WO2024089858A1

WO2024089858A1 - Presentation device, presentation method, and presentation program

Info

Publication number: WO2024089858A1
Application number: PCT/JP2022/040253
Authority: WO
Inventors: 涼平西條; 巌樹戸嶋; 翔平松尾; 愛中根
Original assignee: 日本電信電話株式会社
Priority date: 2022-10-27
Filing date: 2022-10-27
Publication date: 2024-05-02

Abstract

Provided is a presentation device (10) wherein a storage unit (14) stores a risky expression dictionary (14a) that is information pertaining to the risk of language trouble for each word constituting an interaction text. A calculation unit (15b) refers to the risky expression dictionary (14a) and calculates a risk value representing the degree of risk for each word constituting an interaction text that was input.

Description

Presentation device, presentation method, and presentation program

The present invention relates to a presentation device, a presentation method, and a presentation program.

In verbal communication, ambiguous expressions, overbearing expressions, expressions based on stereotypes, and other expressions that may hinder mutual respect and understanding may be used. Previously, a system has been proposed that instantly transcribes what was said so that users can easily review the expressions used after communication (see Patent Document 1).

JP 2020-140629 A

However, with conventional technology, it is difficult to quantitatively analyze the risks inherent in expressions used in language-mediated communication.

The present invention has been made in consideration of the above, and aims to quantitatively analyze the risks inherent in expressions used in language-mediated communication.

In order to solve the above-mentioned problems and achieve the objective, the presentation device according to the present invention is characterized by having a memory unit that stores information regarding the risk of language trouble for each word that constitutes the dialogue, and a calculation unit that refers to the memory unit and calculates a risk value that represents the magnitude of the risk for each word that constitutes the input dialogue.

The present invention makes it possible to quantitatively analyze the risks inherent in expressions used in language-mediated communication.

FIG. 1 is a schematic diagram illustrating a schematic configuration of a presentation device according to the present embodiment. FIG. 2 is a diagram illustrating an example of the data structure of the risk expression dictionary. FIG. 3 is a diagram for explaining the risk expression dictionary. FIG. 4 is a diagram illustrating an example of the data structure of the relationship DB. FIG. 5 is a diagram illustrating an example of the data configuration of the social attribute DB. FIG. 6 is a diagram illustrating an example of the data configuration of the individual characteristic DB. FIG. 7 is a diagram illustrating an example of the data configuration of the communication history DB. FIG. 8 is a diagram for explaining the process of the calculation unit. FIG. 9 is a diagram showing an example of a screen display of the presentation process result. FIG. 10 is a flowchart showing the procedure of the presentation process. FIG. 11 is a diagram illustrating an example of a computer that executes a presentation program.

Below, one embodiment of the present invention will be described in detail with reference to the drawings. Note that the present invention is not limited to this embodiment. In addition, in the drawings, the same parts are denoted by the same reference numerals.

[Configuration of presentation device]
Fig. 1 is a schematic diagram illustrating a schematic configuration of a presentation device according to the present embodiment. As illustrated in Fig. 1, a presentation device 10 according to the present embodiment is realized by a general-purpose computer such as a personal computer, and includes an input unit 11, an output unit 12, a communication control unit 13, a storage unit 14, and a control unit 15.

The input unit 11 is realized using input devices such as a keyboard, mouse, camera, microphone, etc., and inputs various instruction information such as starting processing to the control unit 15 in response to input operations by an operator. The output unit 12 is realized by a display device such as a liquid crystal display, a printing device such as a printer, etc. For example, the output unit 12 displays the results of the presentation processing described below.

The communication control unit 13 is realized by a NIC (Network Interface Card) or the like, and controls communication between the control unit 15 and external devices via telecommunication lines such as a LAN (Local Area Network) or the Internet. For example, the communication control unit 13 controls communication between the control unit 15 and an external management device that manages various types of information.

The storage unit 14 is realized by a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 14 stores in advance the processing program that operates the presentation device 10 and data used during execution of the processing program, or stores it temporarily each time processing is performed. The storage unit 14 may be configured to communicate with the control unit 15 via the communication control unit 13.

