Dialogue evaluation device, dialogue evaluation method, and program

Abstract

This dialog evaluation device evaluates a dialog conducted among a group of at least two participants, and comprises: an activity score calculation unit that extracts at least one feature quantity as an activity score from dialog data; a feature quantity weight calculation unit that extracts dialog experience data from past dialog logs, calculates, from the dialog experience data, a dialog experience score obtained by converting a dialog experience between the participants into numbers, and calculates, from the dialog experience score, the weight of each feature quantity in the activity score; and a dialog evaluation score calculation unit that calculates a dialog evaluation score using the activity score and the weight.

Description

[Technical field]

[0001] The present invention relates to a technique for evaluating a dialogue in a group including two or more dialogue participants (called a group dialogue). [Background technology]

[0002] Technologies for evaluating group dialogues include those that estimate leadership and contribution from the number of utterances made during the dialogue, the frequency of words in the utterances, and the number of nods seen in camera footage. There are also technologies that conduct questionnaire evaluations asking participants how much they contributed directly and how satisfied they were, and technologies that have a third party evaluate the results of the dialogue. When evaluating dialogues generated by dialogue systems, there are also technologies that evaluate the sentences generated by the system. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2012-242528 A [Non-patent literature]

[0004] [Non-Patent Document 1] Indrani Bhattacharya, et al."A Multimodal-Sensor-Enabled Room for Unobtrusive Group Meeting Analysis", ICMI '18: Proceedings of the 20th ACM International Conference on Multimodal Interaction,PP.347-355. https: / / dl.acm.org / doi / pdf / 10.1145 / 3242969.3243022 [Non-Patent Document 2] Soomin Kim, et al. "Bot in the Bunch: Facilitating Group Chat Discussion by Improving Efficiency and Participation with a Chatbot", CHI '20: Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems, PP.1-13. https: / / dl.acm.org / doi / pdf / 10.1145 / 3313831.3376785 Summary of the Invention [Problem to be solved by the invention]

[0005] In conventional technology, when evaluating a dialogue between dialogue participants, the actual dialogue state, such as the number of utterances of the dialogue participants and the characteristics of words, is often quantified. In addition, the personality and values ​​of the dialogue participants, such as leadership ability, can be obtained or estimated and used to evaluate the dialogue.

[0006] However, the points that are emphasized when evaluating a dialogue differ between when dialogue participants are engaged in a dialogue for the first time and when they have been in dialogue continuously for a long period of time.

[0007] For example, when participants who have never met before gather together for a one-off discussion, they may avoid revealing their own personality or values, or may not try to understand the other person's personality or values, and may place importance on livening up the atmosphere. Also, when there is a clear goal, such as arriving at the correct answer through dialogue, they may evaluate the entire dialogue and their own behavior based on whether or not they were able to reach that goal.

[0008] On the other hand, when the same members hold a long-term discussion, such as in a company meeting, the excitement of the moment is not important, but rather it is important to see whether more advanced opinions are presented or whether everyone agrees. Even if there is a clear goal, as in the previous example, it may be enough to reach it by continuing the discussion, and it may not be necessary to arrive at the correct answer within the dialogue alone.

[0009] In this way, even if the dialogue is the same task-oriented dialogue, the points that are emphasized when evaluating the dialogue depend heavily on the relationships between the participants. Therefore, by quantifying the relationships and using them in evaluating the dialogue, a more accurate evaluation can be performed. However, conventional techniques (e.g., Patent Document 1, Non-Patent Documents 1 and 2) do not take into account the relationships between the dialogue participants.

