Dialogue system, dialogue method, and dialogue program

Abstract

To prevent a dialogue system from outputting erroneous information.SOLUTION: A dialogue system according to an embodiment includes: an intention estimation unit that estimates, using an estimation model, intention from voice information or text information; a slot extraction unit that extracts, when the intention is a procedure, using an extraction model, slot information corresponding to the procedure from the voice information or the text information; a reply acquisition unit that acquires, when the intention is a query, reply information corresponding to the query; a first text generation unit that generates, on the basis of at least one of the slot information and the reply information, a first text; a second text generation unit that generates, on the basis of the slot information, a second text; and an output unit that outputs the first text and the second text.SELECTED DRAWING: Figure 11

Description

[Technical field]

[0001] The present invention relates to a dialogue system, a dialogue method, and a dialogue program. [Background technology]

[0002] In recent years, dialogue systems using large language models, which are a type of natural language processing model, have been put to practical use. For example, Cited Document 1 discloses a response generation method performed in an electronic device, the response generation method including the steps of acquiring at least one utterance data, acquiring a first context corresponding to the utterance data from a context candidate set, generating one or more dialogue sets including the first context and the utterance data, receiving a second context from a user, and acquiring a response corresponding to the second context using a language model based on the one or more dialogue sets. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2023-73220 A Summary of the Invention [Problem to be solved by the invention]

[0004] In the above-mentioned conventional technology, responses to a user are generated by a language model. However, since the language model may output erroneous information, it is difficult to use the language model in a dialogue system for automating procedures, such as a reservation system.

[0005] The present invention has been made in consideration of the above-mentioned problems, and has an object to prevent a dialogue system from outputting erroneous information. [Means for solving the problem]

[0006] The dialogue system of one embodiment includes an intention estimation unit that estimates an intention from voice information or text information using an estimation model, a slot extraction unit that, if the intention is a procedure, uses an extraction model to extract slot information corresponding to the procedure from the voice information or text information, an answer acquisition unit that acquires answer information corresponding to the question if the intention is a question, a first text generation unit that generates a first text based on at least one of the slot information and the answer information, a second text generation unit that generates a second text based on the slot information, and an output unit that outputs the first text and the second text. Effect of the Invention

[0007] According to one embodiment, it is possible to prevent the dialogue system from outputting erroneous information. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 illustrates an example of the configuration of a dialogue system 1000. [Diagram 2] 1 is a diagram illustrating an example of a hardware configuration of a dialogue device 1. FIG. [Diagram 3] 2 is a diagram illustrating an example of a hardware configuration of a user terminal 2. FIG. [Figure 4] 2 is a diagram illustrating an example of a functional configuration of the dialogue device 1. FIG. [Diagram 5] FIG. 12 is a diagram showing an example of procedure information 124. [Figure 6] FIG. 11 is a diagram showing an example of subject information. [Figure 7] FIG. 13 is a diagram showing an example of Q&A information. [Figure 8] 10 is a flowchart showing an example of a process executed by the dialogue system 1000. [Figure 9] 11 is a flowchart showing an example of a method for generating a first text. [Figure 10]13 is a flowchart illustrating an example of a method for generating a second text. [Figure 11] FIG. 13 is a schematic diagram showing a specific example of a dialogue. [Figure 12] FIG. 13 is a diagram showing an example of procedure information 124′. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, each embodiment of the present invention will be described with reference to the accompanying drawings. In the description of the specification and drawings of each embodiment, components having substantially the same functional configuration are designated by the same reference numerals, and redundant description will be omitted.

[0010] <System configuration> First, an overview of the dialogue system 1000 according to this embodiment will be described. The dialogue system 1000 is a system that automatically engages in dialogue with a user by utilizing a natural language processing model. The dialogue system 1000 can be used as a dialogue system for a user to execute a procedure with a target person through text chat, voice chat, or call (telephone). Chat may be by text input or voice input.

[0011] The user is a user of the dialogue system 1000 and is a person who performs a procedure.

[0012] The target is a person who accepts procedures from a user. The target is, for example, a service provider (such as an accommodation facility or restaurant), a seller of a product or service (such as a store), a public institution, a government agency, or a person who has been authorized by these to accept procedures on their behalf, but is not limited to these.

[0013] A procedure is something that a user performs on a target person, such as, but not limited to, a reservation, an order, a purchase, an application, or a change or cancellation of these.

[0014] Fig. 1 is a diagram showing an example of the configuration of a dialogue system 1000. As shown in Fig. 1, the dialogue system 1000 includes a dialogue device 1 and a user terminal 2, which are communicatively connected to each other via a network N. The network N is, for example, a wired LAN (Local Area Network), a wireless LAN, the Internet, a public line network, a mobile data communication network, or a combination of these. In the example of Fig. 1, the dialogue system 1000 includes one dialogue device 1 and one user terminal 2, but may include multiple of each.

[0015] The interactive device 1 is an information processing device that automatically responds to an input from a user. The interactive device 1 is, for example, but not limited to, a PC (Personal Computer), a smartphone, a tablet terminal, a server device, or a microcomputer. In the example of FIG. 1, the interactive device 1 is one information processing device, but may be realized as a system consisting of a plurality of information processing devices connected via a network N.

[0016] The user terminal 2 is an information processing device for a user to execute a procedure. The user terminal 2 is, for example, but not limited to, a PC, a smartphone, or a tablet terminal. The user inputs information for the procedure via the user terminal 2. The user inputs information such as, for example, voice, text, or button operation, but is not limited to these.

[0017] <Hardware configuration of the dialogue device 1> Next, a description will be given of the hardware configuration of the dialogue device 1. Fig. 2 is a diagram showing an example of the hardware configuration of the dialogue device 1. As shown in Fig. 2, the dialogue device 1 includes a processor 101, a memory 102, a storage 103, a communication I / F 104, an input device 105, an output device 106, and a drive device 107, which are connected to each other via a bus B1.

[0018] The processor 101 controls each component of the dialogue device 1 and realizes the functions of the dialogue device 1 by expanding into the memory 102 various programs including an OS (Operating System) and a dialogue program stored in the storage 103 and executing them. The processor 101 is, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a GPU (Graphics Processing Unit), an ASIC (Application Specific Integrated Circuit) or a DSP (Digital Signal Processor), but is not limited to these.

[0019] The memory 102 is, for example, a Read Only Memory (ROM), a Random Access Memory (RAM), or a combination thereof. The ROM is, for example, a Programmable ROM (PROM), an Erasable Programmable ROM (EPROM), an Electrically Erasable Programmable ROM (EEPROM), or a combination thereof. The RAM is, for example, but is not limited to, a Dynamic RAM (DRAM) or a Static RAM (SRAM).

