JP7436083B1 - Trust relationship estimation device, trust relationship estimation method, and computer program - Google Patents

Abstract

[Problem] Estimate the strength of the relationship of trust built between instructors and students. [Solution] A trust relationship estimation device 1 that estimates a trust relationship built between a lecturer and students, includes an information acquisition unit 11 that acquires transmissions by the lecturer and students, and an information acquisition unit 11 that refers to transmissions and If it is detected that a student has made alternating messages about the same topic at least three times, it is assumed that a relationship of trust has been established between the instructor and the student through the communication, and and a trust relationship analysis unit 12 that stores information in the storage unit 50. [Selection diagram] Figure 1

Description

The present invention relates to a trust relationship estimation device, a trust relationship estimation method, and a computer program.

It is common practice for instructors to provide training to participants. Instructors and students build a relationship of trust through communication. The stronger this relationship of trust becomes, the more students will be able to understand the instructor's personality and teaching methods, and be able to fully absorb the instructor's guidance. Not accepted. In addition, the stronger the relationship of trust the instructor has built with the student, the more effective the instructor will be able to provide guidance tailored to the student, and the more effective the training will be for the student. In this way, even if the training content, instructor, and participants are the same, the effectiveness of the training will vary greatly depending on the state of trust between the instructor and the students. In other words, in order to measure and estimate the essential training effects, it is essential to consider the relationship of trust, and there is a need for technology to estimate the strength of the relationship of trust built between instructors and trainees. There is.

Patent Document 1 describes an information processing device that analyzes trends in mutual utterances among a plurality of students and presents a utterance map showing a community of students. Patent Document 2 discloses an inter-user relationship calculation device that calculates and outputs the relationship between users based on the number of transmitted e-mails, size, etc. received from the e-mail analysis unit 110. Patent Document 3 describes a personal network information display device that weights the strength of association between people by using metadata such as a schedule. Patent Document 4 describes a human relationship estimation device that estimates the human relationship between users based on how often each user communicates and in which area they are present at the same time.

JP2022-116607 JP2006-260099 JP2007-193685 JP2010-165097

However, none of these documents can be said to be able to appropriately estimate the relationship of trust necessary to ensure thorough instruction in the teacher-pupil relationship between the instructor who conducts the training and the trainees.

Therefore, an object of the present invention is to provide a trust relationship estimating device that can estimate the strength of the trust relationship established between an instructor and students.

In order to achieve the above object, a trust relationship estimating device according to one aspect of the present invention is a trust relationship estimating device that estimates a trust relationship built between an instructor and a student. an information acquisition unit that acquires transmissions made by a person; and a trust relationship analysis unit that estimates that the trust relationship has been established between the lecturer and the student and stores it in a storage unit as information regarding the trust relationship.

The trust relationship analysis unit acquires the transmissions by the lecturer and the students as voice data or text data, and analyzes the content of the transmissions, thereby determining whether the transmissions by the instructor and the students are related to the same topic. It may be assumed that it is a certain thing.

The information acquisition unit acquires texts sent by the lecturer and the student through a terminal connected to the trust relationship estimation device, and the trust relationship analysis unit acquires texts that have been linked and inputted in advance. It may be assumed that the outgoing calls are related to the same topic.

The storage unit stores the technical level of the lecturer and the technical level of the student regarding a predetermined technical field, and the trust relationship analysis unit stores the technical level of the student in which the event occurred, the technical level of the student, and The degree of the trust relationship that is estimated to have increased between the instructor and the student in the event is varied depending on the technical level of the instructor or the difference between the technical level of the student and the instructor. You can also use it as

The storage unit stores information on trainings in which the instructor and the students participate, and the trust relationship analysis unit refers to the storage unit to identify identification information of the training in which the event occurred. However, the degree of trust that is estimated to have increased between the instructor and the trainees in the event may be varied depending on the number of people participating in the training at the same time.

The trust relationship analysis unit decreases the degree of the trust relationship between the instructor and the student as time passes from the event in which the trust relationship between the instructor and the student was established. It may also be possible to do so.

The information regarding the trust relationship stored in the storage unit may be issued for each student.

In order to achieve the above object, a trust relationship estimation method according to another aspect of the present invention is a trust relationship estimation method for estimating a trust relationship built between an instructor and a student. an information acquisition step of acquiring a transmission by a person; and when an event is detected in which the transmission is made alternately at least three times by the lecturer and the student regarding the same topic by referring to the transmission, the information is obtained through the transmission; A trust relationship analysis step of estimating that the trust relationship has been established between the lecturer and the student and storing it in a storage unit as information regarding the trust relationship is executed by a computer.

In order to achieve the above object, a computer program according to still another aspect of the present invention is a computer program for estimating a trust relationship built between a lecturer and a student, and the computer program estimates a trust relationship built between a lecturer and a student. an information acquisition step of acquiring a call made by a student, and when an event is detected in which the call is made alternately at least three times by the lecturer and the student regarding the same topic by referring to the call; a trust relationship analysis step of estimating that the trust relationship has been established between the lecturer and the student through the lecture and storing the trust relationship information in the storage unit as information regarding the trust relationship.

Note that the computer program can be provided by downloading via a network such as the Internet, or can be provided by being recorded on various computer-readable recording media.

According to the present invention, it is possible to estimate the strength of the relationship of trust established between the lecturer and the students.