[0010] The present invention has been made in consideration of the above points, and has an object to provide a technique that makes it possible to evaluate a dialogue held in a group, taking into account the relationships between the dialogue participants. [Means for solving the problem]

[0011] According to the disclosed technology, there is provided a dialogue evaluation device for evaluating a dialogue held by a group of two or more participants, comprising: an activation score calculation unit that extracts one or more feature quantities as an activation score from the dialogue data; a feature weight calculation unit that extracts dialogue experience data from a past dialogue log, calculates a dialogue experience score by quantifying the dialogue experience between the participants from the dialogue experience data, and calculates a weight of each feature in the activity score from the dialogue experience score; a dialogue evaluation score calculation unit that calculates a dialogue evaluation score by using the activity score and the weight; There is provided a dialogue evaluation device comprising: Effect of the Invention

[0012] According to the disclosed technology, it is possible to evaluate a dialogue held in a group by taking into account the relationships between the dialogue participants. [Brief description of the drawings]

[0013] [Figure 1] 1 is a configuration diagram of a dialogue evaluation device according to an embodiment of the present invention. [Diagram 2] 10 is a flowchart illustrating an operation of the dialogue evaluation device. [Diagram 3] FIG. 2 is a diagram illustrating an example of a dialogue log database. [Figure 4] FIG. 2 illustrates an example of a hardware configuration of the dialogue evaluation device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] Hereinafter, an embodiment of the present invention (the present embodiment) will be described with reference to the drawings. The embodiment described below is merely an example, and the embodiment to which the present invention is applied is not limited to the following embodiment.

[0015] (Outline of the embodiment) First, an outline of the present embodiment will be described. In this embodiment, a dialogue evaluation device 100, which will be described later, predicts a score by quantifying an evaluation that reflects the degree of achievement, satisfaction, contribution, etc., of each dialogue participant in a group dialogue of two or more dialogue participants (which may be called members or participants).

[0016] When performing an evaluation, the dialogue evaluation device 100 uses dialogue data that records the dialogue to be evaluated and dialogue experience data that represents past dialogue experiences between the participants. The dialogue data may include personality data that represents the personalities and values ​​of the participants who make up the dialogue group.

[0017] The conversation data is a chronological record of the conversation, and may include, for example, voice data collected by a microphone, text data transcribed from what each member said, video data capturing the movements of each member, vital data such as the heart rate of each member recorded using a device such as a smartwatch, etc. As described above, the conversation data may also include personal data expressing the individuality of each participant taking part in the conversation, such as the results of a personality questionnaire, personal data predicted from past data using existing technology, and data on attributes such as age, work history, and job title.

[0018] The dialogue evaluation device 100 obtains the degree of dialogue activity from this dialogue data. The degree of activity is a value obtained by converting into a comparable numerical value an indication of how lively the dialogue is, an indication of the emotional uplifting of the members, and the individuality of the dialogue participants themselves. For example, in the case of voice data, the volume or change in the voice of each participant can be used as the degree of activity; in the case of text data, the number of times each participant speaks or the number of words spoken; in the case of video data, the magnitude of gestures or the magnitude of nodding; and in the case of vital data, the speed or change in heart rate can be used. The degree of activity may also be called a "feature amount."

[0019] The personal data that can be included in the dialogue data is data that represents the individual participants in the dialogue, and is data obtained by, for example, choosing the answer that suits you from options such as "I think so," "I think a little," "I don't think so much," or "I don't think so at all" in response to the question "I like talking about myself in front of others," or by selecting the word that suits your personality or values ​​from words such as "quiet," "talkative," and "outgoing," or by rating each item on a nine-point scale. Alternatively, data on the evaluation of each participant by others, or a score resulting from predicting individuality using past dialogue data, etc., may be used as the personal data.

[0020] When using the results of a questionnaire on personality and attributes as personal data, if the questionnaire answers are given in graded numbers, the numbers may be used as they are, or the aggregated values ​​may be used. If the questionnaire answers are given in Yes / No, a numerical value such as 1 for Yes and 0 for No is used. If the answers are given in a selection format from non-continuous items such as occupation or preference, a feature value for the number of items can be prepared and the selected items can be converted into a vector with 1 and the rest with 0. In the case of free text, the words contained in the questionnaire can be used as features, or the written content can be categorized, a feature value for the number of categories can be prepared, and the selected items can be converted into a vector with 1 and the rest with 0, and used as the activation score. In addition, questions with different answering methods, such as Yes / No questions, questions answered on a 7-point scale, and free text questions, may be mixed.

