Dialog system and dialog method

Abstract

The purpose of the present invention is to generate a system utterance to be output to a user.　This dialog system comprises a specification means for specifying, on the basis of a user utterance input from a user and a system utterance output immediately before the user utterance, a next system utterance to be output to the user. The dialog system comprises: a storage means for storing, as a dialog history, a user utterance and a system utterance output in response to the user utterance in association with each other, or a storage means for storing, as a dialog history, a system utterance and a user utterance input in response to the system utterance in association with each other; and a specification means for specifying, on the basis of the user utterance input from the user and the dialog history stored in the storage means, a next system utterance to be output to the user.

Description

Dialogue system and dialogue method

[0001] The present invention relates to a dialogue system and a dialogue method.

[0002] As the elderly population increases, there is an increasing need for support for elderly people living alone and for caregivers in facilities.

[0003] In particular, it is known that fewer opportunities for elderly people to interact with others can lead to a decline in their cognitive and swallowing functions, so it is important to ensure that elderly people have opportunities to interact with others.

[0004] For example, Patent Document 1 describes a dialogue system that selects and outputs a response sentence suitable for a user based on attribute information of the user.

[0005] Japanese Patent Application Laid-Open No. 2023-175269

[0006] The object of the present invention can be exemplified as follows, but is not limited to these: The object of the present invention is to identify a system utterance to be output to a user.

[0007] According to the present invention, the above object can be achieved by: [1] a dialogue system including at least one computer device, the dialogue system including a determination means for determining a next system utterance to be output to a user based on a user utterance input by the user and a system utterance output immediately before the user utterance; [2] the dialogue system according to [1] above, in which the determination means determines the next system utterance by executing inference based on the user utterance input by the user and the system utterance output immediately before the user utterance; [3] the dialogue system according to [2] above, in which the determination means determines the next system utterance by executing inference using a language model, using as input the user utterance input by the user and the system utterance output immediately before the user utterance; [4] A dialogue system according to any one of [1] to [3], comprising a dialogue storage means for storing a user utterance and a system utterance output in response to the user utterance as a dialogue history in association with each other, or a dialogue storage means for storing a system utterance and a user utterance input in response to the system utterance as a dialogue history in association with each other, and the specification means specifies a next system utterance to be output to the user based on the user utterance input by the user and the dialogue history stored in the dialogue storage means; [5] A dialogue system comprising at least one computer device, comprising: a dialogue storage means for storing a user utterance and a system utterance output in response to the user utterance as a dialogue history in association with each other, or a dialogue storage means for storing a system utterance and a user utterance input in response to the system utterance as a dialogue history in association with each other, and a specification means for specifying a next system utterance to be output to the user based on the user utterance input by the user and the dialogue history stored in the dialogue storage means; [6] The dialogue system according to [4] or [5], wherein, when a date and time at which a user utterance corresponding to a dialogue history stored in the dialogue storage means is input and / or a date and time at which a system utterance is output satisfies a predetermined time condition, the identification means identifies the next system utterance to be output to the user based on the user utterance input by the user and the dialogue history;[7] The dialogue system according to any one of [4] to [6], wherein, when at least a part of a user utterance input by the user matches at least a part of a user utterance stored in the dialogue storage means, the identification means identifies, as the next system utterance, an utterance generated based on the user utterance matching at least a part of the input user utterance, a system utterance stored in association with a user utterance matching at least a part of the input user utterance, or an utterance generated based on the system utterance; [8] The dialogue system according to any one of [4] to [7], wherein, when at least a part of a user utterance input by the user matches at least a part of a system utterance stored in the dialogue storage means, the identification means identifies, as the next system utterance, an utterance generated based on the user utterance stored in association with a system utterance matching at least a part of the input user utterance, a system utterance matching at least a part of the input user utterance, or an utterance generated based on the system utterance; [9] The dialogue system according to any one of [4] to [8], wherein, when a user utterance input by a user is similar to a user utterance stored in the dialogue storage means, the identification means identifies, as the next system utterance, an utterance generated based on the user utterance similar to the input user utterance, a system utterance stored in association with the user utterance similar to the input user utterance, or an utterance generated based on the system utterance;

[10] The dialogue system according to any one of [4] to [9], wherein, when a user utterance input by a user is similar to a system utterance stored in the dialogue storage means, the identification means identifies, as the next system utterance, an utterance generated based on the user utterance stored in association with the system utterance similar to the input user utterance, a system utterance similar to the input user utterance, or an utterance generated based on the system utterance;

[11] The dialogue system according to any one of [4] to

[10] , wherein, when a user utterance input by a user is similar to a dialogue history stored in a dialogue storage means, the identification means identifies, as the next system utterance, an utterance generated based on a user utterance corresponding to a dialogue history similar to the input user utterance, a system utterance corresponding to a dialogue history similar to the input user utterance, or an utterance generated based on the system utterance;

[12] The dialogue system according to any one of [4] to

[11] , wherein the specifying means specifies the next system utterance by executing inference using a language model using a user utterance input by the user and at least a part of the dialogue history stored in the dialogue storage means as input;

[13] The dialogue system according to any one of [4] to

[12] , wherein the dialogue storage means stores a user utterance and a system utterance output in response to the user utterance as a dialogue history in association with biometric information of the user, or stores a system utterance and a user utterance input in response to the system utterance as a dialogue history in association with user identification information, and further comprises dialogue history specifying means for specifying the dialogue history based on the biometric information of the user, and wherein the specifying means specifies the next system utterance to be output to the user based on the user utterance input by the user and the dialogue history stored in the dialogue storage means;

[14] The dialogue system according to any one of [4] to

[13] , wherein the dialogue storage means stores user utterances and / or system utterances by assigning tags corresponding to information on at least one or more of "when," "where," "who," "what," "why," and "how" in the user utterances and / or the system utterances, and the dialogue system further comprises a search means for searching a response history using the tags stored in the dialogue storage means based on information on at least one or more of "when," "where," "who," "what," "why," and "how" in the user utterance input by the user, and the identification means identifies a next system utterance to be output to the user based on the user utterance input by the user and the searched response history;

[15] The dialogue system according to any one of [4] to

[14] , wherein the identification means identifies a dialogue history to be used for identifying a next system utterance from multiple dialogue histories according to the date and time when the user utterance was input and / or the elapsed time from the date and time when the system utterance was output, and identifies the next system utterance to be output to the user based on the user utterance input by the user and the identified dialogue history;

[16] The dialogue system according to any one of [1] to

[15] , wherein the identification means identifies the next system utterance by performing inference using a language model using, as input, information obtained by replacing at least a part of a user utterance input by the user with information based on user information about the user and / or information obtained by adding information based on user information about the user to the user utterance input by the user;

[17] The dialogue system according to any one of [1] to

[16] , wherein the user information is information about the user's name, date of birth, age, sex, blood type, zodiac sign, belongings, place of residence, birthplace, preferences, habits, experiences, SNS (social networking service), family, friends, and / or acquaintances;

[18] The dialogue system according to any one of [1] to

[17] , wherein the identification means identifies the next system utterance including the user's name;

[19] The dialogue system according to any one of [1] to

[18] , wherein the user utterance input by the user is text, audio, image, or video;

[20] The dialogue system according to any one of [1] to

[19] above, wherein the output system utterance is text, audio, image, or video;

[21] The system according to any one of [1] to

[20] above, comprising a dialogue storage means for storing a user utterance input by a user and / or an output system utterance in association with user identification information for identifying the user, the location of the user terminal when the user utterance was input, and / or the date and time when the user utterance was input and / or the date and time when the system utterance was output;

[22] A method executed in a dialogue system comprising at least one computer device, comprising a specifying step of specifying a next system utterance to be output to a user based on a user utterance input by a user and a system utterance output immediately before the user utterance;

[23] A method executed in a dialogue system having at least one computer device, the method comprising: a dialogue storage means for storing a user utterance and a system utterance output in response to the user utterance as a dialogue history in association with each other; or a storage step for storing a system utterance and a user utterance input in response to the system utterance as a dialogue history in association with each other; and a specifying step for specifying a next system utterance to be output to the user based on the user utterance input by the user and the dialogue history stored in the dialogue storage means.

[0008] According to the present invention, the above object is achieved by providing:

[31] a dialogue system comprising at least one computer device, the dialogue system comprising: system utterance output means for outputting system utterances to a user; user utterance input means for accepting input of a user utterance from the user; prompt generation means for generating a prompt to be input to a language model; and answer sentence acquisition means for acquiring an answer sentence generated by inputting the generated prompt to the language model, wherein the prompt generation means generates a prompt including at least the input user utterance and the system utterance output immediately before the user utterance, and the system utterance output means outputs the acquired answer sentence or a sentence created based on the answer sentence as a next system utterance;

[32] the dialogue system according to above

[31] , wherein the prompt generation means generates a prompt requesting generation of a response to a dialogue history including at least the input user utterance and the system utterance output immediately before the user utterance;

[33] A dialogue system according to the above

[31] or

[32] , comprising: a storage means for storing, as a dialogue history, a user utterance and a system utterance output in response to the user utterance in association with each other, and when at least a part of an input user utterance matches a stored user utterance, the system utterance output means outputs, as a next system utterance, the system utterance stored in association with the user utterance or a sentence created based on the system utterance;

[34] A dialogue system according to any of the above

[31] to

[33] , wherein the prompt generation means generates a prompt by replacing at least a part of the user utterance with predetermined information and / or adding predetermined information to at least a part of the user utterance, based on user information related to the user;

[35] A dialogue system according to any of the above

[31] to

[34] , comprising: a type diagnosis means for diagnosing a user's type based on user information related to the user, and the prompt generation means generates a prompt requesting the user to generate a response sentence including a predetermined word, based on the diagnosed user type;

[36] The dialogue system according to

[34] or

[35] above, wherein the user information is information about the user's name, date of birth, age, sex, blood type, zodiac sign, belongings, place of residence, place of origin, preferences, habits, experiences, SNS (social networking service), family, friends, and / or acquaintances;

[37] The dialogue system according to any one of

[31] to

[36] above, wherein the prompt generation means generates a prompt requesting the user to generate an answer sentence including the user's name;

[38] The dialogue system according to any one of

[31] to

[37] above, wherein the system utterance output means outputs a predetermined system utterance when a predetermined condition is satisfied regarding the state of acquisition of an answer sentence by the answer sentence acquisition means;

[39] A dialogue method executed in a dialogue system having at least one computer device, the dialogue method comprising: a system utterance output step of outputting a system utterance to a user; a user utterance input step of accepting input of a user utterance from the user; a prompt generation step of generating a prompt to be input into a language model; and an answer sentence acquisition step of acquiring an answer sentence generated by inputting the generated prompt into the language model, wherein the prompt generation step generates a prompt including at least the input user utterance and the system utterance output immediately before the user utterance, and the system utterance output step outputs the acquired answer sentence or a sentence created based on the answer sentence as the next system utterance.