FIG. 2 is a functional block diagram showing the functions of the trust relationship estimating device, the trust relationship estimating device, and each component connected through a network according to the first embodiment of the present invention. Examples of data tables stored in the trust relationship estimation device include (a) a student table that stores information regarding students; (b) a student level table that stores information regarding the technical level of students; (c) A lecturer table that stores information regarding instructors, and (d) an instructor level table that stores information regarding instructors' technical levels. Diagrams showing examples of data tables stored in the trust relationship estimating device, including (a) a training menu table that stores information regarding training menus, and (b) a training table that stores information regarding training to be conducted. It is. Examples of data tables stored in the trust relationship estimating device include (a) a trust relationship event table that stores information on events that create a trust relationship; (b) a trust relationship event table that stores information about events that create a trust relationship; FIG. 3 is a diagram showing a trust relationship index table in which trust relationship indexes indicating trust relationships are stored. This is an example of a screen displayed on a terminal connected to the trust relationship estimation device. It is a sequence diagram which shows the flow of processing by the trust relationship estimation device, and is a diagram showing (a) a first example and (b) a second example. It is a sequence diagram which shows the flow of processing by the trust relationship estimating device, and is a diagram showing (a) a third example and (b) a fourth example.

DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of a trust relationship estimation device according to the present invention will be described with reference to the drawings. The trust relationship estimating device is a device that refers to information exchanged between the instructor and the students and estimates the trust relationship built between the instructor and the students. The trust relationship estimating device displays information regarding the trust relationship on an appropriate terminal connected via a network or the like.

As shown in FIG. 1, the trust relationship estimation device 1 is configured to be able to communicate with a plurality of terminals 2 via the network NW. The trust relationship estimation device 1 is, for example, a server. Although the mutual communication between the trust relationship estimating device 1 and each terminal 2 is wireless in this embodiment, some or all of the connections may be wired. Further, although there are two terminals 2 in FIG. 1, there may be any number of terminals. The trust relationship estimation system 100 may be configured by the trust relationship estimation device 1 and one or more terminals 2.

●Terminal 2
The terminal 2 is a terminal that accepts input of information regarding the instructor who provides the training and the trainees who receive the training. The instructor terminal 2a and the student terminal 2b are an example of the terminal 2, and when explaining the instructor terminal 2a and the student terminal 2b without distinguishing them, they may be collectively referred to simply as the terminal 2. In the following description, as an example, the instructor terminal 2a is a terminal operated by an instructor who holds training. The student terminal 2b will be described as a terminal operated by a participant in the training. The functions of the instructor terminal 2a and student terminal 2b are explained separately for convenience, and training can be taken from the instructor terminal 2a, and training and guidance can be performed from the student terminal 2b.

The terminal 2 is, for example, a smart phone, a tablet terminal, or a computer. Further, the terminal 2 may be a device worn by a wearer, such as so-called smart glasses, a headset, or a smart watch. The terminal 2 includes an input section 21 and an output section 22 using a CPU (Central Processing Unit), a computer program executed by the CPU, a RAM (Random Access Memory) and a ROM (Read Only Memory) that store the computer program and predetermined data. and a communication processing unit 23 constitute a functional block. The input units 21a and 21b, the output units 22a and 22b, and the communication processing units 23a and 23b are examples of the input unit 21, the output unit 22, and the communication processing unit 23, respectively, and when described without distinguishing between them, These may be collectively simply referred to as the input section 21, output section 22, and communication processing section 23, respectively.

The input unit 21 is configured to input data, and may be realized by a touch panel or the like, or may include physical keys such as a keyboard. In addition, the input unit 21 includes a microphone that captures audio and a camera that captures still images or moving images. The instructor terminal 2a receives, for example, input from the instructor regarding instructions for students, etc. in the form of text data, audio, video, or the like. The student terminal 2b receives, for example, messages to the instructor, reactions to instructions from the instructor, etc. in the form of text data, audio, video, or the like.

Furthermore, the input unit 21 may accept more direct input of information regarding trust relationships. For example, the input unit 21a may receive a record of an event in which a relationship of trust with a student has been established by an instructor. The input unit 21a may also receive input from the lecturer indicating that a relationship of trust with the student has been established, evaluation information regarding the student's responses, and the like. The input unit 21b of the student terminal 2b may receive evaluation information regarding the lecturer's answers, etc. from the student. Inputting the evaluation information may be performed by displaying options on the screen of the terminal 2, and selectively input by the student or instructor. For example, this information is not transmitted to other terminals 2, but is referred to by the trust relationship estimating device 1 in estimating the trust relationship.

The input unit 21 may include an appropriate sensor that detects information about the person carrying the terminal. Further, the input unit 21 may acquire position information. The input unit 21 may have a beacon function to obtain information about other nearby terminals.

The output unit 22 is configured to output information related to training, etc., and is realized by, for example, a display that outputs video and a speaker that outputs audio. The display may constitute a touch panel display together with the touch panel of the input section 21. For example, the output unit 22 displays a video of the lecturer or the student and reproduces the voice of the lecturer or the student.

The instructor and students can remotely talk to each other and exchange text data using the input units 21a, 21b and output units 22a, 22b of each terminal 2a, 2b.

In addition, instead of the mode in which each person uses different terminals 2a and 2b, a single terminal 2 may be used to record or collect sound from both the lecturer and the students. In this case, the trust relationship analysis unit 12 may perform processing to separate the data acquired by one input unit into transmissions by the lecturer and transmissions by the students. Furthermore, one terminal 2 may be provided with a plurality of input units for respectively acquiring calls from the instructor and students.

