WO2020230353A1

WO2020230353A1 - Interaction device

Info

Publication number: WO2020230353A1
Application number: PCT/JP2019/049004
Authority: WO
Inventors: 優太朗白水
Original assignee: 株式会社Ｎｔｔドコモ
Priority date: 2019-05-13
Filing date: 2019-12-13
Publication date: 2020-11-19
Also published as: JPWO2020230353A1

Abstract

The present invention addresses the problem of providing more interactive responses. An interaction device 1 that responds to a user with words according to a prescribed theme comprises a response unit 15 that responds on the basis of a plurality of words included in a response set configured from words that are response candidates when the interaction device 1 is responding. The response unit 15 assesses an interaction state on the basis of the plurality of words, and may respond on the basis of the assessed interaction state. The response unit 15 may assess the interaction state on the basis of the number of words included in the response set. The response unit 15 may furthermore assess the interaction state on the basis of a theme. The response unit 15 may adjust the timing of responses on the basis of the interaction state. The response unit 15 may include fillers in the response on the basis of the interaction state. The response unit 15 may respond on the basis of the recognizability of each of the plurality of words.

Description

Dialogue device

One aspect of this disclosure relates to a dialogue device that alternately answers words according to a predetermined theme with a user.

Patent Document 1 below discloses an interactive game system that infers a user's emotional level from voice information spoken by the user and develops a predetermined story based on the inferred user's emotional level.

Japanese Unexamined Patent Publication No. 2003-210833

The above-mentioned interactive game system has a problem that it is not possible to give an interactive answer because a predetermined story prepared in advance is developed.

Therefore, one aspect of the present disclosure is made in view of such a problem, and an object thereof is to provide a dialogue device capable of giving a more interactive answer.

In order to solve the above problem, the dialogue device according to one aspect of the present disclosure is a dialogue device that alternately answers words according to a predetermined theme with a user, and is an answer when the dialogue device gives a reply. It is provided with an answer unit for answering based on a plurality of words included in an answer set composed of candidate words.

According to such a dialogue device, since the answer is given based on a plurality of words that are candidates for the answer when the dialogue device gives an answer, it is possible to give a more interactive answer according to the situation when giving an answer. ..

According to one aspect of this disclosure, more interactive answers can be made.

It is a functional block diagram of the dialogue device which concerns on embodiment of this invention. It is a flowchart which shows the process executed by the interactive apparatus which concerns on embodiment of this invention. It is a hardware block diagram of the dialogue apparatus which concerns on embodiment of this invention.

Hereinafter, the embodiment of the dialogue device will be described in detail together with the drawings. In the description of the drawings, the same elements are designated by the same reference numerals, and duplicate description will be omitted. Further, the embodiments in the following description are specific examples of the present invention, and are not limited to these embodiments unless otherwise specified to limit the present invention.

The dialogue device 1 according to the present embodiment is a computer device that alternately answers words (words, expressions, sentences, etc.) according to a predetermined theme (theme) with the user. In the present embodiment, the dialogue device 1 assumes an interactive game device in which a game is played while interacting with a user, but the present invention is not limited to this. In this embodiment, the term "game" may be read as the term "dialogue". For example, when playing a Yamanote Line game, the dialogue device 1 and the user alternately answer the words "Tokyo Station", "Shinagawa Station", "Ikebukuro Station", etc. according to the theme "Yamanote Line Station Name". , The player (user or dialogue device 1) who could not answer during his / her turn or who answered the already mentioned word loses (the other player wins). Further, for example, when playing an associative game (commonly known as "magical banana"), the dialogue device 1 and the user use the word "banana" as the starting word in accordance with the theme "associative game", and the dialogue device 1 and the user perform the starting word (only at the start) or the opponent. Answer the sentences "yellow if you say banana", "lemon if you say yellow", "sour if you say lemon", and so on, including the words associated with the words in the answer, and answer at your turn. The player who could not or answered the existing word loses (the other player wins). Also, for example, when playing a shiritori game, the dialogue device 1 and the user alternately answer the words "apple", "gorilla", "trumpet", etc. according to the theme "shiritori", and at the time of their own turn. The player who could not answer to loses (the other player wins).