In this embodiment, the storage unit 14 stores a risk expression dictionary 14a. The risk expression dictionary 14a includes information about the risk of language trouble for each word that constitutes the dialogue. Specifically, the risk expression dictionary 14a includes information about one or more risks, such as the part of speech of each word, the number of meanings indicated by each word, or the ambiguity of the meaning indicated by each word. This information is collected prior to or during the presentation process described below, via the input unit 11 or from a management device that manages various information, and is stored in the storage unit 14.

Here, FIG. 2 is a diagram illustrating an example of the data structure of the risk expression dictionary. Also, FIG. 3 is a diagram for explaining the risk expression dictionary. First, as illustrated in FIG. 2, the risk expression dictionary 14a includes information items for each word, such as part of speech, meaning, number of meanings, degree of danger, risk type, etc.

The number of meanings is the number of different meanings for the same word. In addition, the number of homonyms may be added. The risk level is a value set by the user for each word, taking into account, for example, the part of speech, risk type, relevance to business, etc. Alternatively, the risk level may be a value based on a predefined classification table of ambiguous words, etc.

The risk type is, for example, a value ranging from 1 to 7 indicating each class of ambiguity classification. Here, FIG. 3 shows an example of 7 classes of ambiguity classification. For example, a risk type of 1 is set for a word with multiple meanings.

The risk expression dictionary 14a may also include information items that change dynamically during use, such as the importance of each word in a sentence. For example, for words with high risk values calculated in the presentation process described below, if the importance is not high, it may be possible to set the risk value to be calculated as low.

In addition, the risk expression dictionary 14a is not limited to information items for each word, but may be information items for each group of expressions consisting of multiple words. In this case, expressions may include verbal expressions of facial expressions, etc.

The storage unit 14 also stores a relationship DB (Data Base) 14b, a social attribute DB 14c, an individual characteristic DB 14d, a communication history DB 14e, etc. The relationship DB (Data Base) 14b includes information about the relationship between speakers. The social attribute DB 14c includes information that represents the social attributes of the speaker and the interlocutor. The individual characteristic DB 14d includes information that represents the speaker's characteristics related to utterances. The communication history DB 14e also includes dialogue history. This information is collected prior to or during the presentation process described below via the input unit 11 or from a management device that manages various information, and is stored in the storage unit 14.

Here, FIG. 4 is a diagram illustrating an example of the data structure of the relationship DB. As illustrated in FIG. 4, the relationship DB 14b includes, for each user, information items that represent the relationship with a specific other user, such as a relationship score, relationship information, and non-work-related interactions. FIG. 4 illustrates the relationship DB 14b of a user with a user ID of 002.

The relationship score ranges from 0.0 to 1.0, with the closer the score is to 1, the closer the relationship is, and the closer the score is to 0, the more distant the relationship is. For example, since a user with whom you interact frequently is more intimate, the relationship score may be calculated using the frequency of interactions in the communication history DB 14e, which will be described later. Alternatively, the relationship score may be set with reference to the job titles in the social attribute DB 14c, which will be described later, to 0.5 for the same job title, and 0.1 for jobs with greater distance between them, such as between the president and an ordinary employee. Alternatively, the relationship score may be calculated comprehensively with reference to the information items in the communication history DB 14e, social attribute DB 14c, and personal characteristic DB 14d, which will be described later, or may be calculated from compatibility using the company's corporate culture, the person's personality evaluation score, such as the Big 5, etc.

Relationship information indicates the business relationship between a user and a specific other user, such as a relationship with a superior in the same department. Non-work interactions indicate whether or not there is interaction outside of work.

Figure 5 is a diagram illustrating an example of the data structure of the social attribute DB. As illustrated in Figure 5, the social attribute DB 14c includes affiliation, job title, years of employment, etc. as information items that represent the social attributes, i.e., social status, of the speaker and interlocutor. The social attribute DB 14c is set for each conversation topic or situation. Figure 5 illustrates the social attribute DB 14c for business topics.

