JP2022025917A - Dialog device - Google Patents

Abstract

To provide a dialog device capable of making responses corresponding to the degree of growth of dialog with users.SOLUTION: A dialog device 100 includes: an utterance receiving unit 11 that accepts an utterance from a user; and a state determination unit 14 that calculates the degree of growth for dialog with the user based on a user's utterance history, and acquires a response sentence corresponding to the degree of growth for the utterance from the user. This configuration allows response sentences to be changed according to the degree of growth of dialogue with the user. Therefore, the more the dialog device 100 grows, the more the user can receive corresponding response sentences, and feeling that the dialogue is mechanical is reduced.SELECTED DRAWING: Figure 1

Description

The present invention relates to a dialogue device.

In recent years, dialogue agents have become widespread, and AIML (Artificial Intelligence Markup Language) is generally mentioned as an elemental technology for realizing dialogue agents. AIML is a descriptive language to which XML is applied, and a dialogue agent using AIML returns a response to an input utterance according to a pre-written rule. Further, as described in Patent Document 1, a technique for performing an accurate response according to the state of the subject is known.

JP-A-2015-14834

Since the dialogue agent using AIML returns a response according to the rules described in AIML in advance, the same response is given to everyone. Also, even if some patterns are prepared, the response pattern will be known when the user interacts with the dialogue agent for a while. Further, also in the technique described in Patent Document 1, it is conceivable that the response is patterned and the same response is repeated. Therefore, it is conceivable that the user feels that the response of the dialogue agent is mechanical and cannot be attached to it and does not continue to use it.

Therefore, in order to solve the above-mentioned problems, it is an object of the present invention to provide a dialogue device capable of responding to a dialogue with a user according to the degree of growth.

The dialogue device of the present invention has an utterance receiving unit that accepts utterances from the user, a growth degree calculation unit that calculates the growth degree for the dialogue with the user based on the utterance history of the user, and a speech from the user. A response sentence acquisition unit for acquiring a response sentence according to the degree of growth is provided.

According to this configuration, it is possible to acquire a response sentence according to the degree of growth, and the user can continue to use the dialogue device with attachment without feeling that it is a mechanical dialogue.

According to the present invention, the user can continue to use the dialogue device with attachment without feeling that it is a mechanical dialogue.

It is a functional block diagram of the dialogue system 1 including the dialogue apparatus 10 which concerns on embodiment of this disclosure. It is a figure which shows an example of the reception screen P presented to a user through a user terminal 20. It is a figure which shows the database of the analysis result stored in the 1st memory 10a. It is a schematic diagram which shows the process which performs the polarity inversion by morphological analysis of an utterance. It is a figure which shows the specific example of the database stored in the 2nd memory 10b. It is a schematic diagram which shows the operation of the user imitation unit 13. It is a schematic diagram which shows the operation of the state determination part 14. It is a figure which shows the specific example of the database stored in the 3rd memory 10c. It is a figure which shows the database of the information corresponding to the growth record. It is a flowchart which shows the operation (first half) of a dialogue device 10. It is a flowchart which shows the operation (the latter half) of the dialogue apparatus 10. It is a figure which shows an example of the hardware composition of the dialogue apparatus 100 which concerns on one Embodiment of this disclosure.

An embodiment of the present invention will be described with reference to the accompanying drawings. When possible, the same parts are designated by the same reference numerals, and duplicate description is omitted.

FIG. 1 is a functional block diagram of a dialogue system 1 including a dialogue device 10 according to an embodiment of the present disclosure. The dialogue device 10 is, for example, a server device configured to be able to communicate with the user terminal 20. The dialogue device 10 may be configured by one device or may be configured by a plurality of devices. The user terminal 20 is, for example, a computer operated by the user. In the present disclosure, as an example, the user and the user terminal 20 have a one-to-one correspondence, and the user terminal 20 is a smartphone owned by the user. However, the form of the user terminal 20 is not limited to a specific form. Other examples of the user terminal 20 include a tablet terminal, a wearable terminal, a personal computer, and the like. Further, the user terminal 20 may be shared by a plurality of users.

The dialogue device 100 has a function of providing a dialogue service by providing a response sentence in response to an utterance from the user terminal 20. The dialogue service is a service that accepts an utterance input by a user and presents a response corresponding to the user to the user. FIG. 2 is a diagram showing an example of a reception screen P presented to the user via the user terminal 20 in the above-mentioned dialogue service. The reception screen P is activated by, for example, selecting an icon corresponding to the dialogue service from a plurality of icons displayed on the display of the user terminal 20 by a user's touch operation or the like.