[0021] The dialogue experience data is a numerical representation of the dialogue experiences that participants have had with each other, such as the number of times that participants have dialogued together and the total duration of dialogues that they have participated in together. Alternatively, a period during which dialogue experience is likely to occur, such as the period during which participants belonged to the same project at work or the period during which they were in the same class at school, may be used instead. One or more types of data may be used as the dialogue experience data. When there are three or more participants, the dialogue experience data may be any combination of participants who have had the same dialogue experience, such as using dialogues that all participants experienced together, or using dialogues that participants in each pair experienced together. For example, dialogue experience data may be extracted for all combinations of participants with different numbers of participants, and used as the dialogue experience data.

[0022] The dialogue evaluation device 100 calculates a dialogue evaluation score by combining the activity score obtained from the dialogue data and the dialogue experience score obtained from the dialogue experience data. The dialogue evaluation score is given to each participant here, and is a score that represents the achievement, satisfaction, and contribution of the participant in the dialogue. The dialogue evaluation score may be a score (vector) of each of the achievement, satisfaction, and contribution, or may be a score of any one of the achievement, satisfaction, and contribution, or may be a score of multiple of the achievement, satisfaction, and contribution. It is also possible to express the score of the entire group by calculating statistics such as the average of the scores of each participant.

[0023] The configuration and operation of the dialogue evaluation device 100 will be described in detail below as an embodiment.

[0024] (Device configuration) Fig. 1 shows an example of the configuration of a dialogue evaluation device 100 in this embodiment. As shown in Fig. 1, the dialogue evaluation device 100 includes an activity score calculation unit 101, a dialogue experience data extraction unit 102, a dialogue experience score calculation unit 103, a feature weight calculation unit 104, a dialogue evaluation calculation unit 105, an input unit 106, an output unit 107, and a dialogue log DB (database) 108.

[0025] The dialogue log DB 108 may be provided outside the dialogue evaluation device 100 and connected to the dialogue evaluation device 100 via a network. The feature weight calculation unit 104 may include a dialogue experience data extraction unit 102 and a dialogue experience score calculation unit 103.

[0026] (Example of device operation) An example of the operation of the dialogue evaluation device 100 will be described below. In the example of the operation described below, the number of participants in the dialogue to be evaluated is k, and the k participants are denoted by h1, ..., h k Let the dialogue evaluation scores of each participant be s1,…,s k and this is calculated by the dialogue evaluation device 100.

[0027] From the input unit 106, dialogue data and a participant list (h1,..., h k ) are input. In this embodiment, as the dialogue data used for input, a transcript of what each participant said and the personality characteristics of each participant obtained through a questionnaire survey are used. As described above, the dialogue data is not limited to this, and data indicating the state of dialogue such as speech audio, video, and biosensor information may be used, or data representing individuality such as attributes such as age, work history, and position, and questionnaire results asking about values, experiences, preferences, etc. may also be used. Also, the number of data types is not limited.

[0028] Hereinafter, it will be described according to the procedure of the flowchart in FIG. 2. Note that the order of calculations shown in the flow shown in FIG. 2 is an example. The order of calculations such as the activity score and the dialogue experience score required for calculating the dialogue evaluation score is arbitrary.

[0029] <S101: Activity Score Calculation> In S101, the activity score calculation unit 101 takes the dialogue data as input, extracts features from the dialogue data, and outputs them. Here, the total speaking time of each participant (u1,..., u k ), the number of backchannels of each participant (b1,..., b k ), the number of important word utterances of each participant (w1,..., w k ), and the personality characteristic score (p1,..., p k ) are extracted as features.