FIG. 6 is a diagram illustrating an example of the data structure of the personal characteristic DB. As illustrated in FIG. 6, the personal characteristic DB 14d includes, for each user, information items that represent the speaker's characteristics regarding each utterance, such as frequency, degree of agreement with usage status, frequently occurring topics, and risk value evaluation.

The frequency is a value between 0.0 and 1.0 that indicates how often the statement occurs. The consistency of usage is a value between 0.0 and 1.0 that indicates the consistency of the topics in which the statement occurs. The risk value evaluation is a value between 0.0 and 1.0 that indicates the user's self-evaluation of the history of risk values calculated for the word, with a higher value indicating a higher evaluation that the risk value is appropriate.

FIG. 7 is a diagram illustrating an example of the data structure of the communication history DB. As illustrated in FIG. 7, the communication history DB 14e represents a dialogue history, and for each utterance, includes information items such as the utterance ID, user ID, time, utterance content, risk value, topic, dialogue partner ID, and miscommunication record.

The risk value is a risk value previously calculated by the presentation process described below. The topic is a label that indicates an overview of the conversation in which the comment was made, and an appropriate social attribute DB14c is selected based on this. The miscommunication record indicates whether or not there is a record of any trouble resulting from the comment.

In addition, the communication history DB14e may also include non-verbal communication expressions such as facial expressions based on video data, etc.

Returning to the explanation of FIG. 1, the control unit 15 is realized using a CPU (Central Processing Unit) or the like, and executes a processing program stored in memory. As a result, the control unit 15 functions as an acquisition unit 15a, a calculation unit 15b, and a presentation unit 15c, as exemplified in FIG. 1, and executes the presentation process. Note that each of these functional units, or some of them, may be implemented in different hardware. The control unit 15 may also have other functional units.

The acquisition unit 15a acquires the words that make up the dialogue to be processed. Specifically, the acquisition unit 15a accepts input of the dialogue to be processed via the input unit 11 or the communication control unit 13, and performs morphological analysis to extract the words that make up the dialogue.

The acquisition unit 15a may store the words constituting the acquired dialogue in the storage unit 14 prior to the presentation process described below. Alternatively, the acquisition unit 15a may immediately transfer this information to the calculation unit 15b.

The calculation unit 15b refers to the risk expression dictionary 14a of the storage unit 14 and calculates a risk value that indicates the magnitude of risk of each word that constitutes the input dialogue. Here, the risk value indicates an estimate of the magnitude of risk of language trouble, i.e., miscommunication, occurring for each word that appears in the sentence, or for the entire sentence. The calculation unit 15b calculates the risk value using risk variables derived from risk-related information contained in the risk expression dictionary 14a.

Here, the risk variable is derived based on, for example, the part of speech or the risk level of the word. Alternatively, the risk variable is derived based on the number of meanings of the word. Alternatively, the risk variable is derived based on the risk type. Note that risk variables related to context are not used.

The calculation unit 15b may also calculate a risk value for each group of expressions consisting of multiple words, which is a unit of information in the risk expression dictionary 14a. In this case, the expressions may include verbal expressions of facial expressions, etc.

The calculation unit 15b calculates a risk value using the product of multiple pieces of risk-related information that have been weighted in a predetermined manner. Specifically, the calculation unit 15b calculates a risk value r _i of the i-th word in the sentence using the following formula (1).

Here, the risk variable p _i1 based on the part of speech of the word and the risk level takes three values from 1 to 3, with the larger value indicating a higher risk. For example, if the part of speech is a modifier such as an adjective or adverb, it is ambiguous and risky, so it is set to 3, while a demonstrative is set to 2, and the rest are set to 1. Alternatively, the risk level may be applied as is, or a value based on the part of speech and a value of the risk level may be used in combination.

In addition, the risk variable p _i2 based on the number of meanings of a word may be, for example, a value registered in the risk expression dictionary 14 a as is, or may be a value classified into about three levels, similar to the risk variable p _i1 .

