Information processing device, information processing method, and program

Abstract

In order to achieve the abovementioned purpose, an information processing device according to one embodiment of the present technology comprises an evaluation unit. The evaluation unit sets an evaluation value relating to an education situation on the basis of the correlation between educator behavior information that is a classification result obtained by classifying the behavior of an educator as any of a plurality of educator behavior patterns, and learner behavior information that is a classification result obtained by classifying the behavior of a learner as any of a plurality of learner behavior patterns.

Description

[Technical field]

[0001] The present technology relates to an information processing device, an information processing method, and a program that can be applied to evaluation of lectures and the like. [Background technology]

[0002] The lecture video analysis device described in Patent Document 1 acquires video of students watching a lecture video. From the acquired video, the students' positive or negative reactions to the lecture are recognized, and the students' level of understanding of the lecture is estimated. This is intended to help improve the students' level of understanding and the content of the lecture video. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2018-155825 A Summary of the Invention [Problem to be solved by the invention]

[0004] There is a demand for new technologies for evaluating lectures and the like as described in Patent Document 1.

[0005] In view of the above circumstances, an object of the present technology is to provide an information processing device, an information processing method, and a program that are capable of performing unprecedented evaluation of lectures and the like. [Means for solving the problem]

[0006] In order to achieve the above object, an information processing device according to an embodiment of the present technology includes an evaluation unit. The evaluation unit sets an evaluation value for the educational situation based on the correlation between educator behavior information, which is a classification result of classifying an educator's behavior into one of a plurality of educator behavior patterns, and learner behavior information, which is a classification result of classifying a learner's behavior into one of a plurality of learner behavior patterns.

[0007] In this information processing device, an evaluation value for the educational situation is set based on the correlation between educator behavior information, which is a classification result of classifying the educator's behavior into one of a plurality of educator behavior patterns, and learner behavior information, which is a classification result of classifying the learner's behavior into one of a plurality of learner behavior patterns, making it possible to perform evaluations that have never been performed before.

[0008] The correlation may be a correlation between the educator behavior information and the learner behavior information, which is a first learner behavior information and a second learner behavior information.

[0009] The correlation may be a correlation between the first learner behavior at a first timing, the educator behavior information at a second timing that is a timing later than the first timing, and the second learner behavior information at a third timing that is a timing later than the second timing.

[0010] The evaluation unit may set the evaluation value higher when the first learner behavior information and the second learner behavior information are different than when the first learner behavior information and the second learner behavior information are the same.

[0011] The evaluation unit may set the evaluation value higher if the first learner behavior information and the second learner behavior information are different and the second learner behavior information is set as more positive behavior information than the first learner behavior information.

[0012] The evaluation unit may set the evaluation value higher if the first learner behavior information and the second learner behavior information are different and the second learner behavior information is set as more negative behavior information than the first learner behavior information.

[0013] The evaluation unit may set the evaluation value lower when the first learner behavior information and the second learner behavior information are the same than when the first learner behavior information and the second learner behavior information are different.

[0014] The information processing device may further include an analysis unit that classifies the educator's behavior into one of the multiple educator behavior patterns to generate the educator behavior information, and classifies the learner's behavior into one of the multiple learner behavior patterns to generate the learner behavior information, and outputs the generated educator behavior information and learner behavior information to the evaluation unit.

[0015] The information processing device may further include a sensor unit that outputs a sensing result to the analysis unit. In this case, the analysis unit may analyze the behavior of the educator and the behavior of the learner based on the sensing result.

[0016] The information processing device may further include an evaluation corresponding processing unit that processes the sensing result based on the evaluation value.

[0017] The evaluation response processing unit may edit the sensing result based on the evaluation value.

[0018] The information processing device may further include an evaluation corresponding processing unit that processes the sensing result based on the evaluation value.

[0019] The evaluation response processing unit may edit the sensing result based on the evaluation value.

[0020] An information processing method according to one embodiment of the present technology is an information processing method executed by a computer system, and includes setting an evaluation value for an educational situation based on a correlation between educator behavior information, which is a classification result obtained by classifying an educator's behavior into one of a plurality of educator behavior patterns, and learner behavior information, which is a classification result obtained by classifying a learner's behavior into one of a plurality of learner behavior patterns.

[0021] A program according to one embodiment of the present technology causes a computer system to execute the following steps. A step of setting an evaluation value regarding the educational situation based on the correlation between educator behavior information, which is a classification result of classifying an educator's behavior into one of a plurality of educator behavior patterns, and learner behavior information, which is a classification result of classifying a learner's behavior into one of a plurality of learner behavior patterns. [Brief description of the drawings]

[0022] [Figure 1] FIG. 1 is a schematic diagram for explaining an example of an evaluation system. [Diagram 2] FIG. 1 is a schematic diagram showing an application example of the evaluation system. [Diagram 3] 2 is a block diagram showing an example of a functional configuration of an evaluation system and an information processing device; [Figure 4] 10 is a flowchart showing an example of generation of evaluation information. [Diagram 5] This is a table showing the comments and actions of TAs and students during class. [Figure 6] 13 is an example of an evaluation table for calculating an evaluation value. [Figure 7] FIG. 1 is a schematic diagram showing the correlation between conversational exchanges between students. [Figure 8] 13 is a schematic diagram showing the classification of partial contents of a lesson and the evaluation value of each partial content. FIG. [Figure 9] FIG. 2 is a schematic diagram showing partial content to be recorded. [Figure 10] FIG. 2 is a block diagram illustrating an example of a hardware configuration of an information processing device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0023] Hereinafter, embodiments of the present technology will be described with reference to the drawings.

[0024] [Rating System] FIG. 1 is a schematic diagram for explaining an example of an evaluation system according to the present technology. In the evaluation system 100 according to the present technology, various evaluations regarding the educational situations of an educator (instructor or teacher) 1 and a learner (student) 2 can be performed. For example, as shown in FIG. 1, a user 3 can use an evaluation system 100 to efficiently and accurately perform various evaluations regarding educational situations.

[0025] The educator 1 includes any person who teaches educational content to the learner 2. Of course, the content to be taught is not limited, and includes any content. For example, "educators" include teachers who teach at schools, TAs (Teaching Assistants) who assist in the progress of classes, coaches who teach sports etc., and seniors who teach jobs. In addition, any person in a teaching position such as a tutor, mentor, master, boss, instructor, etc. is also included.

[0026] The learner 2 includes any person who learns educational content from the educator 1. As described above, the educational content taught by the educator 1 is not limited, so the content learned by the learner 2 is also not limited and may include any content. For example, the "learner 2" may be a student studying at school, an athlete practicing a sport, a junior student learning a trade, etc. In addition, any person in a learning position such as a tutee, mentor, or disciple may be included. Note that there may be cases where multiple people in a position with the same name are Educator 1 and Learner 2. For example, when a student teaches another student, the student teaching is Educator 1, and the student being taught is Learner 2. In addition, in cases where a teacher is shown in a video or the like and students study while watching the video, the teacher shown in the video can be regarded as educator 1 and the students learning while watching the video can be regarded as learners 2.

[0027] In the present disclosure, an educational situation includes any situation in which an educator 1 teaches educational content to a learner 2 and the learner 2 learns the educational content. Examples include a teacher giving a lesson to a student in a classroom at school, a coach giving instructions to an athlete on a sports field, a senior giving an explanation to a junior in a company, etc. In addition, any situation in which education and learning take place, such as a lecture, a training session, an experiment, a practical training, and a practical skill, is included.

[0028] Furthermore, the educational situation can be realized without limiting the number of educators 1 and the number of learners 2. That is, various situations such as those shown below are conceivable. A teaching situation conducted by one educator 1 and one learner 2 A teaching situation conducted by one educator 1 and multiple learners 2 A teaching situation conducted by multiple educators 1 and one learner 2 An educational situation conducted by multiple educators 1 and multiple learners 2 The present technology can be applied to such a variety of educational situations. When there are multiple educators 1, it is possible to express the teaching situation as being conducted by a first group having the attribute of teaching. Also, the educator 1 can be said to be a person belonging to the first group having the attribute of teaching. Similarly, when there are multiple learners 2, it is possible to express the educational situation as being conducted by a second group having the attribute of learning. Also, learner 2 can be said to be a person belonging to the second group having the attribute of learning.