[0020] The storage 103 stores various programs and data including an OS and an interactive program. The storage 103 is, for example, a flash memory, a hard disk drive (HDD), a solid state drive (SSD), or a storage class memory (SCM), but is not limited to these.

[0021] The communication I / F 104 is an interface for connecting the interactive device 1 to an external device via the network N and controlling communication. The communication I / F 104 is, for example, Bluetooth (registered trademark), Wi-Fi (registered trademark), ZigBee (registered trademark), or Ethernet (registered trademark), but is not limited thereto.

[0022] The input device 105 is a device for inputting information to the interactive apparatus 1. The input device 105 is, for example, a mouse, a keyboard, a touch panel, a microphone, a scanner, a photographing device (camera), various sensors, or an operation button, but is not limited to these.

[0023] The output device 106 is a device for outputting information from the dialogue apparatus 1. The output device 106 is, for example, a display device, a projector, a printer, a speaker, or a vibrator, but is not limited to these.

[0024] The drive device 107 is a device that reads and writes data to the recording medium 108. The drive device 107 is, for example, but not limited to, a magnetic disk drive, an optical disk drive, a magneto-optical disk drive, or an SD card reader. The recording medium 108 is, for example, but not limited to, a CD (Compact Disc), a DVD (Digital Versatile Disc), a FD (Floppy Disk), an MO (Magneto-Optical disk), a BD (Blu-ray (registered trademark) Disc), a USB (registered trademark) memory, or an SD card.

[0025] In this embodiment, the dialogue program may be written into memory 102 or storage 103 during the manufacturing stage of the dialogue device 1, or may be provided to the dialogue device 1 via the network N, or may be provided to the dialogue device 1 via a non-transitory computer-readable recording medium such as a recording medium 108.

[0026] <Hardware configuration of user terminal 2> Next, a description will be given of the hardware configuration of the user terminal 2. Fig. 3 is a diagram showing an example of the hardware configuration of the user terminal 2. As shown in Fig. 3, the user terminal 2 includes a processor 201, a memory 202, a storage 203, a communication I / F 204, an input device 205, and an output device 206, which are connected to each other via a bus B2.

[0027] The processor 201 controls each component of the user terminal 2 and realizes the functions of the user terminal 2 by expanding into the memory 202 and executing various programs including the OS and interactive programs stored in the storage 203. The processor 201 is, for example, a CPU, an MPU, a GPU, an ASIC, or a DSP, but is not limited to these.

[0028] The memory 202 may be, for example, a ROM, a RAM, or a combination thereof. The ROM may be, for example, a PROM, an EPROM, an EEPROM, or a combination thereof. The RAM may be, for example, but is not limited to, a DRAM or an SRAM.

[0029] The storage 203 stores various programs and data including the OS and interactive programs. The storage 203 is, for example, a flash memory, a HDD, an SSD, or an SCM, but is not limited to these.

[0030] The communication I / F 204 is an interface for connecting the user terminal 2 to an external device via the network N and controlling communication. The communication I / F 204 is, for example, Bluetooth (registered trademark), Wi-Fi (registered trademark), ZigBee (registered trademark), or Ethernet (registered trademark), but is not limited to these.

[0031] The input device 205 is a device for inputting information to the user terminal 2. The input device 205 is, for example, a mouse, a keyboard, a touch panel, a microphone, a scanner, an imaging device (camera), various sensors, or an operation button, but is not limited to these.

[0032] The output device 206 is a device for outputting information from the user terminal 2. The output device 206 is, for example, a display device, a projector, a printer, a speaker, or a vibrator, but is not limited to these.

[0033] In this embodiment, the dialogue program may be written into memory 202 or storage 203 during the manufacturing stage of the user terminal 2, or may be provided to the user terminal 2 via the network N, or may be provided to the user terminal 2 via a non-transitory computer-readable recording medium such as recording medium 208.

[0034] <Functional configuration of the dialogue device 1> Next, a description will be given of the functional configuration of the dialogue device 1. Fig. 4 is a diagram showing an example of the functional configuration of the dialogue device 1. As shown in Fig. 4, the dialogue device 1 includes a communication unit 11, a storage unit 12, and a control unit 13.

[0035] The communication unit 11 is realized by the communication I / F 104. The communication unit 11 transmits and receives information to and from the user terminal 2 via the network N. The communication unit 11 receives an input from the user terminal 2 and transmits a response to the user terminal 2.

[0036] The storage unit 12 is realized by a memory 102 and a storage 103. The storage unit 12 stores voice information 121, text information 122, an estimation model 123, procedure information 124, an extraction model 125, subject information 126, Q&A information 127, a first response rule 128, a second response rule 129, and procedure content information 130.

[0037] The voice information 121 is information on the voice spoken by the user.

[0038] The text information 122 is information indicating text entered by the user or information obtained by converting the voice information 121 into text.

[0039] The estimation model 123 is a natural language processing model that estimates a user's intention (context) from the text information 122. The estimation model 123 is, for example, but is not limited to, a large-scale language model. When the text information 122 is input, the estimation model 123 learns to output an intention corresponding to the input text information 122 from among one or more intentions set in advance. The estimation model 123 is, for example, but is not limited to, a GPT (Generative Pretrained Transformer) that is fine-tuned by learning the relationship between the text information 122 and the intention.

[0040] The intent corresponds to the purpose of the text indicated by the text information 122, i.e., the intent of the user who input the utterance or text. The intent is, for example, but not limited to, a procedure, a question, a positive or negative. The procedure is, for example, but not limited to, a reservation, an order, a purchase, an application, or a change or cancellation thereof. The question is, for example, but not limited to, a question about business hours, a price, a deadline, a number of people, availability, cancellation conditions, or the possibility of making a reservation.

[0041] The estimation model 123 may be a natural language processing model that estimates a user's intention from the voice information 121. In this case, when the voice information 121 is input, the estimation model 123 is trained to output an intention corresponding to the input voice information 121 from among one or more preset intentions. The estimation model 123 is, for example, a multimodal LLM (Large Language Model) that is fine-tuned by learning the relationship between the voice information 121 and the intention, but is not limited to this.

[0042] The procedure information 124 is information indicating slot information set for each procedure (intention). The slot information is information set in advance as information necessary to execute a procedure. The procedure information 124 may be set in advance or may be arbitrarily set by the subject.