It is assumed that the dialogue device 1 has the functions of general existing technology necessary for playing the above-mentioned game, and the description thereof will be omitted as appropriate. In this embodiment, the characteristic functions of the dialogue device 1 will be described below.

The user uses a terminal such as a smart phone or a computer device to access the dialogue device 1 via a network such as the Internet and then plays a game with the dialogue device 1. For example, the user opens a website for a game with the dialogue device 1 in a browser, inputs a word according to the theme displayed on the website in the text box of the website, and presses the input button to answer. By repeating that the answers from the dialogue device 1 are displayed on the website in sequence, the answers are alternately answered with the dialogue device 1. The game may be offered in an application rather than a website.

FIG. 1 is a functional block diagram of the dialogue device 1. As shown in FIG. 1, the dialogue device 1 includes an acquisition unit 10, an answer set generation unit 11, an answer set storage unit 12, a correctness determination unit 13, an answer set update unit 14, and an answer unit 15.

Hereinafter, each functional block of the dialogue device 1 shown in FIG. 1 will be described.

The acquisition unit 10 acquires information from the user. For example, the acquisition unit 10 acquires a theme from the user as a signal for creating a game. The acquisition unit 10 outputs the acquired theme to the answer set generation unit 11 and the answer unit 15. Further, for example, the acquisition unit 10 acquires an answer from the user during the game. The acquisition unit 10 outputs the acquired answer to the correctness determination unit 13 and the answer set update unit 14.

The answer set generation unit 11 generates an answer set based on the theme acquired (input) by the acquisition unit 10. The answer set is a set of answers composed of words that are candidates for answers to the theme. The answer set generation unit 11 generates an answer set from a database containing various information (words according to every theme) in advance. For example, the answer set generation unit 11 operates a classifier or a generator (both of which are provided in the dialogue device 1) that output SQL, and converts the theme acquired by the acquisition unit 10 into SQL from the database. Extract the answer set according to the theme. If it is a classifier, the most plausible SQL is selected from the default SQL. If it is a generator, it directly generates SQL. The classifier or generator may be a model based on a neural network or a model based on Bayes. The answer set generation unit 11 may generate an answer set based on a predetermined theme instead of the theme acquired by the acquisition unit 10. The answer set generation unit 11 stores the generated answer set by the answer set storage unit 12.

After generating the answer set, the answer set generation unit 11 determines whether the user or the dialogue device 1 answers first, that is, which one is the first attack based on a random number or the like, and if the user is the first attack, answers to the user. If the dialogue device 1 is the first player, the answering unit 15 may be instructed to answer.

The answer set storage unit 12 stores the answer set. For example, the answer set storage unit 12 stores the answer set generated by the answer set generation unit 11. Further, for example, the answer set storage unit 12 may input and store the answer set from another device via the network. The answer set stored by the answer set storage unit 12 is appropriately referred to and updated from other functional blocks.

The correctness determination unit 13 determines the correctness of the user's answer acquired (input) by the acquisition unit 10. Specifically, the correctness determination unit 13 determines whether or not the word that is the answer of the user acquired by the acquisition unit 10 is included in the answer set stored by the answer set storage unit 12, and is included. If it is, it is judged as a correct answer, and if it is not included, it is judged as an incorrect answer. When the correctness determination unit 13 determines that the answer is correct, the answer set update unit 14 is instructed to update the answer set, and the answer unit 15 is urged to answer. When the correctness determination unit 13 determines that the answer is incorrect, the correctness determination unit 13 may prompt the user to re-answer or end the game.