[0009] The effects of the present invention include, but are not limited to, the following: According to the present invention, it is possible to identify system utterances to be output to the user.

[0010] FIG. 1 is a block diagram showing a configuration of a dialogue system according to an embodiment of the present invention. FIG. 2 is a block diagram showing a hardware configuration of an assistant terminal according to an embodiment of the present invention. FIG. 3 is a block diagram showing a hardware configuration of a server device according to an embodiment of the present invention. FIG. 4 is a flowchart of a user registration process according to an embodiment of the present invention. FIG. 5 is a flowchart of a dialogue process according to an embodiment of the present invention. FIG. 6 is a flowchart of a response sentence generation process according to an embodiment of the present invention.

[0011] The following describes embodiments of the present invention, but the present invention is not limited to the following embodiments as long as they do not violate the spirit of the present invention. The order of each process constituting the flowcharts described below is random as long as no contradictions or inconsistencies occur in the process content. Furthermore, it is possible to omit some of the processes constituting the flowcharts or add new processes to each process constituting the flowcharts as long as they do not violate the spirit of the present invention. Furthermore, the device that executes each process constituting the flowcharts can be changed to another device as long as it does not violate the spirit of the present invention. In this case, the process content can be changed so as not to cause contradictions or inconsistencies in the process content.

[0012] [Configuration of Dialogue System] Fig. 1 is a block diagram showing the configuration of a dialogue system according to an embodiment of the present invention. The dialogue system shown in Fig. 1 includes a dialogue device 1, an assistant terminal 2, and a server device 3. The dialogue device 1, the assistant terminal 2, and the server device 3 are communicably connected to one another via a communication network 5. The dialogue device 1, the assistant terminal 2, and the server device 3 are also communicably connected to a language model server 4 via the communication network 5. The dialogue device 1, the assistant terminal 2, the server device 3, and the language model server 4 do not need to be constantly connected, but may be connected as needed.

[0013] In the dialogue system, any one of the dialogue device 1, the assistant terminal 2, the server device 3, and the language model server 4 can function as an information processing device. When any one of the dialogue device 1, the assistant terminal 2, the server device 3, and the language model server 4 functions as an information processing device, information is transmitted and received between the dialogue device 1, the assistant terminal 2, the server device 3, and the language model server 4 as necessary.

[0014] The dialogue device 1 is a device for dialogue with a user. The dialogue device 1 may be any device that can be spoken to by a user and that can make utterances to the user. The dialogue device 1 may include, for example, an audio input unit such as a microphone, an audio output unit such as a speaker, a control unit, a storage unit, a communication interface, etc. The dialogue device 1 may also include any other configuration.

[0015] The shape of the dialogue device 1 is not particularly limited and can be designed as appropriate. The shape of the dialogue device 1 may be, for example, an animal such as a person or a dog, a plant such as grass or a flower, or an object such as a snowman or a scarecrow. Alternatively, the shape of the dialogue device 1 may be a geometric shape such as a sphere or a cylinder. In other words, the dialogue device 1 may have an appearance like a robot or a smart speaker. From the viewpoint of making it easier for users to become attached to the dialogue device 1, the dialogue device 1 may have an appearance like a robot.

[0016] The interactive device 1 may also be a desktop or notebook personal computer, a tablet terminal, a smartphone, a conventional mobile phone, or the like.

[0017] The user who will have a dialogue with the dialogue device 1 is not particularly limited and can be designed as appropriate. The user may be, for example, an elderly person, a child, or a non-elderly adult.

[0018] The assistant terminal 2 is a terminal operated by an assistant who assists the user. "Assistants" include, for example, the user's family, care managers, caregivers, and staff at the facility where the user is staying. By inputting information about the user (hereinafter also referred to as user information) into the assistant terminal 2, user registration, which will be described later, can be performed.

[0019] 2 is a block diagram showing the hardware configuration of an assistant terminal according to an embodiment of the present invention. The assistant terminal 2 includes a control unit 21, a RAM 22, a storage unit 23, an input unit 24, a display unit 25, and a communication interface 26, all of which are connected by a bus.

[0020] The control unit 21 is composed of a CPU and a ROM. The control unit 21 executes programs stored in the storage unit 23 and controls the assistant terminal 2. The RAM 22 is the work area of ​​the control unit 21. The storage unit 23 is a memory area for saving programs and data. In other words, the storage unit 23 functions as a recording medium that stores programs. The control unit 21 performs arithmetic processing based on the programs and data read from the RAM 22 and data input via the input unit 24.

[0021] The display unit 25 has a display screen. The control unit 21 outputs a video signal for displaying an image on the display screen according to the result of the arithmetic processing. Here, the display screen of the display unit 25 may be a touch panel equipped with a touch sensor. In this case, the touch panel functions as the input unit 24.

[0022] The communication interface 26 can be connected to the communication network 5 wirelessly or via a wire, and can transmit and receive data to and from other computer devices via the communication network 5. Data received via the communication interface 26 is loaded into the RAM 22, and the control unit 21 performs arithmetic processing on the data.

[0023] If the user does not have an assistant, the dialogue system may include a user terminal operated by the user instead of the assistant terminal 2. Regarding the hardware configuration of the user terminal, the above description of the hardware configuration of the assistant terminal 2 can be adopted to the extent necessary.

[0024] The server device 3 may be managed by an administrator of the dialogue system.

[0025] 3 is a block diagram showing the hardware configuration of a server device according to an embodiment of the present invention. The server device 3 includes at least a control unit 31, a RAM 32, a storage unit 33 (memory unit), and a communication interface 34, which are connected to each other via an internal bus.

[0026] The control unit 31 is composed of a CPU and a ROM, and executes programs stored in the storage unit 33 to control the server device 3. The control unit 31 also has an internal timer that measures time. The RAM 32 is the work area of ​​the control unit 31. The storage unit 33 is a storage area for saving programs and data. In other words, the storage unit 33 functions as a recording medium that stores programs. The control unit 31 reads the programs and data from the RAM 32, and performs program execution processing based on information received from the dialogue device 1, the assistant terminal 2, and the language model server 4, etc.

[0027] The program may also be stored in a recording medium such as a CD-ROM. In this case, the program stored in the recording medium may be installed in the dialogue device 1, the assistant terminal 2, and / or the server device 3 to execute a predetermined function.

[0028] Alternatively, the program may be distributed from a computer device external to the system. In this case, the program distributed from the computer device external to the system may be installed in the dialogue device 1, the assistant terminal 2, and / or the server device 3 to execute a predetermined function.

[0029] The language model server 4 is a server that uses a language model to perform natural language processing tasks such as sentence generation, question and answer, and sentence summarization. By inputting an instruction sentence called a prompt into the language model server 4, an answer sentence is output from the language model. The language model server 4 is equipped with an inference engine. The inference engine loads model parameters into VRAM. When a prompt is input, the inference engine converts the prompt character string into tokens, executes forward calculations of the Transformer, and sequentially generates tokens based on the obtained probability distribution. The generated output is output as an answer to the input source of the prompt.

[0030] The language model server 4 may be managed by a person other than the administrator of the dialogue system. The server device 3 and the language model server 4 may be configured to cooperate with each other using an API (Application Programming Interface).

[0031] The type of language model is not particularly limited as long as it can process natural language. The language model may be a large-scale language model or a small-scale language model. As the language model, for example, a Transformer-based model such as a Generative Pre-trained Transformer (GPT) or a Bidirectional Encoder Representations from Transformers (BERT) can be adopted.

[0032] The language model server 4 may include a computer device that stores a language model for executing natural language processing. The hardware configuration of the language model server 4 may be the same as that of the server device 3, to the extent necessary.

[0033] Note that the artificial intelligence equipped with a language model may be a specialized artificial intelligence specialized in processing a specific type of task, or may be a general-purpose artificial intelligence capable of processing multiple types of tasks. General-purpose artificial intelligence includes AGI (Artificial General Intelligence) and ASI (Artificial Superintelligence). In other words, the language model is a concept that includes artificial intelligence and / or a server that has the function of outputting answers to questions and / or instructions.

[0034] Furthermore, although the present description explains a mode in which an answer sentence is output from a language model in the language model server 4, the language model may be stored in the server device 3, the assistant terminal 2, or the dialogue device 1, and the server device 3, the assistant terminal 2, or the dialogue device 1 may be configured to output an answer sentence from the language model.

