is an information input that returns or advances the progress of the dialogue scenario by the user interface unit; When information selection or information manipulation is performed, the dialog scenario executed immediately before or the dialog scenario to be executed immediately after may be summarized and the robot may speak.

  The user interface unit has a touch panel, and a first control unit that displays at least one index for controlling the progress of the dialog in the touch panel, and advances, returns, or stops the dialog according to the operation of the index Or a second control unit that performs control of switching.

  The user interface unit outputs a first detection signal indicating a direction in which the touch panel is traced based on the index, and the second control unit controls whether to advance or return the dialogue based on the first detection signal, The correction dialogue scenario utterance unit may summarize the dialogue scenario executed immediately before or the dialogue scenario to be executed immediately after the second control unit performs control to return the dialogue or control to advance the dialogue. Good.

A robot control system according to an embodiment includes a robot that performs an operation according to an instruction signal;
An operation terminal for operating the robot by generating an instruction signal,
An information acquisition unit that acquires dialogue scenario information for interacting with a customer who has visited a restaurant from a plurality of dialogue scenario information, a scenario progress control unit that controls the progress of the conversation scenario corresponding to the acquired dialogue scenario information, and the customer The stay state determination unit that determines the stay state in the restaurant, the scenario correction unit that corrects the dialogue scenario based on the stay state of the customer determined by the stay state determination unit, and the progress of the conversation scenario A dialogue scenario utterance unit that, when instructed to return or proceed, replaces the dialogue scenario executed immediately before or the dialogue scenario to be executed immediately after with the dialogue scenario corrected by the scenario correction unit, and Prepare.

  ADVANTAGE OF THE INVENTION According to this invention, the dialog control apparatus and robot control system which can perform a natural dialog with a customer can be provided.

The block diagram which shows an example of the robot control system which concerns on one Embodiment. The block diagram which shows an example of the input part which concerns on one Embodiment. The block diagram of the scenario control part which concerns on one Embodiment. A flowchart showing an operation example related to the progress control of the dialogue performed by the scenario control. The flowchart which shows the detailed process of step S13 in FIG. The figure which shows an example of the dialogue between a robot and a user. The figure which shows the example of a display of a display part when a choice is selected by the user. FIG. 6 is a diagram illustrating a scene in which a user is instructed to send forward in FIG. 5. The figure which shows the scene which is waiting for order to finish and a dish to come. The block diagram which shows an example of the robot control system which concerns on a 1st modification. The figure which shows the structure of the robot control system which concerns on a 2nd modification.

  Hereinafter, configurations and operations of a dialog control system and a robot control system according to an embodiment of the present invention will be described in detail with reference to the drawings. In addition, embodiment shown below is an example of embodiment of this invention, This invention is limited to these embodiment, and is not interpreted. In the drawings referred to in this embodiment, the same portions or portions having similar functions are denoted by the same reference symbols or similar symbols, and repeated description thereof may be omitted. In addition, the dimensional ratio in the drawing may be different from the actual ratio for convenience of explanation, or a part of the configuration may be omitted from the drawing.

  FIG. 1 is a block diagram showing a robot control system 1 according to an embodiment of the present invention. As shown in FIG. 1, the robot control system 1 includes a robot 2, an operation terminal 3 that is an example of a robot control device, a handy terminal 4, and a store system 5 such as a POS (Point of Sales) system. . The robot control system 1 is, for example, a system for a restaurant customer (hereinafter referred to as a user) to interact with the robot 2 via the operation terminal 3 that operates the robot 2. Note that the dialogue control apparatus according to the present embodiment includes the operation terminal 3.

  The robot 2 in FIG. 1 is a machine having a human-like appearance and interactive function, that is, a humanoid. Note that the robot 2 may have a dissimilar appearance to humans such as animals and characters. Further, the robot 2 may be a virtual robot based on an image displayed on the display unit 35.

(Robot 2)
As shown in FIG. 1, the robot 2 includes a robot drive unit 21 and a robot control unit 22 that is an example of a drive control unit. The robot 2 may be driven by electric power supplied from a commercial power source, or may be driven by a battery such as a battery.

