JP5772051B2 - Information processing apparatus, instruction plan evaluation program, and instruction plan evaluation method - Google Patents

Description

  The present invention relates to an information processing apparatus, a teaching plan evaluation program, and a teaching plan evaluation method.

  Conventionally, teachers plan how to provide instruction based on an annual instruction plan when a teacher conducts a class at an educational site or the like. Based on this, the teaching instruction plan (hereinafter referred to as “instruction proposal”) is a summary of instruction contents for one lesson in a certain format. The teaching plan includes, for example, information such as time allocation of each learning item within class time, class activities such as teacher's action and expected student's reaction, points to be noted in teaching, and the like. In other words, the teaching plan contains the teaching know-how of the teacher.

  Also, in educational settings, particularly in public education, it is not desirable that there be a large difference in instruction to students due to differences in teachers. However, the know-how of each new teacher, such as a new inexperienced teacher and an experienced teacher, will naturally be different. Incorporating the know-how of other teachers is important for better teaching, but classes are held at the same time every day in each class. There are few opportunities to touch the class. As a result, know-how often closes to individual teachers.

  Therefore, there is a teaching plan database that accumulates teaching plans for a plurality of teachers in order to share teaching knowhow among teachers.

JP 2004-229948 A International Publication No. 2005/027092

  However, the conventional guidance plan database has a problem that there is no evaluation information of the guidance plan. Simply storing and sharing the teaching plan in the database will not be used in the end because the quality of the teaching plan is cobblestone mixed. As the search engine ranks the high-quality Web pages so that they are ranked in the top of the search results and presents them to the user, the teaching plan database does not simply show a large amount of teaching plans accumulated, It is preferable to rank and present them in the order of good guidance.

  As a related technique, for example, there is a technique for evaluating teaching materials by measuring the concentration of students in an actual class with an electroencephalogram. For the evaluation of the teaching plan, for example, it is possible to use this technique to make the teaching plan of the class whose evaluation of the teaching materials was good as a good teaching plan, but the class was actually conducted according to the teaching plan There is no limit, and the teaching plan may be ignored and the lesson progressed. In such a case, it is not preferable to evaluate the corresponding instruction plan as a good instruction plan. It is not always appropriate to evaluate whether a guidance plan is good without confirming how the results were against the plan.

  In addition, as a related technology to confirm whether the lesson plan and the results match, for example, the audio data during the meeting is compared with the minutes document created manually to check for omissions. There is a technology to support the creation of minutes. However, unlike the minutes of meetings where the objective is to correctly record the actual conversations, the lesson guidance plan is based on the teachers' key actions and the expected student responses. It is written. That is, the lesson teaching plan does not contain all the words spoken in the class in detail. For this reason, it is difficult to determine whether a class has progressed as planned simply by comparing the audio data of the class with the teaching plan document using the conventional technology that matches each phrase.

  Therefore, the technology disclosed in the present application has been made in view of the above. The technology disclosed in this application is an information that can evaluate the teaching plan by comparing the actual lesson content and the content planned for the teaching plan used in the lesson and looking at the degree of match It aims at providing a processing device, a guidance plan evaluation program, and a guidance plan evaluation method.

  In order to solve the above-described problem and achieve the object, the information processing apparatus disclosed in the present application stores an event indicating a human speech state and a rule for detecting the event in association with each other, and stores the event detection rule storage unit And an instruction plan event storage unit that stores information on the event created from the instruction plan related to the progress of the lesson, an acquisition unit that acquires information on human behavior, and rules stored in the event detection rule storage unit And an event detection unit that detects information about an event from information about a person's behavior acquired by the acquisition unit, and an event detection unit that detects information about an event stored in the instruction plan event storage unit. Calculate the similarity of each piece of information related to the event, and among the calculated similarities, the event whose maximum similarity is equal to or greater than a predetermined threshold Having an event extracting section that extracts an event extracted by the event extracting unit, and an evaluation value calculation unit for calculating an evaluation value of the lesson plan indicating the matching degree of the stored events in the lesson plan event storage unit.