[0035] The dialogue system may also include a plurality of dialogue devices 1. In this case, it is preferable that each dialogue device 1 is assigned identification information (e.g., a dialogue device ID) for identifying the respective dialogue devices 1. It is also preferable that each user of the dialogue device 1 is assigned user identification information (e.g., a user ID) for identifying the user. Here, it is assumed that each dialogue device 1 is assigned a dialogue device ID, and each user is assigned a user ID. The server device 3 can store the user ID and the dialogue device ID in association with each other. The server device 3 can also store information acquired by each dialogue device 1, information about the user of each dialogue device 1, and the like, in association with the user ID and the dialogue device ID.

[0036] The dialogue system may also include multiple assistant terminals 2. Each assistant may be assigned identification information (such as an assistant ID) to identify the assistant. Here, it is assumed that each assistant is assigned an assistant ID. The server device 3 can store a user ID in association with the assistant ID of the assistant assisting the user corresponding to the user ID. The number of assistant IDs stored in association with one user ID may be one or may be two or more. The assistant may be able to register, edit, view, etc., information about the user corresponding to the user ID stored in association with his or her own assistant ID.

[0037] Furthermore, the server device 3 may function in a distributed manner across multiple computer devices. For example, instead of the server device 3, a distributed ledger technology such as a blockchain may be used.

[0038] Furthermore, the number and types of computer devices included in the dialogue system are not particularly limited and can be designed as appropriate. The dialogue system only needs to include at least one computer device. For example, the dialogue system may be composed of the dialogue device 1, or may be composed of the dialogue device 1 and the server device 3.

[0039] [User Registration Process] First, the assistant performs user registration in the dialogue system. User registration may mean storing information about the user in the server device 3 provided in the dialogue system. For example, the assistant may input an assistant ID and a user ID on a login screen for logging in to the dialogue system, which may allow the assistant terminal 2 to display a user management screen for managing the user corresponding to the user ID. Furthermore, the assistant may be able to display a user registration screen for user registration on the assistant terminal 2 via the user management screen. Figure 4 is a flowchart of user registration processing according to an embodiment of the present invention.

[0040] The assistant terminal 2 accepts input of user information (Step S101). The assistant terminal 2 transmits the input user information to the server device 3 (Step S102). The server device 3 receives the transmitted user information (Step S103). The server device 3 diagnoses the user's type based on the received user information (Step S104). The server device 3 stores the user information including the diagnosed user type (Step S105), and the user registration process ends.

[0041] The user information input in step S101 may include the user's name, date of birth, age, gender, blood type, zodiac sign, belongings, place of residence, place of origin, preferences, habits, experiences, SNS (social networking service), information about family, friends, and acquaintances, and biometric information (face, voice, fingerprint, iris, retinal pattern). Information about the user's name includes the user's real name, the user's nickname, etc. Information about the user's belongings includes the name of the interactive device 1 used by the user, the model of the car owned by the user, etc. Information about the user's preferences includes the user's favorite foods, the user's hobbies, etc. Information about the user's habits includes the user's favorite supermarkets, the user's daily routine, etc. Information about the user's experiences includes the user's travel destinations, the user's past occupations, etc.

[0042] The method for inputting the user information in step S101 is not particularly limited and can be designed as appropriate. For example, the assistant may input the user information by typing the specified user information into a specified field on the user registration screen. Alternatively, the assistant may input the user information stored in the SNS server in association with the user's SNS account by referencing the user's SNS account information.

[0043] With the user information entered on the user registration screen, the user may press a registration button or the like displayed on the user registration screen, thereby transmitting the user information in step S102.

[0044] The method for diagnosing the user type in step S104 is not particularly limited and can be designed as appropriate. Here, "type" refers to a pattern obtained by classifying people according to some criteria and extracting their common characteristics. For example, users may be classified into an insightful "visionary type," a pacifist "peace type," a logical "logical type," etc.

[0045] The server device 3 can diagnose the user's type, that is, identify the user's type, based on the user information received in step S103. For example, the server device 3 can diagnose the user's type based on the user's date of birth, the user's blood type, or the user's zodiac sign.

[0046] In step S105, the server device 3 can store the type diagnosed in step S104 and the user information received in step S103 in association with the user ID in the storage unit 33. The type diagnosed in step S104 is information about the user, and therefore can be said to be user information.

[0047] In addition, the assistant may be able to display a reminder registration screen on the assistant terminal 2 via the user management screen to register information that should be reminded to the user. The assistant can register a reminder by inputting the time to be reminded, the content of the reminder, etc. on the reminder registration screen. The content of the reminder may be text corresponding to the voice that is actually output, or may be information that can identify the text that corresponds to the voice that is output. Hereinafter, "text corresponding to the voice that is output" will also be referred to as "text to be output." An example of text that is actually output is "Good morning. Have you woken up?". An example of information that can identify the text to be output is "morning reminder."

[0048] When information capable of identifying the text to be output is input as the content of the reminder, text corresponding to the information, which is predetermined in the dialogue system, may be output, or text corresponding to the information generated by a language model may be output. Note that "outputting a voice corresponding to text" is also referred to as "outputting text." When outputting text generated by a language model, for example, when the time for the reminder arrives, the server device 3 generates a prompt requesting the user to generate a reply sentence for the reminder, and transmits the prompt to the language model server 4, thereby acquiring the reply sentence generated by the language model. The dialogue device 1 can output the acquired reply sentence or a sentence created based on the reply sentence as a reminder. Regarding the manner in which a sentence is created based on the reply sentence, the following description may be adopted to the extent necessary. The prompt requesting the user to generate a reply sentence for the reminder may include information capable of identifying the text to be output. For example, the server device 3 may generate a prompt such as, "Please generate a sentence suitable for a morning reminder in a friendly, conversational tone."

[0049] Furthermore, when registering a reminder, the assistant may be able to set the text of the reminder to include a predetermined word (keyword). For example, the assistant may be able to set the text of a reminder for health management to include the word "jogging," and the text of a reminder for a hobby to include the word "recipes." The predetermined word can be entered and registered by the assistant. The registered word may be included in the text of the reminder with a predetermined probability. The server device 3 can generate a prompt that requests the user to generate an answer to the predetermined reminder by including the registered predetermined word with a predetermined probability. By setting the text of the reminder to include the predetermined word, a reminder that is appropriate for the user can be provided.

[0050] By registering a reminder, the dialogue device 1 can perform a predetermined output at a predetermined time. For example, the reminder function allows the dialogue device 1 to output "Good morning. Have you woken up?" to the user at 7:00 a.m.

[0051] [Dialogue Processing] Next, a mode in which a dialogue is conducted between a user and the dialogue device 1 by the dialogue system will be described. Here, the voice output from the dialogue device 1 to the user is called a system utterance. The system utterance may be a call to the user, or a response to an utterance made by the user to the dialogue device 1. Furthermore, the voice input from the user to the dialogue device 1 is called a user utterance. A dialogue is conducted by alternately outputting system utterances and inputting user utterances.

[0052] The "original text output by voice as a system utterance" is also called "text corresponding to the system utterance" or "system utterance." In other words, the content of the system utterance itself is also called system utterance. Furthermore, the "text obtained by converting the voice input as a user utterance" is also called "text corresponding to the user utterance" or "user utterance." In other words, the content of the user utterance itself is also called user utterance.

[0053] The server device 3 or the language model server 4 of the dialogue system can identify the next system utterance to be output to the user (hereinafter, the next system utterance to be output to the user will be referred to as the "next system utterance") based on the user utterance input by the user and the system utterance output immediately before the user utterance. This process can be executed, for example, by the server device 3 or the language model server 4 as the process of step S212 or S213 described below. The system utterance identified by the server device 3 or the language model server 4 is transmitted to the dialogue device 1 and output.

[0054] There are no particular limitations on the method for identifying the next system utterance based on the user utterance input by the user and the system utterance output immediately before the user utterance.

[0055] As a method for identifying the next system utterance based on the user utterance input by the user and the system utterance output immediately before the user utterance, for example, a method for classifying the user utterance input by the user and the system utterance output immediately before the user utterance using regular expressions or pattern matching rules, and identifying the next system utterance using fixed sentences or templates can be exemplified. This processing can be executed, for example, by the server device 3 as the processing of step S212 or S213 described below.

[0056] Furthermore, a method for identifying the next system utterance can be exemplified by a method of calculating similarity. A large amount of data sets of next system utterances for dialogue data consisting of a user utterance and a system utterance output immediately before the user utterance are collected, and the dialogue data are vectorized. Next, among the vectors of this dialogue data, dialogue data having a higher similarity (cosine similarity) to the vector of dialogue data consisting of a user utterance input by the user to be inferred and a system utterance output immediately before the user utterance is identified, and the next system utterance corresponding to this dialogue data can be identified as the next system utterance. These processes can be executed, for example, by the server device 3 as the process of step S212 or S213 described below.

[0057] The server device 3 or the language model server 4 of the dialogue system can identify the next system utterance by performing inference using a language model using a user utterance input by a user and a system utterance output immediately before the user utterance as input. The prompt used as input for inference using a language model includes the input user utterance, the system utterance output immediately before the user utterance, and information requesting the generation of a new utterance based on these user utterance and system utterance. This process can be executed, for example, by the server device 3 or the language model server 4 as the process of step S213 described below.

[0058] The dialogue system can associate a user utterance with a system utterance output in response to the user utterance and store the associated utterance as a dialogue history. The dialogue system can also associate a system utterance with a user utterance input in response to the system utterance and store the associated utterance as a dialogue history. The device or medium for storing the dialogue history is not particularly limited, and the dialogue history may be stored in a storage unit of the server device 3 or in a database external to the server device 3.