After that, the user inputs the utterance to the user terminal 20. For example, the user may input an utterance in a text data format by inputting text in the text input window T arranged at the bottom of the reception screen.

Alternatively, the user selects the voice input icon V located on the right side of the text input window to activate the voice reception function, and inputs the voice using the voice reception function to input the utterance in the voice data format. May be.

In FIG. 2, when the user inputs a message UD: "It's hot today", the dialogue service has a message M: "It's hot every day and I don't like it" based on the analysis result of the utterance and the past utterances. Is returning a response statement such as.

The user terminal 20 may have a function of providing a dialogue service to the user. Although the user terminal 20 has a known function for receiving the dialogue service from the dialogue device 100, the user terminal 20 may have the function of these dialogue services. For example, the user terminal 20 has a function of accepting a user's utterance, a function of analyzing the utterance by morphological analysis, a function of selecting an appropriate response sentence according to the analysis result of the utterance, and a function of presenting the response sentence to the user. May have.

Further, the user terminal 20 does not have to have all the above-mentioned functions. For example, some functions (for example, a function of analyzing a user's utterance) may be executed by a processing device different from the user terminal 20 configured to be able to communicate with the user terminal 20. In this case, for example, the user terminal 20 may transmit the user's utterance to the processing device and receive the result analyzed by the processing device from the processing device.

Further, the function of determining the response statement according to the analysis result does not necessarily have to be executed on the user terminal 20, and is a processing device different from the user terminal 20 configured to be able to communicate with the user terminal 20 (the processing device described above). It may be executed on). In this case, for example, the user terminal 20 may acquire a response sentence corresponding to the user's utterance from the processing device and present the response sentence to the user. The above functions may be performed by the same processing device, or may be different devices from each other. Further, the dialogue device 10 may function as a part or all of the above-mentioned processing device.

The dialogue system 1 in the present disclosure includes a dialogue device 10 and one or more user terminals 20. The dialogue device 10 includes an utterance receiving unit 11, an utterance decomposition unit 12, a user imitation unit 13, a state determination unit 14, a first memory 10a, a second memory 10b, a third memory 10c, and a fourth memory 10d. Hereinafter, each configuration will be described.

The utterance receiving unit 11 is a portion that receives an utterance composed of text information from the user terminal 20.

The utterance decomposition unit 12 is a part that morphologically analyzes the utterance received by the utterance receiving unit 11. The utterance decomposition unit 12 determines whether or not the analysis result (morpheme) obtained by the morphological analysis is stored in the first memory 10a. If the analysis result is not stored in the first memory 10a, the utterance decomposition unit 12 stores the analysis result in the first memory 10a.

Further, the utterance decomposition unit 12 has a polarity dictionary, and is a portion for determining the polarity of the received utterance by referring to the polarity dictionary. The utterance decomposition unit 12 stores the user's utterance and the polarity determination result (ratio of polarity in the utterance) in the second memory 10b. When the utterance decomposition unit 12 determines the polarity, the polarity is divided into three, positive (hereinafter, pos), negative (hereinafter, neg), and neutral (hereinafter, neu), and each polarity is 0 to 1. Calculate the value between.

Here, the processing of the utterance decomposition unit 12 will be described with reference to FIGS. 3 and 4. FIG. 3 is a diagram showing a database of analysis results stored in the first memory 10a. As shown in the figure, one record (one row) in the table corresponds to one morpheme. The analysis result is information treated as an utterance history, and in the example of FIG. 3, includes "morpheme", "part of speech", "number of times", and "time". The "morpheme" column is a morpheme (expression element) extracted by morphological analysis by the utterance decomposition unit 12. The morpheme to be extracted is not limited. For example, it may be only a noun, a verb, an adjective, or a plurality of parts of speech. The "part of speech" column is information representing the part of speech information of the "vocabulary". The "number of times" column is information indicating how many times the "morpheme" has been expressed in the user's utterances so far. "Time" is information that represents the time when the morpheme was most recently spoken. The number of times, Time, and growth record are used to present information to the user. For example, "The most common utterance of you is the train." "When do you talk a lot?" "Growth is 42.5." In addition, the degree of growth is recorded in order to obtain a growth curve from the numerical value and present it to the user.