Furthermore, the risk variable p _i3 based on the risk type of the word may be set to a value by a user who is familiar with the business situation, for example.

Furthermore, the weighting variables w ₁ to w ₃ and the risk variables p _i1 to p _i3 are adjusted so that the risk value r _i takes a value greater than 0.0.

Here, Fig. 8 is a diagram for explaining the processing of the calculation unit. Fig. 8(1) illustrates risk levels defined in three stages, levels 1 to 3, as a risk variable p _i3 based on the risk type of a word. Fig. 8(2) illustrates a risk variable p _i2 based on the number of meanings of a word.

Fig. 8(3) shows an example of calculating the risk value _ri using the part of speech p _i1 , the number of meanings p _i2 , and the risk level p _i3 of the i-th word. In the example shown in Fig. 8(3), the weight variable 1 (w ₁ ) of the part of speech p _i1 is set to 0, and the risk value _ri is calculated using the number of meanings p _i2 and the risk level p _i3 while suppressing the influence of the part of speech p _i1 .

In the example shown in FIG. 8 (3), in order to prevent the risk value r _i from becoming 0, 1 is added to each of the part of speech p _i1 × weight variable 1 (w ₁ ), the number of meanings p _i2 × weight variable 2 (w ₂ ), and the risk level p _i3 × weight variable 3 (w ₃ ), and then multiplied.

Returning to the description of Fig. 1, the calculation unit 15b may calculate the risk value by using the sum of multiple pieces of risk-related information that have been weighted in a predetermined manner. For example, the calculation unit 15b calculates the risk value r _i of the i-th word in the sentence by the following formula (2).

In this case, each of the risk variables p _i1 to p _i3 is normalized to a value between 0.0 and 1.0, and the weight variables w ₁ to w ₃ are set to values in the range of 0.0 to 1.0. This causes the calculated risk value r _i to also be a value in the range of 0.0 to 1.0, making it easy to compare risk values.

The calculation unit 15b may further calculate the risk value using one or more of information regarding the relationship between the speakers, information representing the social attributes of the speaker and the interlocutor, information representing the characteristics of the speaker, or the dialogue history. For example, the calculation unit 15b calculates the risk value by referring to the relationship DB 14b, the social attribute DB 14c, the personal characteristic DB 14d, or the communication history DB 14e. This makes it possible to calculate a risk value taking into account the context.

In this case, the calculation unit 15b calculates the risk value r _i of the i-th word in the sentence, for example, by the following formula (3).

Here, the risk variables p _i1 to p _i3 are the same as those in formula (1) above. The weight variables w ₁ to w ₇ are set to values in the range of 0.0 to 1.0. The weight variables w ₁ to w ₇ and the risk variables p _i1 to p _i7 are adjusted so that the calculated risk value r _i is a value greater than 0.0.

The risk variable p _i4 based on the relationship between users may be, for example, a value obtained by subtracting the relationship score in the relationship DB 14b from 1, or may be a product of the relationship score subtracted from 1, where 2 is used when there is non-work-related interaction and 1 is used when there is no non-work-related interaction. By calculating in this manner, the risk variable p _i4 becomes a larger value the weaker the relationship is, and the risk value becomes larger.

The risk variable p _i5 based on social attributes may be, for example, the difference between users in years of employment in the social attribute DB 14c, or may be quantified as a larger value for higher-ranking positions and used as the quantified difference in job titles between users in conversation. By calculating in this way, the risk variable p _i5 becomes a larger value the greater the difference in positions within the organization, such as years of employment or job title, and the larger the risk value becomes.

Alternatively, the product or sum of the risk variable p _i4 and the risk variable p _i5 calculated as described above may be substituted for the risk variable p _i4 and the risk variable p _i5 .

The risk variable p _i6 based on the personal characteristics may be, for example, a value obtained by subtracting the degree of agreement of the use situation in the personal characteristics DB 14d from 1, or may be the reciprocal of the degree of agreement of the use situation. Alternatively, the risk variable p _i6 may be the frequency in the personal characteristics DB 14d, or may be the product of the value obtained by subtracting the degree of agreement of the use situation from 1 and the frequency.