The answer set update unit 14 updates the answer set stored by the answer set storage unit 12. For example, when the answer set update unit 14 is instructed to update the answer set by the correctness determination unit 13 or the answer unit 15, the answer set update unit 14 acquires (inputs) from the answer set stored by the answer set storage unit 12 by the acquisition unit 10. Delete the word that is the answer of the user. Further, for example, when the answer set is input by the acquisition unit 10, the answer set update unit 14 deletes the word that is the answer of the input user from the answer set stored by the answer set storage unit 12. Further, for example, when the answer set update unit 14 is instructed to update the answer set by the answer unit 15, the answer set update unit 14 deletes the word answered by the answer unit 15 from the answer set stored by the answer set storage unit 12. The answer set update unit 14 updates the answer set each time there is an answer from each player, and the updated answer set is from the word that is the answer candidate at the present time (the timing when the player in the next order answers). It will be configured.

After updating the answer set, the answer set update unit 14 determines whether or not the end condition is satisfied. The termination condition is, for example, that the answer set is an empty set. For example, the answer set update unit 14 determines that the end condition is satisfied when the answer set becomes an empty set after updating the answer set, and satisfies the end condition when the answer set is not an empty set. Judge that there is no. When the answer set update unit 14 determines that the end condition is satisfied, the answer set update unit 14 ends the game. In this case, the game may be a draw, or the last responding player may win or lose. Further, when the answer set update unit 14 determines that the end condition is not satisfied, the answer set update unit 14 prompts the player who should answer next to answer.

The answering unit 15 gives an answer based on a plurality of words included in the answer set composed of words that are candidates for answering when the dialogue device 1 gives an answer. More specifically, the answer unit 15 is a word that becomes an answer candidate when the dialogue device 1 gives an answer when the answer set generation unit 11, the correctness determination unit 13, or the answer set update unit 14 prompts the answer. One word included in the answer set is selected based on a plurality of words included in the answer set stored by the answer set storage unit 12 which has been updated in advance by the answer set update unit 14 so as to be composed of. Answer by outputting the selected word. Hereinafter, the “plurality of words” shall refer to “a plurality of words included in an answer set composed of words that are candidate answers when the dialogue device 1 gives an answer”. In the present embodiment, "plurality of words (included in the answer set)" may be read as "all words (included in the answer set)".

The response unit 15 may determine the dialogue status based on a plurality of words and give a response based on the determined dialogue status. The dialogue situation is, for example, the degree of urgency, which is the degree of urgency in the game. The response unit 15 may manage the dialogue situation by a numerical situation score. For example, the answering unit 15 manages the situation score as a real number closer to "0" so that the game is not tense (for example, the game has just started and there are many remaining answer candidates), and the game is tense. The more (for example, the fewer answer candidates remain at the end of the game), the closer the situation score is to "1". The response unit 15 determines that the dialogue situation is "tensioned" when the situation score is equal to or higher than a predetermined threshold value (for example, "0.5"), and when the situation score is less than the predetermined threshold value, the dialogue situation is ". It may be determined that "it is not tense".

The response unit 15 may determine the dialogue status based on the number of words (remaining number) included in the response set. For example, the answering unit 15 may determine the dialogue status based on the ratio of the number of remaining words (the number of unanswered words) of the answering set to the original number of words of the answering set (the number of words at the beginning of the game). Good. More specifically, the response unit 15 sets the situation score as a real number closer to "0" as the ratio is larger, and sets the situation score as a real number closer to "1" as the ratio is smaller.

The response unit 15 may determine the dialogue status based on (further) the theme acquired (input) by the acquisition unit 10. For example, the answering unit 15 sets the situation score as a real number closer to "0" as the theme is not difficult (easy), and sets the situation score as a real number closer to "1" as the theme is difficult. Response section 15 defines the difficulty of the theme as the name recognition of the theme, and the appearance of the theme in a predetermined corpus such as Wikipedia (website: https://www.wikipedia.org/), which is an Internet encyclopedia. It may be obtained based on the frequency, the number of pages viewed on the subject in Wikipedia, or the combination of the frequency of appearance and the number of views.