  The robot drive unit 21 includes a voice output device that outputs the speech voice of the robot 2. By driving the robot drive unit 21 as necessary, the robot 2 can speak to perform a dialogue with the user. A drive control signal for controlling the drive of the robot drive unit 21 is input from the robot control unit 22 to the robot drive unit 21. The robot drive unit 21 is driven according to the drive control signal. In addition, the robot drive unit 21 may include an actuator that drives a portion of the robot 2 having a degree of freedom, a lighting device that lights the eyeball unit of the robot 2, and the like.

  The robot control unit 22 receives a robot control command, which is an example of a command signal, from the operation terminal 3. The robot control unit 22 generates the above-described drive control signal based on the received robot control command, and outputs the generated drive control signal to the robot drive unit 21. That is, the robot 2 can operate according to the robot control command. Note that the command for causing the robot 2 to speak includes data indicating the content of the utterance (scenario data described later).

  The robot control unit 22 includes, for example, at least one memory in which software such as an application program and an operating system for operating the application program is stored, and a CPU (Central Processing Unit) that executes the software stored in the memory. The drive control signal may be generated by the CPU executing software stored in the memory.

(Operation terminal 3)
The operation terminal 3 is carried by the user and is, for example, a tablet terminal having a touch function. In addition, the operation terminal 3 may be a smartphone, a desktop display type terminal, or the like. As illustrated in FIG. 1, the operation terminal 3 includes an orientation sensor 31 that is an example of a sensor, and an operation generation unit 32 that is an example of a command signal generation unit and a transmission unit. The operation terminal 3 is driven by electric power supplied from the built-in battery.

  The orientation sensor 31 outputs an orientation detection signal indicating the orientation of the operation terminal 3 to the motion generation unit 32. The direction sensor 31 outputs a direction detection signal indicating the detected direction of the operation terminal 3 to the motion generation unit 32. For example, the motion generation unit 32 generates a robot control command for controlling the posture of the robot 2 so as to face the direction in which the operation terminal 3 exists based on the direction detection signal from the direction sensor 31.

  The motion generation unit 32 generates a robot control command for controlling the motion of the robot 2 based on the output of the direction sensor 31. The motion generation unit 32 transmits the generated robot control command to the robot control unit 22 via wireless communication such as Wi-Fi, for example. The robot control unit 22 receives the robot control command from the motion generation unit 32, and outputs a drive control signal corresponding to the received robot control command to the robot drive unit 21, thereby controlling the operation of the robot 2. Do.

  Further, the motion generation unit 32 generates a robot control command for controlling the robot 2 based on scenario data used for dialogue. Thus, the robot 2 generates a voice by transmitting a robot control command for generating dialogue data as a voice to the robot control unit 22. At this time, a robot control command for opening / closing or illuminating the mouth portion of the robot 2 based on the scenario data is also transmitted to the robot control unit 22 to open / close or illuminate the mouth of the robot 2. it can. The voice output from the robot 2 may be an utterance that includes a meaningful word, or may be an artificial sound that does not include a word.

  The operation of the robot 2 includes an interactive operation in which a conversation with the user is performed using voice. As a configuration for performing a dialogue between the user and the robot 2, the operation terminal 3 includes a scenario DB (database) 33, a scenario control unit 34, and a display unit 35 in addition to the motion generation unit 32 described above. And an input unit 36 and an audio output unit 37.

  As shown in FIG. 1, the scenario DB 33A stores a plurality of pieces of dialog scenario information for performing a dialog between the user and the robot 2. The dialogue scenario information includes a plurality of scenario groups (each scenario group has a plurality of dialogue scenarios) and a plurality of dialogue scenarios. One dialogue scenario is exchanged between the robot 2 and the user. This is a story of dialogue. One dialogue scenario includes robot-side scenario data used by the robot 2 for dialogue, that is, speech and movement, and user-side scenario data used for dialogue, that is, selection by the operation terminal 3. The user-side scenario data includes some dialogue scenario data that can respond to the robot-side scenario data, and the user can select arbitrary data from among these by the input unit 36. Then, different lower-order user-side scenario data different from each other are associated with each of the dialogue scenario options shown in the user-side scenario data. That is, the dialogue scenario data has a tree structure in which the robot side scenario data and the user side scenario data are alternately coupled as nodes. In the tree structure, a predetermined series of nodes ranging from the highest level to the lowest level is managed as a basic scenario used for a typical dialogue, for example. Other node groups may be managed as a correction scenario for correcting the basic scenario.