FIG. 4 is a schematic diagram showing a process of performing morphological analysis of utterances and performing polarity reversal. As shown in the figure, the user's utterance "Today's train was very crowded and painful" is input to the user terminal 20 and transmitted to the dialogue device 10.

The utterance decomposition unit 12 morphologically analyzes this utterance (S11). In this disclosure, Mecab is used as a morphological analysis engine. The utterance decomposition unit 12 acquires "today," "train," "very," "crowded," and "spicy" as part of speech.

The utterance decomposition unit 12 determines the polarity with reference to the polarity dictionary (S12). The polarity dictionary is a dictionary showing the polarity of each morpheme. In this disclosure, it is a dictionary prepared in advance. The utterance decomposition unit 12 refers to the polarity dictionary for each part of speech analyzed by morphological analysis, determines the polarity of the part of speech, and obtains the ratio of the polarity of each part of speech in one utterance. In this disclosure, the ratios of the three polarities of positive, negative, and neutral are calculated.

The user imitation unit 13 is a part that generates information for returning a response that imitates the emotion of the user's utterance. The user imitation unit 13 calculates the total morpheme number (hereinafter, voc) by referring to the first memory 10a. Further, the user imitation unit 13 calculates the ratio of the polarity of the total utterance of one user by referring to the ratio of the polarity determination in each utterance from the second memory 10b. Then, the user imitation unit 13 transmits the total morpheme number, the morpheme having the latest utterance time (time) (hereinafter, rword), and the ratio of the polarity in the total utterance of one user to the state determination unit 14.

The operation of the user imitation unit 13 will be described with reference to FIGS. 5 and 6. FIG. 5 shows a specific example of the database stored in the second memory 10b. As shown in the figure, the second memory 10b stores a database that stores the user's utterance and the polarity determination result. One row of the table shown in FIG. 5 corresponds to one utterance history. In the example of FIG. 5, the utterance history includes "utterance sentence", "pos", "neg", "neu" and "time". The "utterance sentence" is information indicating the content of the user's utterance input by the user. “Pos” is information indicating a value calculated as pos by determining the polarity of the utterance. “Neg” is information indicating a value calculated as neg by determining the polarity of the utterance. “Neu” is information indicating a value calculated as neu by determining the polarity of the utterance. "Time" is information indicating the time when the "utterance sentence" is input.

FIG. 6 is a schematic diagram showing the operation of the user imitation unit 13. The user imitation unit 13 calculates voc with reference to the first memory 10a. Here, voc is set to 50. Further, the user imitation unit 13 calculates the ratio of the polarity of the user's utterance with reference to the second memory 10b. The polarity ratio is calculated by the following formula. Here, x _pol indicates the ratio of polarity (negative / positive / neutral), and n indicates the number of utterances in the second memory 10b. This formula shows the average value for each polarity in the user's utterance.

例えば、図６の例では、ユーザ発話におけるポジティブの平均値は、０．２８、ネガティブの平均値は０．４１、ニュートラルの平均値は０．３１となる。本件明細書において、以降、各極性における平均値であるXpolを、per_pos、per_nega、 per_neuと表記する。それぞれ、Positive、Negative、Neutralの極性の平均値を示す。また、図６における第２メモリ１０ｂの図は発話文欄とtime欄とを省略した図である。

For example, in the example of FIG. 6, the positive average value in the user utterance is 0.28, the negative average value is 0.41, and the neutral average value is 0.31. Hereinafter, in the present specification, Xpol, which is an average value for each polarity, is referred to as per_pos, per_nega, and per_neu. The average values of Positive, Negative, and Neutral polarities are shown, respectively. Further, the figure of the second memory 10b in FIG. 6 is a diagram in which the utterance sentence column and the time column are omitted.

The state determination unit 14 receives the total morpheme number, per_pos, per_neg, and per_neu from the user imitation unit 13, and calculates the degree of growth. Further, the state determination unit 14 is a portion that determines the polarity of the response sentence that is the response target to the utterance by weighted random using the ratio of polarity. Then, the state determination unit 14 extracts the response sentence group stored in the third memory 10c using the rword (the most recent morpheme of the utterances to be responded to) received from the user imitation unit 13. At this time, when a plurality of trigger words and rwords of the third memory 10c are matched, all the matched records are taken out. One response sentence is selected from the response sentence group according to the growth degree determined at the end, and is transmitted to the dialogue transmission unit. Further, the total morpheme number, per_pos, per_neg, per_neu, and the degree of growth are transmitted to the fourth memory 10d.