[0059] In addition, when multiple dialogue histories are consecutive (such as a user utterance, a system utterance output in response to the user utterance, a user utterance input in response to the system utterance, and a system utterance output in response to the user utterance), the dialogue system (for example, the memory unit of the server device 3) can store these as a single dialogue history.

[0060] Furthermore, the server device 3 or the language model server 4 of the dialogue system can identify the next system utterance to be output to the user based on the user utterance input by the user and the stored dialogue history. This process can be executed, for example, by the server device 3 as the process of step S212 described below.

[0061] An example of a method for identifying the next system utterance is a method in which, when at least a part of a user utterance input by a user matches at least a part of a user utterance stored as a dialogue history, an utterance generated based on the user utterance that matches at least a part of the input user utterance, a system utterance stored in association with the user utterance that matches at least a part of the input user utterance, or an utterance generated based on the system utterance, is identified as the next system utterance. This makes it possible to identify the next system utterance that corresponds to the input user utterance and takes into account past user utterances or system utterances.

[0062] For example, if an input user utterance is "I had hamburger steak for dinner today," and if the user utterances stored as the dialogue history include "hamburger steak," an utterance generated based on the user utterance stored as the dialogue history, a system utterance stored in association with the user utterance stored as the dialogue history, or an utterance generated based on the system utterance is identified as the next system utterance. This process can be executed, for example, by the server device 3 as the process of step S212 described below.

[0063] Here, "utterances generated based on user utterances" includes not only utterances generated by processing user utterances stored as a dialogue history in the server device 3, but also utterances generated by executing inference using a language model using a prompt including the user utterances stored as a dialogue history as input (the same applies hereinafter). The prompt may include information requesting the generation of a new utterance in response to the user utterances stored as a dialogue history. This process can be executed, for example, by the server device 3 as the process of step S212 described below.

[0064] Here, "utterances generated based on system utterances" includes not only utterances generated by processing system utterances stored as a dialogue history in the server device 3, but also utterances generated by executing inference using a language model with a prompt including the system utterances stored as a dialogue history as input (the same applies hereinafter). The prompt may include information requesting the generation of a new utterance in accordance with the system utterances stored as a dialogue history. This process can be executed, for example, by the server device 3 as the process of step S212 described below.

[0065] Even if at least a portion of a user utterance input by a user matches at least a portion of a user utterance stored as a dialogue history, if the date and time when the user utterance corresponding to the dialogue history was input and / or the date and time when the system utterance was output satisfies a predetermined temporal condition, an utterance generated based on the user utterance, at least a portion of which matches at least a portion of the input user utterance, a system utterance stored in association with the user utterance that matches at least a portion of the input user utterance, or an utterance generated based on the system utterance may be identified as the next system utterance. The predetermined temporal condition may be set as appropriate. For example, the predetermined temporal condition may be that the elapsed time from the current time is equal to or greater than a predetermined time (longer than the predetermined time), or that the elapsed time from the current time is equal to or less than a predetermined time (less than the predetermined time).

[0066] An example of a method for identifying the next system utterance is a method in which, when at least a part of a user utterance input by a user matches at least a part of a system utterance stored as a dialogue history, an utterance generated based on a user utterance stored in association with a system utterance that matches at least a part of the input user utterance, a system utterance that matches at least a part of the input user utterance, or an utterance generated based on the system utterance is identified as the next system utterance. This makes it possible to identify the next system utterance that corresponds to the input user utterance and takes into account past user utterances or system utterances.

[0067] For example, if the output system utterance is "So you're having hamburger steak for dinner tonight," and the system utterances stored as the dialogue history include "hamburger steak," the next system utterance is identified as an utterance generated based on a user utterance stored in association with the system utterance stored as the dialogue history, the system utterance stored as the dialogue history, or an utterance generated based on the system utterance. This process can be executed, for example, by the server device 3 as the process of step S212 described below.

[0068] Even if at least a portion of a user utterance input by a user matches at least a portion of a system utterance stored as a dialogue history, if the date and time when the user utterance corresponding to the dialogue history was input and / or the date and time when the system utterance was output satisfies a predetermined temporal condition, an utterance generated based on the user utterance stored in association with the system utterance at least a portion of which matches at least a portion of the input user utterance, a system utterance that matches at least a portion of the input user utterance, or an utterance generated based on the system utterance may be identified as the next system utterance. The predetermined temporal condition may be set as appropriate. For example, the predetermined temporal condition may be that the elapsed time from the current time is equal to or greater than a predetermined time (longer than the predetermined time), or that the elapsed time from the current time is equal to or less than a predetermined time (less than the predetermined time).

[0069] An example of a method for identifying the next system utterance is a method in which, when a user utterance input by a user is similar to a user utterance stored as a dialogue history, an utterance generated based on the user utterance similar to the input user utterance, a system utterance stored in association with a user utterance similar to the input user utterance, or an utterance generated based on the system utterance is identified as the next system utterance. This allows the next system utterance to be identified based on the input user utterance and taking into account past user utterances or system utterances. The user utterances stored as a dialogue history and the user utterance input by the user are vectorized, and if the similarity (cosine similarity) between these vectors is equal to or greater than a predetermined threshold, the user utterance input by the user can be determined to be similar to the user utterance stored as a dialogue history. These processes can be executed, for example, by the server device 3 as the process of step S212 described below.

[0070] Even if a user utterance input by a user is similar to a user utterance stored as a dialogue history, if the date and time when the user utterance corresponding to the dialogue history was input and / or the date and time when the system utterance was output satisfies a predetermined temporal condition, an utterance generated based on the user utterance stored as a dialogue history, a system utterance stored in association with the user utterance stored as a dialogue history, or an utterance generated based on the system utterance that is similar to the input user utterance may be identified as the next system utterance. The predetermined temporal condition may be set as appropriate. For example, the predetermined temporal condition may be that the elapsed time from the current time is equal to or greater than a predetermined time (longer than the predetermined time), or that the elapsed time from the current time is equal to or less than a predetermined time (less than the predetermined time).

[0071] An example of a method for identifying the next system utterance is a method in which, when a user utterance input by a user is similar to a system utterance stored as a dialogue history, an utterance generated based on a user utterance stored in association with a system utterance similar to the input user utterance, a system utterance similar to the input user utterance, or an utterance generated based on the system utterance is identified as the next system utterance. This allows the next system utterance to be identified based on the input user utterance and taking into account past user utterances or system utterances. The system utterances stored as a dialogue history and the user utterance input by the user are vectorized. If the similarity (cosine similarity) between these vectors is equal to or greater than a predetermined threshold, the user utterance input by the user can be determined to be similar to the system utterance stored as a dialogue history. These processes can be executed, for example, by the server device 3 as the process of step S212 described below.

[0072] Even if a user utterance input by a user is similar to a system utterance stored as a dialogue history, if the date and time when the user utterance corresponding to the dialogue history was input and / or the date and time when the system utterance was output satisfies a predetermined temporal condition, an utterance generated based on the user utterance stored in association with the system utterance stored as a dialogue history that is similar to the input user utterance, the system utterance stored as a dialogue history, or an utterance generated based on the system utterance may be identified as the next system utterance. The predetermined temporal condition may be set as appropriate. For example, the predetermined temporal condition may be that the elapsed time from the current time is equal to or greater than a predetermined time (longer than the predetermined time), or that the elapsed time from the current time is equal to or less than a predetermined time (less than the predetermined time).

[0073] An example of a method for identifying the next system utterance is a method in which, when a user utterance input by a user is similar to a dialogue history stored in a storage unit, an utterance generated based on a user utterance corresponding to a dialogue history similar to the input user utterance, a system utterance corresponding to a dialogue history similar to the input user utterance, or an utterance generated based on the system utterance is identified as the next system utterance. This allows the next system utterance to be identified based on the input user utterance and taking into account past user utterances and system utterances. The dialogue history stored in the storage unit (i.e., utterance information consisting of user utterances and system utterances) is vectorized, and the user utterance input by the user is vectorized. If the similarity (e.g., cosine similarity) between these vectors is equal to or greater than a predetermined threshold, it can be determined that the user utterance input by the user is similar to the dialogue history stored in the storage unit. These processes can be executed, for example, by the server device 3 as the process of step S212 described below.

[0074] Even if a user utterance input by a user is similar to a dialogue history stored in the storage unit, if the date and time when the user utterance corresponding to the dialogue history was input and / or the date and time when the system utterance was output satisfies a predetermined temporal condition, an utterance generated based on the user utterance stored as the dialogue history, a system utterance stored as the dialogue history, or an utterance generated based on the system utterance that is similar to the input user utterance may be identified as the next system utterance. The predetermined temporal condition may be set as appropriate. For example, the predetermined temporal condition may be that the elapsed time from the current time is equal to or greater than a predetermined time (longer than the predetermined time), or that the elapsed time from the current time is equal to or less than a predetermined time (less than the predetermined time).

[0075] An example of a method for identifying the next system utterance is a method for identifying the next system utterance by performing inference using a language model with a user utterance input by the user and at least a portion of the dialogue history stored in the storage unit as input. The server device 3 generates a prompt including the user utterance input by the user and at least a portion of the dialogue history stored in the storage unit (e.g., at least a portion of the user utterance or at least a portion of the system utterance). The prompt may include information requesting the generation of a new utterance in accordance with the user utterance input by the user and at least a portion of the dialogue history stored in the storage unit. The generated prompt is sent to the language model server 4, and inference using the prompt as input is performed with the language model.

[0076] In addition, the dialogue history stored in the memory unit of the server device 3 can be vectorized, and the user utterances input by the user can be vectorized, and the dialogue history in which the similarity (cosine similarity) between these vectors is equal to or greater than a predetermined threshold can be identified as the dialogue history to be included in the prompt.