The communication processing unit 23 is a processing unit that is capable of transmitting and receiving data according to a predetermined protocol with the trust relationship estimation device 1 via a network NW such as the Internet, and is implemented by an application, a web browser, etc. Ru. The communication processing unit 23a of the instructor terminal 2a transmits the instructor's audio and video input to the input unit 21a of the instructor terminal 2a to the student terminal 2b, and also transmits the student's audio and video input to the student terminal 2b. receive. The communication processing unit 23b of the student terminal 2b transmits the information input to the input unit 21b of the student terminal 2b to the instructor terminal 2a, and receives the student's audio and video input to the instructor terminal 2a.

Further, the communication processing unit 23 may receive an input form or the like that allows information to be input as a call from the trust relationship estimation device 1 or an appropriate external device. Further, the communication processing unit 23 may transmit the information input in the input form to the trust relationship estimation device 1 or another terminal 2.

Further, the communication processing unit 23 transmits the transmissions by the instructor and the students acquired by the input unit 21 to the trust relationship estimation device 1. That is, for example, the communication processing unit 23a transmits the instructor's transmission acquired by the input unit 21a of the instructor terminal 2a to the trust relationship estimation device 1 together with the identification information of the instructor terminal 2a. The communication processing unit 23a may transmit the identification information of the student terminal 2b that is permitted to receive the transmission to the trust relationship estimation device 1 together with the transmission from the instructor. The communication processing unit 23b transmits the instructor's transmission acquired by the input unit 21b of the student terminal 2b to the trust relationship estimation device 1 together with the identification information of the instructor terminal 2a. The communication processing unit 23b may transmit the identification information of the lecturer terminal 2a that received the call from the student to the trust relationship estimation device 1 along with the call from the student. As a result, the trust relationship estimation device 1 obtains the identification information and the content of the transmission between the lecturer and the student who have made the transmission to each other.

●Trust relationship estimation device 1
The trust relationship estimation device 1 includes a CPU (Central Processing Unit), a computer program executed by the CPU, a RAM (Random Access Memory) and a ROM (Read Only Memory) that store the computer program and predetermined data, as shown in FIG. As such, each functional block mainly includes a storage section 50, an information acquisition section 11, a trust relationship analysis section 12, and a communication processing section 13.

Note that the functional units of the trust relationship estimation device 1 may be realized by a plurality of hardware configurations, or may be partially or entirely configured by cloud computing. Furthermore, some of the functional units included in the trust relationship estimation device 1 may be included in the instructor terminal 2a or the student terminal 2b.

The storage unit 50 is a functional unit that stores information regarding instructors and students involved in training. The storage unit 50 includes, for example, a student information database (hereinafter referred to as "DB") 51 that stores information regarding students, an instructor information DB 52 that stores information regarding instructors, and a lecturer information DB 52 that stores information regarding training. The training information DB 53 stores training information DB 53, and a trust relationship information DB 54 stores information regarding trust relationships established between instructors and students.

An example of a table included in each DB of the storage unit 50 will be explained using FIGS. 2 to 4. Note that the table configuration is just one example, and some of the tables described below may be integrated into one table, or one table may be composed of a plurality of tables. Furthermore, although a so-called relational database in a tabular format is described as an example in this specification, the technical scope of the present invention is not limited to this, and other formats such as a graph database may be used. With a graph database storage configuration, information can be stored accurately and concisely even if the same person is a participant in one training course and a lecturer in another, and it is possible to store information accurately and concisely. A mesh-like relational structure such as network services (SNS) can be easily managed.

FIG. 2A is an example of the student table T1 included in the student information DB 51. The student table T1 stores, for example, names, affiliated companies, contact information, etc. in association with student identification information. Further, FIG. 2(b) is an example of a student level table T2 that is included in the student information DB 51 and stores the technical levels of students. In the student level table T2, for example, the technical level of the student is stored for each technical field in association with the student's identification information.

FIG. 2(c) is an example of the lecturer table T3 included in the lecturer information DB 52. The instructor table T3 stores, for example, the instructor's name, contact information, training menus that the instructor can teach, etc. in association with the instructor's identification information. FIG. 2(d) is an example of a lecturer level table T4 that is included in the lecturer information DB 52 and stores the technical levels of lecturers. In the instructor level table T4, for example, the technical level of the instructor is stored for each technical field in association with the instructor's identification information.

FIG. 3A is an example of the training menu information table T5 included in the training information DB 53. The training menu is information indicating the nature of the training itself, such as the technical field of the training and the number of days required. The training menu information table T5 stores, for example, training menu identification information, technical field, technical level, number of training days, etc. in association with each other.

FIG. 3(b) is an example of a training event information table T6 that stores information regarding the holding of individual training sessions conducted according to a certain training menu. The training event information table T6 stores the identification information of the training menu, the identification information of the instructor in charge, the implementation schedule, the number of participants, etc. in association with each other. As for the number of participants, the planned number of participants may be stored, or the actual value may be stored after the training is held. Further, the number of participants may be corrected to the actual value after the training is held, after the planned number of participants is stored. If the training is held over multiple days or multiple hours, the actual value of the number of participants for each day or hour may be stored. Further, in the training event information table T6, identification information of the participants who participated is stored in association with training identification information.