The risk variable p _i7 based on the dialogue history may be, for example, a risk value in the communication history DB 14e, or may be the product of the risk value and a value obtained by quantifying a record of miscommunication (2 if there is, 1 if there is no). Alternatively, assuming that the deeper the relationship to the business, the greater the risk of communication discrepancies, the risk variable p _i7 may be set as a value obtained by quantifying the relationship between the topic and the business, and the greater the relationship to the business. For example, confidential information related to corporate strategy is set to 1, general internal information is set to 0.5, and public information related to recreational events after work is set to 0.1, etc.

Alternatively, the calculation unit 15b may calculate the risk value r _i of the i-th word in the sentence using the following formula (4).

Here, the risk variables p _i1 to p _i7 are values normalized to 0.0 to 1.0 similar to the above formula (3), and the weight variables w ₁ to w ₇ are values in the range of 0.0 to 1.0.

The values of the risk variables p _i1 to p _i7 are not limited to those mentioned above. For example, the following values may be applied by additionally registering a predetermined information item in each piece of information (14a to 14e) in the storage unit 14.

For example, the risk variables p _i1 to p _i3 using the risk expression dictionary 14 a may be the degree of occurrence of miscommunication caused by the word, the degree of danger when miscommunication occurs due to the word, the frequency of occurrence of the word in general conversation, etc.

In addition, as the risk variable p _i4 using the relationship DB 14 b or the risk variable p _i5 using the social attribute DB 14 c, the common background between the speakers, the degree of intensity or overlap of the attributes, the proportion of common understanding between the speakers, the human relationships between the speakers, etc. may be applied.

Furthermore, as the risk variable p _i6 using the individual characteristic DB 14d, the speaker's background, attributes, evaluation of risk values calculated for past statements, and the like may be applied.

In addition, as the risk variable p _i7 using the communication history DB14e, words that appear frequently in the current dialogue, words that appear frequently in past dialogues, words that have caused miscommunication in past dialogues, words that have gained common understanding, etc. may be applied.

Furthermore, the method of calculating the risk value is not limited to using each piece of information (14a to 14e) in the storage unit 14 described above. For example, the risk value may be calculated by using the following pieces of information that can be collected during a conversation in combination:

For example, the risk value may be calculated by combining the analysis results of biological signals such as facial expressions, electroencephalograms, and gaze, with the content of statements in the communication history DB14e. In addition, the evaluation value of the medical or objective changes in the physical condition of the person involved may be additionally applied as a risk variable.

Alternatively, the seriousness of a problem that occurs after a conversation may be fed back and reflected in the risk or importance in the risk expression dictionary 14a, or in the risk value in the communication history DB 14e. The seriousness of this problem may be subjectively evaluated by the user and reflected in the risk or importance in the risk expression dictionary 14a. These pieces of information may also be used in combination.

The weight variables _w1 to _w7 are variables that adjust the influence of each risk variable, and are set according to the topic and participants of the conversation that is the subject of the risk value calculation process. For example, if there is a participant who is not good at guessing the meaning of ambiguous statements, the values of the risk expression dictionary 14a will be strongly reflected in the risk value by increasing the values of the weight variables _w1 to _w3 .

In addition, in the case of frequently held conferences where participants have a deep understanding of the background of each other's comments, the weighting variable _w7 for the value in the communication history DB 14e is increased. This allows the value of the risk variable based on frequently appearing expressions or expressions closely related to the business to be strongly reflected in the risk value.

In addition, when there is a specific relationship such as one-to-one dialogue between a superior and a subordinate, by increasing the values of the weighting variables _w4 and _w5 , the values of the risk variable p _i4 based on the relationship DB 14b and the risk variable p _i5 based on the social attribute DB 14c will be strongly reflected in the risk value.