[0043] Fig. 5 is a diagram showing an example of the procedure information 124. The procedure information 124 in Fig. 5 includes, as information items, a "PID", a "procedure", one or more "slots", and a "confirmation flag".

[0044] "PID" is identification information that uniquely identifies a procedure. In the following, a procedure whose "PID" is "Pxxx" may be referred to as procedure Pxxx.

[0045] "Procedure" is the name of the procedure (intention).

[0046] "Slot" is the name of the slot information required to execute the procedure.

[0047] The "confirmed flag" is information indicating whether or not the slot information of the procedure information 124 has been confirmed. "On" indicates that it has been confirmed, and "off" indicates that it has not been confirmed.

[0048] 5, the "procedure" of procedure P001 is "reservation," "slot 1" is "date," "slot 2" is "time," "slot 3" is "name," "slot 4" is "number of people," and the "confirmed flag" is "off." This indicates that procedure P001 is a reservation procedure, and that "date," "time," "name," and "number of people" are set as information required to execute a reservation, and that procedure information 124 has not been confirmed.

[0049] It should be noted that the information included in the procedure information 124 is not limited to the above examples. The procedure information 124 may not include some of the above information, or may include information other than the above.

[0050] The extraction model 125 is a natural language processing model that extracts slot information from the text information 122. The extraction model 125 is, for example, a large-scale language model, but is not limited to this. When the text information 122 is input, the extraction model 125 is trained to extract slot information corresponding to the input text information 122 from one or more pieces of slot information set in advance. The extraction model 125 is, for example, a GPT that is fine-tuned by learning the relationship between the text information 122, intention, and slot information, but is not limited to this.

[0051] The subject information 126 is information related to the subject. The subject information 126 is stored for each subject.

[0052] Fig. 6 is a diagram showing an example of the target person information 126. The target person information 126 in Fig. 6 includes, as information items, a "TID", a "name", an "address", a "telephone number", and "business hours".

[0053] "TID" is identification information that uniquely identifies a subject. In the following, a subject whose "TID" is "Txxx" may be referred to as subject Txxx.

[0054] "Name" is the name of the subject.

[0055] "Address" is the address of the subject.

[0056] "Phone number" is the subject's phone number.

[0057] "Business hours" refers to the business hours of the target person.

[0058] It should be noted that the information included in the subject information 126 is not limited to the above examples. The subject information 126 may not include some of the above information, or may include information other than the above.

[0059] The Q&A information 127 is information indicating a correspondence relationship between question information indicating a question and answer information indicating an answer. The Q&A information 127 may be set in advance or may be arbitrarily set by the subject.

[0060] Fig. 7 is a diagram showing an example of the Q&A information 127. The Q&A information 127 in Fig. 7 includes, as information items, a "QID," a "question," and an "answer."

[0061] "QID" is identification information that uniquely identifies a question (intention). In the following, a question with "QID" of "Qxxx" may be referred to as question Qxxx.

[0062] "Question" is question information indicating the name and content of a question.

[0063] The "answer" is answer information indicating a text that is an answer corresponding to a question. The "answer" may be set in advance, or may be arbitrarily set by the subject. The "answer" may also refer to subject information 126.

[0064] In the example of Figure 7, the "Question" of question Q001 is "Seats" and the "Answer" is "You're asking about seats, right? We have table seats and private rooms available." This shows that question Q001 is a question about seats, and the answer corresponding to this question is set to the text "You're asking about seats, right? We have table seats and private rooms available."

[0065] Also, the "Question" of question Q002 is "Business hours" and the "Answer" is "You're asking about business hours, right? Our business hours are {business hours}." This indicates that question Q002 is a question about business hours, and the text "You're asking about business hours, right? Our business hours are {business hours}" is set as the answer to this question. Here, {business hours} refers to the "business hours" in the target person information 126.

[0066] It should be noted that the information included in the Q&A information 127 is not limited to the above examples. The Q&A information 127 may not include some of the above information, or may include information other than the above.

[0067] The first response rule 128 is a rule set in advance for generating the first text. The first text is a text that responds to the previous input from the user. The first text is, for example, a text that indicates a backchannel, a text that confirms the contents of the user's input, but is not limited thereto. The first response rule 128 will be described in detail later.

[0068] The second response rule 129 is a preset rule for generating a second text. The second text is the next text generated in response to a series of inputs from the user. The second text is, for example, but not limited to, a text requesting the user to input slot information, or a text requesting the user to confirm slot information, or a text notifying the user that the procedure has been finalized. The second response rule 129 will be described in detail later.

[0069] The procedure content information 130 is information related to the content of a procedure executed by the interactive device 1. The procedure content information 130 includes slot information.

[0070] The control unit 13 is realized by the processor 101 reading and executing a program from the memory 102 and cooperating with other hardware configurations. The control unit 13 includes a text conversion unit 131, an intention estimation unit 132, a slot extraction unit 133, an answer acquisition unit 134, a first text generation unit 135, a second text generation unit 136, an output unit 137, a procedure unit 138, and a notification unit 139.

[0071] The text conversion unit 131 converts the voice information 121 into text information 122 by voice recognition processing.

[0072] The intention estimation unit 132 estimates the user's intention from the text information 122 by using the estimation model 123 .

[0073] The slot extraction unit 133 executes so-called slot filling. That is, when the user's intention is a procedure, the slot extraction unit 133 uses the extraction model 125 to extract slot information corresponding to the procedure from the text information 122, and temporarily stores the extracted slot information in the storage unit 12 as the slot information of the procedure.

[0074] When the user's intention is to ask a question, the answer acquisition unit 134 refers to the Q&A information 127 and acquires answer information corresponding to the question.

[0075] The first text generator 135 generates the first text based on at least one of the slot information and the answer information in accordance with the first response rule 128.

[0076] The second text generator 136 generates the second text in accordance with the second response rule 129 and based on the slot information.

[0077] The output unit 137 outputs the first text and the second text. Specifically, when the dialogue with the user is performed by voice, the output unit 137 synthesizes voice corresponding to the first text and the second text, and outputs the obtained voice information. The output voice information is transmitted to the user terminal 2 and output from the output device 206 (speaker). Also, when the dialogue with the user is performed by text, the output unit 137 generates and outputs text information corresponding to the first text and the second text. The generated text information and the output text information are transmitted to the user terminal 2 and output to the output device 206 (display device).