FIG. 4(a) is an example of a table stored in the trust relationship information DB 54, and is a trust relationship event table T7 that accumulates and stores events related to building trust relationships that occur between students and instructors. This is an example. The trust relationship event table T7 includes, for example, identification information of the student and instructor with whom a trust relationship has been established, the time of occurrence of the event, identification information of the training held where the event occurred, information from the student to the instructor, or from the instructor to the student. The mode of the outgoing call route that was sent out is stored. Examples of the transmission route include information such as online lectures, daily reports, emails, chats, and face-to-face lectures. The mode of the transmission route also includes information as to whether the transmission is from a student or an instructor.

The trust relationship event table T7 stores a plurality of transmissions related to the same topic, integrated as one event. In the following description, the caller who first made a call regarding a certain topic will be referred to as a first caller, and the caller who responded to the first caller regarding the topic will be referred to as a second caller. Both the first caller and the second caller can be both the instructor and the student.

For example, in event No. 001, student S01 asks a question as the first caller in an online lecture (first route), and lecturer T01 answers the question as the second caller in the same lecture. (Second route), and immediately after that, student S01 of the first caller reacts (Third route). Furthermore, event No. 002 is an example in which, in the operation of inputting a daily report on the day of training, the transmission of text data input on the daily report is integrated and stored as one event. Event No. 003 is an example in which the lecturer answers a student's question sent during an online lecture by email after the lecture, and the student sends a response via chat on another day. In the present invention, in this way, the exchanges that took place on the same topic are estimated and stored as one event in which a trust relationship is established. The process of estimating that the topics of the calls are the same will be described later.
Although up to the third route is shown in the figure, four or more detected routes may be stored. The reason for detecting the establishment of a trust relationship three times or more in the present invention will be described separately later.

FIG. 4(b) is an example of a table stored in the trust relationship information DB 54, and is a trust relationship index table T8 in which a trust relationship index indicating the trust relationship established between the student and the instructor is stored. This is an example. The trust relationship index table T8 stores the identification information of students and instructors, and the trust relationship index between the students and instructors in association with each other. The trust relationship index table T8 may be associated with the event number of the trust relationship event table T7 that contributes to the trust relationship between the student and the instructor.

Return to Figure 1. The information acquisition unit 11 is a functional unit that acquires messages from instructors and students. The information acquisition unit 11 acquires input information from the input unit 21 of the terminal 2 . The input information is, for example, information sent to another terminal 2, and may be audio, video, or text data. Text data includes data entered in input forms such as emails, chats, web-based surveys, and daily reports, as well as tasks shared with task management tools such as JIRA (registered trademark), comments regarding the tasks, and GitHub ( It may be a program code shared by a software development platform such as (registered trademark), or a pull request or comment for the program code. For example, the video includes the caller's reactions, such as nodding, tilting his head, and facial expressions. Further, the input information may be information selectively input from the terminal 2. The selectively input information may be, for example, pictograms, pre-registered illustrations, or so-called stamps.

In addition to the information transmitted to other terminals 2 as described above, the input information may include information acquired by trust relationship estimation device 1 and not transmitted to other terminals 2. This information is, for example, evaluation information for the student input from the instructor terminal 2a or evaluation information for the instructor input from the student terminal 2b. As the evaluation information, for example, the instructor or the student inputs information indicating that the relationship of trust has improved or decreased, and the degree thereof. The evaluation information may be input by selecting an icon displayed on the screen of the terminal 2 or by inputting a numerical value. According to this configuration, the actual beliefs of the instructor or the student can be more accurately reflected in the estimation result of the trust relationship.

The trust relationship analysis unit 12 is a functional unit that estimates the trust relationship established between the lecturer and the students.

The trust relationship analysis unit 12 analyzes the information acquired by the information acquisition unit 11 and identifies the identification information of the instructor or student who sent the information.
For example, the trust relationship analysis unit 12 may refer to the identification information of the terminal 2 that received the input and extract the identification information of the instructor or student who made the call. For example, in a mode such as an online lecture where each person transmits from one terminal 2, the identification information of the lecturer or the student can be specified by this method. In addition, even when sending and receiving text data such as web-based input forms such as chats, emails, and daily reports, each person transmits from a terminal 2 linked to his or her own identification information, so the instructor or student can be identified. Can identify information.

In the case where the voices of multiple people are collected by one terminal 2, the trust relationship analysis unit 12 may identify the lecturer or the student by analyzing the voices included in the voice data. In this case, for example, the voiceprint data of the instructor and students may be stored in advance in the storage unit 50 or an external device, and the instructor or student may be identified by comparing the voiceprint data with the voiceprint data.

Furthermore, the trust relationship analysis unit 12 refers to the information acquired by the information acquisition unit 11 and identifies the terminal 2 that received each call. Through this process, the trust relationship analysis unit 12 can estimate that the instructor and the students are communicating with each other.

Further, the trust relationship analysis unit 12 detects that the lecturer and the student, who are communicating with each other, are alternately communicating about the same topic.
The trust relationship analysis unit 12 acquires the messages sent by the instructor and students as voice data or text data, analyzes the content of the messages, and estimates that the messages made by the instructor and students are related to the same topic. Good too.

For example, as one mode of analysis, the trust relationship analysis unit 12 refers to the information acquired by the information acquisition unit 11 and determines whether the transmissions are on the same topic based on information included in the transmission content. Good too. For example, in an online lecture, the trust relationship analysis unit 12 may refer to the time information of the call and estimate that if they have called each other within a predetermined time, they are talking about the same topic. . Furthermore, in a daily report format input form, it may be assumed that transmissions linked on the same day are related to the same topic. In addition, it is not limited to the date, but also calls that are linked and entered in advance, such as posts made by selecting the "Reply" button to a specific post on the chat screen, or posts that are posted in a threaded manner. It may be assumed that the posted messages are related to the same topic. Furthermore, in the case of e-mail as well, an outgoing message sent by a "reply" operation in e-mail software may be presumed to have the same topic as the e-mail from which the e-mail was sent. For example, the trust relationship analysis unit 12 may use a different method for determining whether or not the messages are on the same topic, depending on the mode of the message.