[0077] These processes can be executed, for example, as the processes of steps S212 or S213 described below in the server device 3 or the language model server 4. The processes of generating a prompt and executing inference using a language model are similar to the processes of steps S301 to S305 described below.

[0078] As a method for identifying the next system utterance, the method described above exemplifies a method in which, when a user utterance input by a user is similar to a user utterance, system utterance, or dialogue history stored in a storage unit, the user utterance, system utterance, or dialogue history similar to the input user utterance is used to identify the next system utterance. Here, the next system utterance may be identified not only by a user utterance similar to the input user utterance, but also by a user utterance, system utterance, or dialogue history similar to a system utterance immediately before the input user utterance. The similarity between the system utterance immediately before the input user utterance and the user utterance, system utterance, or dialogue history stored in the storage unit can be calculated using the same method as the similarity between the input user utterance and the stored user utterance, system utterance, or dialogue history.

[0079] The storage unit of the server device 3 of the dialogue system stores input user utterances and / or output system utterances. The storage unit may store tags associated with the input user utterances and corresponding to information relating to at least one of "when," "where," "who," "what," "why," and "how" in the user utterance. Similarly, the storage unit may store tags associated with the input system utterances and corresponding to information relating to at least one of "when," "where," "who," "what," "why," and "how" in the user utterance.

[0080] A tag regarding information regarding "when" corresponds to information regarding time and date and time in a user utterance or a system utterance. For example, a tag regarding information regarding "when" may correspond to information regarding the time, date, and time of a person's or animal's behavior or situation, or an event or phenomenon occurring in nature or society. If "today" is expressed in a user utterance or a system utterance, and if today's date is September 1, 2025, the tag is converted into information that can identify the date and time (e.g., the Gregorian calendar or the Japanese calendar) even after time has passed, and then assigned as a tag, rather than the tag "today." In this way, by converting the date and time into information that can identify the date and time (e.g., the Gregorian calendar or the Japanese calendar) and assigning the tag, even after time has passed, it is possible to make the expressions regarding time and date in the identified system utterance appropriate to the time when the system utterance was identified. For example, even if the identified system utterance includes information about an event that occurred in September 2024, if the system utterance is identified in October 2024, an expression such as "Last month, XX occurred" will be identified, but if the system utterance is identified in September 2025, an expression such as "Last year, XX occurred" will be identified.

[0081] A tag about information about "where" corresponds to information about a position or place in a user utterance or a system utterance. For example, a tag about information about "where" may correspond to information about the behavior or situation of a person or animal, or the position or place where an event or phenomenon that occurs in the natural world or society occurs. Information about "where" includes information about "where" and "where to."

[0082] A tag corresponding to information about "who" is a tag corresponding to information about people (including deceased people) or animals (such as pets) in a user utterance or a system utterance. A tag corresponding to information about "who" is preferably a proper noun. For example, a tag about information about "who" may correspond to information about the subject in a user utterance or a system utterance, or may correspond to information about the object, or may correspond to information about a modifier phrase. For example, information about "who" includes information about "who," "whom," and "to whom."

[0083] Tags corresponding to information about "what" are tags that correspond to information about the behavior of people or animals in user utterances or system utterances (information about what was done or what kind of behavior was performed), the status of people or animals, and information about events or phenomena that occur in the natural world or society (for example, information about what happened, such as changes in the weather, the occurrence of natural disasters, the occurrence of accidents, or changes in economic conditions). For example, information about "what" includes information about "what happened" and "what was done."

[0084] Tags corresponding to information about "why" are tags that correspond to information about the behavior or situation of people or animals in user utterances or system utterances, or the reasons why events or phenomena that occur in the natural world or society occurred.

[0085] Tags corresponding to information about "how" are tags that correspond to information that modifies "what." They are tags that correspond to information that specifies the state of the behavior or situation of people or animals in user utterances or system utterances, or the state of events or phenomena that occur in the natural world or society.

[0086] For example, if the input user utterance is "Today, I ate hamburger steak with Sato-san at Tokyo Station," the date of that day (which may include the time) is assigned as the "when" tag, "Tokyo Station" as the "where" tag, "Sato-san" as the "who" tag, and "I ate hamburger steak" as the "what" tag, and these tags are stored in the storage unit of the server device 3. The same applies to the output system utterance.

[0087] The tagging of the input user utterance or the output system utterance is performed in step S209 or S216, respectively, which will be described later. The tagging method is not particularly limited, but by performing inference using a language model with the input user utterance or the output system utterance and a prompt including tagging rules as input, it is possible to identify tags corresponding to the input user utterance or the output system utterance, and store the identified tags in association with these user utterances or system utterances.

[0088] By tagging in this way, the system utterance can be used to search the dialogue history when identifying the system utterance in step S212 or S213, which will be described later. Based on information about at least one of "when," "where," "who," "what," "why," and "how" of the user utterance input by the user, the dialogue history to be used in step S212 or S213 can be searched by tracing the tag stored in association with the user identification information of the user.

[0089] The storage unit of the server device 3 stores tags associated with user utterances or system utterances, and corresponding to information on at least one of "when," "where," "who," "what," "why," and "how" in the user utterances. For example, a tag corresponding to information on "when" may be stored in association with the user's identification information, and tags corresponding to information on "where," "who," "what," "why," or "how" may be stored in association with the tag corresponding to the information on "when." This can improve search efficiency, for example, when the priority of the dialogue history used to identify system utterances is changed over time.

[0090] When there are multiple available dialogue histories, it is also possible to identify a user utterance, a system utterance, or a dialogue history to be used to identify the next system utterance, depending on the date and time when the user utterance was input and / or the time elapsed since the system utterance was output. This process can be performed in steps S211 to S213, which will be described later.

[0091] For example, the system can be designed so that the longer the time that has passed since the date and time when a user utterance in the dialogue history was input and / or the date and time when a system utterance was output, the lower the priority that the user utterance, system utterance, or dialogue history will have for identifying the next system utterance, and the shorter the time that has passed, the higher the priority that the user utterance, system utterance, or dialogue history will have for identifying the next system utterance.

[0092] A weighting value may be specified according to the time elapsed since the date and time when the user utterance was input and / or the time and date when the system utterance was output, and the specified weighting value may be added to the similarity described above to obtain a priority, or may be multiplied by the similarity to obtain a priority, to determine which user utterance, system utterance, or dialogue history to use as the basis for specifying the next system utterance. The weighting value may be set to a smaller value as the elapsed time increases.

[0093] The weighting value may be the same if the elapsed time is the same, or may be different depending on the content of the user utterance and / or system utterance stored as the dialogue history even if the elapsed time is the same. There is no particular limitation on the method for specifying different weighting values ​​depending on the content of the user utterance and / or system utterance, but different weighting values ​​may be assigned depending on the tags assigned to the user utterance and / or system utterance.

[0094] Furthermore, as a method for specifying different weighting values ​​depending on the content of user utterances and / or system utterances, a method for assigning different weighting values ​​depending on the topic genre of the user utterances and / or system utterances can be exemplified. The topic genre of the user utterances and / or system utterances stored as a dialogue history can also be specified by vectorizing each genre, vectorizing the user utterances, system utterances, or dialogue history, and specifying the genre based on the similarity between the vectors. In this way, topics related to the weather that have been around for only a few days are unlikely to be used as dialogue history, while topics related to hobbies that have been around for several months or more can be used as dialogue history.

[0095] Regarding the dialogue history, if the time elapsed since the date and time when a user utterance was input and / or the date and time when a system utterance was output satisfies a predetermined condition, the user utterance, the system utterance, or the dialogue history may be designed to identify the next system utterance. For example, if the time elapsed since the date and time when a user utterance was input and / or the date and time when a system utterance was output is less than a predetermined time, the dialogue history may be designed not to be used to identify the next system utterance, and if the time elapsed is longer than the predetermined time, the dialogue history may be designed not to be used to identify the next system utterance.

[0096] The dialogue system 1 can store a dialogue history corresponding to a user in association with the user's biometric information. The device or medium for storing the dialogue history corresponding to the user in association with the user's biometric information is not particularly limited, and the dialogue history may be stored in a storage unit of the server device 3 or in a database external to the server device 3. "Storing the dialogue history in association with the user's biometric information" means that the dialogue history of the user can be identified if the user's biometric information can be identified. For example, the user's biometric information may be stored in association with user identification information (user ID), and the user's biometric information may be further stored in association with the user identification information. In this case, if the user's biometric information can be identified, the user identification information can be identified, and the user's dialogue history can be identified.

[0097] As described above, by storing the dialogue history in association with the user's biometric information, the dialogue system can identify the dialogue history corresponding to the user who inputs a user utterance to the dialogue device 1 based on the biometric information of the user, and can identify a system utterance based on the identified user's dialogue history. For example, when person A inputs a user utterance to one dialogue device 1, person A's user identification information is identified based on person A's biometric information (e.g., face, fingerprint, iris, retinal pattern) or the biometric information (e.g., voice) of the input user utterance, and then the dialogue history is identified. Next, a system utterance is identified and output based on person A's user utterance and the identified dialogue history of person A. The user utterance input by person A and the output system utterance are stored in association with person A's identification information or person A's biometric information. On the other hand, when person B inputs a user utterance to the same dialogue device 1, person B's user identification information is identified based on person B's biometric information (e.g., face, fingerprint, iris, retinal pattern) or the biometric information (e.g., voice) of the input user utterance, and then the dialogue history is identified. Next, a system utterance is identified and output based on the user utterance of person B and the dialogue history of the identified person B. The user utterance input by person B and the output system utterance are stored in association with the identification information or biometric information of person B.

[0098] The input of user utterance by the user may be executed in step S206, which will be described later, and the identification of user identification information or dialogue history based on biometric information may be executed in step S210. The identification of user identification information based on biometric information may be executed by the dialogue device 1 or the server device 3.