[0029] As shown in FIG. 1, an evaluation system 100 according to this embodiment includes a sensor unit, an information processing device 10, and a user terminal 25. The sensor unit, the information processing device 10, and the user terminal 25 are connected to each other so as to be able to communicate with each other via wired or wireless communication. The connection form between the devices is not limited, and it is possible to use, for example, wireless LAN communication such as WiFi, or short-distance wireless communication such as Bluetooth (registered trademark).

[0030] The sensor unit is capable of detecting various data relating to the educator 1 and the learner 2. For example, the sensor unit is installed in the environment where teaching and learning are carried out, and is realized by a microphone 4 capable of detecting sounds generated in the surroundings, a camera 5 capable of capturing images of the surroundings, etc. In this embodiment, the sensing results sensed by the sensor unit include both data that can be used as content that can be viewed / listened to by the user 3, and data for detecting the behavior of the educator 1 and the learner 2. Of course, it also includes data that can be used as content and for detecting the behavior of the educator 1 and the learner 2, and data that cannot be used as content but can be used for detecting the behavior of the educator 1 and the learner 2. The contents include, for example, video and audio of the educational situation of the educator 1 and the learner 2. Examples of data for detecting the behavior of the educator 1 and the learner 2 include the sound pressure emitted from the learner 2, position information indicating the position of the educator 1, and the like. For example, the microphone 4 can detect the voices emitted by the educator 1 and the learner 2. Furthermore, the camera 5 can capture images of the faces of the educator 1 and the learner 2 and the actions of the educator 1 and the learner 2. It is also possible to capture images of the environment, such as a classroom, in which the camera 5 is placed. The audio, video, etc. detected by the microphone 4 and camera 5 can be used as content, and can also be used to detect the behavior of the educator 1 and the learner 2. Of course, the audio, video, etc. obtained by the microphone 4 and camera 5 is not necessarily limited to being used as content and to detect the behavior of the educator 1 and the learner 2. There may also be cases where the audio, video, etc. obtained by the microphone 4 and camera 5 is used only as content, or only to detect the behavior of the educator 1 and the learner 2. There is no limitation on the specific device used as the sensor unit. For example, the camera 5 may be an imaging device such as a digital camera, a ToF (Time of Flight) camera, a stereo camera, a monocular camera, an infrared camera, a polarized camera, or other cameras. For example, a biosensor, a laser distance measuring sensor, a contact sensor, an ultrasonic sensor, LiDAR (Light Detection and Ranging, Laser Imaging Detection and Ranging), sonar, a beacon, or the like may be used as the sensor unit. The sensing results detected by these devices may be used as content, data for detecting the behavior of the educator 1 and the learner 2, or both, as appropriate.

[0031] The information processing device 10 has hardware necessary for configuring a computer, such as a processor such as a CPU or a GPU, memories such as a ROM or a RAM, and a storage device such as a HDD (see FIG. 10). For example, the CPU loads a program according to the present technology, which is pre-recorded in a ROM or the like, into a RAM and executes the program, thereby executing the information processing method according to the present technology. For example, the information processing device 10 can be realized by any computer such as a PC (Personal Computer). Of course, hardware such as an FPGA or an ASIC may also be used. In this embodiment, the CPU executes a predetermined program to configure an evaluation information generating unit as a functional block. Of course, dedicated hardware such as an IC (integrated circuit) may be used to realize the functional block. The program is installed in the information processing device 10 via, for example, various recording media. Alternatively, the program may be installed via the Internet or the like. The type of recording medium on which the program is recorded is not limited, and any computer-readable recording medium may be used. For example, any computer-readable non-transitory storage medium may be used.

[0032] As shown in Figure 1, the information processing device 10 sets an evaluation value for the educational situation based on the correlation between educator behavior information 6, which is the classification result of classifying the behavior of an educator 1 into one of a plurality of educator behavior patterns, and learner behavior information 7, which is the classification result of classifying the behavior of a learner 2 into one of a plurality of learner behavior patterns. The behavior of the educator 1 refers to the behavior of the educator 1 in an educational situation, and includes, for example, the remarks and actions of the educator 1 regarding lessons. The remarks and actions of the educator 1 regarding lessons include, for example, various actions toward the learners 2, such as explanations to all the learners 2, and advice (remarks) to one educator 1 or a group consisting of multiple learners 2. Note that the actions of the educator 1 are not limited, and may also include actions that are not directed toward the learners 2. For example, they may include writing on the blackboard or pointing at materials, conversations between educators 1, movement, the volume of the educator 1's voice, etc. The learner's behavior is the behavior of the learner 2 in an educational situation, and includes, for example, the utterances and actions of the learner 2 regarding the lesson. The utterances and actions of the learner 2 regarding the lesson include, for example, questions to the educator 1, discussions between the learners 2, the content of the discussions, the volume of voices, copying notes from the board or taking notes, etc. Note that the writing on the board and the remarks include the action of writing on the board or making a remark, and the content of the writing on the board or making a remark. The behavior of the educator and the learner is not limited. For example, it may include the learner 2 quietly listening to the educator 1's explanation, or the educator 1 standing still and looking at the learner 2. It may also include behavior unrelated to the educational situation, such as doing nothing or sleeping. The educator behavior pattern and the learner behavior pattern are types of behavior of the educator 1 and the learner 2 that are registered in advance in the analysis unit 13. For example, they include explanations to the whole class, advice to the learner 2, movement, and the like. The educator behavior information 6 and the learner behavior information 7 are the results of classification into either educator behavior patterns or learner behavior patterns. For example, when the behavior of educator 1 is analyzed, such as when educator 1 is in front of a monitor and speaking, it is classified into "explanation to the whole class" in the educator behavior pattern. There is no limitation on the method for generating the educator behavior information 6 and the learner behavior information 7. For example, the information processing device 10 may perform machine learning to distinguish between the educator 1 and the learner 2, and generate the educator behavior information 6 and the learner behavior information 7. For example, any machine learning algorithm using DNN (Deep Neural Network) etc. may be used. For example, by using AI (artificial intelligence) that performs deep learning, it is possible to improve the accuracy of generating the educator behavior information 6 and the learner behavior information 7. Hereinafter, educator behavioral information 6 and learner behavioral information 7 may be referred to as behavioral information. The evaluation value 8 generated by the information processing device 10 is output to the evaluation response processing unit 18. Regarding the evaluation value 8 on the educational situation, an evaluation table pre-registered in the evaluation unit 16 is referenced based on the correlation between the educator behavior information and the learner behavior information, which are the classification results of the analysis unit 13, and if there is a corresponding correlation, the score is set as the evaluation value. The evaluation table may be stored in the recording unit 11.

[0033] The user terminal 25 includes various devices that can be used by the user 3. For example, a PC, a smartphone, or the like is used as the user terminal 25. The user 3 can access the evaluation system 100 via the user terminal 25. For example, the user 3 can use the user terminal 25 to perform various settings such as evaluation of the educational situation, view content, and the like.

[0034] Fig. 2 is a schematic diagram showing an application example of the evaluation system 100. In the example shown in Fig. 2, TAs 34 are illustrated as educators 1. Furthermore, students 35 are illustrated as learners 2 in each of pods A, B, C, and D, four in number. In this embodiment, a lesson format called active learning, in which students 35 discuss a topic with each other and actively learn, is conducted in the classroom. The TAs 34 support the students 35 in each pod by giving them advice and facilitating. The students 35 in each pod discuss the agenda and seek answers to the assignments. The TAs 34 and students 35 include a group of TAs 34 consisting of multiple people and a group (pod) of students 35 consisting of multiple people. In other words, when a statement is written as "a TA 34's comment," it includes both a comment by one TA 34 and a comment by a group of TAs 34.

