JP2021082125A - Dialogue device - Google Patents

Abstract

To promote user's use regarding a dialogue device.SOLUTION: A dialogue device 10 includes: a wrong answer determination unit 15 for determining a wrong answer term whose reading is similar to an input term input from a user terminal 50 or a related term thereof; a correct answer determination unit 16 for determining a correct answer term whose meaning is similar to that of the wrong answer term; a question sentence generation unit 17 for generating a question sentence whose answer is the correct answer term; and an output unit 18 for outputting the question sentence.SELECTED DRAWING: Figure 1

Description

The present invention relates to a dialogue device.

A dialogue device that responds to a text input or an utterance from a user is known (see, for example, Patent Document 1). In such a dialogue device, it is possible to provide an answer to a question sentence from a user according to a scenario prepared in advance.

Japanese Unexamined Patent Publication No. 2019-133418

Here, it is difficult to appropriately answer a question for which a scenario is not prepared by the dialogue device as described above. As a result, the user may feel that there are few variations in dialogue and it is not easy to use, and it may not be possible to sufficiently promote the use of the dialogue device.

The present invention has been made in view of the above circumstances, and an object of the present invention is to provide a dialogue device capable of promoting the use of a user.

The dialogue device according to one aspect of the present invention means an erroneous answer determination unit that determines an erroneous answer term whose reading is similar to the term input by the user or a term related to the term, and the erroneous answer term. It is provided with a correct answer determination unit that determines similar correct answer terms, a question sentence generation unit that generates a question sentence that uses the correct answer term as an answer, and an output unit that outputs a question sentence.

In the dialogue device according to one aspect of the present invention, when some term is input by the user, a question sentence based on the input term is generated and output. As a result, even if it is not possible to properly answer the question from the user, for example, some question related to the question content (term input from the user) from the user is output from the dialogue device. , The interactive dialogue between the user and the dialogue device will be continued. As a result, the user's feeling of familiarity with the dialogue device can be improved, and the usability of the dialogue device can be improved. Further, in the dialogue device, specifically, an incorrect answer term having a reading similar to the input term is determined, a correct answer term having a similar meaning to the incorrect answer term is determined, and a question sentence in which the correct answer term is the answer is generated. It is output. Since the wrong answer term has a similar reading to the input term and a similar meaning to the correct answer term of the question, the user's answer to the question sentence can be effectively guided to the wrong answer term. As a result, it is possible to improve the gameplay in a series of dialogues such as inputting terms from the user, asking the user a question, and answering the user, improving the familiarity of the user with the dialogue device, and promoting the use of the user. Can be done.

According to the present invention, it is possible to promote the user's use of the dialogue device.

It is a block diagram which shows the functional structure of the dialogue apparatus included in the dialogue system which concerns on this embodiment. It is a figure explaining the input term, the wrong answer term, and the correct answer term. It is a flowchart which shows the process performed by a dialogue device. It is a figure which shows the hardware configuration of the dialogue device.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the description of the drawings, the same reference numerals are used for the same or equivalent elements, and duplicate description is omitted.

FIG. 1 is a block diagram showing a functional configuration of a dialogue device 10 included in the dialogue system 1 according to the present embodiment. The dialogue system 1 shown in FIG. 1 is a system for providing an answer to an inquiry from a user terminal 50 (user). The user terminal 50 may be a communication terminal, for example, a smartphone, a tablet terminal, a PC, or the like. Hereinafter, the user terminal 50 will be described as a terminal capable of making a call. In the dialogue system 1, when the dialogue device 10 receives an inquiry from the user terminal 50, the dialogue between the user terminal 50 and the dialogue device 10 is started. In the dialogue system 1, for example, when the dialogue device 10 can answer an inquiry from the user terminal 50, the dialogue device 10 provides an answer to the user terminal 50 and interacts with the inquiry from the user terminal 50. If the device 10 cannot answer, the game mode is switched to a predetermined game mode, and the dialogue device 10 outputs a question to the user terminal. The question here is not a question for providing an answer to an inquiry from the user terminal 50, but a question related to an interactive game (details will be described later).