  The scenario DB 33B accumulates a summary of dialogue scenarios. That is, the scenario DB 33B is a database that is paired with the scenario DB 33A, and the scenario DB 33B stores a summary of the dialogue scenario information stored in the scenario DB 33A. The scenario DB 33A according to the present embodiment constitutes a scenario summary accumulation unit.

  The scenario control unit 34 controls the scenario based on the data output from the store system 5. The display unit 35 according to the present embodiment is, for example, a liquid crystal panel constituting a touch panel. The input unit 36 according to the present embodiment inputs various information by touching or swiping (touching or tracing) the touch panel.

  FIG. 2 is a block diagram illustrating an example of the input unit 36. As shown in FIG. 2, the input unit 36 includes a first signal input unit 361 and a second signal input unit 362. The first signal input unit 361 outputs a first detection signal indicating the direction of tracing the touch panel based on the index displayed on the display unit 35. The second signal input unit 362 outputs a second detection signal indicating whether or not an index on the touch panel has been touched. The third signal input unit 363 outputs a third detection signal indicating the coordinates touched on the touch panel and the time. The display unit 35, the input unit 36, and the audio output unit 37 constitute a user interface unit according to the present embodiment. That is, the user interface unit according to the present embodiment has a touch panel, and outputs a first detection signal indicating a direction in which the touch panel is traced based on an index displayed on the display unit 35.

  The sound output unit 37 generates sound according to the control of the scenario control unit 34. The speed detection unit 38 detects the speed of tracing the touch panel constituted by the display unit 35 and the input unit 36 using the third signal output from the third signal input unit 363, for example. In addition, although the display part 35 and the input part 36 which concern on this embodiment comprise a touch panel, it is not limited to this, You may comprise the display part 35 and the input part 36 as a respectively separate apparatus.

  Here, a specific configuration of the scenario control unit 34 will be described with reference to FIG. FIG. 3 is a block diagram of the scenario control unit 34. As shown in FIG. 3, the scenario control unit 34 includes a reception unit 341, a stay state determination unit 342, an information acquisition unit 343, and a dialogue control unit 345. Further, the scenario control unit 34 may include a recommended menu providing unit 344. Thus, the recommended menu providing unit 344 is not an essential component.

  The receiving unit 341 receives information including status data output from the store system 5. The status data can be input, for example, at the handy terminal 4 for ordering carried by the store staff of the restaurant. This status data is transmitted from the handy terminal 4 to the store system 5 and then transmitted from the store system 5 to the receiving unit 341 of the scenario control unit 34. The status data may be transmitted directly from the handy terminal 4 to the operation terminal 3 via the receiving unit 341 without passing through the store system 5.

  Examples of status data include a first state indicating that the user has entered the store, a second state indicating that the user has been seated, a third state indicating that the user has ordered food and drink, and the ordered food and drink being the user. There are a fourth state indicating that the user has been provided, a fifth state indicating that the user has finished eating and drinking food and drink, a sixth state indicating that the user has left the store, and the like. The status data is not limited to this, and the status data may include a leaving state indicating that the user has left the seat, a conversation state in which the users are having a conversation, or a state in which the user has ordered dessert after eating. Good. Thus, the status data is information used to determine the staying state of the user that changes with the passage of time.

  The stay state determination unit 342 determines, for example, the stay state of the user in the restaurant based on the status data among the information received by the reception unit 341. The stay state determination unit 342 is a state from entering the restaurant or ordering food after receiving the signal of the second state indicating that the user is seated via the reception unit 341, for example. Judge. Similarly, when the stay state determination unit 342 receives the signal of the third state via the reception unit 341, for example, the stay state determination unit 342 determines that the food and drink ordered by the user is waiting to be provided. Similarly, when the stay state determination unit 342 receives the signal of the fourth state via the reception unit 341, for example, the stay state determination unit 342 determines that the state is until the user completes the eating and drinking of the food and drink. Similar to the above-described status data, the staying state is information indicating the state of the user that changes over time.

  The relationship between the status data and the staying state may be a configuration other than those described above. For example, the store staff may input the stay state itself as the status data. That is, instead of inputting the user's action as a trigger, the state itself may be input. Specifically, the store staff may not directly input the act of being seated or ordered, but directly input the state of being seated or ordering and waiting for food or drink. . In this case, stay state determination unit 342 determines that the received status data itself is a stay state. This difference in input is basically a matter of design matters.