The operation of the state determination unit 14 will be described with reference to FIG. 7. First, as shown in FIG. 7A, the state determination unit 14 calculates the growth rate g based on the following equation.

g = (1- ｜ a ₁ －per_pos ｜ － ｜ a ₂ －per_nega ｜ － ｜ a ₃ －per_neu |) ・ m
In this equation, a ₁ , a ₂ , and a ₃ indicate ideal polarity values in positive, negative, and neutral, respectively. Further, a ₁ + a ₂ + a ₃ ≦ 1 is set, and a predetermined value is used. m is a morpheme number.

That is, the degree of growth is calculated by (1-(| ideal value of each polarity-actual value of each polarity |)) * morpheme. This formula is a formula set so that the numerical value increases as the ideal state is approached and the number of dialogues (morpheme number) increases.

Since the growth rate is a value indicating the intimacy between the user and the dialogue agent, as described above, the growth rate is designed to increase as the user speaks. However, it is adjusted using morpheme so that the growth rate does not increase even if only the same words are spoken. Further, the balance of the emotional polarities of the utterances from the user terminal 20 is calculated, and if the polar balance is poor, the degree of growth is lowered. Therefore, the degree of growth is determined by the balance between the total number of morphemes obtained from the user's utterance and the polarity.

In general, it cannot be said that the plants are growing normally when the polarity is biased (too negative or too positive). And it is appropriate to judge that it is growing when it is approaching the ideal state.

In the present disclosure, the degree of growth is not determined only by the morpheme number (the number of vocabularies), but is determined by using the balance of polarity. It can be said that the increase in the morpheme number itself is growing, but it is possible to show how much the morpheme number has grown by multiplying the morpheme number by the value of how far it is from the ideal polarity. If the polarity is not deviated from the ideal polarity, the growth rate of morpheme number × 1 can be obtained.

In the above formula, the numerical value related to negative and the numerical value related to neutral are subtracted from the numerical value related to positive (the degree of agreement with the ideal value). Negative emotions are stronger than positive emotions, so negative emotions are subtracted from positive emotions to significantly affect their growth. The degree of growth is not limited to this formula, and may be any formula according to the above definition.

The user imitation unit 13 calculates the morpheme number m = 50, Positive: 0.28, Negative: 0.41, and Neutral: 0.31. By putting these numerical values into the above formula, the state determination unit 14 calculates the growth degree g = 42.5.

For example, when the ideal value is 0.33, the per_pos value is 0.28, the per_neg value is 0.41, the per_neu value is 0.31, and the morphological prime number is 50.
g = (1- | (0.33-0.28) |-| (0.33-0.41) |-| (0.33-0.31) |) * 50 = 42.5
And the growth rate is 42.5.

Further, the state determination unit 14 determines which polarity the response statement belongs to by a weighted random function using the ratio of polarities. For example, as shown in FIG. 7B, from Positive: 0.28, Negative: 0.41, Neutral: 0.31 calculated by the user imitation unit 13 by weighting specified in advance, Positive: 0.3, Negative: 0.41, Neutral: 0.29 are calculated. Then, the state determination unit 14 determines the polarity to which the response statement belongs based on each probability. That is, the probability of becoming Positive: 30%, the probability of becoming Negative: 41%, the probability of becoming Neutral: 29%, and the state determination unit 14 determines the polarity to which the response sentence belongs according to these probabilities. In FIG. 7B, the state determination unit 14 negatively determines the response sentence.

As shown in FIG. 7 (c), the state determination unit 14 determines one or more response statements based on the degree of growth, the polarity of the response statement, and the rword. Specifically, the state determination unit 14 extracts a response sentence group matching the rword from the third memory 10c based on the rword in the trigger word column, and further selects a response sentence group matching the polarity from the response sentence group. Extract.

As shown in FIG. 8, the third memory 10c stores a database of fixed response statements. One record (one row) in the table is the database corresponding to one response statement. In the example of FIG. 8, this database associates a "trigger word", a "response statement", a "growth threshold", and a "PN (polarity)". The "trigger word" is a reference word when selecting a response sentence. If the word indicated by the "trigger word" is included at the end of the utterance, the response to that utterance is selected. The "growth threshold" is a parameter that serves as a reference for selecting a response statement, and the response statement is selected by comparing the growth degree of the user with the growth threshold. "PN" indicates the polarity of the response statement.