The dialogue device 10 is a device that provides an answer to an inquiry of the user terminal 50 by interacting with the user terminal 50. Further, the dialogue device 10 is a device that provides an interactive game to the user terminal 50. That is, the dialogue device 10 is configured to be able to switch between a normal mode in which the answer is provided to the user terminal 50 and a game mode in which the dialogue side game is provided to the user terminal 50. The interactive game is a game provided to the user terminal 50 through a dialogue between the dialogue device 10 and the user terminal 50, for example, I.D. Encourage the dialogue device 10 to repeatedly speak a term (eg, "chandelier") on the user terminal 50, II. The user repeatedly speaks a term, III. The dialogue device 10 asks the user terminal 50 a question (for example, "Why did you die after eating the poisoned apple given by the queen?"), IV. It is a game that is executed in the flow of the user answering a question. In the case of the above example, the user who repeatedly spoke the chandelier should answer "Snow White" to the question "Why did you die after eating the poisoned apple given by the Queen?" It is conceivable that the answer will be "Cinderella" due to the influence of repeated utterances. In the interactive game, the game quality is improved by inducing such an incorrect answer. The dialogue device 10 is a device using a so-called chatbot. A chatbot is a term that combines chat and a bot, and is an automatic dialogue program that provides information to a user while interacting with the user using, for example, artificial intelligence.

As shown in FIG. 1, the dialogue device 10 includes an input unit 11, an answer determination unit 12, an information DB 13, a score derivation unit 14, an incorrect answer determination unit 15, a correct answer determination unit 16, and a question sentence generation. A unit 17 and an output unit 18 are provided.

The input unit 11 receives an incoming call from the user terminal 50 and acquires an inquiry from the user terminal 50. The inquiry is acquired according to, for example, the result of voice recognition for the utterance of the user terminal 50. It should be noted that voice recognition is performed by using a conventionally well-known technique. The voice recognition may be performed by the dialogue device 10, or may be performed by an external device (not shown) and the result may be acquired by the dialogue device 10. The input unit 11 outputs the inquiry acquired from the user terminal 50 to the answer determination unit 12.

The answer determination unit 12 receives an input of an inquiry from the input unit 11 and determines an answer to the inquiry. The answer determination unit 12 refers to the scenario stored in the information DB 13 and determines whether or not it is possible to answer the inquiry based on the scenario. When the answer to the inquiry is specified in the scenario, the answer determination unit 12 determines the answer to the inquiry based on the scenario. In this case, the answer determination unit 12 outputs the answer to the output unit 18. On the other hand, when the answer determination unit 12 does not specify the answer to the inquiry in the scenario and cannot answer, the answer determination unit 12 outputs the inquiry of the user terminal 50 to the wrong answer determination unit 15.

The information DB 13 is a database that stores various information used for processing of the dialogue device 10. The information DB 13 stores a scenario that defines an answer to an inquiry. In addition, the information DB 13 stores a word dictionary that defines information related to the reading and meaning of a plurality of words. The dialogue device 10 does not have to have the information DB 13. In this case, the dialogue device 10 acquires various information stored in the above-mentioned information DB 13 from an external database.

The erroneous answer determination unit 15 receives an input of an inquiry from the answer determination unit 12, and based on the inquiry, identifies a term input from the user terminal 50 or an input term that is a term related to the term, and uses the input term as an input term. Determine incorrect terms with similar readings. For example, as shown in FIG. 2, an example of an incorrect answer term when the input term is "chandelier" is "Cinderella". The term input from the user terminal 50 is the term itself included in the inquiry. The terms related to the terms input from the user terminal 50 include, for example, a term in which a term included in the query is combined with another term, a term in a superordinate concept or a subordinate concept of the term included in the query, and a term included in the query. These are terms that are closely related to.