The trust relationship analysis unit 12 may employ an appropriate machine learning technique to analyze whether the topics are the same or not. For example, the trust relationship analysis unit 12 performs audio analysis of the audio data to identify the content of the question in the utterance section uttered by the student, and also identifies the content of the answer in the utterance section uttered by the instructor following the utterance section. do. Furthermore, the trust relationship analysis unit 12 may implement a neural network that includes the contents of video data, audio data, or text data, transmission mode, and data transmission time as input data of the input layer. According to such a configuration, even if the messages are sent in different ways, it can be presumed that they are communicating about the same topic. For example, the event number in the trust relationship event table T7 in FIG. 4(a). Even a case like 003 can be detected as an event in which a trust relationship has been established.

According to such a configuration, the trust relationship analysis unit 12 can calculate the number of times the lecturer and the student have alternately made messages regarding the same topic. When the trust relationship analysis unit 12 detects that transmissions have been made alternately at least three times regarding the same topic, it estimates that a trust relationship has been established between the instructor and the student through the transmissions.

A relationship of trust between instructors and students is built through communication during instruction and instruction. Since it is communication, a trust relationship is not built only by the first caller talking unilaterally (the "first route" in the trust relationship event table T7 in FIG. 4(a)), but also by at least the second caller A reaction (corresponding to the "second route" in the trust relationship event table T7 in FIG. 4(a). Note that "the mere fact of acceptance or viewing" is also included in the reaction) is a necessary condition. However, from the perspective of creating guidance and a relationship of trust, rather than just friendship, two mutual communications are not a sufficient condition for the establishment of such a relationship. For example, after a lecturer provides instruction to a student as the first caller, and the student responds as the second caller, the instructor may further ask the student, ``I hope that the instruction I gave was understood as expected.'' This is because the guidance is established by further confirming whether the request was received or received (the "third route" in the trust relationship event table T7 in FIG. 4(a)).

In other words, communication in teaching activities is a type of "feedback." Feedback is known in control engineering as ``applying an output obtained based on a certain input to the next input.'' In other words, if the definition of feedback in control engineering is applied to instructional activities, the first caller makes a further call after the second caller makes a call, and this call is input to the second caller, creating a feedback loop. It can be said that this holds true. According to the trust relationship analysis unit 12, it is estimated that a trust relationship between the instructor and the student will be built through the establishment of this feedback loop, and by detecting that alternate transmissions have been made three or more times, It is possible to appropriately estimate whether or not a trusting relationship has been established.

Furthermore, when a student sends a question to the instructor as the first caller, they do not only receive an answer from the instructor as the second caller, but also receive the answer and explain their understanding to the instructor. By expressing their understanding, for example, by rephrasing their understanding in their own words and conveying it to the instructor, both the instructor and the students realize that mutual guidance has been established, and a relationship of trust is formed.

The trust relationship analysis unit 12 may refer to the information acquired by the information acquisition unit 11 and estimate the degree of the established trust relationship. The degree of trust relationship is expressed, for example, by a trust relationship index, and the calculated trust relationship index is added to the previous trust relationship index and accumulated.

The degree of trust relationship is estimated, for example, from the second caller's response in the second route or the first caller's reaction in the third route. For example, if the first caller asks a question in the first route and the second caller answers in the second route, the first caller may respond in the third route with a positive response, that is, a response that seems to be satisfied. If you do so, it may be assumed that a greater trust relationship has been built than if you showed a negative reaction, that is, a reaction in which you seemed unconvinced. Furthermore, even if only information indicating that the message has been read rather than a specific message is transmitted in the third route, a trust relationship may be established to some extent. In this case, the trust relationship index to be increased may be smaller than when a specific message is sent.

The trust relationship analysis unit 12 uses appropriate artificial intelligence technology to analyze and estimate the strength of the logical connection between messages that are presumed to be on the same topic, and if the logical connection is weak, the trust relationship analysis unit 12 estimates the strength of the logical connection between the messages that are presumed to be on the same topic. The relationship index may be made smaller. This is because it is difficult to build a relationship of trust in conversations with weak logical connections, that is, conversations where the meanings do not mesh.

The trust relationship analysis unit 12 may vary the degree of trust relationship that is built depending on the number of times transmissions have been made alternately about the same topic. For example, the trust relationship analysis unit 12 may increase the degree of trust relationship as the number of calls increases.

Note that the degree of trust that is estimated to have been established due to a certain event may vary depending on the skill level of the student, the skill level of the instructor, or the difference between the skill levels of the student and the instructor. For example, in a situation where a student reacts negatively, if the student's technical level is sufficiently low, there is a high possibility that a relationship of trust has not been built, but if the student's technical level is above a certain level, then , or if the difference with the instructor's technical level is within a predetermined range, even an outwardly negative reaction may turn into a constructive dialogue and a relationship of trust may increase. Therefore, when a student gives a negative reaction, the trust relationship analysis unit 12 determines whether the relationship of trust increases as the skill level of the student increases or as the difference in skill level between the student and the instructor decreases. It may be assumed that Note that, since the technical levels of students and instructors differ depending on the technical field, the trust relationship analysis unit 12 may refer to the technical level in the technical field of the training in which the event of alternate transmission occurred. The trust relationship analysis unit 12 may also analyze the content of the transmission and estimate the technical field.