The response unit 15 may adjust the timing of the response based on the dialogue situation. For example, in the answering unit 15, the closer the situation score is to "0", the earlier the response timing (predetermined timing) (pretending that the dialogue device 1 is answering immediately), or the closer the situation score is to "1". The timing of the answer may be delayed (from a predetermined timing) (the dialogue device 1 may appear to be silent / troubled).

The response unit 15 may include a filler in the response based on the dialogue situation. Filler is a word that is inserted between utterances, such as "um", "that", "well", "difficult", and "troublesome". For example, the answering unit 15 may include more fillers in the answer as the situation score approaches "1" (pretending that the dialogue device 1 is in trouble).

The answering unit 15 may give an answer based on the name recognition (popularity) of each of the plurality of words. The response unit 15 may manage the name recognition numerically in the same manner as the situation score. For example, the response unit 15 calculates the name recognition of each of the plurality of words based on the frequency of appearance of the word in a predetermined corpus such as Wikipedia or the number of pages viewed about the word in Wikipedia. Further, for example, the answering unit 15 may use the number of views of the above page, which has been logarithmically converted, as the name recognition. Further, for example, the answering unit 15 may use the appearance frequency of an arbitrary word in Wikipedia and the ratio of the anchor text as the name recognition (specifically, the word "desk" has a high appearance frequency but is an anchor text. It is rarely converted, and the names of entertainers are rarely displayed, but they are often converted into anchor text). Further, for example, the answering unit 15 may calculate the name recognition by combining some or all of the above-mentioned plurality of examples. For example, in the case of the Yamate line game, the answering unit 15 may answer from the word with high name recognition, and in the case of the associative game, the answering unit 15 may suppress the answer of the word with low name recognition.

The answering unit 15 may give an answer based on the answer possibility that the user of each of the plurality of words can answer. The answering unit 15 may manage the possibility of answering numerically as well as the situation score and the name recognition. For example, the answering unit 15 may calculate the answering possibility by a clustering method such as a list prepared in advance or k-means. For example, the answering unit 15 answers from the word with high possibility of answering in the case of the Yamate line game (answers in a form that proactively answers the user's answer), and the word with low possibility of answering in the case of the associative game (user answers). You may answer from words that are unlikely, words that are unexpected to the user). Also, for example, in the case of the Yamanote Line game, if the theme is "Yamanote Line station name", the answer unit 15 holds the station name (in station order) in advance as a set of answers (because the order of the stations is fixed). You may answer the station names before and after the station name that the user answered immediately before in the list, or if the theme is "Japanese professional baseball player name", the user immediately before based on the player name vector estimated by Word2Vec etc. The name of the player who has the closest cosine distance to the name of the player who answered in may be answered.

The answering unit 15 may give an answer based on a value associated with each of the plurality of words in advance. For example, for a plurality of words, the answer set is managed in an array such as [(word 1, score 1), (word 2, score 2), ..., (Word n, score n)], and the answer unit 15 Answers the word k associated with the highest score k in the answer set.

The response unit 15 may output (display) the answer to the user when the answer is given.

Subsequently, the processing of the dialogue method in the dialogue device 1 according to the present embodiment will be described with reference to the flowchart shown in FIG.

First, the theme is acquired from the user by the acquisition unit 10, the answer set is generated based on the theme acquired by the answer set generation unit 11 (step S1), and the generated answer set is stored by the answer set storage unit 12. , The answer set generation unit 11 prompts the user to answer. Next, in response to the user being prompted to answer, the acquisition unit 10 acquires the answer from the user (step S2). In S2, the correctness determination unit 13 determines whether the acquired answer is correct or not, and if it is determined that the answer is incorrect, the user is prompted to re-answer and the process returns to S2. If it is determined to be correct, then the answer set update unit 14 deletes the word that is the answer obtained in S2 from the answer set stored by the answer set storage unit 12, and updates the answer set. (Step S3). Next, the response set update unit 14 determines whether or not the end condition is satisfied (step S4). When it is determined in S4 that the end condition is not satisfied (S4: NO), the response set update unit 14 prompts the dialogue device 1 to answer, and the response unit 15 responds accordingly (step S5). The answer you made is output (displayed) to the user. Next, the answer set update unit 14 deletes the word that is the answer made in S5 from the answer set stored by the answer set storage unit 12, and updates the answer set (step S6). Next, the response set update unit 14 determines whether or not the end condition is satisfied (step S7). When it is determined in S7 that the end condition is not satisfied (S7: NO), the answer set update unit 14 prompts the user to answer and returns to S2.