In FIG. 7 (c), three response sentence groups whose rword is "spicy" and whose polarity is Negative are extracted. Further, the state determination unit 14 determines one response sentence in which the growth degree threshold is set to be equal to or lower than the growth degree based on the growth degree (42.5) and the growth degree threshold stored in the third memory 10c. do. For example, when the response sentence is determined using the growth degree 42.5, the growth degree threshold value of the first sentence is 870, the growth degree threshold value of the second sentence is 280, and the growth degree threshold value of the third sentence is 280. If 0, the third response statement is selected as the response statement. Here, "Kana" is selected.

The response sentence transmission unit 15 transmits the response sentence determined by the state determination unit 14 to the user terminal 20. Further, the response sentence transmission unit 15 may transmit the growth record of the user and the frequency of the utterance (morpheme unit) used by the user to the user terminal 20. As the growth record, there is information stored in the fourth memory 10d, which will be described later. Further, as the frequency of utterance, there is information stored in the first memory 10a. The transmission may be made by a request from the user terminal 20 or may be made periodically.

When transmitting the frequency of utterances, the response sentence transmitting unit 15 generates, for example, the message "The most utterances of yours are XX." You may also use the utterance history to generate the message "When do you often speak?". In that case, the dialogue device 100 includes a history table (not shown) for each utterance, and the response sentence transmission unit 15 uses the information. Further, the response transmission unit 15 may generate a message "Growth degree is XX.". The degree of growth is information stored in the fourth memory 10d. Further, for the growth degree, a growth curve may be calculated from a numerical value of the past growth degree (growth degree history, the horizontal axis is time or total morpheme) and transmitted to the user terminal 20. Further, only numerical values may be sent and processed so as to form a growth curve in the user terminal 20.

The first memory 10a is a portion that stores a database that stores morphemes transmitted from the dialogue decomposition unit. As described above, the specific example is as shown in FIG. 3, and the part of speech, the number of extractions, and the most recently analyzed time are stored for each morpheme.

The second memory 10b is a portion that stores a database that stores the user's utterance and the polarity determination result.

The third memory 10c is a portion for storing a database of standard response statements.

The fourth memory 10d is a database that stores a user's growth record. One record in the table shown in FIG. 9 is information corresponding to the growth record of one utterance of the user. In the example of FIG. 9, it has "total morpheme number", "pos", "neg", "neu", "growth degree", and "time". “Time” indicates the date and time when the utterance was made. In the fourth memory 10d, each time the state determination unit 14 acquires a response sentence, the growth record is stored. The total morpheme is the accumulation of the morphemes extracted for each response sentence creation. One utterance often contains 5 to 10 morphemes, but may include more morphemes.

The operation of the dialogue device 10 configured in this way will be described. 10 and 11 are flowcharts showing the operation of the dialogue device 10. Hereinafter, each step of the flowchart will be described. This flowchart describes the process for one user.

The utterance receiving unit 11 receives the utterance sentence input by the user by voice or text as input 1 (S101). The utterance decomposition unit 12 performs morphological analysis on the input 1 received by the utterance receiving unit 11 using a morphological analyzer such as Mecab, decomposes the utterance sentence into morphological elements (the smallest unit having meaning in the language), and decomposes the part of speech. Determine (S102). The utterance decomposition unit 12 determines whether or not the determined morpheme is stored in the first memory 10a (S103). If the utterance decomposition unit 12 is not stored in the first memory 10a (S103: NO), the utterance decomposition unit 12 stores the morpheme and the part of speech in the first memory 10a (S104). When the utterance decomposition unit 12 is stored in the first memory 10a (S103: YES), the utterance decomposition unit 12 updates the value of the “number of times” of the first memory 10a so as to increase the number of appearances by one. Further, the utterance decomposition unit 12 records the time (hereinafter, time) when the input 1 is received in the first memory 10a. At this time, if the morpheme has already been registered, the value is updated at the latest time when the morpheme appears.