Furthermore, the degree of trust that is estimated to have been established due to a certain event may differ depending on the trust that was established before the event. If a strong relationship of trust has been built before a certain event, there is a high probability that the person will react differently than if there was relatively little trust. For example, it is thought that people with whom they have built a strong relationship of trust will react more honestly than those with whom they do not have a relationship of trust. That is, for example, in a relationship where a high level of trust has been established, even if the reaction is negative, it may be assumed that a high level of trust has been established compared to a relationship where the level of trust is relatively small.

In addition, the trust relationship analysis unit 12 refers to the training information DB 53, and if an event occurs in which a trust relationship is established between a specific instructor and a student, the trust relationship analysis unit 12 determines whether the participant participated in the training in which the event occurred. Information about another student may also be extracted. In this case, the trust relationship analysis unit 12 may also increase the trust relationship between the other student and the instructor. This is because other students may strengthen their trust in the instructor by indirectly listening to the instructor's instructions. Note that the trust relationship that increases for another student may be smaller than the trust relationship that increases for a student who is receiving direct instruction from the instructor. Further, depending on the number of people participating in the training at the same time, the trust relationship index that increases for the different trainees may be made different. In other words, the smaller the number of people participating at the same time, the larger the increasing trust relationship index may be. This is because it is thought that the smaller the number of participants, the easier it will be for other students to hear instructions, which will contribute to increasing trust.

When a lecturer gives advice to a group of trainees all at once, the trust relationship analysis unit 12 refers to the training information DB 53 to extract training information, and extracts training information according to the number of people participating in the training at the same time. Then, the degree of trust relationship building in the event may be varied and added to the trust relationship index. For example, it may be estimated that the larger the number of participants in the training, the lower the degree of trust built in the event, and the smaller the number of participants, the higher the degree of trust built. More specifically, the increasing trust relationship index may be calculated by dividing the index when one person receives guidance by the number of participants in the training. For example, it is thought that the more people have a conversation in an environment with fewer people, the more seriously the other party's message will be taken, and the relationship of trust will become stronger. According to this configuration, it is possible to estimate the relationship of trust based on the actual situation. Become.

The trust relationship analysis unit 12 accumulates a trust relationship index as information regarding the trust relationship between each instructor and student. Based on the estimated trust relationship, the trust relationship analysis unit 12 stores information regarding the trust relationship, that is, for example, a trust relationship index, in the trust relationship index table T8 of the storage unit 50.

The trust relationship analysis unit 12 may reduce the trust relationship between the lecturer and the students based on the elapsed time from the event in which the trust relationship was established. That is, the trust relationship analysis unit 12 may reduce the trust relationship as time passes from the event. This is because the relationship of trust diminishes over time after the period of interaction. According to this configuration, it is possible to estimate a trust relationship closer to the actual situation.

The trust relationship analysis unit 12 may reduce the trust relationship between the instructor and the students depending on the communication status between the instructor and the students. For example, if the other party reacts negatively to a transmission from one party, the trust relationship index between the lecturer and the student may be decreased. Note that the degree to which the trust relationship index is decreased may vary depending on the trust relationship index before the event. For example, if the previous trust relationship index is large, the decreasing trust relationship index may be made small. If a relationship of trust has been built up relatively well, a single reaction will not destroy the trust, and it is possible that the person can express his or her honest opinion precisely because he/she trusts the other person. If there is a misunderstanding, it is likely that it can be corrected quickly. In this respect, this configuration makes it possible to estimate trust relationships that match human senses.

The degree of trust that can be increased or decreased is not limited to rule-based estimation processing, but can also be determined by, for example, the responses and reactions described above, the number of calls, the technical level of the student, the technical level of the instructor, or the relationship between the student and instructor. It may be estimated by an appropriate artificial intelligence technique that refers to a neural network that uses the difference in technical level, the trust relationship index before the event, the number of participants in training, etc. as input layers.

The communication processing unit 13 is a processing unit that is capable of transmitting and receiving data according to a predetermined protocol with the trust relationship estimation device 1 via a network NW such as the Internet, and is implemented by an application, a web browser, etc. Ru. In particular, the communication processing unit 13 receives calls from the instructor and students from the terminal 2. Further, the communication processing unit 13 receives calls made by the lecturer from the lecturer terminal 2a, and the communication processing unit 13 receives calls made by the students from the student terminals 2b. Further, the communication processing unit 13 may transmit the estimated trust relationship between the lecturer and the student, the student's technical level for each technical field, etc. to the lecturer terminal 2a or the student terminal 2b. Furthermore, the communication processing unit 13 may transmit information regarding the trust relationship between the instructor and the student and the technical level of the student to an appropriate management device connected via the network NW.

Further, the communication processing unit 13 may communicate with an appropriate terminal different from the lecturer terminal 2a or the student terminal 2b. This terminal is a terminal used by, for example, the trainee's boss or the company to which the trainee belongs, the instructor's boss or the instructor's affiliated company, or a person in charge of the training company that plans the training. This terminal may have the same configuration as the lecturer terminal 2a and the student terminal 2b, and includes an input section, an output section, and a communication processing section.