[0099] The biometric information stored in association with the dialogue history is not particularly limited. Examples of biometric information include face, voice, fingerprint, iris, and retinal pattern. That is, the user can be identified by face authentication, voice authentication, fingerprint authentication, iris authentication, and retinal pattern authentication, and the system utterance corresponding to the user can be specified and output.

[0100] The process of storing the user's biometric information in association with the user identification information may be performed in the user registration process of steps S101 to S105, which will be described later. The process of storing the user's biometric information in association with the user identification information is performed prior to the interactive process of steps S201 to S219, which will be described later.

[0101] The storage unit of the server device 3 can store a dialogue history consisting of user utterances input by the user and / or system utterances output in association with user identification information, the location of the user terminal when the user utterance was input, and / or the date and time when the user utterance was input and / or the date and time when the system utterance was output. The process of storing this information is executed in step S209 or S216, which will be described later.

[0102] 5 is a flowchart of a dialogue process according to an embodiment of the present invention. First, the server device 3 identifies text corresponding to a system utterance to be output to the user (step S201). The server device 3 stores the identified text corresponding to the system utterance (step S202) and transmits it to the dialogue device 1 (step S203). The dialogue device 1 receives the text corresponding to the transmitted system utterance (step S204) and outputs it by voice (step S205).

[0103] The system utterance specified in step S201 may be specified based on the contents of the reminder registration described above. In other words, the system utterance in step S201 may be output as a reminder.

[0104] In step S202, the server device 3 may store the time (date and time) when the system utterance was identified in step S201 or the time (date and time) when the system utterance was stored in step S202, in association with the system utterance. Alternatively, after the dialogue device 1 outputs the system utterance in step S205, the time (date and time) when the system utterance was output may be transmitted to the server device 3, and the server device 3 may store the time (date and time) when the system utterance was output in association with the system utterance. The time (date and time) when the system utterance was identified, the time (date and time) when the system utterance was stored, or the time (date and time) when the system utterance was output may also be referred to as the "time when the system utterance was made." In other words, the server device 3 may store the time when the system utterance was made in association with the system utterance. Furthermore, the server device 3 may store the dialogue device ID of the dialogue device 1 that outputs the system utterance in association with the system utterance.

[0105] In step S203, the server device 3 transmits the system utterance identified in step S201 and stored in step S202 to the dialogue device 1 used by the user.

[0106] In order to respond to the system utterance, the user who has heard the system utterance output in step S205 speaks to the dialogue device 1. It is preferable that the system utterance output by the remind function has content that is easy for the user to respond to.

[0107] The dialogue device 1 accepts input of a user utterance from the user (step S206). The method of inputting the user utterance is not particularly limited. The input of the user utterance may be, for example, input of text information using a keyboard or a touch panel, input of voice, or input of image data, voice data, or video data. For example, image data or video data captured by an imaging device provided in the dialogue device 1 may be input as the user utterance.

[0108] The dialogue device 1 transmits text corresponding to the input user utterance to the server device 3 (step S207). The server device 3 receives the transmitted text corresponding to the user utterance (step S208) and stores it (step S209). The server device 3 searches the dialogue history stored in the cache memory to determine whether text corresponding to a user utterance that matches the text corresponding to the received user utterance is stored (step S210). The server device 3 determines whether to use the dialogue history stored in the cache memory (step S211).

[0109] In step S206, the dialogue apparatus 1 receives input of voice spoken by the user to the dialogue apparatus 1 via a microphone or the like. The dialogue apparatus 1 may convert the user's voice input into text.

[0110] In step S207, the user utterance converted into text may be transmitted to the server device 3.

[0111] In step S209, the server device 3 may store, in association with the user utterance, the time (date and time) at which the input of the user utterance was accepted in step S206, the time (date and time) at which the user utterance was received in step S208, or the time (date and time) at which the user utterance was stored in step S209. Hereinafter, the time (date and time) at which the input of the user utterance was accepted, the time (date and time) at which the user utterance was received, or the time (date and time) at which the user utterance was stored will also be referred to as the "time at which the user utterance was made." Furthermore, the server device 3 may store, in association with the user utterance, the dialogue device ID of the dialogue device 1 that accepted the input of the user utterance. Furthermore, the server device 3 may store the user utterance in association with the system utterance stored in step S202.

[0112] The server device 3 can store system utterances output in a dialogue and user utterances input in the dialogue as a dialogue history. In the dialogue history, the system utterances and user utterances constituting one dialogue are preferably stored in association with each other. For example, a system utterance and a user utterance input in response to the system utterance are preferably stored in association with each other. Also, for example, a user utterance and a system utterance output in response to the user utterance are preferably stored in association with each other. Also, in the dialogue history, the system utterances and user utterances constituting one dialogue are preferably stored so that their chronological order can be identified. For example, in the dialogue history, the system utterances and user utterances may be stored together with the time (date and time) at which the utterances were made, or may be stored together with the order in which they were made. Also, in the dialogue history, it is preferable that the chronological order of each dialogue be stored so that it can be identified. The dialogue history may include multiple dialogues.

[0113] The range of what constitutes one dialogue, i.e., the start and end conditions of a dialogue, are not particularly limited and can be designed as appropriate. For example, the end condition of a dialogue may be that a user utterance is not input within a predetermined time after a system utterance is output, or that a predetermined system utterance that satisfies the end condition (e.g., "See you later") is output. Furthermore, for example, the start condition of a dialogue may be that a system utterance is output after the dialogue end condition is satisfied, or that a user utterance is input after the dialogue end condition is satisfied.

[0114] The server device 3 can store the dialogue history in a main memory and / or a cache memory. The server device 3 may hold dialogue history for a predetermined number of days and / or a predetermined capacity in the cache memory. For example, the server device 3 may delete from the cache memory dialogue history that has been stored for a predetermined number of days and / or dialogue history whose storage capacity exceeds a predetermined capacity.

[0115] In step S210, the server device 3 searches the dialogue history stored in the cache memory for a user utterance that matches the received user utterance. Here, it is sufficient to search whether at least a part of the received user utterance matches at least a part of the user utterance in the dialogue history stored in the cache memory. In other words, it is sufficient to search whether the received user utterance and the user utterance in the cache memory partially match.

[0116] In step S211, the conditions for determining whether or not to use the dialogue history stored in the cache memory are not particularly limited and can be designed as appropriate.

[0117] For example, if the search in step S210 finds that the received user utterance partially matches the user utterance in the cache memory, it may be determined that the dialogue history stored in the cache memory is to be used.

[0118] Alternatively, for example, if the search in step S210 finds that the received user utterance partially matches the user utterance in the cache memory and the time at which the matching user utterance was made satisfies a predetermined time condition, it may be determined that the dialogue history stored in the cache memory is to be used. The predetermined time condition is not particularly limited and can be designed as appropriate. For example, from the perspective of preventing the user from getting bored of the same response, the predetermined time condition may be that the dialogue history is from a predetermined time before the time of determination. Specifically, for example, if the dialogue history is from two days or more before the time of determination, it may be determined that the dialogue history is to be used.

[0119] Alternatively, for example, in the search of step S210, if the received user utterance and the user utterance in the cache memory partially match, and if the system utterance made immediately before the partially matching user utterance in the cache memory partially matches the system utterance made immediately before the received user utterance, it may be determined that the dialogue history stored in the cache memory is to be used. If the user utterance and the system utterance made immediately before the user utterance both match, it is considered that the dialogue flow is the same.

[0120] In step S211, if it is determined that the dialogue history stored in the cache memory is to be used (YES in step S211), the server device 3 identifies the text corresponding to the system utterance by using the dialogue history (step S212).

[0121] In step S212, using the dialogue history stored in the cache memory may mean using, for the next system utterance, a system utterance previously output in response to a matching user utterance in the dialogue history. The system utterance previously output in response to a user utterance is stored in the dialogue history in association with the user utterance.

[0122] In step S212, the server device 3 may, for example, specify the text of a system utterance previously output in response to the matching user utterance as the next system utterance, as is, or may specify a sentence (text) created based on a system utterance previously output in response to the matching user utterance as the next system utterance. The "sentence created based on a system utterance previously output" refers to a sentence that has been modified from a system utterance previously output, and may be a sentence with specified information added, a sentence with specified information deleted, or a sentence with modified expression. The server device 3 can create a sentence (text) based on a system utterance previously output.

[0123] On the other hand, if it is determined in step S211 that the dialogue history stored in the cache memory is not to be used (NO in step S211), the server device 3 and the language model server 4 execute a response sentence generation process (step S213). The language model server 4 transmits the response sentence generated in the response sentence generation process to the server device 3 (step S214). The server device 3 receives the transmitted response sentence (step S215). The server device 3 identifies the text corresponding to the system utterance based on the received response sentence (step S212).

[0124] The response sentence generation process in step S213 will be described later.

[0125] In step S212, the server device 3 may specify the response sentence received in step S215 as the next system utterance as is, or may specify a sentence (text) created based on the received response sentence as the next system utterance. The "sentence created based on the response sentence" refers to a sentence that has been modified from the response sentence, and may be a sentence with specified information added, a sentence with specified information deleted, or a sentence with modified expression. The server device 3 can create a sentence (text) based on the response sentence.

[0126] The server device 3 stores the text corresponding to the system utterance identified in step S212 (step S216) and transmits it to the dialogue device 1 (step S217). The dialogue device 1 receives the text corresponding to the transmitted system utterance (step S218) and outputs it by voice (step S219).

[0127] Note that there is no particular limitation on the method of outputting the user utterance in step S219 in the dialogue device 1. The output of the user utterance may be, for example, displaying text information on a display screen, outputting audio, or outputting an image or video.