If it is determined in S4 that the end condition is satisfied (S4: YES), or if it is determined in S7 that the end condition is satisfied (S7: YES), which player is the winner by the dialogue device 1? The process ends after the process such as the output of is performed to the user is executed.

In the flowchart shown in FIG. 2, the process when the user is the first player is shown, but the process proceeds to S5 after S1 (prompting the user for an answer by the answer set generating unit 11 and skipping S2 to S4). Then, the process is performed when the dialogue device 1 is the first player. Further, if the answer set is stored in advance by the answer set storage unit 12, S1 may be omitted. Further, the acquisition unit 10 measures the elapsed time from the time when the dialogue device 1 gives an answer to the time when the user's answer is acquired, determines that the user loses after the predetermined elapsed time, and outputs the determination result to the user ( It may be displayed) and the process may be terminated. Further, in S5, based on the answer set, the answer unit 15 may (intentionally) admit the loss (win the user) without answering even though the answer is possible, and end the process.

Next, the operation and effect of the dialogue device 1 configured as in the present embodiment will be described.

According to the dialogue device 1 of the present embodiment, the response unit 15 gives an answer based on a plurality of words included in the answer set composed of words that are candidates for the answer when the dialogue device 1 gives an answer. As a result, since the answer is given based on a plurality of words that are candidates for the answer when the dialogue device 1 gives an answer, it is possible to give a more interactive answer according to the situation when giving an answer.

Further, according to the dialogue device 1 of the present embodiment, the response unit 15 determines the dialogue status based on a plurality of words, and makes a reply based on the determined dialogue status. As a result, it is possible to provide a more interactive answer according to the dialogue situation.

Further, according to the dialogue device 1 of the present embodiment, the response unit 15 determines the dialogue status based on the number of words included in the response set. As a result, a more accurate dialogue situation is determined based on the number of words included in the answer set, so that a more interactive answer can be made according to the more accurate dialogue situation.

Further, according to the dialogue device 1 of the present embodiment, the response unit 15 further determines the dialogue status based on the theme. As a result, a more accurate dialogue situation is determined based on the theme, so that a more interactive answer can be given according to the more accurate dialogue situation.

Further, according to the dialogue device 1 of the present embodiment, the response unit 15 adjusts the timing of the response based on the dialogue situation. This makes it possible to provide more human-like interactive answers that are not mechanical.

Further, according to the dialogue device 1 of the present embodiment, the response unit 15 includes a filler in the response based on the dialogue situation. This makes it possible to provide more human-like interactive answers that are not mechanical.

Further, according to the dialogue device 1 of the present embodiment, the answering unit 15 gives an answer based on the name recognition of each of the plurality of words. As a result, it is possible to provide a more human-like interactive answer that is close to human thinking.

Further, according to the dialogue device 1 of the present embodiment, the answering unit 15 gives an answer based on the possibility that the user of each of the plurality of words answers. As a result, the user can be annoyed or surprised, and an interactive answer that enhances the game can be given.

Further, according to the dialogue device 1 of the present embodiment, the answering unit 15 gives an answer based on the values associated with each of the plurality of words in advance. As a result, the answer can be adjusted in advance, and a more flexible answer can be given.

As described above, according to the dialogue device 1 of the present embodiment, the system utterance (word) can be selected according to the user utterance (word) and the progress of the game, and the response timing and the difficulty level are conscious. You can choose the answer. As a result, it is possible to enhance the game characteristics of an interactive game such as a Yamate line game, an associative game, or a shiritori game, and to realize an interactive dialogue. Further, the dialogue device 1 of the present embodiment can be applied not only to the Yamate line game, the associative game and the shiritori game, but also to various interactive games.