The utterance decomposition unit 12 determines the polarity of the input 1 using a polarity dictionary such as a Japanese evaluation polarity dictionary (S105). When the polarity determination is performed, the user imitation unit 13 calculates the score of each polarity. For example, the utterance decomposition unit 12 determines the polarity of "Today's train was so crowded and painful ..." and calculates the scores of pos, neg, and neu, respectively. It is assumed that the polarity dictionary used at this time already exists. The utterance decomposition unit 12 records the input 1, the calculated scores of pos, neg, and neu, and the time in the second memory 10b.

The user imitation unit 13 counts the total number of morphemes stored in the first memory 10a (hereinafter referred to as the total number of morphemes) (S107). The user imitation unit 13 receives the result of the polarity determination of all utterances from the second memory 10b. From the result of the received polarity determination, the ratio of the polarity (per_pos, per_neg, per_neu) of the entire user utterance is calculated (S108).

The state determination unit 14 receives the polarity ratio and the number of vocabularies from the user imitation unit 13, and calculates the degree of growth (S109).

The state determination unit 14 probabilistically determines the polarity of the response sentence according to a weight designated in advance by the ratio of the polarity obtained from the second memory 10b (S110).

The state determination unit 14 extracts the response sentence group corresponding to the determined polarity of the response sentence from the third memory 10c. At this time, it is assumed that the response sentence group is stored in the third memory 10c in advance. In the extracted response sentence group, the response sentence, the growth threshold and the polarity are recorded. The state determination unit 14 compares the calculated growth degree with the growth degree threshold value, and when the growth degree threshold value is exceeded, sets the corresponding response sentence in the response sentence 1 (S111).

The state determination unit 14 records the total morpheme number, per_pos, per_neg, per_neu, growth rate, and time in the fourth memory 10d (S112).

The response text transmission unit 15 transmits the selected response text to the user terminal 20 (S113).

Next, the operation and effect of the dialogue device 100 in the present disclosure will be described. The dialogue device 100 in the present disclosure calculates the growth degree of the dialogue with the user based on the utterance receiving unit 11 that receives the utterance from the user and the utterance history of the user, and responds to the utterance from the user according to the growth degree. It is provided with a state determination unit 14 for acquiring a response statement. The state determination unit 14 functions as a growth degree calculation unit and a response sentence acquisition unit.

With this configuration, the response statement can be changed according to the degree of growth of the dialogue with the user. Therefore, as the dialogue device 100 grows, the user can receive the corresponding response sentence, and the user does not feel that the dialogue is mechanical.

Further, the state determination unit 14 functioning as a growth degree calculation unit is a ratio of the morpheme number (number of expression elements) used for the utterance of the user and the polarity type (positive, negative, neutral) in the utterance of the user in the utterance history. The degree of growth is calculated based on. The morpheme number here is the number of morphemes stored in the first memory 10a, and indicates the number of vocabularies. The polarity type ratio is an average value of the positive, negative, and neutral ratios of all the polarity types stored in the second memory 10b, or a value obtained by subjecting the average value to a predetermined weighting process.

That is, the degree of growth is based on the morpheme number that the user has used for dialogue and the ratio of the user's polarity type in the utterance. The proportion of the polarity type can be seen as the tendency of the user's utterance, and indicates whether the user's utterance has a positive tendency, a negative tendency, or a neutral tendency that is neither of them.

Then, the state determination unit 14 that functions as a response sentence acquisition unit selects a response sentence according to the degree of growth and the tendency of the user's utterance.

The degree of growth of the dialogue device 100 of the present disclosure is a value representing intimacy, and is designed so that the more the user speaks to the dialogue device 100, the higher the degree of growth. However, it is designed so that the growth rate does not increase even if you speak only the same words. Further, the balance of the polarity types indicating the emotions of the utterance from the user terminal 20 is calculated, and if the polarity balance is poor, the degree of growth is lowered. Therefore, the degree of growth is determined by the balance between the total number of vocabularies obtained from the user's utterances and the polarity. It is said that it is ideal for a general user (human being) to be able to receive both negative emotions and positive emotions.

This enables an ideal response by calculating the degree of growth considering the balance of the polarity types. As a result, the user can have an intimacy with the dialogue device 100 and contributes to the continuation of the dialogue.

More specifically, the dialogue device 100 functions as an utterance decomposition unit 12 that decomposes utterances from the user for each part of speech and acquires morphemes (expression elements), and a part of speech history storage unit that stores the morphemes as utterance history. A first memory 10a is provided. Then, the state determination unit 14 calculates the degree of growth based on the morpheme number stored in the first memory 10a. In the present disclosure, the number of vocabularies is stored by performing morphological analysis and storing this as an utterance history.