The wrong answer determination unit 15 captures, for example, a sentence related to an inquiry with a regular expression. Alternatively, the wrong answer determination unit 15 divides the sentence related to the inquiry into morphemes and characters by a model constructed based on machine learning (for example, a method such as CRF (conditional random field)), and then specifies the input term. I do. Alternatively, the wrong answer determination unit 15 may specify the input term by extracting one term from the sentence that exactly matches the word in the wrong answer candidate dictionary. After that, when estimating the reading of the input term, the wrong answer determination unit 15 may use the reading as the reading of the input term if there is a reading in the wrong answer candidate dictionary. If there is no reading in the wrong answer candidate dictionary, the wrong answer determination unit 15 may estimate the reading of the input term. The wrong answer determination unit 15 decomposes the input term into subwords by performing morphological analysis, for example, and estimates the reading of the input term based on the reading of the subword. For example, the wrong answer determination unit 15 converts the input term into Hepburn romanization, refers to the word dictionary stored in the information DB 13, and extracts a plurality of wrong answer term candidates having similar readings to the input term. The wrong answer determination unit 15 may estimate a term that is not in the word dictionary as a wrong answer term candidate. The erroneous answer determination unit 15 outputs the extracted or estimated erroneous answer term candidate to the score deriving unit 14. Then, the erroneous answer determination unit 15 acquires the score of each erroneous answer term candidate (score regarding validity as an erroneous answer term) from the score deriving unit 14, and a plurality of erroneous answers based on the score derived by the score deriving unit 14. Determine the wrong answer term from the term candidates. The wrong answer determination unit 15 determines, for example, the wrong answer term candidate having the lowest score as the wrong answer term. The erroneous answer determination unit 15 outputs the determined erroneous answer term to the correct answer determination unit 16. Further, the wrong answer determination unit 15 outputs the specified input term to the score derivation unit 14 and the output unit 18.

The correct answer determination unit 16 receives an input of an incorrect answer term from the incorrect answer determination unit 15 and determines a correct answer term having a meaning similar to the incorrect answer term. For example, as shown in FIG. 2, an example of the correct answer term when the incorrect answer term is “Cinderella” is “Snow White”. The correct answer determination unit 16 refers to the word dictionary stored in the information DB 13 and extracts a plurality of correct answer term candidates that are considered to have similar meanings to the incorrect answer terms. The correct answer determination unit 16 may estimate a term that is not in the word dictionary as a correct answer term candidate. The correct answer determination unit 16 outputs the extracted or estimated correct answer term candidates to the score derivation unit 14. Then, the correct answer determination unit 16 acquires the score of each correct answer term candidate (score regarding validity as a correct answer term) from the score derivation unit 14, and correct answers from a plurality of correct answer term candidates based on the score derived by the score derivation unit 14. Determine terms. The correct answer determination unit 16 determines, for example, the correct answer term candidate having the lowest score as the correct answer term. The correct answer determination unit 16 outputs the determined correct answer term to the question sentence generation unit 17.

The score derivation unit 14 derives a score regarding the validity as an erroneous answer term for a plurality of erroneous answer term candidates input from the erroneous answer determination unit 15. The score deriving unit 14 outputs the score of each derived erroneous answer term candidate to the erroneous answer determining unit 15. The score deriving unit 14 derives a score regarding the validity of each of the plurality of erroneous answer term candidates as an erroneous term by calculating the sound distance from the input term, for example. The sonic distance indicates the closeness (similarity) of reading. The score derivation unit 14 determines, for example, the sonic distance between consonants excluding n from the input term and the sonic distance between vowels, n, and long vowels from the input term for each of a plurality of incorrect answer term candidates. Obtained by Stein distance. The score derivation unit 14 derives the score of the erroneous term candidate as the sonic distance between the input term and the erroneous term candidate, for example, the sum of the above two types of sonic distances. Therefore, the closer the sound distance, the lower the score. The score derivation unit 14 may derive the score of the erroneous term candidate by deriving the sonic distance between the input term and the erroneous term candidate without separating the consonant and the vowel.