  The information acquisition unit 343 acquires dialogue scenario information for interacting with a user who has visited the restaurant from a plurality of dialogue scenario information in the scenario DB 33A. That is, the information acquisition unit 343 acquires dialogue scenario information for interacting with the user from the plurality of dialogue scenario information stored in the scenario DB 33A according to the control of the dialogue control unit 345, and sends it to the dialogue control unit 345. Output. The information acquisition unit 343 may acquire scenario data for dialogue according to the staying state of the user, or after the scenario information is acquired by the information acquisition unit 343, scenario data to be used for dialogue from the scenario group. You may make it select and output.

  When there is a recommended menu in the menu, the recommended menu providing unit 344 transmits recommended menu information related to the recommended menu to the information acquisition unit 343. The information acquisition unit 343 acquires dialogue scenario information related to the recommended menu from the scenario DB 33A.

  For example, the recommended menu providing unit 344 may output the recommended menu based on the dialogue scenario information regarding the recommended menu acquired by the information acquiring unit 343 when the user is in the stay state before ordering after sitting. .

The dialogue control unit 345 advances the dialogue scenario based on the dialogue scenario information. That is, the dialogue control unit 345 according to the present embodiment includes a first control unit 345A, a second control unit 345B, a scenario correction unit 345C, and a corrected dialogue scenario utterance unit 345D.
The first control unit 345A performs display control for displaying the index on the touch panel of the user interface unit. That is, the first control unit 345A displays at least one index for controlling the progress of the dialogue in the touch panel.

  For example, the first control unit 345A causes the display unit 35 to display, as an index, image information indicating a “conversation scenario option” on the user side based on the input dialogue scenario information. In addition, the first control unit 345A causes the input unit 36 to display character displays such as “advance”, “return”, and “stop” as an index. These indicators such as “Past”, “Return”, “Stop”, “Dialogue scenario options” are “Progress”, “Return”, “Stop”, “Switch”, etc., respectively. It corresponds to the operation of.

  The second control unit 345B controls the progress of the dialogue scenario based on the dialogue scenario information acquired by the information acquisition unit 343. The second control unit 345B outputs the robot-side scenario data included in the dialogue scenario information to the action generation unit 32 and outputs the user-side scenario data to the second control unit 345B while the dialogue scenario proceeds. In addition, the second control unit 345B performs control for advancing, returning, stopping, or switching the dialogue according to the operation of the index displayed by the first control unit 345A. For example, the user may trace the index according to the direction indicated by the index displayed on the display unit 35 or may touch the index. For example, the second control unit 345B controls whether to advance or return the dialogue based on the first detection signal indicating the direction of tracing the touch panel generated by the first signal input unit 361. That is, the first control unit 345A controls the progress of the dialogue with the robot based on the instruction signals corresponding to the above-described “advance”, “return”, “stop”, “switch”, and the like.

  The scenario correction unit 345C performs a correction process for the dialogue scenario based on the stay state of the user determined by the stay state determination unit 342. For example, the scenario correction unit 345C performs a correction process for summarizing the dialogue scenario based on the stay state of the user determined by the stay state determination unit 342. Specifically, based on the stay state of the user determined by the stay state determination unit 342, a summary scenario summarizing the dialog scenario executed immediately before or the dialog scenario to be executed immediately after is generated. In other words, the dialogue scenario correction processing includes dialogue scenario summarization processing.

  More specifically, the scenario correction unit 345C is indispensable in the previous utterance or the subsequent utterance when the user enters the restaurant or sits in the restaurant and orders the food and drink, that is, before the order. Amend the summary to ensure that For example, if the previous utterance or the subsequent utterance is “My recommended menu is a special hamburger”, the information is corrected without dropping information, such as “Special hamburger is my recommendation”. For this reason, the user does not miss the information about the menu that the store side wants to convey to the user reliably, and further, since the inside of the utterance has been changed, the user gets a sense of realism in the dialogue with the robot 2 be able to.

  Moreover, when it is in the state waiting for provision of the food and drink which the user ordered, 345C scenario correction | amendment performs correction | amendment which makes the content of the front utterance or the back utterance simplified. For example, in a conversation scenario of chatting, a simple utterance like “I was surprised by yesterday's car” compared to the previous or later utterance that “I was very surprised when a car jumped out of a side street yesterday” Correction that conveys only correct information. For this reason, the user hears the same information again, but has been changed to a simple utterance content, so that the user can obtain a sense of realism through dialogue with the robot 2.