  One aspect of the information processing device, the teaching plan evaluation program, and the teaching plan evaluation method disclosed in the present application is to compare the actual lesson content with the content planned for the instruction plan used in that lesson, By seeing, the teaching plan can be evaluated.

FIG. 1 is a diagram illustrating a system configuration including an information processing apparatus according to the first embodiment. FIG. 2 is a diagram illustrating a configuration example of the information processing apparatus according to the first embodiment. FIG. 3 is a diagram illustrating an example of information stored in the user profile table. FIG. 4 is a diagram illustrating an example of information stored in the lesson record sensor information table. FIG. 5 is a diagram illustrating an example of information stored in the event detection rule table. FIG. 6 is a diagram illustrating an example of information stored in the lesson record event table. FIG. 7 is a diagram illustrating an example of a teaching plan created by a teacher. FIG. 8 is a diagram illustrating an example of information stored in the guidance plan event table. FIG. 9 is a diagram illustrating an example of information stored in the association table. FIG. 10 is a diagram illustrating an example of information stored in the instruction plan sharing DB. FIG. 11A is an image diagram of class record generation. FIG. 11B is an image diagram of class record generation. FIG. 11C is an image diagram of class record generation. FIG. 11D is an image diagram of class record generation. FIG. 12A is an image diagram of correspondence between a teaching plan event and a class recording event. FIG. 12B is an image diagram of correspondence between a teaching plan event and a class recording event. FIG. 12C is an image diagram of correspondence between a teaching plan event and a class recording event. FIG. 12D is an image diagram of correspondence between a teaching plan event and a class recording event. FIG. 13A is a diagram for explaining a shift pattern when time is left. FIG. 13B is a diagram for explaining a shift pattern when time is insufficient. FIG. 13C is a diagram illustrating a shift pattern when the schedule is not met from the middle. FIG. 14 is a flowchart illustrating an example of a flow of sensor information acquisition processing according to the first embodiment. FIG. 15 is a flowchart illustrating an example of a lesson recording process according to the first embodiment. FIG. 16 is a flowchart illustrating an example of a flow of association processing according to the first embodiment. FIG. 17 is a flowchart illustrating an example of a flow of an event reproduction rate calculation process according to the first embodiment. FIG. 18 is a flowchart illustrating an example of a flow of time score calculation processing according to the first embodiment. FIG. 19 is a diagram illustrating a screen example of a guidance plan creation support application. FIG. 20 is a diagram illustrating a computer that executes a teaching plan evaluation program.

  Embodiments of an information processing apparatus, a teaching plan evaluation program, and a teaching plan evaluation method disclosed in the present application will be described below with reference to the accompanying drawings. In addition, this invention is not limited by the following examples.

[System configuration]
A system configuration including an information processing apparatus according to the first embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating a system configuration including an information processing apparatus according to the first embodiment.

  For example, as illustrated in FIG. 1, the system according to the present embodiment includes terminals 10 a to 10 n (n is a natural number) and an information processing apparatus 100. Each of the terminals 10a to 10n and the information processing apparatus 100 can communicate with each other via a network such as the Internet, for example. Moreover, the terminals 10a to 10n are owned by a teacher or student located in one classroom as one aspect. On the other hand, the information processing apparatus 100 is a PC (Personal Computer), a server apparatus, or the like, and is installed in an arbitrary place as one aspect.

  In the above configuration, each of the terminals 10a to 10n has a voice data file obtained from the utterance of the owner during the class, a log of the operation by the owner, time information at the time of utterance and operation, and a sensor ID (identifier) of the own terminal. ) To the information processing apparatus 100. Examples of the operation log include character data obtained by character input, handwritten character image files, and the like. That is, the terminals 10a to 10n have sensors that acquire voice, operation logs, and the like. On the other hand, the information processing apparatus 100 compares the actual lesson contents with the contents planned in the instruction plan used in the lesson based on various data transmitted from the terminals 10a to 10n, and determines the degree of match. Evaluate the teaching plan by looking at it. Detailed processing by the information processing apparatus 100 will be described later.