[0078] The procedure unit 138 executes the procedure according to the contents of the procedure information 124. For example, if the procedure is a reservation, the procedure unit 138 executes the reservation according to the contents of the procedure information 124. Here, it is assumed that the procedure unit 138 functions as a procedure system (e.g., a reservation system) that executes the procedure, but a procedure system connected to the interactive device 1 via the network N may be provided separately from the interactive device 1. In this case, the procedure unit 138 instructs the procedure system to execute the procedure according to the contents of the procedure information 124.

[0079] The notification unit 139 notifies the user terminal 2 of the contents of the executed procedure. The notification is performed by, for example, SMS, chat, email, voice, or push notification.

[0080] The functional configuration of the dialogue device 1 is not limited to the above example. For example, the dialogue device 1 may have a part of the functional configuration described above, and the user terminal 2 may have the rest. The dialogue device 1 may also have functional configurations other than those described above. As described above, each functional configuration of the dialogue device 1 may be realized by software, or may be realized by hardware such as an IC chip, a SoC (System on Chip), an LSI (Large Scale Integration), or a microcomputer.

[0081] <Learning process executed by the dialogue system 1000> Next, a process executed by the dialogue system 1000 will be described. Fig. 8 is a flowchart showing an example of a process executed by the dialogue system 1000. The following describes an example in which a user performs a procedure over a call (telephone). The dialogue system 1000 repeatedly executes the following process until the call is ended.

[0082] (Step S101) The user terminal 2 acquires voice information of a voice uttered by the user through the input device 205 (microphone) (step S101).

[0083] (Step S102) The communication unit 21 of the user terminal 2 transmits the acquired voice information to the interactive apparatus 1 (step S102).

[0084] (Step S103) The communication unit 11 of the interactive device 1 receives (acquires) the voice information from the user terminal 2 (step S103), and stores it in the storage unit 12 as voice information 121.

[0085] (Step S104) The text conversion unit 131 converts the voice information 121 into text information 122 by voice recognition processing (step S104), and stores the text information 122 in the storage unit 12.

[0086] (Step S105) The intention estimation unit 132 estimates the user's intention from the text information 122 using the estimation model 123 (step S105). The intention estimation unit 132 estimates the user's intention as, for example, a procedure, a question, an affirmative, a negative, or a combination of these. For example, when the user utters, "We would like to make a reservation for three people. Are there any vacant tables?", the intention estimation unit 132 estimates that the user's intention is a procedure and a question.

[0087] If the user's intention is a procedure, the process proceeds to step S106. If the user's intention is a question, the process proceeds to step S109. If the user's intention is a positive one, the process proceeds to step S118. If the user's intention is at least one combination of a procedure, a question, and a positive one, the process proceeds to the corresponding step.

[0088] (Step S106) The slot extraction unit 133 checks whether the procedure information 124 corresponding to the procedure estimated in step S105 has been set (step S106). If the procedure information 124 has not been set (step S106: NO), the process proceeds to step S107. If the procedure information 124 has been set (step S106: YES), the process proceeds to step S108.

[0089] (Step S107) The slot extraction unit 133 refers to the procedure information 124, and sets the procedure information 124 corresponding to the procedure estimated in step S105 as the procedure information 124 for this call (step S107). Hereinafter, the procedure information 124 set here is referred to as procedure information 124'. At this point, the value of the slot information included in the set procedure information 124' is blank.

[0090] (Step S108) The slot extraction unit 133 uses the extraction model 125 to extract slot information corresponding to the procedure information 124' from the text information 122 (step S108), and adds it to the procedure information 124'. After that, the process proceeds to step S110.

[0091] (Step S109) The answer acquisition unit 134 refers to the Q&A information 127 and acquires answer information corresponding to the question estimated in step S105 (step S109).

[0092] (Step S110) The first text generating unit 135 generates the first text based on at least one of the slot information extracted in step S108 and the answer information acquired in step S109 in accordance with the first response rule 128 (step S111). More specifically, when the user's intention is a procedure, the first text generating unit 135 generates the first text based on the slot information extracted in step S108. When the user's intention is a question, the first text generating unit 135 generates the first text based on the answer information acquired in step S109. When the user's intention is a procedure and a question, the first text generating unit 135 generates the first text based on the slot information extracted in step S108 and the answer information acquired in step S109. The first text generating unit 135 may generate the first text based on the priority of the procedure and the question set in advance. For example, if the priority of the procedure is higher than the priority of the question, the first text generation unit 135 may generate text based on the slot information, and then generate text based on the answer information, and output the whole of these as the first text.

[0093] (Step S111) The second text generator 136 generates the second text based on the slot information of the procedure information 124' in accordance with the second response rule 129 (step S111). If the procedure information 124' is not set, the process proceeds to step S112.

[0094] (Step S112) The output unit 137 synthesizes a voice corresponding to the first text and the second text (step S112).

[0095] (Step S113) The output unit 137 transmits the voice information obtained in step S112 to the user terminal 2 via the communication unit 11 (step S113).

[0096] (Step S114) The user terminal 2 outputs the voice information received from the interactive device 1 by the output device 206 (speaker) (step S114). Through the above process, a voice dialogue (conversation) between the user and the interactive device 1 is realized.

[0097] (Step S115) Meanwhile, the procedure unit 138 of the interactive device 1 refers to the procedure information 124' and determines whether the slot information has been confirmed (step S115). Specifically, if the "confirmation flag" of the procedure information 124' is "on", it is determined that the slot information has been confirmed (step S115: YES), and the process proceeds to step S116. On the other hand, if the "confirmation flag" of the procedure information 124' is "off" or if the procedure information 124' has not been set, it is determined that the slot information has not been confirmed (step S115: NO), and the process ends.

[0098] (Step S116) The procedure unit 138 executes the procedure based on the contents of the procedure information 124' (step S116). Through the above processing, the procedure is executed by voice (telephone call).

[0099] (Step S117) The notification unit 139 notifies the user terminal 2 of the contents of the procedure executed in step S117. The notified contents include the slot information of the procedure information 124'.

[0100] When the user interacts with the dialogue device 1 through text, the user terminal 2 acquires text information input by the user (step S101) and transmits it to the dialogue device 1 (step S102). The dialogue device 1 then omits steps S103 and S104 and estimates the user's intention from the text information received from the dialogue device 1 (step S105). After generating the first text and the second text (steps S110 and S111), the dialogue device 1 generates text information corresponding to the first text and the second text (step S113) and transmits the text information to the user terminal 2 (step S113). The user terminal 2 displays the text information received from the dialogue device 1 on the output device 206 (display device) (step S114).