  When the user is in a meal state, the scenario correction unit 345C corrects the utterance content different from the previous utterance or the later utterance, for example, “I will talk later because I am eating”. As a result, the user is restricted from interacting and can concentrate on the meal. The scenario correction unit 345C summarizes the dialog scenario executed immediately before or the dialog scenario to be executed immediately after the meal ends and before the accounting. In this case, since the content of the utterance is summarized, the user can feel the real time through the dialogue with the robot 2.

  The corrected dialog scenario utterance unit 345D corrects the dialog scenario executed immediately before or the dialog scenario to be executed immediately after by the scenario correction unit 345C when an instruction to return or advance the progress of the dialog scenario is given. Replace with a dialogue scenario to utter. In addition, the corrected dialogue scenario utterance unit 345D replaces the dialogue scenario executed immediately before or the dialogue scenario to be executed immediately after with the dialogue scenario corrected by the scenario correction unit 345C before uttering. Speak a predetermined word. More specifically, the corrected dialogue scenario utterance unit 345D causes the voice output unit 37 to output a predetermined word corresponding to the content of the operation after an operation is performed on the indicator displayed on the touch panel. For example, when the progress of the dialogue scenario is returned, words such as “I say it again” are uttered as predetermined words. On the other hand, when advancing the progress of the dialogue scenario, a word such as “I'll go ahead” is determined in advance and uttered as a predetermined word. As described above, the predetermined predetermined words include words for informing that the dialogue scenario or the utterance of the dialogue scenario to be executed immediately after is started.

  On the other hand, the corrected dialogue scenario utterance unit 345D can also obtain and utter an acquired scenario from the scenario summary DB 33B in which the summary of the dialogue scenario to be executed immediately before and the summary of the dialogue scenario to be executed immediately after are accumulated. In this case, without using the scenario correction unit 345C, the dialog scenario executed immediately before and the summary of the dialog scenario to be executed immediately after are spoken. As described above, the corrected dialogue scenario utterance unit 345D performs the dialogue scenario executed immediately before when the information input, information selection, or information operation for returning or advancing the dialogue scenario is performed by the user interface unit having the display unit 35. Alternatively, it is possible to summarize the dialogue scenario to be executed immediately after and let the robot 2 speak.

  With the above configuration, a dialogue between the user and the robot 2 can be performed using the dialogue scenario data.

  Next, an example of the progress control of the dialogue performed by the scenario control unit 34 will be described based on FIG. FIG. 4 is a flowchart showing an operation example related to the progress control of the dialogue performed by the scenario control unit 34.

  First, the second control unit 345B of the scenario control unit 34 causes the robot 2 to perform normal speech based on the conversation scenario information acquired by the information acquisition unit 343 (step S10). Next, the second control unit 345B determines whether or not an instruction to return the utterance has been issued (step S11).

  When the second control unit 345B determines that the return of the utterance is not instructed (step S11: NO), the process returns to step S10.

  On the other hand, when the second control unit 345B determines that the return of the utterance has been instructed (step S11: YES), the scenario correction unit 345C displays the conversation scenario executed immediately before, more specifically, the content uttered immediately before. (Hereinafter also referred to as the previous utterance) is called from the scenario DB 33A (step S12), and a summary scenario summarizing the dialog scenario executed immediately before, more specifically, a summary of the previous utterance is generated (step S13).

  Next, the corrected dialogue scenario utterance unit 345D causes the robot 2 to utter the dialogue scenario corrected by the scenario correction unit 345C (step S14). In this case, the corrected dialogue scenario utterance unit 345D determines in advance before replacing the dialogue scenario executed immediately before or the dialogue scenario to be executed immediately after with the dialogue scenario corrected by the scenario correction unit 345C. Speak the given word.

  Next, the second control unit 345B determines whether or not the dialogue based on the dialogue scenario has ended (step S15), and when determining that the dialogue has not ended (step S15: NO), returns to step S10. .

  On the other hand, when it is determined that the dialogue has ended (step S15: YES), the second control unit 345B ends the entire process.

  Next, based on FIG. 5, the detailed process of step S13 in FIG. 4 is demonstrated. FIG. 5 is a flowchart showing detailed processing of step S13 in FIG. The stay state determination unit 342 acquires status data from the store system 5 via the reception unit 341 (step S20). The stay state determination unit 342 determines whether the received signal is a signal indicating the first state indicating that the user has entered the store or a signal indicating the second state indicating that the user has been seated ( Step S21).