[Configuration of information processing device]
The configuration of the information processing apparatus according to the first embodiment will be described with reference to FIG. FIG. 2 is a diagram illustrating a configuration example of the information processing apparatus according to the first embodiment. For example, as illustrated in FIG. 2, the information processing apparatus 100 includes a storage unit 110 and a control unit 120.

  The storage unit 110 stores, for example, data required for various processes by the control unit 120 and various processing results by the control unit 120. The storage unit 110 includes sensor data 111, a user profile table 112, a lesson record sensor information table 113, and an event detection rule table 114. Furthermore, the storage unit 110 includes a lesson recording event table 115, a guidance plan event table 116, an association table 117, and a guidance plan sharing DB (database) 118. The storage unit 110 is, for example, a semiconductor memory device such as a RAM (Random Access Memory), a ROM (Read Only Memory), and a flash memory, or a storage device such as a hard disk or an optical disk.

  In this embodiment, it is assumed that teachers and students own one terminal during class, and the user of each terminal is fixed. The sensor data 111 stores, for example, audio data files transmitted from the terminals 10a to 10n, operation logs, terminal sensor IDs, time information, and the like. The user profile table 112 stores, for example, the sensor ID of each of the terminals 10a to 10n, the sensor type of each of the terminals 10a to 10n, and the person ID of the person who owns each of the terminals 10a to 10n.

  FIG. 3 is a diagram illustrating an example of information stored in the user profile table 112. For example, as illustrated in FIG. 3, the user profile table 112 stores “sensor ID”, “sensor type”, and “person ID” in association with each other. Among these, sensor ID is the information which identifies each terminal 10a-10n. The sensor type is information indicating the type of data obtained by the sensors of the terminals 10a to 10n. The person ID is information for identifying the owner of each of the terminals 10a to 10n.

For example, the user profile table 112 stores a sensor ID “1 _A ”, a sensor type “voice”, and a person ID “teacher 01” in association with each other. As another example, the user profile table 112 stores a sensor ID “1 _B ”, a sensor type “terminal operation”, and a person ID “teacher 01” in association with each other. As another example, the user profile table 112 stores a sensor ID “2 _A ”, a sensor type “voice”, and a person ID “student 01” in association with each other. As another example, the user profile table 112 stores a sensor ID “2 _B ”, a sensor type “terminal operation”, and a person ID “student 01” in association with each other.

Here, the sensor IDs “1 _A ” and “1 _B ” illustrated in FIG. 3 indicate sensor IDs for the same terminal. Similarly, sensor IDs “2 _A ” and “2 _B ” illustrated in FIG. 3 indicate sensor IDs for the same terminal. Since there is a sensor type related to image data or the like in addition to “voice” and “terminal operation” even in one terminal, a sensor ID corresponding to each sensor type is assigned.

  The class record sensor information table 113 is constructed based on, for example, the sensor data 111 and the user profile table 112, and stores the behaviors of teachers and students in the class for each data unit acquired by the sensor. FIG. 4 is a diagram illustrating an example of information stored in the lesson record sensor information table 113. For example, as shown in FIG. 4, the lesson record sensor information table 113 includes a “log ID”, “start time”, “end time”, “person ID”, “sensor type”, and “text”. Are stored in association with each other. Among these, the log ID is information for identifying information stored in the lesson record sensor information table 113. The start time and end time are information indicating the start and end times of each sensor data indicating the behavior of teachers and students as elapsed time from the start of the lesson. The person ID is information for identifying the owner of each of the terminals 10a to 10n. The sensor type is information for identifying the sensor type of each of the terminals 10a to 10n. The text is information obtained by text-converting the behavior of teachers and students indicated by the corresponding sensor data.