[0035] Also, the camera and microphone are omitted from Fig. 2. In this embodiment, a camera and microphone are provided to capture the actions and remarks of the TA 34. For example, a camera is installed on the ceiling of a classroom where active learning is carried out, and the actions of the TA 34 are captured. Also, the TA 34 may carry a microphone to capture the voice of the TA 34. In this embodiment, cameras and microphones are provided to capture the actions and remarks of the students 35. For example, a camera and a microphone are provided in each pod, thereby capturing the actions and remarks of the students 35. A whiteboard 36 is provided in each pod for the students 35 to write on. The camera provided in each pod can capture the contents of the writing on the whiteboard 36. In this embodiment, a monitor 37 for displaying materials and the like used by the TAs 34 in class and a table 38 for the TAs 34 are also provided. The equipment used for active learning is not limited. For example, monitors and PCs may be placed in each pod.

[0036] FIG. 3 is a block diagram showing an example of the functional configuration of the evaluation system 100 and the information processing device 10. As shown in FIG. In this embodiment, the evaluation system 100 includes a sensor unit, a recording unit 11, a playback unit 12, an information processing device 10, an evaluation response processing unit 18, and a user terminal 25.

[0037] The recording unit 11 acquires and records the sensing results output from a sensor unit having a microphone 29 (31) and a camera 30 (32). In this embodiment, audio data and image data output from the microphone 29 and camera 30 for the TA 34 and the microphone 31 and camera 32 for the student 35 are acquired and recorded. In the following description, the audio and video recorded in the recording unit 11 will be referred to as content. The content includes the audio and overhead video captured by the microphone 29 and the camera 30, and the audio and video of each pod captured by the microphone 31 and the camera 32. The recording unit 11 outputs the recorded content to the playback unit 12.

[0038] The playback unit 12 is capable of playing back content. In this embodiment, the content acquired by the microphone 29 (31) and the camera 30 (32) is input to the recording unit 11, and the content can be played back. The reproduction unit 12 outputs the input sensing result to the analysis unit 13 .

[0039] The information processing device 10 includes an analysis unit 13, an evaluation unit 16, and an evaluation table DB17.

[0040] The analysis unit 13 includes an educator behavior analysis unit 14 and a learner behavior analysis unit 15 . The educator behavior analysis unit 14 analyzes the behavior of the educator 1 from the sensing results input from the playback unit 12. In this embodiment, the behavior of the TA 34 is analyzed based on the sensing results. For example, from the sensing results acquired by the microphone 29, audio analysis is performed to analyze the presence or absence of remarks made by the TA 34 to the students 35 and the contents of the remarks. Also, for example, from the sensing results acquired by the camera 30, video recognition is performed to analyze the movements of the TA 34 in the classroom. The educator behavior analysis unit 14 classifies the behavior of the educator 1 based on the analysis result and on educator behavior patterns registered in advance in the evaluation table DB17. The educator behavior analysis unit 14 outputs the behavior of the educator 1 classified as one of the educator behavior patterns to the evaluation unit 16 as educator behavior information.

[0041] The learner behavior analysis unit 15 analyzes the behavior of the learner 2 from the sensing results input from the playback unit 12. In this embodiment, the behavior of the student 35 is analyzed based on the sensing results. For example, from the sensing results acquired by the microphone 31, audio analysis is performed to analyze the presence or absence of any remarks made by the student 35 regarding the class and the contents of the remarks. Also, for example, from the sensing results acquired by the camera 32, video recognition is performed to analyze the behavior of the student 35, such as writing on the blackboard. The learner behavior analysis unit 15 classifies the behavior of the learner 2 based on the analysis result and on the learner behavior patterns registered in advance in the evaluation table DB17. The learner behavior analysis unit 15 outputs the behavior of the learner 2 classified as one of the learner behavior patterns to the evaluation unit 16 as learner behavior information.

[0042] The evaluation unit 16 sets an evaluation value based on the correlation between the educator behavior information and the learner behavior information output from the analysis unit 13. In this embodiment, an evaluation value is set based on the correlation between first learner behavior information at a first timing, educator behavior information at a second timing that is a timing later than the first timing, and second learner behavior information at a third timing that is a timing later than the second timing. That is, in the present disclosure, the chronological order in which the actions of the educator 1 intervene with the actions of the learner 2 constitutes a correlation. For example, there is a correlation between the amount of conversation of learner 2 at a first timing, the advice of educator 1 at a second timing which is later than the first timing, and the amount of conversation of learner 2 at a third timing which is later than the second timing. The correlation can also be said to include a relationship in which the behavior of the learner 2 changes as a result of the behavior of the educator 1 toward the learner 2. Without being limited to this, the correlation may include various relationships between the educator 1 and the learner 2. For example, the number of educators 1 and the amount of speech of the learner 2 may be treated as a correlation. Furthermore, when the first learner behavior information and the second learner behavior information are different, the evaluation unit 16 sets the evaluation value higher than when the first learner behavior information and the second learner behavior information are the same. In this embodiment, when the first learner behavior information and the second learner behavior information are different, if the second learner behavior information is set as more positive behavior information than the first learner behavior information, the evaluation value is set higher. For example, if the amount of comments made by the students 35 in the pod A increases due to the comments made by the TA 34, a high evaluation value is assigned to the TA 34. The method of setting the evaluation value set for the behavioral information is not limited. For example, when it is desired to focus on the negative behavioral information of the educator 1, if the first learner behavioral information and the second learner behavioral information are different, the evaluation value may be set higher if the second learner behavioral information is set as more negative behavioral information than the first learner behavioral information. In other words, the height of the evaluation value is set based on the behavioral information of the educator 1 or the learner 2 that the user 3 wishes to focus on. Typically, positive includes making the educational situation more active. For example, this is advice that increases the amount of speech by the learner 2. Negative includes making the educational situation more negative. For example, this is advice that decreases the amount of speech by the learner 2. However, this is not limiting, and any behavior that is desirable for the educational situation may be set as positive. In this embodiment, an evaluation value of the relevant correlation is set by referring to an evaluation table registered in advance in the evaluation table DB 17. Specific examples of correlations and evaluation values ​​will be described with reference to FIG.

[0043] The evaluation table DB17 stores an evaluation table for setting an evaluation value related to the educational situation. In this embodiment, the table stores the target of the TA34's remarks and actions, the educator behavior information of the TA34, and the added points (see FIG. 6A). Also, specific examples of changes in the learner behavior information of the students 35 in each pod triggered by the educator behavior information of the TA34, and the added points (see FIG. 6B). In this embodiment, the evaluation value is the cumulative total of the added points.

[0044] The evaluation response processing unit 18 can execute various processes based on the evaluation value input from the evaluation unit 16. In this embodiment, it is possible to edit the sensing result including the content for checking the educational situation based on the evaluation value. In this embodiment, the evaluation response processing unit 18 includes an editing unit 19, a recording and editing unit 20, and a notification unit 21. The editing unit 19 generates editing points along the time axis for the content obtained by filming a lesson, based on the evaluation value input from the evaluation unit 16. In this embodiment, editing points are generated at predetermined times along the time axis of the content, based on the educator behavior information of the TAs 34, the learner behavior information of the students 35, and the evaluation values ​​of the TAs 34 and the students 35. For example, the editing unit 19 generates an editing point based on a time when the evaluation value fluctuates significantly. Furthermore, the editing unit 19 smoothes the evaluation values ​​of the content in the time period between the editing points (hereinafter, referred to as partial content). For example, if one partial content is one minute long and the evaluation value is calculated every 10 seconds, the average of the calculated evaluation values ​​is calculated as the representative evaluation value of the partial content. The editing unit 19 outputs each of the partial contents and the representative evaluation value calculated for each of the partial contents to the recording and editing unit 20 as content information.

[0045] The recording and editing unit 20 edits the sensing results (usable as content) recorded in the recording unit 11 based on the editing points set by the editing unit 19. For example, a process is executed such that partial content having a low representative evaluation value of the sensing results (usable as content) recorded in the recording unit 11 is not recorded. It is also possible to execute a process such as recording a partial content when the representative evaluation value of the partial content output by the editing unit 19 exceeds a threshold value. The recording and editing unit 20 can also increase the amount of information of partial content recorded in the recording unit 11 . The amount of information is typically defined by the amount of data of the content. For example, the amount of information can be defined by the number of bits of an image per unit time, the number of pixels of an image per unit time, etc. Alternatively, the amount of information may be defined based on a gradation value, etc. For example, the amount of information of the recorded partial content is increased by increasing the bit rate, increasing the resolution, increasing the gradation value, converting the display format, etc. Of course, the present invention is not limited to this. The recording and editing unit 20 may reduce the amount of information, such as by reducing the resolution, for partial contents whose representative evaluation values ​​do not exceed the threshold value, i.e., partial contents whose representative evaluation values ​​are low. The partial contents whose amount of information has been reduced may be recorded in the recording unit 11.