In addition, when the conversation includes statements or expressions unique to individuals, such as a conversation between speakers with specific excellent skills, the values of the weighting variables _w4 and _w6 are increased so that the values of the risk variable p _i4 based on the relationship DB 14b and the risk variable p _i5 based on the personal characteristic DB 14d are more strongly reflected in the risk value.

In addition, the weighting variables _w1 to _w7 may be dynamically adjusted based on a judgment of the quality of consensus reached in the most recent dialogue or discussion, a measurement of satisfaction with past dialogues, a measurement of proficiency with the topic that is the subject of the conversation, etc.

The risk value of an entire sentence or a group of expressions consisting of multiple words (for example, a phrase or clause) can also be calculated using the risk value of each word calculated by the above formulas (1) to (4). In this case, the average value of the risk values r _i calculated for the words contained in each sentence may be used as the risk value of the sentence. In addition, the risk value of the sentence may be determined by calculating a weighted average of the risk values r ₁ to r _N weighted based on the risk level or importance of the risk expression dictionary 14a or a value set in advance. Alternatively, the sum or product of the risk values r _i may be used.

The presentation unit 15c presents the presentation information generated based on the calculated risk value to the user. For example, the presentation unit 15c presents the risk value calculated by the calculation unit 15b, or presentation information such as a message, a notification sound, or a vibration generated based on the risk value, to the user via the output unit 12.

Here, FIG. 9 is a diagram showing an example of a screen display of the results of the presentation process. In the example shown in FIG. 9, information on the calculated risk value is presented on an online conference tool. For example, the presentation unit 15c displays the text of words with high risk values by highlighting them. For example, the presentation unit 15c changes the color of the text of words with high risk values, underlines them, makes the font larger, makes them bold, or highlights them.

Alternatively, the presentation unit 15c displays text with a high risk value in a format that attracts the user's attention, such as by displaying the text in a pop-up. The presentation unit 15c may also display words with a high risk value in a position that is easily noticeable to the user.

In addition, instead of or in addition to displaying text, the presentation unit 15c may present words with a high risk value using audio information or tactile information. For example, the volume of the notification sound for words with a high risk value may be increased, a sound that is likely to make the user feel the need to take action, such as an incorrect answer sound, may be used, vibrations may be increased, or a vibration frequency or pattern that is likely to attract attention may be used.

The presentation unit 15c may also present words with high risk values in the form of advice from a CG or image agent placed on the screen.

In the online conference tool illustrated in FIG. 9, the presentation unit 15c may present the same screen to user 1 and user 2, or different screens. For example, when the presentation unit 15c presents the same screen, both users are more likely to feel that they are on an equal footing, and mutual understanding is promoted. On the other hand, when the presentation unit 15c presents different screens, the promotion of mutual understanding is lessened, but the efficiency of communication is improved by allowing users with better communication skills to more flexibly engage in dialogue.

Furthermore, the presentation unit 15c may adjust the presentation method or cancel the presentation itself. For example, the presentation unit 15c may present in a different format, such as reducing the degree of highlighting or stopping the highlighting for a user who is bothered by the highlighting, or changing the visual information to sound information, in response to a user's operation or in response to the user's characteristics. Furthermore, the way in which the user characteristics are reflected may differ depending on the composition of the conference participants.

[Presentation Processing]
Next, a presentation process by the presentation device 10 according to the present embodiment will be described with reference to Fig. 10. Fig. 10 is a flowchart showing a procedure of the presentation process. The flowchart in Fig. 10 is started, for example, when a user performs an operation input to instruct the start of the process.

First, the acquisition unit 15a acquires the words that make up the dialogue to be processed (step S1). For example, the acquisition unit 15a accepts input of the dialogue to be processed via the input unit 11 or the communication control unit 13, and performs morphological analysis to extract the words that make up the dialogue.

Next, the calculation unit 15b refers to the risk expression dictionary 14a and calculates a risk value that indicates the degree of risk of language trouble for the words that make up the input dialogue (step S2). For example, the calculation unit 15b calculates the risk value using the product of multiple pieces of information that have been weighted in a predetermined manner in the risk expression dictionary 14a. Alternatively, the calculation unit 15b calculates the risk value using the sum of multiple pieces of information that have been weighted in a predetermined manner in the risk expression dictionary 14a.