[0030] Here, the backchannel refers to things like responses, and can be extracted by definitions such as considering utterances that do not include verbs, nouns, adjectives, numerals, etc. as backchannels. The number of important word utterances refers to the number of times a word included in a pre-determined list of important words is uttered. As the personality characteristic score, the results of the questionnaire are tabulated and those quantified using a classification method such as the Big Five personality characteristics or existing scales are used.

[0031] Each feature of each participant may be a scalar value or a vector value. For example, the number of important word utterances w i =(w´ i1 ,..., w´ic ) The number of occurrences of each of the c words may be used as a feature amount, or the personality characteristic score p i =(p´ i1 ,...,p´ id ) The d types of personality characteristic factors or attributes may be used as feature amounts. Also, it is not always necessary to have feature amounts for each of all the participants. For example, only the feature amounts of the person who is the subject of the dialogue evaluation may be extracted and used, or values obtained by aggregating such as the average, maximum value, minimum value, and variance of all the participants may be used.

[0032] The feature amounts are not limited to the above, and any numerical value that can be extracted and calculated from the dialogue data is acceptable, such as the average volume, maximum volume of the microphone, the number of nodding operations, the number of times exceeding the maximum heart rate or average heart rate, etc. Also, attributes such as age and job may be classified from the data representing individuality, and numbers representing the group to which the participants belong may be used as feature amounts. In this embodiment, as shown below, the feature amounts a1,..., a l concatenated as described above are used as the activity scores.

[0033]

Number

[0034] An example of the dialogue log DB108 storing the dialogue logs is shown in FIG. 3. As shown in FIG. 3, the dialogue logs include data indicating how much the participants have interacted with each other, such as the dialogue participant list, dialogue time (start date and time, end date and time), and number of utterances. For example, in the dialogue with dialogue ID = 2 in FIG. 3, it is shown that a dialogue was conducted between participant A and participant C from 17:00 to 19:12 on March 31, 2021, and the number of utterances of participant A is 200 and the number of utterances of participant C is 100.

[0035] The dialogue experience data extraction unit 102 extracts the dialogue experience data in which the dialogue participants to be evaluated participated from the dialogue log DB 108. At this time, only the data in which all the dialogue participants participated together may be extracted, or the extraction may be performed in a plurality of combinations such as data in which some of the participants participated together. In this embodiment, the log of the dialogue in which all the dialogue participants participated together and the log of the dialogue in which two-person pairs are formed from the dialogue participants and the two-person pairs participated together are extracted as the dialogue experience data.

[0036] <S103: Dialogue Experience Score Calculation> In S103, the dialogue experience score calculation unit 103 takes the dialogue experience data extracted in S102 as input, calculates the dialogue experience score, and outputs it. Specifically, the dialogue experience score calculation unit 103 numerically extracts the dialogue experience that the participants who participated in the dialogue to be evaluated had with each other in the past from the dialogue experience data.

[0037] More specifically, in this embodiment, the values of the past dialogue count and the dialogue frequency in the most recent one month are used as the dialogue experience score. The dialogue experience score calculation unit 103 calculates the past dialogue count (s all , s 12 ,..., s (k-1)k ) and the dialogue frequency in the most recent one month (f all , f 12 ,..., f (k-1)k ) from the dialogue logs of all the participants and the two-person pairs output by the dialogue experience data extraction unit 102. Note that s all is the number of dialogues among all the participants, and s 12 is the number of dialogues between participant 1 and participant 2. Also, f all is the dialogue frequency in the most recent one month among all the participants, and f 12 is the dialogue frequency in the most recent one month between participant 1 and participant 2. Note that the unit of the dialogue frequency in the most recent one month may be any unit, for example, it may be the number of dialogues in the most recent one month.

[0038] As follows, in this embodiment, the dialogue experience score calculation unit 103 outputs the concatenation of the past dialogue count and the dialogue frequency in the most recent one month as the dialogue experience score E.