  When the received signal is a signal indicating the first state indicating that the user has entered the store, or a signal indicating the second state indicating that the user has been seated (step S21: YES), the stay state determining unit 342 , It is determined that the user is in a state before entering the restaurant or sitting at the restaurant and before ordering the food, that is, before ordering. In this case, since the scenario correction unit 345C is in a state before ordering, the scenario correction unit 345C performs correction to make a summary in which essential information is reliably left. (Step S22).

  On the other hand, if the received signal is not a signal indicating the first state indicating that the user has entered the store and a signal indicating the second state indicating that the user has been seated (step S21: NO), the stay state determining unit It is determined whether 342 is a signal which shows the 3rd state which shows that the user ordered food and drink (step S23).

  When the received signal is a signal indicating the third state indicating that the user has ordered food and drink (step S23: YES), the stay state determination unit 342 indicates that the user has ordered food and drink. It is determined that the state is the state before the product is provided. In this case, the scenario correction unit 345C performs correction that simply summarizes the information of the previous utterance (step S24).

  On the other hand, when the received signal is not a signal indicating the third state indicating that the user has ordered food and drink (step S23: NO), the stay state determination unit 342 provides the user with the ordered food and drink. It is determined whether or not the signal indicates the fourth state (step S25).

  When the received signal is a signal indicating the fourth state indicating that the ordered food and drink is provided to the user (step S25: YES), the stay state determination unit 342 provides the ordered food and drink to the user. It is judged that it is the 4th state which shows that, ie, a state until a user completes eating and drinking of food and drink. In this case, the scenario correction unit 345C corrects the utterance content different from the previous utterance (step S26).

  On the other hand, when the received signal is not a signal indicating the fourth state indicating that the ordered food or drink is provided to the user (step S25: NO), the user has completed the food or drink provided. It is determined that this is the fifth state shown. In this case, the scenario correction unit 345C performs correction that simply summarizes the information of the previous utterance (step S27). In addition, the correction process of each step S22, S24, S26, S27 is an example, and it is possible to appropriately change whether the summary includes essential information, a simple summary, or utterance content other than the summary. It is. In the above example, the correction process for the previous utterance is shown, but the correction process for the subsequent utterance can be performed in the same manner.

  As described above, the scenario correction unit 345C performs the dialogue scenario correction process based on the stay state of the user determined by the stay state determination unit 342. Next, a specific application example of the dialogue scenario will be described. FIG. 6 is a diagram illustrating an example of a dialogue between the robot 2 and the user. As shown in FIG. 6, the dialogue is performed using the robot 2 and the operation terminal 3. The operation terminal 3 is, for example, a tablet-type portable terminal that includes a display unit 35 and a touch panel type input unit 36 integrated into the display unit 35. From the robot 2, for example, an utterance “What to order?” Is executed based on the robot-side scenario data selected by the information acquisition unit 343.

  FIG. 7 is a diagram illustrating a display example of the display unit 35 when “Tell me a recommended menu!” In FIG. 6 is selected by the user. As shown in FIG. 6, the letters “Italian cheese hamburger” provided by the recommended menu providing unit 344 are displayed together with images and videos as the recommended menu for today. At the same time, other recommended menus may be displayed together. Further, regarding the explanation of the Italian cheese hamburger from the robot 2, the contents of the menu, the reason for recommendation, etc. may be spoken. Here, a scene in which an index indicating return is instructed by the user is shown. Since this scene is still before ordering, it is said that “a special hamburger is my recommendation”, which is a summary of the previous utterance “My recommended menu is a special hamburger”. Further, the robot 2 makes a predetermined statement “I say it again. What I said before” by the corrected dialogue scenario utterance unit 345D.

  FIG. 8 is a diagram showing a scene in which the user is instructed to move forward in FIG. This scene is the same display as in FIG. Since this scene is still before ordering, it is an interactive scenario that should be executed immediately after that "My recommended menu is a special hamburger" which is almost simply summarized as "Special hamburger is my recommendation" Yes. Further, the robot 2 makes a predetermined statement “Go ahead” by the corrected dialogue scenario utterance unit 345D.