Furthermore, the calculation unit 15b calculates the risk value using one or more pieces of information from the relationship DB 14b, the social attribute DB 14c, the personal characteristic DB 14d, or the communication history DB 14e.

The presentation unit 15c also presents the presentation information generated based on the calculated risk value to the user (step S3). For example, the presentation unit 15c presents the risk value calculated by the calculation unit 15b to the user via the output unit 12. This completes the series of presentation processes.

[Other embodiments]
In the presentation device 10 of the above embodiment, the risk value based on the ambiguous expression is calculated, but the present invention is not limited to this. For example, the presentation device 10 can calculate a risk value of an expression based on a stereotype instead of or in addition to the risk value based on the ambiguous expression. In this case, the calculation unit 15b calculates the risk value using information on the risk based on the stereotype.

For example, risk variables p _i1 to p _i3 based on the risk expression dictionary 14a may be risk levels set from the perspective of stereotypes, ambiguous expressions, or risk types set from the perspective of stereotypes.

Furthermore, as the risk variable p _i4 using the relationship DB 14b or the risk variable p _i5 using the social attribute DB 14c, a background common to the speakers, the degree of intensity of attributes, the degree of overlap, or the like may be applied.

Furthermore, the background, attributes, and the like of the speaker may be applied as the risk variable p _i6 using the individual characteristic DB 14d.

Specifically, for example, when the degree of overlap of the common backgrounds of the speakers is low, it is assumed that there is a high possibility that the speakers will misinterpret the language, and the values of the risk variables p _i4 and p _i6 are set to be large. In addition, the background of the speaker, such as gender and age, is compared with the background of the parties in past trouble cases, and the risk variable p _i6 is set based on the risk values in the past trouble cases. This enables the calculation unit 15b to calculate a risk value based on a stereotype.

[effect]
As described above, in the presentation device 10 of this embodiment, the storage unit 14 stores the risk expression dictionary 14a, which is information on the risk of language trouble for each word constituting the dialogue. The calculation unit 15b refers to the risk expression dictionary 14a and calculates a risk value indicating the magnitude of risk of each word constituting the input dialogue.

Specifically, the risk expression dictionary 14a stores information related to one or more risks, such as the part of speech of each word, the number of meanings indicated by each word, or the ambiguity of the meaning indicated by each word.

The calculation unit 15b also calculates the risk value using the product of information about multiple risks that have been weighted in a predetermined manner. Alternatively, the calculation unit 15b calculates the risk value using the sum of information about multiple risks that have been weighted in a predetermined manner.

This enables the presentation device 10 to quantitatively analyze the risks inherent in expressions used in language-mediated communication.

The calculation unit 15b further calculates the risk value using one or more of the relationship DB 14b including information on the relationship between speakers, the social attribute DB 14c including information representing the social attributes of the speaker and interlocutor, the personal characteristic DB 14d including information representing the speaker's characteristics related to utterances, and the communication history DB 14e including the dialogue history. This enables the presentation device 10 to calculate the risk value with higher accuracy.

The calculation unit 15b also calculates the risk value using information about risks based on stereotypes. This also makes it possible to calculate a risk value with higher accuracy.

[program]
A program in which the process executed by the presentation device 10 according to the above embodiment is written in a language executable by a computer can also be created. As an embodiment, the presentation device 10 can be implemented by installing a presentation program that executes the above presentation process as package software or online software on a desired computer. For example, the information processing device can function as the presentation device 10 by executing the above presentation program on an information processing device. The information processing device referred to here includes desktop or notebook personal computers. In addition, the information processing device also includes mobile communication terminals such as smartphones, mobile phones, and PHS (Personal Handyphone System), and even slate terminals such as PDA (Personal Digital Assistant). The functions of the presentation device 10 may be implemented on a cloud server.