For example, as shown in FIG. 2, a case where the input term is "chandelier" and the wrong answer term candidate is "Cinderella" will be described as an example. In this case, the sonic distance between consonants excluding n is derived by comparing "shdr" (chandelier) and "shdrr" (cinderella). Further, the sonic distance between the vowel, n, and long vowel is derived by comparing "aneia" (chandelier) and "ineea" (cinderella).

The score derivation unit 14 obtains the sonic distance between consonants excluding n by biasing it based on, for example, an IPA consonant table. Specifically, for example, the sonic distance between p and b is close, and the sonic distance between ph and h is long. Further, the score deriving unit 14 obtains the sonic distance between vowels, n, and long vowels by biasing them based on, for example, a basic vowel table. Specifically, for example, the sonic distance between i and e is close, and the sonic distance between a and u is long. For long vowels, the score deriving unit 14 is set to, for example, the vowel distance of one vowel before. The score deriving unit 14 may derive the score of the erroneous answer term by comparing the input term and the voice waveform of the erroneous answer term candidate.

The score derivation unit 14 derives a score regarding the validity as a correct answer term for a plurality of correct answer term candidates input from the correct answer determination unit 16. The score derivation unit 14 outputs the score of each derived correct answer term candidate to the correct answer determination unit 16. The score derivation unit 14 derives a score regarding the validity of each of the plurality of correct answer term candidates as a correct answer term by calculating the semantic distance from the incorrect answer term input from the incorrect answer determination unit 15, for example. Semantic distance indicates the closeness (similarity) of meaning. The score derivation unit 14 derives the semantic distance of each correct answer term candidate with respect to the incorrect answer term based on, for example, the cosine similarity based on the word vector and the tf-idf value, and derives the score of each correct answer term candidate. Therefore, the closer the semantic distance, the lower the score.

The score derivation unit 14 calculates the popularity (widely used degree) of the term to obtain a score regarding the validity of each of the plurality of incorrect answer term candidates as an incorrect answer term, and each of the plurality of correct answer term candidates. You may derive a score regarding the validity of the term as a correct answer. The degree of popularity of a term can be calculated, for example, by the frequency of appearance in a corpus (set of sentences). For example, the score deriving unit 14 lowers the score as the wrong answer term candidate (correct answer term candidate) has a higher degree of popularity so that the wrong answer term (correct answer term) can be easily determined. The score derivation unit 14 derives the scores of a plurality of incorrect answer term candidates and the scores of a plurality of correct answer term candidates based on, for example, the following equation (1). α and β are adjustable parameters.
Score = α ・ log (sound distance) + β ・ log (semantic distance) -γlog (term popularity) ・ ・ ・ (1)

The score derivation unit 14 makes α in the above equation (1) sufficiently larger than β when deriving the score of the wrong answer term candidate, and when deriving the score of the correct answer term candidate, the above ( The hyperparameters in Eq. 1) are adjusted appropriately, such as making β in Eq. 1) sufficiently larger than α, and the scores of wrong answer term candidates and correct answer term candidates are derived. When the sum or product of the score of the correct answer term determined by the correct answer determination unit 16 and the score of the incorrect answer term determined by the incorrect answer determination unit 15 uses the correct answer term and the incorrect answer term. It may be a game score. The game property score is derived, for example, based on the following equation (2). X and Y are adjustable parameters.
Game score = X, correct term score + Y, incorrect term score ... (2)

For example, the lower the game quality score, the higher the game performance. That is, the closer the sonic distance of the incorrect answer term to the input term, the closer the semantic distance of the correct answer term to the incorrect answer term, and the higher the popularity of the incorrect answer term and the correct answer term, the higher the game quality.