[0046] The notification unit 21 makes a suggestion to the user 3. In this embodiment, suggested information regarding the educational situation is presented based on the evaluation value. For example, when the average of the evaluation values ​​calculated for each partial content falls below a predetermined threshold, an image or sound indicating a warning may be presented to the user 3 as suggested information. Also, for example, a button or the like that allows the user to select whether or not to record each partial content selected by the recording and editing unit 20 may be displayed on the display of the user terminal 25 as suggested information. Furthermore, the notification unit 21 presents instructions regarding the educational situation of the TA 34 based on the evaluation value. For example, when the evaluation value of the TA 34 falls below a predetermined threshold, proposal information indicating whether or not to propose a teaching method for the class to the TA 34 may be presented. In other words, the proposal of a teaching method for the class to the TA 34 corresponds to an instruction regarding the class. The notification unit 21 may also display the above-mentioned suggested information on the display unit of the user terminal 25. For example, a dedicated GUI may be generated, and the user 3 may be able to control the position of the editing point or view the content in which the educational situation is recorded via the GUI. In this case, it can be said that the notification unit 21 functions as a UI display control unit. Of course, a UI display control unit may be configured separately from the notification unit 21.

[0047] The user terminal 25 includes a display unit 26 and a processing unit 27 . The display unit 26 includes any UI device, such as an image display device such as a projector or a display, an audio output device such as a speaker, an operation device such as a keyboard, a switch, a pointing device, a remote controller, etc. Of course, it also includes a device having the functions of both an image display device and an operation device, such as a touch panel. In addition, various GUIs displayed on a display, touch panel, or the like can also be considered as elements included in the display unit 26.

[0048] The processing unit 27 can execute various processes based on instructions input by the user 3, control signals input from the information processing device 10, etc. For example, various processes including viewing of content, checking of evaluation values, suggestions regarding lessons, etc. are executed. The user 3 can evaluate the educational situation by checking the partial content selected by the recording and editing unit 20 via the user terminal 25. Therefore, the evaluation value can be said to be one index for the user 3 to evaluate the educational situation. The evaluation value can also be said to be a criterion for the user 3 to evaluate the educational situation. In other words, the partial content selected by the recording and editing unit 20 can be said to contain information that is useful for the user 3 to evaluate the educational situation. It is also possible to regard the partial content itself generated by the editing unit 19 as the evaluation.

[0049] In this embodiment, the evaluation unit 16 corresponds to an evaluation unit that sets an evaluation value regarding the educational situation based on the correlation between educator behavior information, which is a classification result of classifying an educator's behavior into one of a plurality of educator behavior patterns, and learner behavior information, which is a classification result of classifying a learner's behavior into one of a plurality of learner behavior patterns. In this embodiment, the analysis unit 13 corresponds to an analysis unit that classifies the educator's behavior into one of a plurality of educator behavior patterns to generate educator behavior information, classifies the learner's behavior into one of a plurality of learner behavior patterns to generate learner behavior information, and outputs the generated educator behavior information and learner behavior information to the evaluation unit. In this embodiment, the microphone 29 (31) and the camera 30 (32) correspond to a sensor unit that outputs the sensing result to the analysis unit. In this embodiment, the evaluation response processing unit 18 corresponds to an evaluation response processing unit that processes the sensing result based on the evaluation value.

[0050] FIG. 4 is a flowchart showing an example of setting the evaluation value.

[0051] As shown in FIG. 4, the educator behavior analysis unit 14 classifies the educator behavior information of the TA 34 from the sensing results acquired from the microphone 29 and the camera 30 (step 101).

[0052] FIG. 5 is a table showing the statements and actions of TA 34 and student 35 in class. In this embodiment, the TA 34 is set as an evaluation target. That is, the target, behavior information, and added points shown in Fig. 6 are points for evaluating the TA 34, and when evaluating the student 35, a different target, different behavior information, and different added points are stored as an evaluation table.

[0053] Fig. 5A is a table showing remarks and actions in the lesson of TA 34. An example of step 101 will be specifically described with reference to Fig. 5A. 5A, TA 34 gives a lecture to all students 35 in front of monitor 37 from 0:00 to 1:30. 0:00 includes the start time of the lesson. Of course, it is not limited to this, and may include the start time of recording when recording is started from a specific time within the lesson.

[0054] Between 1:30 and 2:00, TA 34 moves from table 38 for TA 34 to Pod A (dashed line 45). As shown in FIG. 5A, TA 34 stays near Pod A between 2:00 and 3:30. TA 34 also speaks to student 35 in Pod A between 2:30 and 3:00. For example, the educator behavior analysis unit 14 analyzes that the educator is staying in pod A from the information acquired by the camera 30 between 2:00 and 2:30, and analyzes that the educator is not making any noise because sound pressure cannot be detected by the microphone 29. Also, the educator behavior analysis unit 14 analyzes that the educator is staying in pod A between 2:30 and 3:00 from the information acquired by the camera 30, and analyzes that the educator is making noise because sound pressure can be detected by the microphone 29. For example, when TA34 is staying in the pod without speaking out, TA34 checks the contents of the discussion in the pod he is staying in. Also, when TA34 is speaking out and staying in the pod, TA34 supports the discussion in the pod he is staying in by giving advice, etc. These analysis results are output to the evaluation unit 16 as educator behavior information of the TA 34.

[0055] TA34 moves from pod A to pod C between 3:30 and 4:00 (dashed line 46). As shown in FIG. 5A, TA34 stays in pod C between 4:00 and 6:00. Note that, since the microphone 29 does not detect sound pressure at this time, TA34 does not make any noise in pod C. In this way, in FIG. 5A, when the sensing results obtained from the microphone 29 and the camera 30 show that the TA 34 has not stayed or occurred, "None" is written.

[0056] TA34 moves from pod C to pod D between 6:00 and 6:30 (dashed line 47). As shown in FIG. 5A, TA34 stays in pod C between 6:30 and 10:00. TA34 also vocalizes between 7:00 and 9:00.

[0057] Furthermore, the learner behavior analysis unit 15 classifies the learner behavior information of the students 35 from the sensing results acquired from the microphone 31 and the camera 32 (step 102). For example, personal identification is performed based on the face from the image of the camera 32 arranged in each pod, and the behavior of each student 35 is understood by tracking and estimating the posture, etc. Also, sound pressure is detected from the microphone 31 arranged in each pod, and the presence or absence of speech is understood.

[0058] FIG. 5B is a table showing the actions of students 35 in pod D. An example of step 102 will be specifically described with reference to Fig. 5B. In this embodiment, attention is focused on student 35 in pod D. 5B, in this embodiment, students 35 in pod D are silent between 0:00 and 2:00 because they are listening to the explanation by TA 34. As a result, the learner behavior analysis unit 15 classifies the behavior of students 35 into the learner behavior information of students 35 called “silent time.” The students 35 in pod D have a high speaking rate between 2:00 and 5:00. As a result, the learner behavior analysis unit 15 classifies the behavior of the students 35 into the learner behavior information of the students 35 as "heavy speech." The speaking rate is the rate at which the students 35 speak within a specified period of time. For example, if the student 35 speaks for two and a half minutes out of three minutes, the student 35 is classified into the learner behavior information of "heavy speech" since the speaking rate is high. The students 35 in pod D have a low rate of speaking between 5:00 and 6:30. As a result, the learner behavior analysis unit 15 classifies the behavior of the students 35 into the learner behavior information of the students 35 that "speaks little." The students 35 in pod D have a low rate of speaking between 6:30 and 9:00. As a result, the learner behavior analysis unit 15 classifies the behavior of the students 35 into the learner behavior information of the students 35 called "silent time." In this embodiment, as shown in FIG. 5A, the TA 34 supports the discussion of the students 35 in pod D between 7:00 and 9:30, so the students 35 listen to the advice of the TA 34. The students 35 in pod D had a high rate of speaking between 9:00 and 10:00. As a result, the learner behavior analysis unit 15 classifies the behavior of student 35 into the learner behavior information of student 35, "talks a lot." In addition, the camera 32 captures that student 35 has started writing on the whiteboard 36, so the behavior of student 35 is classified into the learner behavior information of student 35, "writing on the board."