FIG. 11 is a diagram showing an example of a computer that executes a presentation program. The computer 1000 has, for example, a memory 1010, a CPU 1020, a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. These components are connected by a bus 1080.

The memory 1010 includes a ROM (Read Only Memory) 1011 and a RAM 1012. The ROM 1011 stores a boot program such as a BIOS (Basic Input Output System). The hard disk drive interface 1030 is connected to a hard disk drive 1031. The disk drive interface 1040 is connected to a disk drive 1041. A removable storage medium such as a magnetic disk or optical disk is inserted into the disk drive 1041. The serial port interface 1050 is connected to a mouse 1051 and a keyboard 1052, for example. The video adapter 1060 is connected to a display 1061, for example.

Here, the hard disk drive 1031 stores, for example, an OS 1091, an application program 1092, a program module 1093, and program data 1094. Each piece of information described in the above embodiment is stored, for example, in the hard disk drive 1031 or memory 1010.

The presentation program is stored in the hard disk drive 1031, for example, as a program module 1093 in which instructions to be executed by the computer 1000 are written. Specifically, the program module 1093 in which each process executed by the presentation device 10 described in the above embodiment is written is stored in the hard disk drive 1031.

In addition, data used for information processing by the presentation program is stored as program data 1094, for example, in the hard disk drive 1031. Then, the CPU 1020 reads the program module 1093 and program data 1094 stored in the hard disk drive 1031 into the RAM 1012 as necessary, and executes each of the above-mentioned procedures.

The program module 1093 and program data 1094 related to the presentation program are not limited to being stored in the hard disk drive 1031, but may be stored in a removable storage medium, for example, and read by the CPU 1020 via the disk drive 1041 or the like. Alternatively, the program module 1093 and program data 1094 related to the presentation program may be stored in another computer connected via a network, such as a LAN or WAN (Wide Area Network), and read by the CPU 1020 via the network interface 1070.

The above describes an embodiment of the invention made by the inventor, but the present invention is not limited to the description and drawings that form part of the disclosure of the present invention according to this embodiment. In other words, other embodiments, examples, operational techniques, etc. made by those skilled in the art based on this embodiment are all included in the scope of the present invention.

REFERENCE SIGNS LIST 10 Presentation device 11 Input unit 12 Output unit 13 Communication control unit 14 Storage unit 14a Risk expression dictionary 14b Relationship DB
14c Social attribute DB
14d Personal characteristics DB
14e Communication history DB
15 Control unit

15a Acquisition unit

15b Calculation unit 15c Presentation unit

Claims

A storage unit that stores information regarding a risk of language trouble for each word that constitutes a dialogue;
a calculation unit that refers to the storage unit and calculates a risk value representing the magnitude of the risk of each word constituting the input dialogue;
A presentation device comprising:
The presentation device according to claim 1, characterized in that the storage unit stores information related to the risk, which is one or more of the part of speech of each word, the number of meanings indicated by each word, and the ambiguity of the meaning indicated by each word.
The presentation device according to claim 1, characterized in that the calculation unit calculates the risk value using a product of multiple pieces of information related to the risks that have been weighted in a predetermined manner.
The presentation device according to claim 1, characterized in that the calculation unit calculates the risk value using the sum of information related to multiple risks that have been weighted in a predetermined manner.
The presentation device according to claim 1, characterized in that the calculation unit further calculates the risk value using one or more of the following: information on the relationship between speakers, information representing the social attributes of the speaker and interlocutor, information representing the speaker's characteristics related to the utterance, or dialogue history.
The presentation device according to claim 1, characterized in that the calculation unit calculates the risk value using information about the risk based on stereotypes.
A presentation method executed by a presentation device, comprising:
The presentation device has a storage unit that stores information regarding a risk of language trouble for each word constituting a dialogue,
A presentation method comprising the step of: referring to the storage unit and calculating a risk value representing the magnitude of risk of each word constituting the input dialogue.
A presentation program for causing a computer to function as a presentation device according to any one of claims 1 to 6.