The instructor terminal 2a, the student terminal 2b, or the above-mentioned appropriate terminal displays the information received by the communication processing section 13 on the output section 22a or the output section 22b in an appropriate manner.
FIG. 5 is an example of a screen G10 that displays information regarding training for a student whose identification information is S01 (hereinafter referred to as student S01). The screen G10 may be displayed on the instructor terminal 2a and the student terminal 2b of the student S01, for example. Screen G10 displays the history of training attended by student S01. The attendance history includes, for example, information on training content, attendance schedule, and instructor in charge. Furthermore, for each technical field, the technical level of the student S01 in the technical field and the relationship of trust with the instructor in charge of the training are displayed in association with each other on the screen G10. In the example shown in the figure, a scatter diagram is displayed in which technical level and trust relationship are expressed on two axes as mutually orthogonal indicators. Further, in the same figure, scatter diagrams for the technical field G01 and the technical field G02 are displayed. In technical field G01, students have a good relationship of trust with their instructors and their technical level is high, while in technical field G02, they have a low relationship of trust with their instructors and their technical level is relatively low. Recognize.

The display mode regarding the training attendance history of the trainee may be the same or different between the instructor terminal 2a, the trainee terminal 2b, and other terminals. For example, among other terminals, a terminal used by a person in charge of a training company may display a list of trust relationships among a plurality of instructors for one student. According to this configuration, the person in charge of the training company can easily decide which training the trainee should participate in, taking into account the relationship of trust with the instructor. In addition, when running a system that automatically determines the format of the training, such as the training to be held, the instructor, and the participants, on the terminal used by the person in charge of the training company, the system will refer to the trust relationship and The manner in which the training is held may be determined in such a way that the relationship of trust between the participants and the instructor in the training will be increased.

Furthermore, other terminals may be terminals used by instructors or students, their affiliated companies, or external companies different from the training company. The external company is, for example, a company where the trainee wishes to find employment or change jobs. With this configuration, trainees can show their training history to external companies, as well as their relationship of trust with instructors. Furthermore, participants can demonstrate to outside companies looking for employment or career change that they did not participate in the training mindlessly, but instead took the training while building a relationship of trust with the instructor. .
Furthermore, on terminals used by external companies, for example, the course history of a given student will only be displayed if permission to view the terminal is entered from the terminal of the training company that manages the training. You can leave it there. Further, the training company's terminal may be able to issue the course history as a certificate for each student so that it can be viewed by an external company. According to this configuration, the training company can present the history of students who have participated in the training it manages to the external company, along with the relationship of trust with the instructor, as background information.

●Sequence diagram of processing by the trust relationship estimation device 1 and each terminal 2 The flow of information in the trust relationship estimation device 1 and each terminal 2 in trust relationship estimation will be explained using FIGS. 6 and 7.
FIG. 6(a) is an example of a mode in which the lecturer and students make calls via their respective terminals 2a and 2b, and is a sequence diagram assuming an online lecture, for example. In the example shown in the figure, first, the student terminal 2b acquires a question sent by a student to the instructor in audio and video format, and transmits it to the trust relationship estimation device 1 (step S101). The student's question voice and video are transmitted to the instructor terminal 2a via the trust relationship estimation device 1 or directly from the student terminal 2b. Next, the instructor terminal 2a acquires the response in the form of audio or video, and transmits it to the trust relationship estimation device 1 (step S102). Next, the student terminal 2b acquires the reaction from the student in the form of audio or video, and transmits it to the trust relationship estimation device 1 (step S103). The student's reaction is transmitted to the instructor terminal 2a via the trust relationship estimation device 1 or directly from the student terminal 2b.

The trust relationship estimation device 1 uses the trust relationship analysis unit 12 to analyze the information collected in steps S101 to S103 (step S104). When it is detected that the lecturer and student have made the above-mentioned calls alternately at least three times regarding the same topic (Y in step S105), the trust relationship index is increased (step S106).

FIG. 6(b) is a sequence diagram assuming a mode in which the lecturer and students transmit data via their respective terminals 2a and 2b. The transmitted data is, for example, an email or a chat message sent from the lecturer via the lecturer terminal 2a, and is, for example, text data, but may also be audio, image, or video data. Furthermore, the data transmitted in steps S111 to S113 may be of different types. Note that the data transmitted in any of steps S111 to S113 may be transmitted in an online lecture as shown in FIG. 6(a).
In addition, in the following description, the same reference numerals are given to the same processes as those in the sequence diagrams already shown.

In the example of FIG. 6(b), first, the student terminal 2b accepts input of data contents, and transmits the data to the instructor terminal 2a via the trust relationship estimation device 1 or directly from the student terminal 2b ( Step S111). Next, after receiving the data from the student terminal 2b, the instructor terminal 2a accepts input of the content of the data as a reply, and sends an email to the student terminal 2b via the trust relationship estimation device 1 or directly from the instructor terminal 2a. Transmit (step S112). Next, after receiving the data from the instructor terminal 2a, the student terminal 2b accepts input of the content of the data as a reaction, and sends the data to the instructor terminal 2a via the trust relationship estimation device 1 or directly from the student terminal 2b. Transmit (step S113). In step S113, instead of or in addition to the configuration of transmitting a specific message to the instructor, when data from the instructor is displayed or viewed on the student terminal 2b, information indicating that it has been read is displayed in the trust relationship. It may be transmitted to the estimation device 1 or the instructor terminal 2a.

FIG. 7A is a sequence diagram assuming a mode in which data is input into an input form realized by a web-based application or a predetermined application. The input form may be, for example, a daily report or a questionnaire. Furthermore, the input form may be a test that the instructor administers to the students. The input form may be realized by a software development platform, and the data input in this case may be a program code shared between the instructor and students, or a pull request for the program code.