[0039] [Number] <S104: Feature Weight Calculation> In S104, the feature weight calculation unit 104 takes the dialogue experience score as input, calculates and outputs the weight of each feature in the activity score. The weight of the feature may be a continuous value corresponding to the continuous value of the dialogue experience score, or may be classified according to the magnitude or distribution of the dialogue experience score, and the weight of the feature may be determined for each class.

[0040] Regarding the method of generating the weight, for example, there is a method of generating and using a model that outputs the weight of the feature when the dialogue experience score E is input using the data in which the participant annotates the dialogue evaluation score in the past dialogue log. Such a model may be a machine learning model such as a neural network, for example.

[0041] For example, if the above model is represented by the function f and the weight of the feature is w, the feature weight calculation unit 104 can calculate the weight as f(E)=w. When generating the model, the activity score A is calculated using the above annotated dialogue log, and the parameters of the model f may be adjusted so that "(f(E))A" becomes the correct dialogue evaluation score s.

[0042] By using the dialogue evaluation score s of a specific participant as the correct dialogue evaluation score s, it is possible to obtain the weight w that can calculate the dialogue evaluation score s of that specific participant. Also, by using the dialogue evaluation score s of a specific factor (for example, a vector having satisfaction and contribution as elements) as the correct dialogue evaluation score s, it is possible to obtain the weight w that can calculate the dialogue evaluation score s of that specific type.

[0043] The weight of the feature is considered to include a value indicating which feature among the features included in the activity score should be more considered for dialogue evaluation. For example w=(w1,…,w l ) can be expressed as follows. Here, any w i corresponds to a in the activity score A i and is a value that can determine how much each feature amount a i is weighted by the weight w i . In the above example, w is a vector, but w may also be a matrix.

[0044] As described above, when calculating the weight w, since the dialogue experience score E is used, a weight w that takes into account the dialogue experience (the relationship between dialogue participants) can be obtained.

[0045] <S105: Dialogue Evaluation Calculation> In S105, the dialogue evaluation calculation unit 105 uses the activity score A and the weight w of each feature amount to calculate the dialogue evaluation score s i of a certain dialogue participant h i as follows. The calculated result is output from the output unit 107.

[0046] s i = wA In the above example, since w and A are vectors respectively, the dialogue evaluation score is a scalar value. Note that the feature amounts in the activity score A in the above formula may be only the feature amounts related to the participant h i for which the score is calculated, or may include feature amounts other than the feature amounts related to the participant h i for which the score is calculated.

[0047] Calculating the dialogue evaluation score as a scalar value as described above is just an example, and the dialogue evaluation score may also be calculated as a vector value. For example, when calculating the dialogue evaluation score as a vector value by using a matrix as w, the dialogue evaluation may be determined by the magnitude of the vector, or each element of the vector may be a factor of dialogue evaluation such as "degree of agreement", "activity degree", "satisfaction degree", etc.

[0048] In the above formula s iBy performing the calculation of =wA for each participant, it is possible to obtain the dialogue evaluation score for each participant. However, obtaining the dialogue evaluation score for each participant is just one example.

[0049] By including the activity scores for the dialogue of all participants as features and calculating weights based on the dialogue experience of all participants in the feature weight calculation unit 104, the calculation result of wA can also be used as an evaluation score for the entire dialogue regardless of the participants.

[0050] Furthermore, after determining the dialogue evaluation score for each participant, the statistics (for example, the average or sum) may be used as the evaluation score for the entire dialogue in the group.

[0051] (Hardware configuration example) The dialogue evaluation device 100 can be realized, for example, by causing a computer to execute a program. This computer may be a physical computer or a virtual machine on the cloud.

[0052] That is, the dialogue evaluation device 100 can be realized by using hardware resources such as a CPU and memory built into a computer to execute a program corresponding to the processing performed by the dialogue evaluation device 100. The above program can be recorded on a computer-readable recording medium (such as a portable memory) and stored or distributed. The above program can also be provided via a network such as the Internet or email.