  FIG. 9 is a diagram illustrating a scene in which the order is finished and waiting for a dish to come. Here, a scene in which an index indicating return is instructed by the user is shown. This scene is a state where the order is finished and waiting for the food to come, so we say “dessert” which is a simplified summary of the previous utterance “Desert recommends vanilla ice cream” . Further, the robot 2 makes a predetermined statement “I say it again. What I said before” by the corrected dialogue scenario utterance unit 345D.

  As described above, according to the present embodiment, when an instruction to return or advance the progress of the dialogue scenario is given, the dialogue scenario executed immediately before or the dialogue scenario to be executed immediately after is given to the stay state determination unit 342. Based on the stay state of the user determined in this way, it is decided to replace the dialogue scenario corrected by the scenario correction unit 345C and speak. Thereby, when returning or advancing the dialogue with the robot, the robot 2 again speaks the dialogue scenario executed immediately before or corrected according to the staying state of the user. Can do. Thereby, a natural dialogue suitable for a user's state, for example, a state before ordering or a state where food is being eaten can be performed, and the satisfaction of the user can be increased.

  In the above description, the stay state is assumed to change when the store staff inputs from the handy terminal 4, but the present invention is not limited to this. For example, after a user's order is confirmed, after the waiting time until the average provision of the food and drink ordered by the user has elapsed, the state may transition to a staying state during eating and drinking. Further, for example, after the provision of food and drink is completed, the user may automatically transition to a stay state in which the user has finished eating after a predetermined time such as 30 minutes or 45 minutes.

  In particular, when an order is received, the store staff does not forget to update the stay status in order to operate the handy terminal 4, but other stay information is confirmed by the store staff and operated by the handy terminal 4. Since it is necessary, the stay information may not be updated via the handy terminal 4. In such a case, it is effective to automatically change the stay state after a predetermined time has elapsed.

(First modification)
FIG. 10 is a block diagram illustrating an example of the robot control system 1 according to the first modification. In the embodiment described above, the scenario DB 33A is installed in the operation terminal 3, but is not limited to this. For example, as shown in FIG. 10, the scenario DB 33 </ b> A may be outside the operation terminal 3. The scenario control unit 34 is connected to the scenario DB 33A via the network 6.

  The scenario DB 33A may be provided in a predetermined server outside the operation terminal 3, or a database (including a distributed database) existing on a so-called cloud connected by the network 6 instead of a specific server. There may be. The network 6 and the operation terminal 3 or the scenario DB 33A are connected via wired or wireless communication.

  According to this modification, by having the scenario DB 33A outside the operation terminal 3, it is not necessary to manage the scenario DB at the operation terminal 3, and the scenario data can be centrally managed. . In addition, the scenario DB 33A exists on the cloud, and it is possible to select more varied content of dialogue by setting so that a specific number of editors can edit or add scenario data. It becomes possible.

(Second modification)
FIG. 11 is a diagram illustrating a configuration of the robot control system 1 according to the second modification. As illustrated in FIG. 11, the motion generation unit 32, the scenario control unit 34, and the scenario DB 33 </ b> A may be provided in the robot 2 instead of the operation terminal 3. That is, the main control function may be provided not in the operation terminal 3 but in the robot 2. The operations of the operation generation unit 32 and the scenario control unit 34 are not significantly different from the operations in the above-described embodiment, and in this modification as well, the dialogue process is executed according to the flowchart shown in FIG.

  According to this modification, the configuration of the operation terminal 3 can be simplified, and the amount of data transmitted from the operation terminal 3 to the robot 2 can be reduced, so that the performance of the communication line between the operation terminal 3 and the robot 2 can be reduced. Even when the value is low, dialogue with the robot 2 can be performed without any trouble. The motion generation unit 32 may be provided outside the operation terminal 3 and the robot 2. For example, the motion generation unit 32 may be built in the store system 5 or provided in a communication device separate from the store system 5. May be.

  In all the embodiments and modifications described above, the dialogue is described as a state in which the user or the robot 2 outputs some information, but is not limited thereto. For example, since it is less necessary to interact with the robot 2 during a meal, a silent scenario may be prepared in advance and the silent scenario may be output. .

  The robot control system 1 according to all the embodiments and the modifications described above can be suitably applied to the eating and drinking service as described above, but may be applied to various services other than the eating and drinking service.