[0101] (Step S118) The intention estimation unit 132 checks whether the slot information has a vacancy (a "slot" whose value is blank) by referring to the procedure information 124' (step S118). If the slot information has a vacancy (step S118: YES), the process proceeds to step S110. If the slot information does not have a vacancy (step S118: NO), the process proceeds to step S119.

[0102] (Step S119) The intention estimation unit 132 sets the "confirmation flag" of the procedure information 124' to "on" (step S119). This defines the slot information of the procedure information 124'. After that, the process proceeds to step S110.

[0103] <How to generate the first text> Next, a method for generating the first text (first response rule 128) will be described. Fig. 9 is a flowchart showing an example of a method for generating the first text defined by the first response rule 128. Fig. 9 corresponds to the internal processing of step S110 in Fig. 8.

[0104] (Step S201) If the user's intention estimated in step S105 is a question (step S201: YES), the process proceeds to step S202. If the user's intention estimated in step S105 is not a question (step S201: NO), the process proceeds to step S203.

[0105] (Step S202) The first text generating unit 135 generates the first text based on the answer information acquired in step S109 (step S202). The first text generating unit 135 may use the answer information as the first text as it is, or may generate the first text by referring to the target person information 126. As a result, a text including a backchannel and an answer to the question is generated as the first text.

[0106] (Step S203) If the user's intention estimated in step S105 is a procedure (step S203: YES), the process proceeds to step S204. If the user's intention estimated in step S105 is not a procedure (step S203: NO), the process proceeds to step S208.

[0107] (Step S204) If it is the first time that the user's intention is estimated to be a procedure (step S204: YES), the process proceeds to step S205. If it is not the first time that the user's intention is estimated to be a procedure, that is, if the user's intention has already been estimated to be a procedure in the previous dialogue (step S204: NO), the process proceeds to step S206.

[0108] (Step S205) The first text generating unit 135 generates text "It's {procedure name}, isn't it?" as the first text. {procedure name} is the name of the procedure. For example, "Procedure" in procedure information 124' is referenced as {procedure name}. When the procedure is a reservation and procedure information 124 in FIG. 5 is referenced, text "It's a reservation, isn't it?" is generated. Also, an information item referenced by {procedure name} may be provided in procedure information 124 in addition to "Procedure". This allows for polite expressions such as "It's a reservation, isn't it?". This generates text indicating a backchannel as the first text.

[0109] (Step S206) If slot information is extracted in step S108 (step S206: YES), the process proceeds to step S207. If slot information is not extracted in step S108 (step S206: NO), the process ends.

[0110] (Step S207) The first text generator 135 refers to the procedure information 124' and generates text "{S} is {s}, isn't it?" as the first text. {S} is the name of the extracted slot information, and {s} is the value of the extracted slot information. The procedure information 124' may be provided with information items referenced by {S} and {s} in addition to "slot". This allows for polite expressions such as "Your name is Sato-sama, isn't it?" When multiple slot information are extracted, text is generated in which "{S} is {s}" is repeated for each slot information. This generates text for confirming the user's input as the first text.

[0111] (Step S208) The first text generator 135 refers to the procedural information 124' and checks whether the "confirmation flag" is "on" (step S208). If the "confirmation flag" is "on" (step S208: YES), the process proceeds to step S209. If the "confirmation flag" is "off" (step S208: NO), the process ends.

[0112] (Step S209) The first text generating unit 135 generates a text "{S} will confirm {procedure name} with {s}" as the first text (step S209). {S} is the name of the slot information of the procedure information 124'. {s} is the value of the slot information of the procedure information 124'. The procedure information 124' may be provided with information items referenced by {S}, {s}, and {procedure name} in addition to "slot" and "procedure". This allows for polite expressions such as "your name is Sato and we will confirm your reservation". When multiple slot information are set, a text in which "{S} will {s}" is repeated for each slot information is generated. This generates a text notifying the user that the procedure has been confirmed as the first text.

[0113] In this manner, the first text is generated according to the first response rule 128. More specifically, the first text is generated by applying preset answer information and slot information to a predefined text format. By generating the first text in this manner, it is possible to prevent erroneous information from being output as the first text (hallucination). In addition, since the first text is not generated by a natural language processing model, attacks such as prompt injection against the dialogue system 1000 can be prevented.

[0114] <How to generate the second text> Next, a method for generating the second text (second response rule 129) will be described. Fig. 10 is a flowchart showing an example of a method for generating the second text defined by the second response rule 129. Fig. 10 corresponds to the internal processing of step S111 in Fig. 8.

[0115] (Step S301) The second text generator 136 checks whether there is a vacancy in the slot information (a "slot" whose value is blank) by referring to the procedure information 124' (step S301). If there is a vacancy in the slot information (step S301: YES), the process proceeds to step S302. If there is no vacancy in the slot information (step S301: NO), the process proceeds to step S303.

[0116] (Step S302) The second text generator 136 references the procedure information 124' and generates text "Please tell me {S}" as the second text (step S302). {S} is the name of the slot information whose value is blank in the procedure information 124' ("slot"). An information item referenced by {S} may be provided in the procedure information 124' in addition to "slot". This allows for polite expressions such as "Please tell me your name". Also, if multiple pieces of slot information are blank, similar text is generated for each piece of slot information. This generates text requesting the user to input slot information as the second text.

[0117] (Step S303) The second text generator 136 refers to the procedural information 124' and checks whether the "confirmation flag" is "on" (step S303). If the "confirmation flag" is "on" (step S303: YES), the process proceeds to step S304. If the "confirmation flag" is "off" (step S303: NO), the process ends.

[0118] (Step S304) The second text generator 136 refers to the procedure information 124' and generates text "Are you sure that {S} is {s}?" as the second text (step S304). {S} is the name of the slot information of the procedure information 124' ("slot"). {s} is the value of the slot information of the procedure information 124'. An information item referred to by {S} and {s} may be provided in the procedure information 124' in addition to "slot". This allows for polite language expressions such as "Are you sure that your name is Sato-san?". When multiple slot information are set, text is generated in which "{S} is {s}" is repeated for each slot information. This generates text requesting the user to confirm the slot information as the second text.

[0119] In this manner, the second text is generated according to the second response rule 129. More specifically, the second text is generated by applying preset answer information and slot information to a predefined text format. By generating the second text in this manner, it is possible to prevent erroneous information from being output as the second text (hallucination). In addition, since the second text is not generated by a natural language processing model, attacks such as prompt injection against the dialogue system 1000 can be prevented.