[0059] The evaluation unit 16 sets an evaluation value based on the correlation between the educator behavior information of the TA 34 and the learner behavior information of the student 35 (step 103).

[0060] Fig. 6 is an example of an evaluation table for calculating an evaluation value. Fig. 6A is a table showing specific examples of the behavioral information of the TA 34 and each added point.

[0061] As shown in FIG. 6A, the evaluation table of the TA 34 stores "subject," "TA's educator behavior information," and "additional points." The "target" indicates a target for which the TA 34 performs educator behavior information. Typically, the target is a student 35 who is spoken to by the TA 34, a teacher who instructs the TA 34, etc. In this embodiment, the "target" is classified into an individual pod, the whole, other educators, and others. The individual pods are pods A, B, C, and D. The term "all" refers to all of the pods. Other educators are people who fall under the same category as educator 1 as TA34. For example, this includes the same TA as TA34 and teachers who supervise TA34. Others include movement between pods. The pod also includes the students 35 placed therein. In other words, the description that the TA 34 made a statement to the pod A is the same as the statement being made to multiple students 35 placed in the pod A, or to one student 35. Of course, if a TA 34 speaks to all pods (the whole classroom), it can be said that the TA 34 has spoken to all students 35 in the classroom. Also, if a TA 34 speaks to a student 35, it is the same as speaking to the individual pod in which that student is located.

[0062] "TA educator behavior information" is information obtained by classifying educator behavior information of the TA 34 performed on each subject. In this embodiment, the educator behavior information of the TA 34 is classified as follows. The "additional points" are indices for evaluating the TA 34. In this embodiment, since the TA 34 is the evaluation target, a high score (evaluation value) is given to educator behavior information when the TA 34 is evaluated as excellent. The discussion with students in each pod includes a situation in which the TA 34 and the student 35 exchange opinions with each other. The "added points" for this educator behavior information are 30 points. Explanations using writing on the board in each pod include situations where the TA 34 gives explanations to the students 35 using the whiteboard 36 arranged in each pod. For example, this applies to a case where the TA 34 gives an explanation while drawing on the whiteboard 36. The "additional points" for this educator behavior information is 30 points. Explanations by pointing to displays in each pod or materials for discussion include situations in which the TA 34 gives explanations to the students 35 in ways other than writing on the board. For example, this applies to cases in which the TA 34 gives explanations using paper materials used in active learning or materials displayed on a display as data files. The "additional points" for this educator behavior information are 20 points. Explanations to students in each pod include situations where the TA 34 unilaterally explains things to the students 35. For example, this applies when the students 35 are silent while the TA 34 is explaining things. The "additional points" for this educator behavior information is 10 points. Stopping at each pod includes situations where TA34 stays near the pod and does not speak. For example, this applies when TA34 checks the discussion taking place in the pod. The "additional points" for this educator behavior information are 5 points. The initial explanation to the whole class includes the situation where the topic of the lesson is explained. For example, this is the case where TA34 explains the background of the problem and the issues that will be discussed regarding the topic of active learning. The "additional points" for this educator behavior information is 50 points. Explanations to the whole class other than the initial explanation include situations where explanations are given to the whole class after the initial explanation. For example, when the discussions in all pods are moving away from the answer, TA34 explains the course correction to the whole class. The "additional points" for this educator behavior information are 30 points. A conversation from a TA to a teacher includes a situation where the TA talks to an educator other than the TA 34 and to a person who is more senior than the TA 34. For example, this is the case where the TA 34 reports the overall progress to the teacher. The "additional points" for this educator behavior information is 15 points. A conversation between TAs includes a situation in which the TAs talk to educators other than the TA 34, who are in the same position as the TA 34. For example, this applies when the TAs 34 exchange opinions, such as giving advice to the student 35. The "additional points" for this educator behavior information is 5 points. Movement between pods includes situations where no speech or action is made toward the target of movement within each pod or classroom, etc. The "additional points" for this educator behavior information is 0 points.

[0063] FIG. 6B is a table showing specific examples of state changes in the learner behavior information of the student 35 triggered by the educator behavior information of the TA 34 and the respective added points. As shown in FIG. 6B, the evaluation table stores "indexes," "student behavior information," and "additional points." The "indicators" include indicators of changes in the learner behavior information of the students 35. For example, indicators of the students 35 include activation of discussions in the pod, taking actions such as writing on the blackboard, etc. In other words, the indicators can also be said to be reactions of the students 35 to the actions of the TAs 34. In this embodiment, the "indicators" are classified into the amount of conversation (amount of speech), writing on the blackboard, special keywords, and correlations. The conversation volume indicates the volume of conversation among the students 35 in the pod. Writing on the board indicates the behavior of the students 35 writing content related to the discussion on the whiteboard 36 or the like. A special keyword indicates the occurrence of a predetermined keyword through writing on the board or speech by the students 35. The correlation indicates the impact that the behavioral information of the TAs 34 has had on the pod.

[0064] "Student's learner behavior information" is information that classifies changes in the state of the learner behavior information of the student 35 triggered by the educator behavior information of the TA 34. In other words, "student's learner behavior information" is a specific example of changes in indicators before and after the TA 34 speaks or acts on the student 35. In this embodiment, the learner behavior information of the student 35 is classified as follows: An increase in the amount of conversation of all pod members includes a situation in which the amount of conversation of all students 35 placed in the pod has increased. In this embodiment, the pod members are the four students 35 placed in the pod. The "additional points" for this learner behavior information is 30 points. An increase in the amount of conversation by more than half of the pod members includes a situation in which the amount of conversation by more than half of the students 35 placed in the pod has increased. The "additional points" for this learner behavior information are 20 points. An increase in the amount of conversation by less than half of the pod members includes a situation in which the amount of conversation by less than half of the students 35 placed in the pod has increased. The "additional points" for this learner behavior information are 10 points. No change in the amount of conversation includes a situation in which there is no change in the amount of conversation of the student 35 before and after the utterance or action of the TA 34. The "additional points" for this learner behavior information is 0 points. The use of the blackboard includes a situation in which the student 35 writes down the contents of the discussion on the whiteboard 36, etc. For example, the act of taking notes of the remarks of the TA 34 on the whiteboard 36 corresponds to this. The "additional points" for this learner behavior information is 10 points. Keyword extraction refers to a situation in which a pre-defined keyword that leads to an answer to a discussion is extracted. For example, this is the case when a pre-registered keyword is detected from the content of a student's utterance by voice recognition or image recognition. The "additional points" for this learner behavior information is 20 points. A change in conversation correlation includes a situation in which the conversation in the pod changes when the TA 34 speaks or acts on the pod. For example, this would be the case where the conversation between the students 35 changes for the better due to the TA 34's speech. FIG. 7 is a schematic diagram showing the correlation of conversational exchanges between students 35. FIG. 7 illustrates the correlations of conversations between students A, B, C, and D. The lines connecting each person indicate the conversational relationships. In this embodiment, the thickness of the line represents the total amount of conversation between the two people over a certain period of time. The length of the line represents the frequency of conversation. FIG. 7 also provides an overall rating for each correlation. Note that D is the lowest overall rating and A is the highest. For example, in Fig. 7A, this means that the total amount and frequency of conversations between students B, C, and D is high. Also, in Fig. 7B, this means that the total amount and frequency of conversations between students A and B, between students A and C, and between students A and D is high. Also, in Fig. 7B, this means that the total amount and frequency of conversations between students B and C, between students B and D, and between students C and D is low. In this embodiment, the evaluation is performed based on the change in each correlation in Figures 7A to 7D. For example, when the TA 34 gives advice and the correlation changes from Figure D to Figure B, the overall evaluation increases from C to A, and 20 points are added. Also, when the correlation changes from Figure A to Figure C or Figure D, the overall evaluation remains the same or decreases, and 0 points are added. In addition, the overall evaluation and the addition of the evaluation value are not limited to those based on the relationships between students A, B, C, and D. For example, if the overall evaluation is lowered, points may be deducted.