Note that the block diagram used in the explanation of the above embodiment shows a block for each functional unit. These functional blocks (components) are realized by any combination of at least one of hardware and software. Further, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized by using one device that is physically or logically connected, or directly or indirectly (for example, by two or more devices that are physically or logically separated). , Wired, wireless, etc.) and may be realized using these plurality of devices. The functional block may be realized by combining the software with the one device or the plurality of devices.

Functions include judgment, decision, judgment, calculation, calculation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, solution, selection, selection, establishment, comparison, assumption, expectation, and assumption. There are broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, assigning, etc., but only these. I can't. For example, a functional block (constituent unit) that functions transmission is called a transmitting unit or a transmitter. As described above, the method of realizing each of them is not particularly limited.

For example, the dialogue device 1 in the embodiment of the present disclosure may function as a computer that processes the dialogue method of the present disclosure. FIG. 3 is a diagram showing an example of the hardware configuration of the dialogue device 1 according to the embodiment of the present disclosure. The above-mentioned dialogue device 1 may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like.

In the following explanation, the word "device" can be read as a circuit, device, unit, etc. The hardware configuration of the dialogue device 1 may be configured to include one or more of the devices shown in the figure, or may be configured not to include some of the devices.

For each function in the dialogue device 1, the processor 1001 performs an operation by loading predetermined software (program) on hardware such as the processor 1001 and the memory 1002, and controls communication by the communication device 1004, or the memory 1002. And by controlling at least one of reading and writing of data in the storage 1003.

The processor 1001 operates, for example, an operating system to control the entire computer. The processor 1001 may be configured by a central processing unit (CPU: Central Processing Unit) including an interface with peripheral devices, a control device, an arithmetic unit, a register, and the like. For example, the acquisition unit 10, the answer set generation unit 11, the correctness determination unit 13, the answer set update unit 14, the answer unit 15, and the like may be realized by the processor 1001.

Further, the processor 1001 reads a program (program code), a software module, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002, and executes various processes according to these. As the program, a program that causes a computer to execute at least a part of the operations described in the above-described embodiment is used. For example, the acquisition unit 10, the answer set generation unit 11, the correctness determination unit 13, the answer set update unit 14, and the answer unit 15 may be stored in the memory 1002 and realized by a control program that operates in the processor 1001 or other. The functional block may be realized in the same manner. Although it has been described that the various processes described above are executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. Processor 1001 may be implemented by one or more chips. The program may be transmitted from the network via a telecommunication line.

The memory 1002 is a computer-readable recording medium, and is composed of at least one such as a ROM (Read Only Memory), an EPROM (Erasable Programmable ROM), an EPROM (Electrically Erasable Programmable ROM), and a RAM (Random Access Memory). May be done. The memory 1002 may be referred to as a register, a cache, a main memory (main storage device), or the like. The memory 1002 can store a program (program code), a software module, or the like that can be executed to implement the wireless communication method according to the embodiment of the present disclosure.

The storage 1003 is a computer-readable recording medium, and is, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (for example, a compact disk, a digital versatile disk, or a Blu-ray). It may consist of at least one (registered trademark) disk), smart card, flash memory (eg, card, stick, key drive), floppy (registered trademark) disk, magnetic strip, and the like. The storage 1003 may be referred to as an auxiliary storage device. The storage medium described above may be, for example, a database, server or other suitable medium containing at least one of memory 1002 and storage 1003.

The communication device 1004 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as, for example, a network device, a network controller, a network card, a communication module, or the like. The communication device 1004 includes, for example, a high frequency switch, a duplexer, a filter, a frequency synthesizer, and the like in order to realize at least one of frequency division duplex (FDD: Frequency Division Duplex) and time division duplex (TDD: Time Division Duplex). It may be composed of. For example, the acquisition unit 10 and the response unit 15 described above may be realized by the communication device 1004.