[0053] Fig. 4 is a diagram showing an example of the hardware configuration of the computer. The computer in Fig. 4 includes a drive device 1000, an auxiliary storage device 1002, a memory device 1003, a CPU 1004, an interface device 1005, a display device 1006, an input device 1007, an output device 1008, and the like, all of which are interconnected via a bus BS.

[0054] The program for realizing the processing on the computer is provided by a recording medium 1001 such as a CD-ROM or a memory card. When the recording medium 1001 storing the program is set in the drive device 1000, the program is installed from the recording medium 1001 to the auxiliary storage device 1002 via the drive device 1000. However, the program does not necessarily have to be installed from the recording medium 1001, but may be downloaded from another computer via a network. The auxiliary storage device 1002 stores the installed program as well as necessary files, data, etc.

[0055] The memory device 1003 reads out and stores the program from the auxiliary storage device 1002 when an instruction to start the program is received. The CPU 1004 realizes functions related to the dialogue evaluation device 100 in accordance with the program stored in the memory device 1003. The interface device 1005 is used as an interface for connecting to a network, etc. The display device 1006 displays a GUI (Graphical User Interface) or the like according to a program. The input device 1007 is composed of a keyboard and mouse, buttons, a touch panel, etc., and is used to input various operational instructions. The output device 1008 outputs the results of calculations.

[0056] (Summary of the embodiment, effects) The evaluation of a group dialogue is influenced by the remarks and behavior of the participants in the actual dialogue, and the relationships between the participants. Since the relationships between the participants change, such as deepening the more experience they have of dialogue together, in this embodiment, this is expressed as a dialogue experience score, and by combining the dialogue experience scores, it is possible to accurately judge the evaluation of the dialogue.

[0057] That is, in this embodiment, when evaluating a group dialogue, a dialogue evaluation score is calculated based on an activity score calculated from dialogue data representing the state of the dialogue and the individuality of the participants, and a dialogue experience score calculated from dialogue experience data representing past dialogue experiences between the participants in the dialogue. This makes it possible to predict an evaluation representing the degree of contribution, satisfaction, achievement, etc., taking into account the relationship between the participants.

[0058] In addition, based on the predicted evaluation, it is possible to consider group composition that will increase participants' satisfaction and to intervene in the way the conversation proceeds. For example, if a participant places importance on the number of times they speak in a conversation between first-timers, it may be possible to have a conversation with a high level of satisfaction by intervening to increase the number of times they speak.

[0059] In addition, when engaging in a dialogue with someone with whom you have little conversational experience, you can predict the other person's dialogue evaluation after the fact, and consciously take the necessary steps to improve the participant's dialogue evaluation in the next dialogue, or reflect this in your materials.

[0060] Alternatively, by virtually simulating a dialogue and observing changes in the dialogue evaluations of the participants, it may be possible to devise a strategy for what kind of dialogue should be conducted and what kind of intervention should be made.