The question sentence generation unit 17 generates a question sentence in which the correct answer term input from the correct answer determination unit 16 is the answer. The question sentence generation unit 17 extracts, for example, a sentence related to a correct answer term from the Internet by a search function, and generates a question sentence based on the sentence. The question sentence generation unit 17 extracts sentences related to correct answer terms from, for example, encyclopedias, dictionaries, example collections, etc. on the Internet. Now, suppose that the correct term is "Snow White" as shown in FIG. In this case, for example, suppose that the sentence "... but it was too late, and Snow White was breathing out of the poisoned apple given by the Queen ..." was extracted from the collection of examples. The question sentence generation unit 17 removes the subject from such a sentence or adds "What?" To the end of the sentence so that it becomes a question sentence. Generate the question "What was it extinct?" The question sentence generation unit 17 outputs the generated question sentence to the output unit 18.

The output unit 18 outputs information in response to the user's utterance. Specifically, when the answer determination unit 12 determines the answer to the user's inquiry, the output unit 18 outputs the answer to the user terminal 50 by voice or the like. Further, when the question sentence in the game mode is generated by the question sentence generation unit 17, the output unit 18 outputs the generated question sentence to the user terminal 50 by voice or the like. Further, in the game mode, the output unit 18 first outputs a repetitive utterance guidance sentence for repeatedly (for example, 10 times) speaking the input term specified by the wrong answer determination unit 15 to the user terminal 50. For example, the above-mentioned question sentence may be output after the input term is repeatedly spoken by the user.

The flow of the game mode in this case is as follows. First, the output unit 18 voice-outputs a repeated utterance guidance sentence "Please say chandelier 10 times" to the user terminal 50 in order to make the user repeatedly speak the input term ("chandelier"). On the other hand, the user of the user terminal 50 utters the "chandelier" 10 times. After that, the output unit 18 voice-outputs a question sentence, "Why did you die after eating the poisoned apple given by the queen?" The correct answer (correct answer term) is "Snow White", but users who repeatedly say "chandelier" in the previous stage are likely to answer the wrong answer (wrong answer term) "Cinderella". In this way, by repeating the input terms in the previous stage, the game quality can be improved.

Next, the flow of processing performed by the dialogue device 10 will be described with reference to the flowchart of FIG. As shown in FIG. 3, the dialogue device 10 first receives an utterance from the user terminal 50 (step S1). The dialogue device 10 acquires a user inquiry according to, for example, the result of voice recognition for an utterance.

Next, the dialogue device 10 determines whether or not it is possible to answer the inquiry (step S2). Specifically, the dialogue device 10 refers to a scenario stored in the information DB 13 and determines whether or not it is possible to answer an inquiry based on the scenario.

If the inquiry can be answered in step S2 (there is an answer in the scenario), the dialogue device 10 identifies the answer to the inquiry based on the scenario and outputs the answer to the user terminal 50 (step S3). ..

On the other hand, in step S2, when it is not possible to answer the inquiry (there is no answer to the scenario), the dialogue device 10 provides the user terminal 50 with the interactive game from the normal mode of providing the answer to the user terminal 50. Switch to the game mode and process the game mode. Specifically, the dialogue device 10 first identifies an input term from the user terminal 50 based on an inquiry, and determines an erroneous answer term from the input term (step S4). The dialogue device 10 extracts a plurality of incorrect answer term candidates whose readings are similar to those of the input term, derives a score regarding the validity of each incorrect answer term candidate as an incorrect answer term, and derives a score regarding the validity of the incorrect answer term based on the score. To determine.

Subsequently, the dialogue device 10 determines the correct answer term from the incorrect answer term (step S5). The dialogue device 10 extracts a plurality of correct answer term candidates having similar meanings to the incorrect answer terms, derives a score regarding the validity of each correct answer term candidate as a correct answer term, and determines the correct answer term based on the score. ..