  For example, the class record sensor information table 113 includes a log ID “1”, a start time “04 minutes 00 seconds 00”, an end time “04 minutes 06 seconds 00”, and a person ID “teacher 01”. Store in association with each other. In addition to the above, the class record sensor information table 113 stores the sensor type “speech” and the text “various vegetables, what vegetables have been picked” in association with each other. As another example, the class record sensor information table 113 includes a log ID “2”, a start time “04 minutes 07 seconds 00”, an end time “04 minutes 07 seconds 59”, and a person ID “student 01”. And the sensor type “voice” and the text “cucumber” are stored in association with each other. As another example, the class record sensor information table 113 includes a log ID “3”, a start time “04 minutes 08 seconds 12”, an end time “04 minutes 09 seconds 01”, and a person ID “student 02”. And the sensor type “voice” and the text “the most tomatoes” are stored in association with each other. In other words, in the lesson, it is shown that there were answers from students such as “cucumber” and “the most tomatoes” in response to the question “what kind of vegetables were picked” by the teacher.

  The event detection rule table 114 is a table constructed in advance, and stores, for example, an event indicating a state of behavior by a person such as a teacher or a student and a rule for detecting the event in association with each other. FIG. 5 is a diagram illustrating an example of information stored in the event detection rule table 114. For example, as shown in FIG. 5, the event detection rule table 114 associates “No.”, “event tag”, “state of combination of class record sensor information”, and “how to organize events”. And remember. Of these, No. Is information for identifying information stored in the event detection rule table 114. The event tag is information indicating the type of an in-class event performed by a teacher or student. An event tag may include a plurality of events. Moreover, the combination state of lesson record sensor information is information which shows the speech and behavior combination conditions of a teacher and a student which comprise a certain event. The event summarization means information indicating which event tag is associated with which sensor information when the combination condition of the lesson record sensor information is established.

  For example, the event detection rule table 114 has a No. “1” and the event tag “teacher's question, individual pursuit” are stored in association with each other. In addition, the event detection rule table 114 shows the state of the combination of lesson record sensor information “Student terminal operation is started within 5 seconds after the end of the teacher's voice, and the time period during which the student terminal operation is continued for a total of 20 seconds or more. “The number of inputs is 1/3 or more of the class” is stored in association. Also, the event detection rule table 114 stores a method of event summarization in association with a “teacher's voice to a“ teacher's question ”tag and a group of consecutive student terminal operations and a“ personal pursuit ”tag”.

  As another example, the event detection rule table 114 has a No. “2” and the event tag “teacher's question, student's speech” are stored in association with each other. In addition, the event detection rule table 114 stores the state of the combination of lesson record sensor information in association with “the time zone in which one or more student voices continue after the teacher's voice ends for a total of 5 seconds or more”. Also, the event detection rule table 114 stores a method of grouping events, “teacher's voice with“ teacher's question ”tag, continuous student terminal voices together with“ student's speech ”tag”.

  The lesson record event table 115 is constructed based on, for example, the lesson record sensor information table 113 and the event detection rule table 114. The lesson event detected from the sensor information that records the behavior of teachers and students during the lesson, Store in event units. FIG. 6 is a diagram illustrating an example of information stored in the lesson record event table 115. For example, as shown in FIG. 6, the class record event table 115 stores “class record event ID”, “start time”, “event”, and “text” in association with each other. Of these, the lesson record event ID is information for identifying information stored in the lesson record event table 115. The start time is information indicating the start time of the corresponding event as the elapsed time from the start of the lesson. An event is information indicating the type of an in-class event performed by a teacher or student. The text is information obtained by text-converting the behavior of teachers and students in the corresponding event.

  For example, the class record event table 115 has a class record event ID “1”, a start time “04 minutes 00 seconds 00”, an event “question of the teacher”, and the text “Various vegetables, whatever vegetables were picked” Is stored in association with each other. As another example, the class record event table 115 has the class record event ID “2”, the start time “04 minutes 07 seconds 00”, the event “student remarks”, and the text “cucumber tomatoes”. Is also stored in association with each other.