  The aspect of the present invention is not limited to the individual embodiments described above, and includes various modifications that can be conceived by those skilled in the art, and the effects of the present invention are not limited to the contents described above. That is, various additions, modifications, and partial deletions can be made without departing from the concept and spirit of the present invention derived from the contents defined in the claims and equivalents thereof.

DESCRIPTION OF SYMBOLS 1 Robot control system, 2 Robot, 3 Operation terminal, 33B Scenario summary DB, 34 Scenario control part, 342 Stay state judgment part, 343 Information acquisition part, 345C Scenario correction part, 345D correction dialogue scenario speech part

Claims (10)

An information acquisition unit that acquires dialogue scenario information for interacting with a customer who has visited a restaurant from a plurality of dialogue scenario information;
A scenario progress control unit for controlling the progress of the dialog scenario corresponding to the acquired dialog scenario information;
A stay state determination unit for determining a stay state of the customer in the restaurant;
A scenario correction unit that performs correction processing of the dialogue scenario based on the stay state of the customer determined by the stay state determination unit;
When an instruction is given to return or advance the progress of the dialog scenario, the dialog scenario executed immediately before or the dialog scenario to be executed immediately after is replaced with the dialog scenario corrected by the scenario correction unit, and uttered. Correction dialogue scenario utterance part,
A dialogue control device comprising:   The corrected dialogue scenario utterance unit is determined in advance before the utterance is performed by replacing the dialogue scenario executed immediately before or the dialogue scenario to be executed immediately after with the dialogue scenario corrected by the scenario correction unit. The dialogue control apparatus according to claim 1, wherein a predetermined word is uttered.   The dialogue control apparatus according to claim 2, wherein the predetermined word includes a word for notifying that the utterance of the dialogue scenario executed immediately before or the dialogue scenario to be executed immediately after is started.   The dialogue control according to any one of claims 1 to 3, wherein the scenario correction unit performs a correction process for summarizing the dialogue scenario based on a stay state of the customer determined by the stay state determination unit. apparatus. The scenario correction unit generates a summary scenario that summarizes the dialog scenario executed immediately before or the dialog scenario to be executed immediately after,
The dialogue control apparatus according to claim 4, wherein the corrected dialogue scenario utterance unit utters the generated summary scenario.   6. The dialogue control apparatus according to claim 5, wherein the corrected dialogue scenario utterance unit obtains and speaks from the scenario summary accumulation unit that accumulates the dialogue scenario executed immediately before and the summary of the dialogue scenario to be executed immediately after. . A user interface unit that performs at least one of information input, information selection, and information operation for dialogue with the robot;
The corrected dialogue scenario utterance unit is executed immediately before or immediately after the dialogue scenario executed immediately before or after information input, information selection, or information operation is performed by the user interface unit to return or advance the progress of the dialogue scenario. The dialogue control apparatus according to claim 5 or 6, wherein the dialogue scenario to be summed up is made to cause the robot to speak. The user interface unit has a touch panel,
A first control unit for displaying at least one index for controlling the progress of the dialogue in the touch panel;
The dialogue control device according to claim 7, further comprising: a second control unit that performs control to advance, return, stop, or switch the dialogue according to the operation of the index. The user interface unit outputs a first detection signal indicating a direction of tracing the touch panel based on the index;
The second control unit controls whether to advance or return the dialogue based on the first detection signal,
The corrected dialogue scenario utterance unit summarizes the dialogue scenario executed immediately before or immediately after the dialogue scenario when the second control unit performs control to return the dialogue or control to advance the dialogue. The dialogue control device according to claim 8, which causes the user to speak. A robot that operates in response to the instruction signal;
An operation terminal that generates the instruction signal and operates the robot,
The operation terminal is
An information acquisition unit that acquires dialogue scenario information for interacting with a customer who has visited a restaurant from a plurality of dialogue scenario information;
A scenario progress control unit for controlling the progress of the dialog scenario corresponding to the acquired dialog scenario information;
A stay state determination unit for determining a stay state of the customer in the restaurant;
A scenario correction unit that performs correction processing of the dialogue scenario based on the stay state of the customer determined by the stay state determination unit;
When an instruction is given to return or advance the progress of the dialog scenario, the dialog scenario executed immediately before or the dialog scenario to be executed immediately after is replaced with the dialog scenario corrected by the scenario correction unit, and uttered. Dialogue scenario utterance part,
A robot control system comprising:

Images