Subsequently, the dialogue device 10 generates a question sentence in which the correct answer term is the answer (step S6). The dialogue device 10 extracts a document related to a correct answer term from the Internet by, for example, a search function, and generates a question sentence based on the sentence. Then, the dialogue device 10 outputs the generated question sentence to the user terminal 50 by voice or the like. In the game mode, the dialogue device 10 first outputs a repetitive utterance guidance sentence for repeatedly (for example, 10 times) speaking the input term to the user terminal 50, and the input term is repeatedly spoken by the user, for example. After that, the above-mentioned question sentence may be output.

Next, the operation and effect of the dialogue device 10 according to the present embodiment will be described.

The dialogue device 10 according to the present embodiment has an erroneous answer determination unit 15 for determining an erroneous answer term whose reading is similar to a term input from the user terminal 50 or an input term which is a term related to the term, and an erroneous answer term. A correct answer determination unit 16 for determining correct answer terms having similar meanings to the above, a question sentence generation unit 17 for generating a question sentence for which the correct answer term is an answer, and an output unit 18 for outputting a question sentence are provided.

In such a dialogue device 10, when some term is input from the user terminal 50, a question sentence based on the input term is generated and output. As a result, even if it is not possible to properly answer the question from the user terminal 50, for example, some question related to the question content (terms input from the user terminal 50) from the user terminal 50. Is output from the dialogue device 10, and the interactive dialogue between the user terminal 50 and the dialogue device 10 is continued. As a result, the user's feeling of familiarity with the dialogue device 10 can be improved, and the usability of the dialogue device 10 can be improved. Further, in the dialogue device 10, specifically, an incorrect answer term having a similar reading to the input term is determined, a correct answer term having a similar meaning to the incorrect answer term is determined, and a question sentence in which the correct answer term is the answer is generated. Is output. Since the wrong answer term has a similar reading to the input term and a similar meaning to the correct answer term of the question, the user's answer to the question sentence can be effectively guided to the wrong answer term. As a result, it is possible to improve the gameplay in a series of dialogues such as inputting terms from the user, asking a question to the user, and answering the user, improving the familiarity of the user with the dialogue device 10 and promoting the use of the user. be able to.

The dialogue device 10 further includes a score deriving unit 14 for deriving a score regarding validity as an incorrect answer term for a plurality of incorrect answer term candidates and deriving a score regarding validity as a correct answer term for a plurality of correct answer term candidates. , The wrong answer determination unit 15 determines an incorrect answer term from a plurality of incorrect answer term candidates based on the score derived by the score derivation unit 14, and the correct answer determination unit 16 determines a plurality of incorrect answer terms based on the score derived by the score derivation unit 14. Determine the correct answer term from the correct answer term candidates. In this way, by determining the incorrect answer term and the correct answer term based on the scores of the plurality of candidates, it is possible to select an appropriate incorrect answer term and the correct answer term based on a certain criterion.

The score deriving unit 14 derives a score regarding the validity of each of the plurality of erroneous answer term candidates as an erroneous term by calculating the sonic distance from the input term. By considering whether or not the sounds are similar (the sound distance is small), it is possible to appropriately derive the wrong answer terms having similar readings.

The score deriving unit 14 derives a score regarding the validity of each of the plurality of correct answer term candidates as a correct answer candidate by calculating the semantic distance from the incorrect answer term. By considering whether or not the semantic distance is small, the correct answer term having a similar meaning to the incorrect answer term can be appropriately derived.

By calculating the popularity of the term, the score deriving unit 14 relates to a score regarding the validity of each of the plurality of incorrect answer term candidates as an incorrect answer term, and regarding the validity of each of the plurality of correct answer term candidates as a correct answer candidate. Derive the score. As a result, for example, popular terms can be easily selected as incorrect or correct answers, and user satisfaction can be improved. Further, since the popular term is regarded as an incorrect answer term, the user's answer to the question sentence can be effectively guided to the incorrect answer term, and the game property can be deducted.