[0065] The type of behavioral information is not limited. For example, the behavioral information may include a search for keywords related to the class by the student 35 using a terminal such as a smartphone, the creation of materials, etc. Also, for example, the behavioral information may include the facial expression of the student 35. Also, the type of evaluation information and the method of addition are not limited. For example, the behavioral information and the addition points may be set according to the type of class.

[0066] The editing unit 19 generates an editing point at a predetermined time for the content 50 in which the teaching situation is filmed, based on the educator behavior information of the TA 34, the learner behavior information of the students 35, and the evaluation information (step 104).

[0067] 8 is a schematic diagram showing the classification of partial contents of a lesson and the evaluation value of each partial content. In this embodiment, the evaluation unit 16 generates an evaluation value for TA 34 for a 10-minute lesson based on the educator behavior information of TA 34 and the learner behavior information of student 35. In addition, the editing unit 19 generates an editing point for each time when the evaluation value changes.

[0068] As shown in Fig. 5A and Fig. 8, TA 34 gives an initial explanation of the lesson to the entire pod between 0:00 and 1:30. From the sensing results of microphone 29 and camera 30, educator behavior analysis unit 14 generates educator behavior information of TA 34, "Initial explanation to the whole pod." Based on the evaluation table shown in Fig. 6, evaluation unit 16 evaluates TA 34's additional points between 0:00 and 1:30 as 50 points. Furthermore, TA 34 moves from table 38 for TA 34 to pod A between 1:30 and 2:00. As shown in Fig. 6, the added score for this educator behavior information is 0 points. That is, as shown in Fig. 8, because the evaluation value has changed, the editing unit 19 generates partial content 51 from 0:00 to 1:30 with a representative evaluation value of 50 points. That is, an editing point is generated at the time of 1:30.

[0069] TA34 stayed near Pod A between 2:00 and 2:30, but did not speak. From the sensing results of the microphone 29 and the camera 30, the educator behavior analysis unit 14 generates educator behavior information of TA34, "stopped at Pod A." The evaluation unit 16 evaluates the additional points of TA34 between 2:00 and 2:30 as 5 points, based on the evaluation table shown in FIG. 6. The editing unit 19 generates a partial content 52 from 1:30 to 2:00 with a representative evaluation value of 0 points.

[0070] TA 34 stayed near pod A between 2:30 and 3:00 and spoke. In addition, the microphone 31 and camera 32 detected a student 35 in pod A talking with TA 34. From the sensing results of the microphone 29 and camera 30, the educator behavior analysis unit 14 generates educator behavior information of TA 34, "discussion with students in each pod," and the learner behavior analysis unit 15 generates behavior information of student 35, "increased conversation volume to less than half of pod members." The evaluation unit 16 evaluates the additional points of TA 34 between 2:30 and 3:00 as 40 points based on the evaluation table shown in FIG. 6. The editing unit 19 generates a partial content 53 from 2:00 to 2:30 with a representative evaluation value of 5 points.

[0071] TA 34 stayed near Pod A between 3:00 and 3:30, but did not speak. In addition, an increase in the amount of conversation between students 35 in Pod A was detected by microphone 31 and camera 32. From the sensing results of microphone 29 and camera 30, educator behavior analysis unit 14 generates educator behavior information of TA 34, "stopping at each pod," and learner behavior analysis unit 15 generates learner behavior information of student 35, "increased amount of conversation by more than half of pod members." Based on the evaluation table shown in FIG. 6, evaluation unit 16 evaluates the additional points of TA 34 between 3:00 and 3:30 as 25 points. The editing unit 19 generates a partial content 54 from 2:30 to 3:00 with a representative evaluation value of 40 points.

[0072] Between 3:30 and 4:00, TA34 moves from pod A to pod C and does not speak. From the sensing results of the microphone 29 and the camera 30, the educator behavior analysis unit 14 generates educator behavior information of TA34 that is "movement between pods." Based on the evaluation table shown in FIG. 6, the evaluation unit 16 evaluates the added points of TA34 between 3:30 and 4:00 as 0 points. The editing unit 19 generates a partial content 55 from 3:00 to 3:30 with a representative evaluation value of 25 points.

[0073] TA34 stayed near pod C between 4:00 and 6:00, and did not speak. From the sensing results of the microphone 29 and the camera 30, the educator behavior analysis unit 14 generates educator behavior information of TA34, "stopping at each pod." The evaluation unit 16 evaluates the additional points of TA34 between 4:00 and 6:00 as 5 points, based on the evaluation table shown in FIG. 6. The editing unit 19 generates a partial content 56 from 3:30 to 4:00 with a representative evaluation value of 0 points.

[0074] Between 6:00 and 6:30, TA34 moves from pod C to pod D and does not speak. From the sensing results of the microphone 29 and the camera 30, the educator behavior analysis unit 14 generates educator behavior information of TA34, "movement between pods." Based on the evaluation table shown in FIG. 6, the evaluation unit 16 evaluates the added points of TA34 between 6:00 and 6:30 as 0 points. The editing unit 19 generates a partial content 57 from 4:00 to 6:00 with a representative evaluation value of 5 points.

[0075] TA34 stayed near pod D between 6:30 and 7:00, and did not speak. From the sensing results of the microphone 29 and the camera 30, the educator behavior analysis unit 14 generates educator behavior information of TA34, "stopping at each pod." The evaluation unit 16 evaluates the additional points of TA34 between 6:30 and 7:00 as 5 points, based on the evaluation table shown in FIG. 6. The editing unit 19 generates a partial content 58 from 6:00 to 6:30 with a representative evaluation value of 0 points.

[0076] TA 34 stayed near pod D between 7:00 and 9:00 and made a speech. In addition, the camera 32 detected a student 35 in pod D writing on the blackboard. From the sensing results of the microphone 29 and the camera 30, the educator behavior analysis unit 14 generates educator behavior information of TA 34, such as "explanation using blackboard writing in each pod," "explanation by pointing to the display or discussion materials in each pod," and "explanation to students in each pod," and the learner behavior analysis unit 15 generates learner behavior information of student 35, such as "use of blackboard writing." The evaluation unit 16 evaluates the additional points of TA 34 between 7:00 and 9:00 as 70 points based on the evaluation table shown in FIG. 6. The editing unit 19 generates a partial content 59 from 6:30 to 7:00 with a representative evaluation value of 5 points.

[0077] TA 34 stayed near pod D between 9:00 and 10:00, but did not speak. In addition, the microphone 31 and camera 32 detected the conversation and writing on the blackboard of student 35 in pod D. From the sensing results of microphone 29 and camera 30, educator behavior analysis unit 14 generates educator behavior information of TA 34, such as "stopping at each pod." In addition, learner behavior analysis unit 15 generates learner behavior information of student 35, such as "increased conversation volume of all pod members," "use of blackboard," "keyword extraction," and "change in conversation correlation." Based on the evaluation table shown in FIG. 6, evaluation unit 16 evaluates the additional points of TA 34 between 7:00 and 9:00 as 85 points. The editing unit 19 generates a partial content 60 from 7:00 to 9:00 with a representative evaluation value of 70 points. The editing unit 19 also generates a partial content 61 from 9:00 to 10:00 (end of class) with a representative evaluation value of 85 points.

[0078] The recording and editing unit 20 selects partial content to be recorded from the divided content based on the representative evaluation value (step 105).

[0079] FIG. 9 is a schematic diagram showing partial content to be recorded. In this embodiment, the recording and editing unit 20 selects partial contents having a representative evaluation value of 50 points or more. The threshold value of the representative evaluation value of the partial contents selected by the recording and editing unit 20 is not limited and may be determined arbitrarily. For example, it may be set by the user 3. 9, the recording and editing unit 20 selects partial content 51, partial content 60, and partial content 61, each of which has a representative evaluation value of 50 points or more (YES in step 105). The recording and editing unit 20 records a video for a time period corresponding to each of the selected partial contents (step 106). Moreover, partial content with a representative evaluation value of 50 points or less is not recorded (NO in step 105).