The input device 1005 is an input device (for example, a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives an input from the outside. The output device 1006 is an output device (for example, a display, a speaker, an LED lamp, etc.) that outputs to the outside. The input device 1005 and the output device 1006 may have an integrated configuration (for example, a touch panel).

Further, each device such as the processor 1001 and the memory 1002 is connected by the bus 1007 for communicating information. The bus 1007 may be configured by using a single bus, or may be configured by using a different bus for each device.

Further, the dialogue device 1 includes hardware such as a microprocessor, a digital signal processor (DSP: Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array). It may be configured, and the hardware may realize a part or all of each functional block. For example, processor 1001 may be implemented using at least one of these hardware.

The notification of information is not limited to the mode / embodiment described in the present disclosure, and may be performed by using another method.

Each aspect / embodiment described in the present disclosure includes LTE (Long Term Evolution), LTE-A (LTE-Advanced), SUPER 3G, IMT-Advanced, 4G (4th generation mobile communication system), and 5G (5th generation mobile communication). system), FRA (Future Radio Access), NR (new Radio), W-CDMA (registered trademark), GSM (registered trademark), CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi (registered trademark)) )), LTE 802.16 (WiMAX®), IEEE 802.20, UWB (Ultra-WideBand), Bluetooth®, and other systems that utilize suitable systems and have been extended based on these. It may be applied to at least one of the next generation systems. Further, a plurality of systems may be applied in combination (for example, a combination of at least one of LTE and LTE-A and 5G).

The order of the processing procedures, sequences, flowcharts, etc. of each aspect / embodiment described in the present disclosure may be changed as long as there is no contradiction. For example, the methods described in the present disclosure present elements of various steps using exemplary order, and are not limited to the particular order presented.

The input / output information and the like may be saved in a specific location (for example, memory), or may be managed using a management table. Input / output information and the like can be overwritten, updated, or added. The output information and the like may be deleted. The input information or the like may be transmitted to another device.

The determination may be made by a value represented by 1 bit (0 or 1), by a boolean value (Boolean: true or false), or by comparing numerical values (for example, a predetermined value). It may be done by comparison with the value).

Each aspect / embodiment described in the present disclosure may be used alone, in combination, or switched with execution. Further, the notification of predetermined information (for example, the notification of "being X") is not limited to the explicit one, but is performed implicitly (for example, the notification of the predetermined information is not performed). May be good.

Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described in the present disclosure. The present disclosure may be implemented as an amendment or modification without departing from the purpose and scope of the present disclosure, which is determined by the description of the scope of claims. Therefore, the description of this disclosure is for purposes of illustration only and does not have any restrictive meaning to this disclosure.

Software is an instruction, instruction set, code, code segment, program code, program, subprogram, software module, whether called software, firmware, middleware, microcode, hardware description language, or another name. , Applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, etc. should be broadly interpreted to mean.

In addition, software, instructions, information, etc. may be transmitted and received via a transmission medium. For example, a website that uses at least one of wired technology (coaxial cable, fiber optic cable, twist pair, digital subscriber line (DSL: Digital Subscriber Line), etc.) and wireless technology (infrared, microwave, etc.) When transmitted from a server, or other remote source, at least one of these wired and wireless technologies is included within the definition of transmission medium.

The information, signals, etc. described in this disclosure may be represented using any of a variety of different techniques. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be voltage, current, electromagnetic waves, magnetic fields or magnetic particles, light fields or photons, or any of these. It may be represented by a combination of.

Note that the terms explained in the present disclosure and the terms necessary for understanding the present disclosure may be replaced with terms having the same or similar meanings.

The terms "system" and "network" used in this disclosure are used interchangeably.

In addition, the information, parameters, etc. described in the present disclosure may be expressed using absolute values, relative values from predetermined values, or using other corresponding information. It may be represented. For example, the radio resource may be one indicated by an index.

The names used for the above parameters are not limited in any respect. Further, mathematical formulas and the like using these parameters may differ from those explicitly disclosed in this disclosure.