  The guidance plan event table 116 is a table that is preliminarily constructed by external input, and stores, for example, information related to events in the class described in the guidance for the course progress. FIG. 7 is a diagram illustrating an example of a teaching plan created by a teacher. For example, as shown in FIG. 7, the teaching plan includes a lesson unit, a teaching teacher, phases for all class hours, time required for each phase, contents of learning activities in each phase, and guidance for learning activities. The above points to note are included. For example, the unit is "Organize the number by picture or figure (1st year / arithmetic)". The teaching teacher is “Fujio XX Elementary School”. The phase and the time required for the phase are “introduction 10 minutes”, “deployment 1 20 minutes”, and the like. In addition, the learning activities are “the teacher's question“ I picked a variety of vegetables. What kind of vegetables were you picked ”” and “Students' answers“ Tomato ”,“ Nasu ”,“ Cucumber ”,“ The most tomatoes. ] "Etc. In addition, the point to be noted in the instruction is “After showing the picture of the vegetable, confirming the name of the vegetable, and taking the remarks of the students who focused on the number of“ the most tomatoes ”etc., It is linked to the subject of the main guidance to arrange. "

  FIG. 8 is a diagram illustrating an example of information stored in the guidance plan event table 116. 7 is a table expressing the configuration of the teaching plan. For example, as illustrated in FIG. 8, the teaching plan event table 116 includes “teaching plan event ID”, “phase”, “time allocation”, and “ The “event”, “text”, and “notice points for guidance” are stored in association with each other. Among these, the guidance plan event ID is information for identifying information stored in the guidance plan event table 116. A phase is information indicating a situation in one class. The time allocation is information indicating the time allocation scheduled in each phase, and as one aspect, the scheduled start time of each phase is indicated by the elapsed time from the start of the lesson. An event is information indicating the type of an in-class event assumed to be performed by a teacher or student. The text is information indicating the behavior of students and teachers expected in the corresponding event in text. In addition, points to be noted in the guidance are information indicating the purpose of each event in the class.

  For example, the instruction plan event table 116 includes an instruction plan event ID “1”, a phase “introduction”, a time allocation “00 minutes 00 seconds 00”, an event “question of a teacher”, and a text “Various types”. “Vegetables, what kind of vegetables have been picked” are stored in association with each other. As another example, the teaching plan event table 116 includes a teaching plan event ID “2”, a phase “introduction”, a time allocation “00 minutes 00 seconds 00”, an event “student remarks”, and a text “tomato”. "The most cucumber eggplant cucumber tomato" is stored in association. In addition, the guidance plan event table 116 is a main instruction to arrange the number of vegetables based on the notes of the students, focusing on the number of vegetables such as “Tomato is the most” after confirming the name of the vegetables. “Associated with the task” is stored in association with each other. As another example, the guidance plan event table 116 includes a guidance plan event ID “3”, a phase “deployment 1”, a time allocation “10 minutes 00 seconds 00”, an event “question of a teacher”, a text “Draw as many cards as there are vegetables and compare the numbers” in association with each other. In addition, in the example shown in FIG. 8, the time allocation is the same time (start time) even if there are multiple events within the same phase. In consideration, a finer time may be given for each event.

  The association table 117 is constructed based on, for example, the lesson record event table 115 and the instruction plan event table 116, and stores information on association between events actually performed in the class and events scheduled to be taught in the class. Remember. FIG. 9 is a diagram illustrating an example of information stored in the association table 117. For example, as shown in FIG. 9, the association table 117 correlates “instruction plan event ID”, “instruction plan event start time”, “class record event ID”, and “class record event start time”. Add and remember. Among these, the guidance plan event ID is information for identifying information stored in the guidance plan event table 116. The guidance plan event start time is information indicating the scheduled start time of the corresponding guidance plan event as an elapsed time from the start of the class. The class record event ID is information for identifying information stored in the class record event table 115. The class record event start time is information indicating the start time of the corresponding class record event as an elapsed time from the class start.