Further, the dialogue device 100 further includes a second memory 10b that functions as a polarity type storage unit that stores the ratio of the polarity types for each utterance. The utterance decomposition unit 12 acquires the ratio of the polarity type for each morpheme in the utterance and stores it in the second memory 10b. Then, the state determination unit 14 calculates the degree of growth based on the ratio of the polarity type in the second memory 10b in addition to the morpheme number.

In the dialogue device 100 of the present disclosure, the state determination unit 14 that functions as the response sentence acquisition unit acquires the response sentence according to the polarity type in the user's utterance in addition to the growth degree. At that time, the state determination unit 14 that functions as the growth degree calculation unit determines the type of the response sentence based on the ratio of the polarity type in the user's utterance. The response sentence according to the polarity type in the user's utterance indicates the emotional tendency of the user's utterance, and the response sentence according to the tendency can be acquired.

The dialogue device 100 of the present disclosure further includes a third memory 10c as a response sentence storage unit associated with a response sentence and a growth threshold value. Then, the state determination unit 14 that functions as the response sentence acquisition unit acquires the response sentence according to the degree of growth from the third memory 10c. At that time, a response statement in which a growth threshold value equal to or lower than the growth degree is set is acquired. By this process, the response sentence according to the degree of growth can be selected.

Here, the third memory 10c stores the polarity types in association with each other. Then, the state determination unit 14 narrows down the response sentences by selecting one or a plurality of response sentences according to the tendency of the polarity type of the user's utterance, and further selects the response sentences according to the degree of growth. ..

Further, in the dialogue device 100 of the present disclosure, the third memory 10c further stores the trigger word in association with it. The state determination unit 14 acquires one or a plurality of response statements in which the morpheme included in the utterance of the user to be responded matches the trigger word of the third memory 10c. This makes it possible to appropriately select a response sentence for the user's utterance.

Further, the dialogue device 100 of the present disclosure stores the morpheme included in the user's utterance, its polarity type, and the degree of growth.

The block diagram used in the description of the above embodiment shows a block of functional units. 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 using one physically or logically coupled device, or two or more physically or logically separated devices can be directly or indirectly (eg, for example). , 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 (component) that makes transmission function is called a transmitting unit or a transmitter. In each case, as described above, the realization method is not particularly limited.

For example, the dialogue device 100 in one embodiment of the present disclosure may function as a computer that processes the dialogue method of the present disclosure. FIG. 12 is a diagram showing an example of the hardware configuration of the dialogue device 100 according to the embodiment of the present disclosure. The above-mentioned dialogue device 100 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 100 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 100, by loading predetermined software (program) on hardware such as the processor 1001 and the memory 1002, the processor 1001 performs an calculation, controls communication by the communication device 1004, and the memory 1002. And by controlling at least one of reading and writing of data in the storage 1003.

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) including an interface with a peripheral device, a control device, an arithmetic unit, a register, and the like. For example, the above-mentioned utterance decomposition unit 12 and the like may be realized by the processor 1001.

Further, the processor 1001 reads a program (program code), a software module, data, and the like 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 utterance decomposition unit 12, the user imitation unit 13, and the state determination unit 14 may be realized by a control program stored in the memory 1002 and operating in the processor 1001, and may be realized in the same manner for other functional blocks. good. 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 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 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 implement the dialogue method according to the embodiment of the present disclosure.

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 at least one of the memory 1002 and the 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 FDD (Frequency Division Duplex) and Time Division Duplex (TDD). It may be composed of. For example, the above-mentioned utterance receiving unit 11 and response text transmitting unit 15 may be realized by the communication device 1004. The utterance receiving unit 11 and the response sentence transmitting unit 15 may be physically or logically separated from each other, or may have the same implementation.

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. 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 100 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 some or all of each functional block may be realized by the hardware. For example, processor 1001 may be implemented using at least one of these hardware.

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 and extend 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.

Information and the like can be output from the upper layer (or lower layer) to the lower layer (or upper layer). Input / output may be performed via a plurality of network nodes.