[0120] <Examples of dialogue> Next, a specific example of a dialogue between a user and the dialogue device 1 will be described. Fig. 11 is a schematic diagram showing a specific example of a dialogue. In the following, a case where a user makes a reservation by telephone will be described as an example.

[0121] (Step S401) After a call between the interactive device 1 and the user terminal 2 starts, when the user utters "Excuse me, I'd like to make a reservation," the user terminal 2 acquires voice information of the utterance (step S101) and transmits the voice information to the interactive device 1 (step S102).

[0122] (Step S402) When the interactive device 1 acquires the voice information 121 from the user terminal 2 (step S103), the text conversion unit 131 converts the voice information 121 into text information 122 (step S104), and the intention estimation unit 132 estimates the user's intention by using the estimation model 123 (step S105). Here, the user's intention is estimated to be "reservation" (step S105: procedure). At this point, the procedure information 124' for "reservation" has not been set (step S106: NO), so the slot extraction unit 133 refers to the procedure information 124 and sets the procedure information 124' for "reservation" (step S107).

[0123] Fig. 12 is a diagram showing an example of procedure information 124' for "reservation." In the example of Fig. 12, procedure information 124' has "date," "time," "name," and "number of people" as slot information. At the time of step S402, "date," "time," and "name" are blank, and the "confirmation flag" is "off."

[0124] After setting the procedure information 124', the slot extraction unit 133 extracts slot information included in the procedure information 124' from the text information 122 (step S108). Here, no slot information is extracted.

[0125] Since this is the first time that the user's intention is estimated to be a procedure (step S201: NO, step S203: YES, step S204: YES) and slot information has not been extracted (step S206: NO), first text generator 135 generates the text "You'd like to make a reservation" as the first text (step S205). In this manner, the first text is generated (step S110).

[0126] Since there is a vacancy in the slot information of the procedure information 124' (step S301: YES), the second text generator 136 generates text "Please tell me the date" as the second text (step S302). In this manner, the second text is generated (step S111). Note that, although it is assumed here that the slot information with blank values ​​is checked in order from the top, the slot information with blank values ​​may be checked all at once.

[0127] The output unit 137 synthesizes voice information corresponding to the first text and the second text (step S112), and the communication unit 11 transmits the obtained voice information to the user terminal 2 (step S113). Upon receiving the voice information, the user terminal 2 outputs a voice message saying, "This is a reservation, right? Please tell me the date" (step S114).

[0128] Since the slot information of the procedure information 124' has not been determined (step S115: NO), the procedure section 138 of the interactive device 1 does not execute the reservation and ends the process.

[0129] (Step S403) When the user utters "August 10th, please," the user terminal 2 acquires voice information of the utterance (step S101) and transmits the voice information to the dialogue apparatus 1 (step S102).

[0130] (Step S404) When the dialogue device 1 acquires the voice information 121 from the user terminal 2 (step S103), the text conversion unit 131 converts the voice information 121 into text information 122 (step S104), and the intention estimation unit 132 estimates the user's intention using the estimation model 123 (step S105). Here, the user's intention is estimated to be "reservation" (step S105: procedure). Since the procedure information 124' for "reservation" has already been set (step S106: YES), the slot extraction unit 133 extracts slot information included in the procedure information 124' from the text information 122 (step S108). Here, "August 10th" is extracted as the "date". The slot extraction unit 133 adds the extracted slot information to the procedure information 124'.

[0131] Since this is not the first time that the user's intention has been estimated as a procedure (step S201: NO, step S203: YES, step S204: NO), and "August 10th" has been extracted as the "date" (step S206: YES), first text generating unit 135 generates text "The date is August 10th, isn't it?" as the first text (step S207). In this manner, the first text is generated (step S110).

[0132] Since there is an empty slot in the procedure information 124' (step S301: YES), the second text generator 136 generates the text "Please tell me the time" as the second text (step S302). In this manner, the second text is generated (step S111).

[0133] The output unit 137 synthesizes voice information corresponding to the first text and the second text (step S112), and the communication unit 11 transmits the obtained voice information to the user terminal 2 (step S113). Upon receiving the voice information, the user terminal 2 outputs a voice message saying, "The date is August 10th, right? Please tell me the time" (step S114).

[0134] Since the slot information of the procedure information 124' has not been determined (step S115: NO), the procedure section 138 of the interactive device 1 does not execute the reservation and ends the process.

[0135] (Step S405) When a user speaks (asks) "What time does it start?", the user terminal 2 acquires voice information of the utterance (step S101) and transmits the voice information to the dialogue apparatus 1 (step S102).

[0136] (Step S406) When the dialogue device 1 acquires the voice information 121 from the user terminal 2 (step S103), the text conversion unit 131 converts the voice information 121 into text information 122 (step S104), and the intention estimation unit 132 estimates the user's intention by using the estimation model 123 (step S105). Here, the user's intention is estimated to be a question about "business hours" (step S105: question), and the answer acquisition unit 134 acquires answer information corresponding to "business hours" (text such as "Your question is about business hours. Our business hours are {business hours}") by referring to the Q&A information 127 (step S109).

[0137] Since the user's intention is estimated to be a question (step S201: YES, step S203: NO), the first text generation unit 135 generates text "Your question is about business hours. Business hours are from 9:00 to 17:00" as the first text based on the answer information (step S202). Here, since the answer information includes {business hours}, the first text generation unit 135 generates the first text by referring to the target person information 126. In this manner, the first text is generated (step S110).

[0138] Since there is an empty slot in the procedure information 124' (step S301: YES), the second text generator 136 generates the text "Please tell me the time" as the second text (step S302). In this manner, the second text is generated (step S111).

[0139] The output unit 137 synthesizes voice information corresponding to the first text and the second text (step S112), and the communication unit 11 transmits the obtained voice information to the user terminal 2 (step S113). Upon receiving the voice information, the user terminal 2 outputs a voice message saying, "You're asking about business hours, right? Our business hours are from 9:00 to 18:00. Please tell us the hours" (step S114).

[0140] Since the slot information of the procedure information 124' has not been determined (step S115: NO), the procedure section 138 of the interactive device 1 does not execute the reservation and ends the process.

[0141] (Step S407) When the user utters "Three people please, starting at 5 pm," the user terminal 2 acquires voice information of the utterance (step S101) and transmits the voice information to the dialogue apparatus 1 (step S102).