The question sentence generation unit 17 extracts a sentence related to the correct answer term by the search function, and generates a question sentence based on the sentence. As a result, it is possible to generate a question sentence in which the correct answer term is simply and appropriately answered.

The output unit 18 outputs a question sentence after outputting a repeated utterance guidance sentence for repeatedly speaking the input term. As a result, when the question sentence is output, it is possible to easily answer the wrong answer term.

Finally, the hardware configuration of the dialogue device 10 included in the dialogue system 1 will be described with reference to FIG. The above-mentioned dialogue device 10 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 description, the word "device" can be read as a circuit, a device, a unit, or the like. The hardware configuration of the dialogue device 10 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.

Each function in the dialogue device 10 is performed by loading predetermined software (program) on hardware such as the processor 1001 and the memory 1002, so that the processor 1001 performs an calculation, and communication by the communication device 1004, memory 1002, and storage 1003 are performed. It is realized by controlling the reading and / or writing of the data in.

Processor 1001 operates, for example, an operating system to control the entire computer. The processor 1001 may be composed of a central processing unit (CPU) including an interface with a peripheral device, a control device, an arithmetic unit, a register, and the like. For example, the control function of the erroneous answer determination unit 15 of the dialogue device 10 may be realized by the processor 1001.

Further, the processor 1001 reads a program (program code), a software module, and data from the storage 1003 and / or 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 control function of the erroneous answer determination unit 15 of the dialogue device 10 or the like may be realized by a control program stored in the memory 1002 and operated by the processor 1001, or may be realized in the same manner for other functional blocks. .. 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 mounted on 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 EEPROM (Erasable Programmable ROM), an EEPROM (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 carry out the wireless communication method according to the embodiment of the present invention.

The storage 1003 is a computer-readable recording medium, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, an optical magnetic disk (for example, a compact disk, a digital versatile disk, 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 memory 1002 and / or storage 1003.

The communication device 1004 is hardware (transmission / reception device) for performing communication between computers via a wired and / or 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 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 a bus 1007 for communicating information. Bus 1007 may be composed of a single bus, or may be composed of different buses between devices.

Further, the dialogue device 10 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 on at least one of these hardware.

Although the present embodiment has been described in detail above, it is clear to those skilled in the art that the present embodiment is not limited to the embodiment described in the present specification. This embodiment can be implemented as a modified or modified mode without departing from the spirit and scope of the present invention determined by the description of the claims. Therefore, the description of the present specification is for the purpose of exemplifying explanation, and does not have any restrictive meaning to the present embodiment.

Each aspect / embodiment described herein includes LTE (Long Term Evolution), LTE-A (LTE-Advanced), SUPER 3G, IMT-Advanced, 4G, 5G, FRA (Future Radio Access), W-CDMA. (Registered Trademarks), GSM (Registered Trademarks), CDMA2000, UMB (Ultra Mobile Broad-band), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, UWB (Ultra-Wide) Band), WiMAX®, and other systems that utilize suitable systems and / or extended next-generation systems based on them may be applied.

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

The input / output information and the like may be stored in a specific location (for example, memory) or may be managed by 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 specification 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.

Software, whether referred to as software, firmware, middleware, microcode, hardware description language, or by any other name, is an instruction, instruction set, code, code segment, program code, program, subprogram, software module. , Applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, features, etc. should be broadly interpreted.

Further, software, instructions, and the like may be transmitted and received via a transmission medium. For example, the software uses wired technology such as coaxial cable, fiber optic cable, twisted pair and digital subscriber line (DSL) and / or wireless technology such as infrared, wireless and microwave to websites, servers, or other When transmitted from a remote source, these wired and / or wireless technologies are included within the definition of transmission medium.