The terms "determining" and "determining" used in this disclosure may include a wide variety of actions. "Judgment" and "decision" are, for example, judgment (judging), calculation (calculating), calculation (computing), processing (processing), derivation (deriving), investigation (investigating), search (looking up, search, inquiry). (For example, searching in a table, database or another data structure), confirming (ascertaining) may be regarded as "judgment" or "decision". In addition, "judgment" and "decision" are receiving (for example, receiving information), transmitting (for example, transmitting information), input (input), output (output), and access. (Accessing) (for example, accessing data in memory) may be regarded as "judgment" or "decision". In addition, "judgment" and "decision" mean that "resolving", "selecting", "choosing", "establishing", "comparing", etc. are regarded as "judgment" and "decision". Can include. That is, "judgment" and "decision" may include that some action is regarded as "judgment" and "decision". Further, "judgment (decision)" may be read as "assuming", "expecting", "considering" and the like.

The terms "connected", "coupled", or any variation thereof, mean any direct or indirect connection or connection between two or more elements, and each other. It can include the presence of one or more intermediate elements between two "connected" or "combined" elements. The connection or connection between the elements may be physical, logical, or a combination thereof. For example, "connection" may be read as "access". As used in the present disclosure, the two elements use at least one of one or more wires, cables and printed electrical connections, and, as some non-limiting and non-comprehensive examples, the radio frequency domain. Can be considered to be "connected" or "coupled" to each other using electromagnetic energies having wavelengths in the microwave and light (both visible and invisible) regions.

The phrase "based on" as used in this disclosure does not mean "based on" unless otherwise stated. In other words, the statement "based on" means both "based only" and "at least based on".

Any reference to elements using designations such as "first", "second", etc. as used in this disclosure does not generally limit the quantity or order of those elements. These designations can be used in the present disclosure as a convenient way to distinguish between two or more elements. Thus, references to the first and second elements do not mean that only two elements can be adopted, or that the first element must somehow precede the second element.

The "means" in the configuration of each of the above devices may be replaced with "part", "circuit", "device" and the like.

When "include", "including" and variations thereof are used in the present disclosure, these terms are as comprehensive as the term "comprising". Is intended. Furthermore, the term "or" used in the present disclosure is intended not to be an exclusive OR.

In the present disclosure, if articles are added by translation, for example a, an and the in English, the disclosure may include that the nouns following these articles are in the plural.

In the present disclosure, the term "A and B are different" may mean "A and B are different from each other". The term may mean that "A and B are different from C". Terms such as "separate" and "combined" may be interpreted in the same way as "different".

1 ... Dialogue device, 10 ... Acquisition unit, 11 ... Answer set generation unit, 12 ... Answer set storage unit, 13 ... Correctness judgment unit, 14 ... Answer set update unit, 15 ... Answer unit.

Claims

It is a dialogue device that alternately answers words according to a predetermined theme with the user.
An answering unit that answers based on a plurality of words included in an answer set consisting of words that are candidates for answering when the dialogue device answers.
A dialogue device comprising.
The answering unit determines the dialogue situation based on the plurality of words, and makes a reply based on the determined dialogue situation.
The dialogue device according to claim 1.
The answer unit determines the dialogue status based on the number of words included in the answer set.
The dialogue device according to claim 2.
The answering unit further determines the dialogue situation based on the theme.
The dialogue device according to claim 2 or 3.
The answering unit adjusts the timing of answering based on the dialogue situation.
The dialogue device according to any one of claims 2 to 4.
The answer section includes a filler in the answer based on the dialogue situation.
The dialogue device according to any one of claims 2 to 5.
The answering unit responds based on the name recognition of each of the plurality of words.
The dialogue device according to any one of claims 1 to 6.
The answering unit gives an answer based on the possibility that the user of each of the plurality of words answers.
The dialogue device according to any one of claims 1 to 7.
The answering unit gives a reply based on a value associated with each of the plurality of words in advance.
The dialogue device according to any one of claims 1 to 8.