[0142] (Step S408) When the dialogue device 1 acquires the voice information 121 from the user terminal 2 (step S103), the text conversion unit 131 converts the voice information 121 into text information 122 (step S104), and the intention estimation unit 132 estimates the user's intention using the estimation model 123 (step S105). Here, the user's intention is estimated to be "reservation" (step S105: procedure). Since the procedure information 124' for "reservation" has already been set (step S106: YES), the slot extraction unit 133 extracts slot information included in the procedure information 124' from the text information 122 (step S108). Here, "17:00" is extracted as the "time" and "3" is extracted as the "number of people". The slot extraction unit 133 adds the extracted slot information to the procedure information 124'.

[0143] Since it is not the first time that the user's intention is estimated to be a procedure (step S201: NO, step S203: YES, step S204: NO), and "17:00" is extracted as "time" and "3" is extracted as "number of people" (step S206: YES), first text generating unit 135 generates text "The time is 17:00 and the number of people is 3, right" as the first text (step S207). In this way, the first text is generated (step S110).

[0144] Since there is a vacancy in the slot information of the procedure information 124′ (step S301: YES), the second text generator 136 generates the text “Please tell me your name” as the second text (step S302). In this manner, the second text is generated (step S111).

[0145] The output unit 137 synthesizes voice information corresponding to the first text and the second text (step S112), and the communication unit 11 transmits the obtained voice information to the user terminal 2 (step S113). Upon receiving the voice information, the user terminal 2 outputs a voice message saying, "The time is 5 p.m. and there are three people. Please tell me your names" (step S114).

[0146] Since the slot information of the procedure information 124' has not been determined (step S115: NO), the procedure section 138 of the interactive device 1 does not execute the reservation and ends the process.

[0147] (Step S409) When the user utters "Sato desu," the user terminal 2 acquires voice information of the utterance (step S101) and transmits the voice information to the dialogue apparatus 1 (step S102).

[0148] (Step S410) When the dialogue device 1 acquires the voice information 121 from the user terminal 2 (step S103), the text conversion unit 131 converts the voice information 121 into text information 122 (step S104), and the intention estimation unit 132 estimates the user's intention using the estimation model 123 (step S105). Here, the user's intention is estimated to be "reservation" (step S105: procedure). Since the procedure information 124' for "reservation" has already been set (step S106: YES), the slot extraction unit 133 extracts slot information included in the procedure information 124' from the text information 122 (step S108). Here, "Sato" is extracted as the "name". The slot extraction unit 133 adds the extracted slot information to the procedure information 124'.

[0149] Since this is not the first time that the user's intention has been estimated as a procedure (step S201: NO, step S203: YES, step S204: NO), and "Sato" has been extracted as the "name" (step S206: YES), first text generating unit 135 generates the text "Your name is Sato-sama, isn't it?" as the first text (step S207). In this way, the first text is generated (step S110).

[0150] Since there is no vacancy in the slot information of the procedure information 124' (step S301: NO) and the "confirmation flag" is "off" (step S303: NO), the second text generator 136 generates the text "Are you sure the date is August 10th, the time is 5pm, the name is Sato, and the number of people is 3?" as the second text (step S304). In this way, the second text is generated (step S111).

[0151] The output unit 137 synthesizes voice information corresponding to the first text and the second text (step S112), and the communication unit 11 transmits the obtained voice information to the user terminal 2 (step S113). Upon receiving the voice information, the user terminal 2 outputs a voice message saying, "Your name is Sato, right? The date is August 10, the time is 5:00 p.m., your name is Sato, and the number of people is three, is that correct?" (step S114).

[0152] Since the slot information of the procedure information 124' has not been determined (step S115: NO), the procedure section 138 of the interactive device 1 does not execute the reservation and ends the process.

[0153] (Step S411) When the user utters "Yes," the user terminal 2 acquires voice information of the utterance (step S101), and transmits the voice information to the dialogue apparatus 1 (step S102).

[0154] (Step S412) When the dialogue device 1 acquires the voice information 121 from the user terminal 2 (step S103), the text conversion unit 131 converts the voice information 121 into text information 122 (step S104), and the intention estimation unit 132 estimates the user's intention by using the estimation model 123 (step S105). Here, the user's intention is estimated to be "affirmative" (step S105: affirmative). Since there is no vacancy in the slot information of the procedure information 124' (step S118: NO), the intention estimation unit 132 sets the "confirmation flag" of the procedure information 124' to "on" (step S119).

[0155] Since the user's intention is neither a question nor a procedure (step S201: NO, step S203: NO) and the "confirmation flag" is "on" (step S208: YES), first text generating unit 135 generates the text "We will confirm the reservation for the date August 10th, the time 17:00, the name Sato, and the number of people 3" as the first text (step S209). In this way, the first text is generated (step S110).

[0156] Since there is no vacancy in the slot information of the procedure information 124' (step S301: NO) and the "confirmation flag" is "on" (step S303: YES), second text generator 136 ends the process without generating second text.

[0157] The output unit 137 synthesizes voice information corresponding to the first text (step S112), and the communication unit 11 transmits the obtained voice information to the user terminal 2 (step S113). Upon receiving the voice information, the user terminal 2 outputs a voice message saying, "The reservation is confirmed for August 10th, the time 17:00, the name is Sato, and the number of people is 3" (step S114).

[0158] Since the slot information of the procedure information 124' has been confirmed (step S115: YES), the procedure unit 138 of the interactive device 1 executes the reservation with the contents of the procedure information 124' (step S116) and stores the contents as the procedure content information 130 in the storage unit 12. As a result, a reservation is made for three people named Sato at 17:00 on August 10th.

[0159] Thereafter, the notification unit 139 notifies the user terminal 2 of the procedure content information 130 by a method such as SMS, push notification, or email (step S117).

[0160] <Summary> As described above, according to this embodiment, a dialogue system 1000 is realized which includes an intention estimation unit 132 that estimates an intention from the text information 122 using the estimation model 123, a slot extraction unit 133 that extracts slot information corresponding to the procedure from the text information 122 using the extraction model 125 if the intention is a procedure, an answer acquisition unit 134 that acquires answer information corresponding to the question if the intention is a question, a first text generation unit 135 that generates a first text based on at least one of the slot information and the answer information, a second text generation unit 136 that generates a second text based on the slot information, and an output unit 137 that outputs the first text and the second text.

[0161] According to the dialogue system 1000, the first text and the second text are generated according to the first response rule 128 and the second response rule 129. More specifically, the first text and the second text are generated by applying preset answer information and slot information to a predefined text format. By generating the first text and the second text in this manner, it is possible to prevent erroneous information from being output as the first text and the second text (hallucination). In addition, since the first text and the second text are not generated by a natural language processing model, attacks such as prompt injection against the dialogue system 1000 can be prevented.