[0061] (Additional Note) This specification discloses at least the following dialogue evaluation device, dialogue evaluation method, and program: (Section 1) A dialogue evaluation device for evaluating a dialogue conducted by a group of two or more participants, comprising: an activation score calculation unit that extracts one or more feature quantities as an activation score from the dialogue data; a feature weight calculation unit that extracts dialogue experience data from a past dialogue log, calculates a dialogue experience score by quantifying the dialogue experience between the participants from the dialogue experience data, and calculates a weight of each feature in the activity score from the dialogue experience score; a dialogue evaluation score calculation unit that calculates a dialogue evaluation score by using the activity score and the weight; A dialogue evaluation device comprising: (Section 2) The dialogue data includes personal data including personality traits of participants constituting the group, and the one or more features include features related to utterances and features related to personality traits. 2. The dialogue evaluation device according to claim 1. (Section 3) The feature weight calculation unit calculates the weight using a model that receives the dialogue experience score as an input and outputs the weight. 3. The dialogue evaluation device according to claim 1 or 2. (Section 4) The dialogue evaluation score calculation unit calculates a vector having a plurality of dialogue evaluation factors as a plurality of elements as the dialogue evaluation score. Dialogue evaluation device according to any one of claims 1 to 3. (Section 5) The dialogue evaluation score calculation unit calculates a dialogue evaluation score for each participant in the group, and calculates a statistic of the dialogue evaluation scores of all the participants as a dialogue evaluation score for the entire group. Dialogue evaluation device according to any one of claims 1 to 4. (Section 6) 1. A dialogue evaluation method executed by a dialogue evaluation device for evaluating a dialogue conducted by a group of two or more participants, comprising: extracting one or more feature quantities as an activation score from the dialogue data; extracting dialogue experience data from a past dialogue log, calculating a dialogue experience score by quantifying the dialogue experience between the participants from the dialogue experience data, and calculating a weight of each feature amount in the activity score from the dialogue experience score; calculating a dialogue evaluation score using the liveness score and the weight; The dialogue evaluation method includes: (Section 7) A program for causing a computer to function as each unit in the dialogue evaluation device according to any one of claims 1 to 5.

[0062] Although the present embodiment has been described above, the present invention is not limited to such a specific embodiment, and various modifications and variations are possible within the scope of the gist of the present invention described in the claims. [Explanation of symbols]

[0063] 100 Dialogue evaluation device 101 Activity score calculation unit 102 Dialogue experience data extraction unit 103 Dialogue experience score calculation unit 104 Feature weight calculation unit 105 Dialogue Evaluation Calculation Department 106 Input section 107 Output section 108 Dialogue Log DB 1000 Drive Device 1001 Recording media 1002 Auxiliary storage 1003 Memory device 1004 CPU 1005 Interface device 1006 Display device 1007 Input Device 1008 Output device

Claims

1. A dialogue evaluation device for evaluating a dialogue conducted by a group of two or more participants, comprising: an activity score calculation unit that extracts one or more feature quantities as an activity score from the dialogue data; a feature weight calculation unit that extracts dialogue experience data from a past dialogue log, calculates a dialogue experience score by quantifying the dialogue experience between the participants from the dialogue experience data, and calculates a weight of each feature in the activity score from the dialogue experience score; a dialogue evaluation score calculation unit that calculates a dialogue evaluation score by using the activity score and the weight; A dialogue evaluation device comprising:

2. The dialogue data includes personal data including personality traits of participants constituting the group, and the one or more features include features related to utterances and features related to personality traits. The dialogue evaluation device according to claim 1 .

3. The feature weight calculation unit calculates the weight using a model that receives the dialogue experience score as an input and outputs the weight. The dialogue evaluation device according to claim 1 .

4. The dialogue evaluation score calculation unit calculates a vector having a plurality of dialogue evaluation factors as a plurality of elements as the dialogue evaluation score.

4. The dialogue evaluation device according to claim 1.

5. The dialogue evaluation score calculation unit calculates a dialogue evaluation score for each participant in the group, and calculates a statistic of the dialogue evaluation scores of all the participants as a dialogue evaluation score for the entire group.

5. The dialogue evaluation device according to claim 1.

6. 1. A dialogue evaluation method executed by a dialogue evaluation device for evaluating a dialogue conducted by a group of two or more participants, comprising: extracting one or more features from the dialogue data as an activity score; extracting dialogue experience data from a past dialogue log, calculating a dialogue experience score by quantifying the dialogue experience between the participants from the dialogue experience data, and calculating a weight of each feature amount in the activity score from the dialogue experience score; calculating a dialogue evaluation score using the liveness score and the weight; The dialogue evaluation method includes:

7. A program for causing a computer to function as each unit in the dialogue evaluation device according to any one of claims 1 to 5.

Images