[0128] If the user responds to the system utterance output in step S219, step S206 is executed again, and the dialogue device 1 accepts input of a user utterance. Steps S206 to S219 are repeated until the dialogue ends. The conditions for ending the dialogue may be as described above, if necessary. If the conditions for ending the dialogue are met, the dialogue process ends.

[0129] For the processes in steps S216 to S219, the descriptions for the processes in steps S202 to S205 can be adopted to the extent necessary. In step S216, the system utterance is stored in the server device 3 as a dialogue history.

[0130] [Answer Sentence Generation Processing] Next, the answer sentence generation processing in the above-mentioned step S213 will be described. Fig. 6 is a flowchart of the answer sentence generation processing according to an embodiment of the present invention.

[0131] The server device 3 generates a prompt to be input to the language model server 4 (step S301) and transmits it to the language model server 4 (step S302). The language model server 4 receives the transmitted prompt (step S303). The language model server 4 performs inference using a language model based on the received prompt (step S304) and generates a response sentence (step S305). Steps S301 to S305 complete the response sentence generation process.

[0132] In step S301, the server device 3 generates a prompt including at least text corresponding to an input user utterance and text corresponding to a system utterance output immediately before the user utterance. Note that the "input user utterance" refers to a user utterance input immediately before the prompt is generated. The server device 3 may generate a prompt requesting the generation of a response to a dialogue history including at least the input user utterance and the system utterance output immediately before the user utterance.

[0133] The input user utterance refers to the user utterance input in step S206, and the system utterance output immediately before the user utterance may refer to the system utterance output in step S205. For example, if the system utterance in step S205 is "Good morning. Are you up?" and the user utterance in step S206 is "Yes. I've already had breakfast," the server device 3 may generate a prompt such as "Please generate a response to follow 'Good morning. Are you up?' and 'Yes. I've already had breakfast' in a friendly, conversational tone."

[0134] Furthermore, if a user utterance is input again in step S206 after a system utterance is output in step S219, the input user utterance refers to the user utterance input again in step S206, and the system utterance output immediately before the user utterance may refer to the system utterance output in step S219. For example, if the system utterance in step S219 is "Wow! What did you eat?" and the user utterance in response in step S206 is "Bread today," the server device 3 may generate a prompt such as "Please generate a response following 'Wow! What did you eat?' and 'Bread today,' in a friendly, conversational tone."

[0135] The server device 3 may generate a prompt that includes at least the input user utterance and the system utterance output immediately before the user utterance, or may generate a prompt that includes a dialogue history that precedes the input user utterance and the system utterance output immediately before the user utterance. For example, in the above example, the server device 3 may generate a prompt such as, "Please generate a response in a friendly, conversational tone that follows 'Good morning. Are you awake?' 'Yes, I've already had breakfast.' 'Wow! What did you have for breakfast?' 'Today, bread.'

[0136] Furthermore, the user utterance and the system utterance included in the prompt may not be the entire text corresponding to each utterance, but may be a portion of the text corresponding to each utterance. For example, in the above example, the server device 3 may generate a prompt such as, "Please generate a response following 'What did you eat?' 'Bread.' in a friendly, conversational tone."

[0137] By generating a prompt that includes not only the input user utterance but also the system utterance output immediately before the user utterance, it is possible to obtain an appropriate response sentence according to the flow of the dialogue.

[0138] Furthermore, by controlling the generation of prompts that include at least a part of the dialogue history, including the input user utterance and the system utterance output immediately before the user utterance, rather than a prompt that includes the entire dialogue history, it is possible to reduce the processing load on the server device 3 and / or the language model server 4, and shorten the time required to generate the prompt and / or the response sentence.

[0139] The number of dialogue histories to be included in the prompt is not particularly limited and can be designed as appropriate. The server device 3 may generate a prompt that includes several or several rounds of system utterances and user utterances immediately before the input user utterance. The dialogue histories to be included in the prompt may also be limited by an indicator other than the number. For example, the server device 3 may generate a prompt that includes a dialogue history of a predetermined number of characters, including at least the input user utterance and the system utterance output immediately before the user utterance. By limiting the dialogue histories to be included in the prompt based on a predetermined criterion, the server device 3 can obtain appropriate response sentences in accordance with the flow of the conversation while reducing the processing load.

[0140] In addition, in step S301, the server device 3 may generate a prompt by replacing at least a portion of the text corresponding to the user utterance with specified information and / or by adding specified information to at least a portion of the text corresponding to the user utterance based on registered user information.

[0141] That is, the server device 3 may introduce so-called variables into the prompt. For example, if the name of a frequent supermarket is included in the user's utterance, the server device 3 may generate a prompt by replacing the name with a variable such as {frequently visited supermarket}. The server device 3 may also generate a prompt by adding information about the specific content of the variable to the user's utterance, such as "frequently visited supermarket: XXX."

[0142] Alternatively, the server device 3 may generate a prompt by adding predetermined information to at least a part of the user's utterance without introducing a variable into the prompt. For example, if a word included in the user's utterance is included in the user information, information about the meaning of the word to the user may be added. Specifically, for example, the server device 3 may generate a prompt by adding information such as "XXX is the name of a supermarket I often go to."

[0143] When the server device 3 stores user utterances and / or system utterances, it may store the text corresponding to the user utterances and / or system utterances as is, or it may store the text corresponding to the user utterances and / or system utterances with at least a portion of the text replaced with a variable.

[0144] In step S301, the server device 3 may generate a prompt to prompt the user to generate an answer sentence including the user's name. For example, the server device 3 may generate a prompt that causes the user to generate an answer sentence including the user's name with a predetermined probability.

[0145] Furthermore, in step S301, the server device 3 may generate a prompt that requests the user to generate an answer sentence that includes a predetermined word, based on the registered user type. For example, the server device 3 may generate a prompt that causes the user type to include a different word in the answer sentence with a predetermined probability. The type of word is not particularly limited and can be designed as appropriate. The type of word may be a compliment or an exclamation mark.

[0146] Specifically, for example, if a user has been diagnosed and registered as either an insightful "vision type," a pacifist "peace type," or a logical "logical type," as described above, a prompt may be generated that causes a "vision type" user to include in their answer one of the words "amazing," "amazing," "number one," and "best," a "peace type" user to include one of the words "thank you," "happy," "kind," and "reassuring," and a "logical type" user to include one of the words "as expected," "interesting," "wonderful," and "sincere," with a predetermined probability.

[0147] By generating answer sentences containing different words for each type of user, it is possible to obtain answer sentences that suit the type of user.

[0148] In step S301, the server device 3 may generate a prompt requesting the user to generate a reply sentence of a predetermined number of characters or less. By limiting the number of characters in the reply sentence, the processing load can be reduced and a conversation can be conducted at a good tempo.

[0149] In step S305, the language model server 4 generates a response sentence in response to the prompt input in step S304.

[0150] The response sentence generated in step S305 is transmitted to the server device 3 in step S214 of the dialogue processing. When the server device 3 receives the response sentence, the dialogue system can acquire the response sentence.

[0151] In addition, if a language model is stored in the server device 3, the server device 3 may obtain the answer sentence output from the language model by performing inference using the language model with the prompt generated in step S301 as input.

[0152] Although not shown, if a predetermined condition is satisfied regarding the acquisition status of the answer sentence, the server device 3 may identify a predetermined system utterance in step S212. The dialogue device 1 can output the identified predetermined system utterance.

[0153] The predetermined condition for the acquisition status of the answer sentence is not particularly limited and can be designed as appropriate. The predetermined condition for the acquisition status of the answer sentence may be, for example, that no answer sentence is received from the language model server 4 even after a predetermined time has elapsed since the prompt was sent in step S302, or that the answer sentence received in step S215 contains an error.

[0154] The content of the predetermined system utterance is not particularly limited and can be designed as appropriate. For example, the predetermined system utterance may be, "Yes, I understand."

[0155] By outputting a predetermined system utterance when the response sentence acquisition status is not good, it becomes possible to continue the dialogue even when the language model server 4 is not functioning well.

[0156] Although the above describes a mode in which a dialogue is started from a system utterance, if a dialogue is started from a user utterance, the server device 3 may generate a prompt by treating the system utterance immediately before the input user utterance as blank.

[0157] The dialogue system of the present invention can also be used to dialogue with unregistered users. Even in response to an utterance from an unregistered user, the server device 3 can generate a prompt that includes at least the input user utterance and the system utterance output immediately before the user utterance.

[0158] The number of users who interact with one interaction device 1 may be one or more. When there are two or more users who interact with one interaction device 1, the interaction system may identify the user who made the input user utterance. For example, the interaction system may identify the user based on an image of the user's face, or may identify the user based on information about the user's voice. The image of the user's face may be acquired by a camera provided in the interaction device 1.

[0159] When multiple users who are engaged in a dialogue with one dialogue device 1 are registered users, information for identifying the users may be registered as user information. The information for identifying the users may be an image of the users' faces or information about the users' voices. In this case, the server device 3 can identify the user ID of the user who made the user utterance.

[0160] Although the above describes an embodiment in which the dialogue system is used in a real space, the dialogue system of the present invention may also be used for dialogue in a virtual space. That is, the dialogue system may be used when a user dialogues with a character or object existing in a virtual space. In this case, the user may dialogue with the character or object existing in the virtual space through the user's own avatar existing in the virtual space, or may dialogue with the character or object existing in the virtual space from within the real space via a screen displaying the virtual space. The character or object existing in the virtual space may be automatically controlled by a computer device. The dialogue system may be used to generate utterances from the character or object existing in the virtual space as system utterances.