[0162] <Additional Notes> The present embodiment includes the following disclosure.

[0163] (Appendix 1) an intention estimation unit that estimates an intention from speech information or text information by using an estimation model; a slot extraction unit that extracts slot information corresponding to the procedure from the speech information or text information by using an extraction model when the intention is a procedure; an answer acquisition unit that acquires answer information corresponding to the question when the intention is a question; a first text generator configured to generate a first text based on at least one of the slot information and the answer information; a second text generator that generates a second text based on the slot information; an output unit that outputs the first text and the second text; A dialogue system comprising:

[0164] (Appendix 2) The first text is generated according to a first preset response rule. 2. The dialogue system according to claim 1.

[0165] (Appendix 3) The second text is generated according to a second preset response rule. 2. The dialogue system according to claim 1.

[0166] (Appendix 4) The answer information is set in advance. 2. The dialogue system according to claim 1.

[0167] (Appendix 5) The estimation model is a natural language processing model. 2. The dialogue system according to claim 1.

[0168] (Appendix 6) The extraction model is a natural language processing model. 2. The dialogue system according to claim 1.

[0169] (Appendix 7) The apparatus further includes a text conversion unit that converts voice information into the text information. 2. The dialogue system according to claim 1.

[0170] (Appendix 8) The said procedures are reservations, orders, purchases, applications, or changes or cancellations thereof. 2. The dialogue system according to claim 1.

[0171] (Appendix 9) The procedure includes presetting one or more slot information. 2. The dialogue system according to claim 1.

[0172] (Appendix 10) The output unit outputs audio information corresponding to the first text and the second text.

[0173] (Appendix 11) The output unit outputs text information corresponding to the first text and the second text.

[0174] (Appendix 12) The apparatus further includes a procedure unit for executing the procedure. 2. The dialogue system according to claim 1.

[0175] (Appendix 13) The system further includes a notification unit that notifies the contents of the procedure executed by the procedure unit. 2. The dialogue system according to claim 1.

[0176] (Appendix 14) A dialogue method executed by a dialogue system, comprising: an intention estimation step of estimating the intention of the speech information or the text information by using the estimation model; a slot extraction step of extracting slot information corresponding to the procedure from the speech information or text information using an extraction model when the intention is a procedure; an answer acquisition step of acquiring answer information corresponding to the question when the intention is a question; a first text generating step of generating a first text based on at least one of the slot information and the answer information; a second text generating step of generating a second text based on the slot information; an output step of outputting the first text and the second text; The method of interaction comprising:

[0177] (Appendix 15) For dialogue systems, an intention estimation step of estimating the intention of the speech information or the text information by using the estimation model; a slot extraction step of extracting slot information corresponding to the procedure from the speech information or text information using an extraction model when the intention is a procedure; an answer acquisition step of acquiring answer information corresponding to the question when the intention is a question; a first text generating step of generating a first text based on at least one of the slot information and the answer information; a second text generating step of generating a second text based on the slot information; an output step of outputting the first text and the second text; An interactive program for executing an interactive method comprising the steps of:

[0178] The embodiments disclosed herein are illustrative in all respects and should not be considered as limiting. The scope of the present invention is indicated by the claims, not by the above meaning, and is intended to include all modifications within the meaning and scope of the claims. The present invention is not limited to the above-mentioned embodiments, and various modifications are possible within the scope of the claims, and embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention. [Explanation of symbols]

[0179] 1: Interactive device 2: User terminal 11: Communications Department 12: Storage part 13: Control unit 121: Audio information 122: Text information 123: Estimation model 124: Procedural information 125: Extraction model 126: Target information 127:Q&A Information 128: First response rule 129: Second response rule 130: Procedure information 131: Text conversion section 132: Intention estimation unit 133: Slot extraction section 134: Answer acquisition part 135: First text generation unit 136: Second text generation unit 137: Output section 138: Procedure Division 139: Notification Department

Claims

1. an intention estimation unit that estimates an intention from speech information or text information by using an estimation model; a slot extraction unit that extracts slot information corresponding to the procedure from the speech information or text information by using an extraction model when the intention is a procedure; an answer acquisition unit that acquires answer information corresponding to the question when the intention is a question; a first text generator configured to generate a first text based on at least one of the slot information and the answer information; a second text generator that generates a second text based on the slot information; an output unit that outputs the first text and the second text; A dialogue system comprising:

2. The first text is generated according to a first preset response rule. The dialogue system according to claim 1 .

3. The second text is generated according to a second preset response rule. The dialogue system according to claim 1 .

4. The answer information is set in advance. The dialogue system according to claim 1 .

5. The estimation model is a natural language processing model. The dialogue system according to claim 1 .

6. The extraction model is a natural language processing model. The dialogue system according to claim 1 .

7. Further provided is a text conversion unit for converting voice information into text information. The dialogue system according to claim 1 .

8. The said procedures are reservations, orders, purchases, applications, or changes or cancellations thereof. The dialogue system according to claim 1 .

9. The procedure includes presetting one or more slot information. The dialogue system according to claim 1 .

10. The output unit outputs audio information corresponding to the first text and the second text.

11. The output unit outputs text information corresponding to the first text and the second text.

12. The apparatus further includes a procedure unit for executing the procedure. The dialogue system according to claim 1 .

13. The system further includes a notification unit that notifies the contents of the procedure executed by the procedure unit. The dialogue system according to claim 1 .

14. A dialogue method executed by a dialogue system, comprising: an intention estimation step of estimating the intention of the speech information or the text information by using the estimation model; a slot extraction step of extracting slot information corresponding to the procedure from the speech information or text information using an extraction model when the intention is a procedure; an answer acquisition step of acquiring answer information corresponding to the question when the intention is a question; a first text generating step of generating a first text based on at least one of the slot information and the answer information; a second text generating step of generating a second text based on the slot information; an output step of outputting the first text and the second text; The method of interaction comprising:

15. For dialogue systems, an intention estimation step of estimating the intention of the speech information or the text information by using the estimation model; a slot extraction step of extracting slot information corresponding to the procedure from the speech information or text information using an extraction model when the intention is a procedure; an answer acquisition step of acquiring answer information corresponding to the question when the intention is a question; a first text generating step of generating a first text based on at least one of the slot information and the answer information; a second text generating step of generating a second text based on the slot information; an output step of outputting the first text and the second text; An interactive program for executing an interactive method comprising the steps of:

Images