[0080] As described above, the information processing device 10 according to this embodiment sets an evaluation value 8 regarding the educational situation based on the correlation between educator behavior information 6, which is a classification result of classifying the behavior of the educator 1 into one of a plurality of educator behavior patterns, and learner behavior information 7, which is a classification result of classifying the behavior of the learner 2 into one of a plurality of learner behavior patterns. This makes it possible to perform evaluations that have never been performed before.

[0081] In educational programs such as lectures and classes at schools, etc., there is a trend away from a passive style in which students learn from teachers and towards active learning styles in which students can learn actively.

[0082] In educational styles such as active learning, it is important to properly evaluate and guide not only students but also teachers or TAs. For example, attempts are being made to film active learning classes in order to evaluate teachers or TAs after the class. However, checking the video of each pod when reviewing the lesson footage is a very time-consuming task, and since all the videos must be recorded and saved, storage costs are also high.

[0083] In the present invention, a more detailed evaluation value is calculated by analyzing the behavior of the teacher or TA and the behavior of the students and correlating the two pieces of information. Furthermore, optimal partial content division is automatically performed according to the evaluation value. The divided partial content is recorded based on the evaluation value. This makes it possible to perform evaluation efficiently and with high accuracy. It is also possible to reduce the time required for confirmation when performing evaluation. Furthermore, it is possible to reduce storage costs during recording.

[0084] <Other embodiments> The present technology is not limited to the above-described embodiment, and various other embodiments can be realized.

[0085] In the above embodiment, the evaluation system 100 includes both the educator 1 and the learner 2. However, the present invention is not limited to this, and may include only the educator 1 or the learner 2. For example, a student 35 watching a video of a lecture may be the subject of evaluation. In this case, actions such as opening a reference book, looking away, or taking notes in a notebook may be treated as evaluation information. Also, for example, the TA 34 practicing a lesson may be evaluated. In this case, the number of gestures, the volume of the voice, etc. may be treated as evaluation information.

[0086] In the above embodiment, the method of evaluating the evaluation target is to add points. However, the present invention is not limited to this, and points may be subtracted for specific behavioral information. For example, if a conversation unrelated to the lesson occurs, 20 points may be subtracted. Also, for example, if the amount of conversation of the students 35 decreases due to the remarks of the TA 34, the evaluation value of the TA 34 may be subtracted.

[0087] In the above embodiment, the analysis results of the educator behavior analysis unit 14 and the learner behavior analysis unit 15 are treated as behavior information. However, the present invention is not limited to this, and the sensing results obtained by the sensor units such as the microphone 29 (31) and the camera 30 (32) may be treated as behavior information. For example, the evaluation unit 16 may generate an evaluation value of TA34 when the sound pressure of pod A increases.

[0088] In the above embodiment, the movement, stay, etc. of the TA 34 was detected by the camera 30 for the TA 34. However, without being limited to this, a beacon capable of detecting the position information of the TA 34 may be included in the sensor unit. Furthermore, the microphone 29 (31) detects what the TA 34 and the student 35 say. Without being limited to this, what the TA 34 and the student 35 say may be detected by recognizing the movement of their mouths using the camera 30 (32).

[0089] In the above embodiment, the bit rate of the partial content not selected by the recording and editing unit 20 was lowered or recording was not performed. However, the present invention is not limited to this, and the bit rate of the partial content selected by the recording and editing unit 20 may be increased. Furthermore, the partial content not selected may be recorded as audio or video only.

[0090] In the above embodiment, the evaluation unit 16 evaluates the behavioral information of the student 35 in real time. However, this is not limited to the above, and an evaluation value may be generated only when the behavioral information of the student 35 changes.

[0091] In the above embodiment, an additional point (evaluation information) is set for each piece of behavioral information. However, the present invention is not limited to this, and the evaluation information may be generated by the information processing device 10 performing machine learning.

[0092] In the above embodiment, the sensing result acquired by the sensor unit is input to the information processing device 10 via the playback unit 12. This is not limiting, and the sensing result may be input to the information processing device 10 from the recording unit 11.

[0093] In the above embodiment, the recording unit 11 records the content of the educational situation, and the analysis unit 13 analyzes the behavioral information. However, the present invention is not limited to this, and the analysis unit 13 and the evaluation unit 16 may execute the processing in real time. In this case, the recording unit 11 may have a function of buffering the sensing result.

[0094] In the above embodiment, the information processing device 10 has the analysis unit 13, the evaluation unit 16, and the evaluation table DB 17. However, the present invention is not limited to this, and may have the recording unit 11, the playback unit 12, and the evaluation response processing unit 18. Also, a cloud computing configuration may be applied in which the recording unit 11, the playback unit 12, and the evaluation response processing unit 18 share and jointly process one function among a plurality of devices via a network.

[0095] In the above embodiment, the analysis unit 13 analyzes the educator behavior information and the learner behavior information, and inputs them to the evaluation unit 16. However, this is not limiting, and educator behavior information and learner behavior information analyzed from outside may be input to the evaluation unit 16.

[0096] FIG. 10 is a block diagram showing an example of a hardware configuration of the information processing device 10. As shown in FIG.

[0097] The information processing device 10 includes a CPU 81, a ROM (Read Only Memory) 82, a RAM 83, an input / output interface 85, and a bus 84 connecting these to one another. A display unit 86, an input unit 87, a storage unit 88, a communication unit 89, a drive unit 90, and the like are connected to the input / output interface 85.

[0098] The display unit 86 is a display device using, for example, liquid crystal, EL (Electro-Luminescence), etc. The input unit 87 is, for example, a keyboard, a pointing device, a touch panel, or other operating device. When the input unit 87 includes a touch panel, the touch panel can be integrated with the display unit 86.

[0099] The storage unit 88 is a non-volatile storage device, such as a HDD, a flash memory, or other solid-state memory. The drive unit 90 is a device capable of driving a removable recording medium 91, such as an optical recording medium, a magnetic recording tape, or the like.

[0100] The communication unit 89 is a modem, a router, or other communication device that can be connected to a LAN, a WAN, or the like and is used to communicate with other devices. The communication unit 89 may communicate either wired or wirelessly. The communication unit 89 is often used separately from the information processing device 10. In this embodiment, the communication unit 89 enables communication with other devices via a network.

[0101] Information processing by the information processing device 10 having the above-described hardware configuration is realized by cooperation between software stored in the storage unit 88 or the ROM 82, etc., and the hardware resources of the information processing device 10. Specifically, a program constituting the software stored in the ROM 82, etc., is loaded into the RAM 83 and executed, thereby realizing the information processing method according to the present technology.

[0102] The program is installed in the information processing device 10 via, for example, the recording medium 81. Alternatively, the program may be installed in the information processing device 10 via a global network or the like. Alternatively, any computer-readable non-transitory storage medium may be used.

[0103] An information processing device, information processing method, program, and information processing system related to the present technology may be executed by linking a computer installed in a communication terminal with another computer capable of communicating via a network, etc., thereby constructing an information processing device related to the present technology.

[0104] That is, the information processing device, information processing method, and program according to the present technology can be executed not only in a computer system composed of a single computer, but also in a computer system in which multiple computers operate in conjunction with each other. In this disclosure, a system means a collection of multiple components (devices, modules (parts), etc.), regardless of whether all the components are in the same housing. Therefore, multiple devices housed in separate housings and connected via a network, and a single device in which multiple modules are housed in a single housing are both systems.

[0105] The execution of the information processing device, information processing method, and program according to the present technology by a computer system includes both cases where, for example, generation of behavioral information and division of content are executed by a single computer, and cases where each process is executed by a different computer. Furthermore, the execution of each process by a specific computer includes causing another computer to execute a part or all of the process and acquiring the result.

[0106] In other words, the information processing device, information processing method, and program according to the present technology can also be applied to a cloud computing configuration in which a single function is shared and processed jointly by multiple devices via a network.

[0107] The configurations of the educator behavior analysis unit, learner behavior analysis unit, evaluation unit, record editing unit, etc., and the control flow of the communication system, etc., described with reference to the drawings, are merely one embodiment, and can be arbitrarily modified without departing from the spirit of the present technology. In other words, any other configurations, algorithms, etc. for implementing the present technology may be adopted.