[0161] In this way, a dialogue system is provided which comprises at least one computer device, and which comprises a system utterance output means for outputting system utterances to a user, a user utterance input means for accepting input of user utterances from the user, a prompt generation means for generating a prompt for making inferences using a language model, and an answer sentence acquisition means for acquiring an answer sentence generated by making inferences using a language model using the generated prompt as input, wherein the prompt generation means generates a prompt including at least the input user utterance and the system utterance output immediately before the user utterance, and the system utterance output means outputs the acquired answer sentence or a sentence created based on the answer sentence as the next system utterance, thereby providing a dialogue system which enables dialogues using a language model.

[0162] Furthermore, by generating a prompt that includes at least the input user utterance and the system utterance output immediately before the user utterance, a natural response sentence that corresponds to the flow of the dialogue can be obtained, and the processing load on the dialogue system can be reduced.

[0163] Furthermore, in this way, the prompt generation means generates a prompt that requests the generation of a response to a dialogue history that includes at least the input user utterance and the system utterance output immediately before the user utterance, thereby making it possible to obtain a response to the dialogue history using a language model.

[0164] Furthermore, in this way, the dialogue system is provided with a storage means for storing user utterances in association with system utterances output in response to the user utterances as a dialogue history, and when at least a part of the input user utterance matches the stored user utterance, the system utterance output means outputs the system utterance stored in association with the user utterance, or a sentence created based on the system utterance, as the next system utterance, thereby enabling output using the dialogue history.

[0165] In this way, the prompt generation means can generate a prompt by replacing at least a portion of the user's utterance with specified information and / or adding specified information to at least a portion of the user's utterance based on user information about the user, thereby obtaining an answer sentence that corresponds to the user information.

[0166] In this way, the dialogue system is provided with a type diagnosis means for diagnosing a user's type based on user information about the user, and the prompt generation means generates a prompt that requests the user to generate an answer sentence containing a specified word based on the diagnosed user type, thereby making it possible to obtain an answer sentence that corresponds to the user's type.

[0167] Furthermore, since the user information is information about the user's name, date of birth, age, gender, blood type, zodiac sign, belongings, place of residence, birthplace, preferences, habits, experiences, SNS (social networking service), family, friends, and / or acquaintances, it is possible to obtain an answer sentence that corresponds to the user's name, etc.

[0168] Furthermore, by having the prompt generating means generate a prompt requesting the generation of an answer sentence including the user's name, an answer sentence including the user's name can be obtained.

[0169] Furthermore, in this way, when predetermined conditions are met regarding the acquisition status of the answer sentence by the answer sentence acquisition means, the system utterance output means outputs a predetermined system utterance, thereby making it possible to perform a predetermined output when predetermined conditions are met regarding the acquisition status of the answer sentence.

[0170] REFERENCE SIGNS LIST 1 Dialogue device 2 Assistant terminal 3 Server device 4 Language model server 5 Communication network 21 Control unit 22 RAM 23 Storage unit 24 Input unit 25 Display unit 26 Communication interface 31 Control unit 32 RAM 33 Storage unit 34 Communication interface

Claims

1. A dialogue system comprising at least one computer device, and comprising a determination means for determining the next system utterance to be output to a user based on a user utterance input by the user and a system utterance output immediately before the user utterance.

2. The dialogue system according to claim 1, wherein the specifying means specifies the next system utterance by performing inference based on the user utterance input by the user and the system utterance output immediately before the user utterance.

3. The dialogue system according to claim 2, wherein the identification means identifies the next system utterance by performing inference using a language model, using as input a user utterance input by the user and a system utterance output immediately before the user utterance.

4. A dialogue system according to any one of claims 1 to 3, comprising a dialogue storage means for storing a user utterance and a system utterance output in response to the user utterance as a dialogue history in association with each other, or a dialogue storage means for storing a system utterance and a user utterance input in response to the system utterance as a dialogue history in association with each other, wherein the identification means identifies the next system utterance to be output to the user based on the user utterance input by the user and the dialogue history stored in the dialogue storage means.

5. A dialogue system comprising at least one computer device, comprising: a dialogue storage means for storing a user utterance and a system utterance output in response to the user utterance in association with each other as a dialogue history; or a dialogue storage means for storing a system utterance and a user utterance input in response to the system utterance in association with each other as a dialogue history; and a determination means for determining the next system utterance to be output to the user based on the user utterance input by the user and the dialogue history stored in the dialogue storage means.

6. A dialogue system as described in claim 4 or 5, wherein, when the date and time at which a user utterance corresponding to a dialogue history stored in the dialogue storage means is input and / or the date and time at which a system utterance is output satisfies a predetermined time condition, the identification means identifies the next system utterance to be output to the user based on the user utterance input by the user and the dialogue history.

7. A dialogue system according to any one of claims 4 to 6, wherein, when at least a part of a user utterance input by a user matches at least a part of a user utterance stored in the dialogue storage means, the identification means identifies, as the next system utterance, an utterance generated based on the user utterance that matches at least a part of the input user utterance, a system utterance stored in association with the user utterance that matches at least a part of the input user utterance, or an utterance generated based on the system utterance.

8. A dialogue system according to any one of claims 4 to 7, wherein, when at least a part of a user utterance input by a user matches at least a part of a system utterance stored in the dialogue storage means, the identification means identifies, as the next system utterance, an utterance generated based on the user utterance stored in association with the system utterance that matches at least a part of the input user utterance, a system utterance that matches at least a part of the input user utterance, or an utterance generated based on the system utterance.

9. A dialogue system according to any one of claims 4 to 8, wherein, when a user utterance input by a user is similar to a user utterance stored in the dialogue storage means, the identification means identifies, as the next system utterance, an utterance generated based on the user utterance similar to the input user utterance, a system utterance stored in association with the user utterance similar to the input user utterance, or an utterance generated based on the system utterance.

10. A dialogue system as described in any one of claims 4 to 9, wherein, when a user utterance input by a user is similar to a system utterance stored in the dialogue storage means, the identification means identifies, as the next system utterance, an utterance generated based on a user utterance stored in association with a system utterance similar to the input user utterance, a system utterance similar to the input user utterance, or an utterance generated based on the system utterance.

11. A dialogue system according to any one of claims 4 to 10, wherein, when a user utterance input by a user is similar to a dialogue history stored in the dialogue storage means, the identification means identifies, as the next system utterance, an utterance generated based on a user utterance corresponding to a dialogue history similar to the input user utterance, a system utterance corresponding to a dialogue history similar to the input user utterance, or an utterance generated based on the system utterance.

12. A dialogue system according to any one of claims 4 to 11, wherein the identification means identifies the next system utterance by performing inference using a language model, using as input a user utterance input by the user and at least a part of the dialogue history stored in the dialogue storage means.

13. A dialogue system according to any one of claims 4 to 12, wherein the dialogue storage means stores a user utterance and a system utterance output in response to the user utterance as a dialogue history, in association with the user's biometric information, or stores a system utterance and a user utterance input in response to the system utterance as a dialogue history, in association with user identification information; the system comprises a dialogue history identification means for identifying the dialogue history based on the user's biometric information; and the identification means identifies the next system utterance to be output to the user based on the user utterance input by the user and the dialogue history stored in the dialogue storage means.

14. A dialogue system according to any one of claims 4 to 13, wherein the dialogue storage means stores user utterances and / or system utterances by assigning tags corresponding to information relating to at least one of "when," "where," "who," "what," "why," and "how" in the user utterances and / or system utterances; the system comprises a search means for searching a response history using the tags stored in the dialogue storage means based on information relating to at least one of "when," "where," "who," "what," "why," and "how" in a user utterance input by the user; and the identification means identifies the next system utterance to be output to the user based on the user utterance input by the user and the searched response history.

15. A dialogue system according to any one of claims 4 to 14, wherein the identification means identifies a dialogue history from multiple dialogue histories to be used to identify the next system utterance, depending on the date and time when a user utterance was input and / or the time elapsed since the date and time when a system utterance was output, and identifies the next system utterance to be output to the user based on the user utterance input by the user and the identified dialogue history.

16. A dialogue system according to any one of claims 1 to 15, wherein the identification means identifies the next system utterance by performing inference using a language model, using as input information obtained by replacing at least a portion of a user utterance input by the user with information based on user information about the user, and / or information obtained by adding information based on user information about the user to a user utterance input by the user.

17. A dialogue system according to any one of claims 1 to 16, wherein the user information is information about the user's name, date of birth, age, sex, blood type, zodiac sign, possessions, place of residence, place of origin, preferences, habits, experiences, SNS (social networking service), family, friends, and / or acquaintances.

18. A dialogue system according to any one of claims 1 to 17, wherein the identifying means identifies the next system utterance that includes the user's name.

19. A dialogue system according to any one of claims 1 to 18, wherein the user utterance input by the user is text, audio, an image or a video.

20. A dialogue system according to any one of claims 1 to 19, wherein the system utterances output are text, audio, images or videos.

21. A system according to any one of claims 1 to 20, comprising a dialogue storage means for storing user utterances input by a user and / or output system utterances in association with user identification information for identifying the user, the location of the user terminal when the user utterance was input, and / or the date and time when the user utterance was input and / or the date and time when the system utterance was output.

22. A method executed in a dialogue system having at least one computer device, comprising a step of specifying a next system utterance to be output to a user based on a user utterance input by the user and a system utterance output immediately before the user utterance.

23. A method executed in a dialogue system having at least one computer device, comprising: a dialogue storage means for storing a user utterance and a system utterance output in response to the user utterance as a dialogue history in association with each other; or a storage step for storing a system utterance and a user utterance input in response to the system utterance as a dialogue history in association with each other; and a specifying step for specifying the next system utterance to be output to the user based on the user utterance input by the user and the dialogue history stored in the dialogue storage means.

Images