In the example of FIG. 7A, first, information on the input form is distributed to the student, and the input form is displayed on the screen of the student terminal 2b (step S121). Note that the input form may be distributed from the trust relationship estimation device 1 or from an appropriate external device. When receiving an input to the input form as a call from the student terminal 2b (step S122), the trust relationship estimation device 1 receives the input information and transmits it to the instructor terminal 2a. The lecturer terminal 2a displays the information sent from the student terminal 2b, and also accepts input as a call (step S123). This transmission is, for example, text data containing comments, advice, guidance, etc. in response to the transmission from the student. The trust relationship estimation device 1 receives the input information and transmits it to the student terminal 2b. The student terminal 2b displays the information transmitted from the lecturer terminal 2a and accepts input as a transmission (step S124).

Note that the data acquired in steps S122 to S124 may be input directly to the trust relationship estimation device 1 together with the sender's information instead of being input from the terminal 2. In this embodiment, for example, data written on paper or the like may be read through an appropriate input device such as a scanner or a keyboard connected to the trust relationship estimation device 1.
Further, in the above example, all calls are made via the input form, but it goes without saying that some calls may be made in a different format, such as email or chat.

FIG. 7B is a sequence diagram assuming a mode in which calls from a plurality of people are received from one terminal 2, and the trust relationship estimation device 1 separates the callers and analyzes trust relationships. In this case, for example, a single terminal 2 provided in a classroom may be used to widely collect the voices of the instructor and the students. First, the terminal 2 acquires a plurality of calls from the instructor or the students (steps S131 to S133), and the trust relationship estimation device 1 receives these. The transmission is, for example, audio or video data. Next, the trust relationship estimation device 1 identifies the sender of the call obtained in steps S131 to S133 using an appropriate voiceprint authentication technology, face identification technology, or the like (step S134). In addition, the trust relationship estimation device 1 analyzes the topics that the instructor and the students are talking about, and analyzes whether they alternately communicate about the same topic three or more times.

As described above, according to the trust relationship estimation device according to the present invention, it is possible to estimate the strength of the trust relationship established between the lecturer and the students.

Although the present invention has been described above using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments, and various modifications and changes can be made within the scope of the gist. be.

1 Trust relationship estimation device 11 Input acquisition unit 12 Trust relationship analysis unit 13 Communication processing unit 50 Storage unit 2 Terminal 2a Instructor terminal 2b Student terminal

Claims (9)

A trust relationship estimation device that estimates a trust relationship built between an instructor and a student,
an information acquisition unit that acquires transmissions from the instructor and the student;
Referring to the transmission, if an event is detected in which the transmission is made alternately at least three times by the instructor and the student regarding the same topic, the trust between the instructor and the student through the transmission is detected. a trust relationship analysis unit that estimates that a relationship has been established and stores it in a storage unit as information regarding the trust relationship;
Equipped with
Trust relationship estimation device.
The trust relationship analysis unit acquires the transmissions by the lecturer and the students as voice data or text data, and analyzes the content of the transmissions, thereby determining whether the transmissions by the instructor and the students are related to the same topic. presume that
The trust relationship estimation device according to claim 1.
The information acquisition unit acquires transmissions by the lecturer and the students as text data via a terminal connected to the trust relationship estimation device,
The trust relationship analysis unit estimates that the transmissions inputted in a linked manner are related to the same topic.
The trust relationship estimation device according to claim 1.
The storage unit stores the technical level of the instructor and the technical level of the student regarding a predetermined technical field,
The trust relationship analysis unit is configured to determine whether or not the instructor is responsible for the event in accordance with the technical level of the student at whom the event occurred, the technical level of the instructor, or the difference between the technical level of the student and the instructor. and varying the degree of the trust relationship that is estimated to have increased between the students,
The trust relationship estimation device according to claim 1.
The storage unit stores information on training in which the instructor and the trainees participate,
The trust relationship analysis unit refers to the storage unit to identify the identification information of the training in which the event occurred, and identifies the instructor and the participant in the event according to the number of people participating in the training at the same time. varying the degree of the trust relationship that is estimated to have increased between the parties;
The trust relationship estimation device according to claim 1.
The trust relationship analysis unit decreases the degree of the trust relationship between the instructor and the student as time passes from the event in which the trust relationship between the instructor and the student was established. let,
The trust relationship estimation device according to claim 1.
issuing information regarding the trust relationship stored in the storage unit for each student;
The trust relationship estimation device according to claim 1.
A trust relationship estimation method for estimating a trust relationship built between an instructor and a student,
an information acquisition step of acquiring transmissions by the instructor and the student;
Referring to the transmission, if an event is detected in which the transmission is made alternately at least three times by the instructor and the student regarding the same topic, the trust between the instructor and the student is established through the transmission. a trust relationship analysis step of estimating that a relationship has been established and storing it in a storage unit as information regarding the trust relationship;
executed by a computer,
Trust relationship estimation method.
A computer program that estimates a relationship of trust built between an instructor and a student,
to the computer,
an information acquisition step of acquiring transmissions from the instructor and the student;
Referring to the transmission, if an event is detected in which the transmission is made alternately at least three times by the instructor and the student regarding the same topic, the trust between the instructor and the student through the transmission is detected. a trust relationship analysis step of estimating that a relationship has been established and storing it in a storage unit as information regarding the trust relationship;
In order to execute
computer program.