[0108] The effects described in this disclosure are merely examples and are not limiting, and other effects may be present. The description of multiple effects above does not necessarily mean that these effects are exhibited simultaneously. It means that at least one of the effects described above can be obtained depending on the conditions, etc., and it is of course possible that effects not described in this disclosure will be exhibited.

[0109] It is also possible to combine at least two of the characteristic features of each embodiment described above. In other words, the various characteristic features described in each embodiment may be arbitrarily combined without distinction between the embodiments.

[0110] The present technology can also be configured as follows. (1) an evaluation unit that sets an evaluation value regarding an educational situation based on a correlation between educator behavior information, which is a classification result obtained by classifying an educator's behavior into one of a plurality of educator behavior patterns, and learner behavior information, which is a classification result obtained by classifying a learner's behavior into one of a plurality of learner behavior patterns; An information processing device comprising: (2) An information processing device according to (1), The correlation is a correlation between the educator behavior information and the learner behavior information, which is a first learner behavior information and a second learner behavior information. Information processing device. (3) An information processing device according to (1) or (2), The correlation is a correlation between the first learner behavior at a first timing, the educator behavior information at a second timing that is a timing later than the first timing, and the second learner behavior information at a third timing that is a timing later than the second timing. Information processing device. (4) An information processing device according to (3), The evaluation unit sets the evaluation value higher when the first learner behavior information and the second learner behavior information are different than when the first learner behavior information and the second learner behavior information are the same. Information processing device. (5) An information processing device according to (4), The evaluation unit sets the evaluation value higher if the first learner behavior information and the second learner behavior information are different and the second learner behavior information is set as more positive behavior information than the first learner behavior information. Information processing device. (6) An information processing device according to (4), The evaluation unit sets the evaluation value higher if the first learner behavior information and the second learner behavior information are different and the second learner behavior information is set as more negative behavior information than the first learner behavior information. Information processing device. (7) An information processing device according to (3), The evaluation unit sets the evaluation value lower when the first learner behavior information and the second learner behavior information are the same than when the first learner behavior information and the second learner behavior information are different. Information processing device. (8) The information processing device according to any one of (1) to (7), further comprising: an analysis unit that classifies the educator's behavior into one of the plurality of educator behavior patterns to generate the educator behavior information, and classifies the learner's behavior into one of the plurality of learner behavior patterns to generate the learner behavior information, and outputs the generated educator behavior information and learner behavior information to the evaluation unit. Information processing device. (9) The information processing device according to (8), further comprising: A sensor unit that outputs a sensing result to the analysis unit, The analysis unit analyzes the behavior of the educator and the behavior of the learner based on the sensing result. Information processing device. (10) The information processing device according to (4), further comprising: The sensing device further includes an evaluation processing unit that processes the sensing result based on the evaluation value. Information processing device. (11) The information processing device according to (10), The evaluation processing unit edits the sensing result based on the evaluation value. Information processing device. (12) The information processing device according to (7), further comprising: The sensing device further includes an evaluation processing unit that processes the sensing result based on the evaluation value. Information processing device. (13) An information processing device according to (12), The evaluation processing unit edits the sensing result based on the evaluation value. Information processing device. (14) An evaluation value regarding the educational situation is set based on a correlation between educator behavior information, which is a classification result of classifying an educator's behavior into one of a plurality of educator behavior patterns, and learner behavior information, which is a classification result of classifying a learner's behavior into one of a plurality of learner behavior patterns. The information processing method is executed by a computer system. (15) A step of setting an evaluation value regarding the educational situation based on a correlation between educator behavior information, which is a classification result of classifying an educator's behavior into one of a plurality of educator behavior patterns, and learner behavior information, which is a classification result of classifying a learner's behavior into one of a plurality of learner behavior patterns. A program that causes a computer system to execute the above. [Explanation of symbols]

[0111] 1…Educator 2. Learners 4. Microphone 5. Camera 10...Information processing device 13…Analysis department 16…Evaluation section 18...Evaluation and Response Processing Unit 34…TA 35…Student 50…Content

Claims

1. an evaluation unit that sets an evaluation value regarding an educational situation based on a correlation between educator behavior information, which is a classification result obtained by classifying an educator's behavior into one of a plurality of educator behavior patterns, and learner behavior information, which is a classification result obtained by classifying a learner's behavior into one of a plurality of learner behavior patterns; Equipped with the correlation is a correlation between first learner behavior information at a first timing, the educator behavior information at a second timing that is a timing later than the first timing, and second learner behavior information at a third timing that is a timing later than the second timing; The evaluation unit sets the evaluation value higher when the first learner behavior information and the second learner behavior information are different than when the first learner behavior information and the second learner behavior information are the same, and sets the evaluation value higher when the second learner behavior information is set as behavior information more negative than the first learner behavior information. Information processing device.

2. 2. The information processing device according to claim 1, The evaluation unit sets the evaluation value higher if the first learner behavior information and the second learner behavior information are different and the second learner behavior information is set as more positive behavior information than the first learner behavior information. Information processing device.

3. 2. The information processing device according to claim 1, The evaluation unit sets the evaluation value lower when the first learner behavior information and the second learner behavior information are the same than when the first learner behavior information and the second learner behavior information are different. Information processing device.

4. The information processing device according to claim 1 , further comprising: an analysis unit that classifies the educator's behavior into one of the plurality of educator behavior patterns to generate the educator behavior information, and classifies the learner's behavior into one of the plurality of learner behavior patterns to generate the learner behavior information, and outputs the generated educator behavior information and learner behavior information to the evaluation unit. Information processing device.

5. The information processing device according to claim 4, further comprising: A sensor unit that outputs a sensing result to the analysis unit, The analysis unit analyzes the behavior of the educator and the behavior of the learner based on the sensing result. Information processing device.

6. The information processing device according to claim 5, further comprising: An evaluation corresponding processing unit that processes the sensing result based on the evaluation value is provided. Information processing device.

7. 7. The information processing device according to claim 6, The evaluation processing unit edits the sensing result based on the evaluation value. Information processing device.

8. The information processing device according to claim 3, further comprising: an analysis unit that classifies the educator's behavior into one of the plurality of educator behavior patterns to generate the educator behavior information, and classifies the learner's behavior into one of the plurality of learner behavior patterns to generate the learner behavior information, and outputs the generated educator behavior information and learner behavior information to the evaluation unit; a sensor unit that outputs a sensing result to the analysis unit; and an evaluation response processing unit that processes the sensing result based on the evaluation value. Information processing device.

9. 9. The information processing device according to claim 8, The evaluation processing unit edits the sensing result based on the evaluation value. Information processing device.

10. setting an evaluation value for the educational situation based on a correlation between educator behavior information, which is a classification result of classifying the educator's behavior into one of a plurality of educator behavior patterns, and learner behavior information, which is a classification result of classifying the learner's behavior into one of a plurality of learner behavior patterns; the correlation is a correlation between first learner behavior information at a first timing, the educator behavior information at a second timing that is a timing later than the first timing, and second learner behavior information at a third timing that is a timing later than the second timing; When the first learner behavior information and the second learner behavior information are different, the evaluation value is set higher than when the first learner behavior information and the second learner behavior information are the same, and when the second learner behavior information is set as behavior information that is more negative than the first learner behavior information, the evaluation value is set higher. The information processing method is executed by a computer system.

11. setting an evaluation value for the educational situation based on a correlation between educator behavior information, which is a classification result of classifying an educator's behavior into one of a plurality of educator behavior patterns, and learner behavior information, which is a classification result of classifying a learner's behavior into one of a plurality of learner behavior patterns; the correlation is a correlation between first learner behavior information at a first timing, the educator behavior information at a second timing that is a timing later than the first timing, and second learner behavior information at a third timing that is a timing later than the second timing; a step of setting the evaluation value higher when the first learner behavior information and the second learner behavior information are different than when the first learner behavior information and the second learner behavior information are the same, and setting the evaluation value higher when the second learner behavior information is set as behavior information more negative than the first learner behavior information; A program that causes a computer system to execute the above.

Images