The input / output information and the like may be stored in a specific place (for example, a memory), or may be managed using a management table. Information to be input / output may 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 may be switched and used according to the 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 amendments and modifications without departing from the spirit and scope of the present disclosure as determined by the description of the scope of claims. Therefore, the description of this disclosure is for purposes of illustration and does not have any limiting meaning to this disclosure.

Software, whether called software, firmware, middleware, microcode, hardware description language, or other names, instructions, instruction sets, codes, code segments, program codes, programs, subprograms, software modules. , Applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, features, etc. should be broadly interpreted.

Further, software, instructions, information and the like 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, twisted pair, Digital Subscriber Line (DSL), 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 the present 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 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 in the present disclosure and the terms necessary for understanding the present disclosure may be replaced with terms having the same or similar meanings. For example, at least one of a channel and a symbol may be a signal (signaling). Also, the signal may be a message. Further, the component carrier (CC: Component Carrier) may be referred to as a carrier frequency, a cell, a frequency carrier, or the like.

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

Further, 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.

The terms "determining" and "determining" used in this disclosure may include a wide variety of actions. "Judgment" and "decision" are, for example, judgment, calculation, computing, processing, deriving, investigating, looking up, search, inquiry. It may include (eg, searching in a table, database or another data structure), ascertaining 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. It may include (for example, accessing data in memory) to be regarded as "judgment" or "decision". In addition, "judgment" and "decision" are considered to be "judgment" and "decision" when 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". 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 energy 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" and "second" 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. Therefore, 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 a "part", a "circuit", a "device" and the like.

When "include", "including" and variations thereof are used in the present disclosure, these terms are as inclusive as the term "comprising". Is intended. Moreover, 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 the plural nouns following these articles.

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".

10a ... 1st memory, 10b ... 2nd memory, 10c ... 3rd memory, 10d ... 4th memory, 11 ... utterance receiving unit, 12 ... utterance decomposition unit, 13 ... user imitation unit, 14 ... state determination unit, 15 ... Response text transmitter.

Claims (10)

The utterance reception section that accepts utterances from users,
A growth degree calculation unit that calculates the growth degree for a dialogue with the user based on the utterance history of the user, and a growth degree calculation unit.
A response sentence acquisition unit that acquires a response sentence according to the degree of growth in response to the utterance from the user.
A dialogue device equipped with. The growth degree calculation unit is
The degree of growth is calculated based on the number of expression elements used in the utterance of the user and the ratio of the polarity type in the utterance of the user in the utterance history.
The dialogue device according to claim 1. An utterance decomposition unit that decomposes utterances from the user for each part of speech and acquires expression elements,
A part-speech history storage unit that stores the expression element as an utterance history,
Equipped with
The growth degree calculation unit is
The degree of growth is calculated based on the number of expression elements stored in the part of speech history storage unit.
The dialogue device according to claim 1 or 2. It also has a polarity type storage unit that stores the ratio of polarity types for each utterance.
The utterance decomposition part is
The ratio of the polarity type for each expression element in the utterance is acquired and stored in the polarity type storage unit.
The growth degree calculation unit calculates the growth degree based on the ratio of the polarity type in the polarity type storage unit in addition to the number of expression elements.
The dialogue device according to claim 3. In addition to the degree of growth, the response sentence acquisition unit acquires a response sentence according to the polarity type in the utterance of the user.
The dialogue device according to any one of claims 1 to 4. The growth degree calculation unit is
The type of response sentence is determined based on the ratio of the polarity type in the user's utterance.
The dialogue device according to claim 5. A response sentence storage unit associated with a response sentence and a growth threshold is further provided.
The response sentence acquisition unit
The response sentence corresponding to the growth degree is acquired from the response sentence storage unit.
The dialogue device according to any one of claims 1 to 6. The response sentence storage unit further associates and stores the polarity types, and stores the polar types.
The response sentence acquisition unit selects one or more response sentences according to the tendency of the polarity type of the user's utterance.
In addition, select a response statement according to the degree of growth,
The dialogue device according to claim 7. The response sentence storage unit further stores the trigger words in association with each other.
The response sentence acquisition unit acquires one or more response sentences in which the expression element included in the utterance of the user who is the response target matches the trigger word of the response sentence storage unit.
The dialogue device according to claim 7 or 8. The dialogue device according to any one of claims 1 to 9, further comprising a growth degree storage unit for storing the number of expression elements included in the user's utterance, the polarity type thereof, and the growth degree.

Images