The information, signals, etc. described herein 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 are voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, light fields or photons, or any of these. It may be represented by a combination of.

The terms described herein and / or the terms necessary for understanding the present specification may be replaced with terms having the same or similar meanings.

Further, the information, parameters, etc. described in the present specification may be represented by an absolute value, a relative value from a predetermined value, or another corresponding information. ..

User terminals may be mobile communication terminals, subscriber stations, mobile units, subscriber units, wireless units, remote units, mobile devices, wireless devices, wireless communication devices, remote devices, mobile subscriber stations, access terminals, etc. It may also be referred to as a mobile device, wireless device, remote device, handset, user agent, mobile client, client, or some other suitable term.

The terms "determining" and "determining" as used herein may include a wide variety of actions. "Judgment", "decision" is, for example, calculating, computing, processing, deriving, investigating, looking up (eg, table, database or another). It can include searching in the data structure), and assuming that the confirmation (ascertaining) is regarded as "judgment" or "decision". Also, "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 the things such as solving, selecting, choosing, establishing, and comparing are regarded as "judgment" and "decision". Can include. That is, "judgment" and "decision" may include considering some action as "judgment" and "decision".

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

When the terms "first", "second", etc. are used herein, any reference to the elements does not generally limit the quantity or order of those elements. These designations can be used herein 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 there, or that the first element must somehow precede the second element.

As long as "include", "including", and variations thereof are used within the scope of the present specification or claims, these terms are similar to the term "comprising". Is intended to be inclusive. Furthermore, the term "or" as used herein or in the claims is intended not to be an exclusive OR.

In the present specification, a plurality of devices shall be included unless the device has only one device, which is apparently present in the context or technically.

In the whole of the present disclosure, if the context clearly does not indicate the singular, it shall include more than one.

10 ... Dialogue device, 14 ... Score derivation unit, 15 ... Wrong answer determination unit, 16 ... Correct answer determination unit, 17 ... Question sentence generation unit, 18 ... Output unit, 50 ... User terminal (user).

Claims (7)

An erroneous answer determination unit that determines an erroneous answer term whose reading is similar to the term input by the user or a term related to the term.
The correct answer determination unit that determines the correct answer terms that have similar meanings to the incorrect answer terms,
A question sentence generation unit that generates a question sentence that uses the correct answer term as an answer,
A dialogue device including an output unit that outputs the question text. It is further equipped with a score derivation unit that derives a score regarding the validity of a plurality of incorrect answer term candidates as an incorrect answer term and derives a score regarding the validity of a plurality of correct answer term candidates.
The erroneous answer determination unit determines an erroneous answer term from the plurality of erroneous answer term candidates based on the score derived by the score deriving unit.
The dialogue device according to claim 1, wherein the correct answer determination unit determines a correct answer term from the plurality of correct answer term candidates based on the score derived by the score derivation unit. The dialogue device according to claim 2, wherein the score deriving unit derives a score relating to the validity of each of the plurality of erroneous answer term candidates as the erroneous term by calculating the sound distance from the input term. .. The dialogue according to claim 2 or 3, wherein the score deriving unit derives a score regarding the validity of each of the plurality of correct answer term candidates as the correct answer term by calculating the semantic distance from the incorrect answer term. apparatus. By calculating the popularity of the term, the score deriving unit obtains a score regarding the validity of each of the plurality of incorrect answer term candidates as the incorrect answer term, and as the correct answer term of each of the plurality of correct answer term candidates. The dialogue device according to any one of claims 2 to 4, which derives a score relating to the validity of the above. The dialogue device according to any one of claims 1 to 5, wherein the question sentence generation unit extracts a sentence related to the correct answer term by a search function and generates the question sentence based on the sentence. The dialogue device according to claim 1, wherein the output unit outputs the question sentence after outputting the repeated utterance guidance sentence for repeatedly speaking the input term.

Images