  For example, the correspondence table 117 includes a guidance plan event ID “1”, a guidance plan event start time “00 minutes 00 seconds 00”, a lesson record event ID “1”, and a lesson record event start time “04”. "Minute 00 seconds 00" is stored in association with each other. That is, the association table 117 stores an ID and a start time corresponding to an event actually performed in a class, and an ID and a start time corresponding to an event scheduled to be taught in the class in association with each other. The process related to the association will be described later.

  The instruction plan sharing DB 118 is constructed based on, for example, the class recording event table 115, the instruction plan event table 116, and the association table 117, and stores an evaluation score that is an evaluation value for each instruction plan. FIG. 10 is a diagram illustrating an example of information stored in the instruction plan sharing DB 118. For example, as shown in FIG. 10, the instruction plan sharing DB 118 corresponds to “No.”, “Teaching plan”, “Class record No.”, “Evaluation score”, and “Detailed evaluation score”. Add and remember. Of these, No. Is information for identifying information stored in the instruction plan sharing DB 118. The guidance plan includes a unit name, a teacher name, a guidance plan file name, etc., and is basic information for the guidance plan shown in FIG. 7 and information such as a pointer to the guidance plan event table 116 shown in FIG. . In addition, class record No. Is information such as pointers to the corresponding sensor data 111, the class record sensor information table 113, and the class record event table 115. Moreover, an evaluation score is information which shows the evaluation value with respect to a corresponding guidance plan, for example, is information which shows the comprehensive score based on the detailed evaluation score mentioned later. The detailed evaluation score is, for example, information indicating a degree of coincidence between an actual lesson and a lesson instruction schedule, and includes an event reproduction rate, a time score, and the like. The event recall rate is information indicating a degree of coincidence with a schedule related to an event, that is, information indicating how many scheduled events are actually performed. The time score is information indicating the degree of coincidence with the schedule related to the event occurrence time. In FIG. 10, the event recall rate and the time score are listed as the detailed scores. In addition, the student's comprehension score, the teacher's self-evaluation score, the teaching material evaluation, and the teaching plan reference count score. Various scores such as the above may be used.

  For example, the instruction plan sharing DB 118 is No. “1”, unit name “Organize the number by picture or figure (1st grade / arithmetic)”, teacher name “XX Elementary School, Fujitsuo”, and teaching plan file name “201200819-1-0” Store in association with each other. The instruction plan sharing DB 118 is a class record No. “20100819-1-46”, the evaluation score “82”, the event recall rate “1”, and the time score “0.2” are stored in association with each other. The details of the event recall and time score calculation will be described later.

  The control unit 120 has, for example, an internal memory for storing a control program, a program that defines various processing procedures, and necessary data, an acquisition unit 121, an event detection unit 122, an event extraction unit 123, And an evaluation value calculation unit 124. The control unit 120 is an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array), or an electronic circuit such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit).

  The acquisition unit 121 acquires, from the terminals 10a to 10n, sensor data related to human speech such as a log of terminal operations by teachers and students and voice data obtained by a terminal sensor by utterance. Here, the terminal operation log includes, for example, character data obtained by keyboard input, an image file of handwritten character input, and the like. The sensor data acquired by the acquisition unit 121 includes a sensor ID, a generation time of sensor data, and the like in addition to an operation log and audio data. Then, the acquisition unit 121 stores the acquired sensor data in the sensor data 111. That is, the sensor data 111 stores raw data obtained by the sensors of the terminals 10a to 10n.

  Subsequently, based on the sensor data stored in the sensor data 111, the acquisition unit 121 uses a known technique such as voice recognition or image recognition to convert the voice data or the image file into text and extract the text. Moreover, the acquisition part 121 converts the generation time of sensor data into the elapsed time information from a lesson start. Thereafter, the acquisition unit 121 acquires the person ID and sensor type from the user profile table 112 using the sensor ID of the sensor data, and associates the start time, end time, person ID, sensor type, and text with the log ID. Stored in the class record sensor information table 113. Moreover, if the acquisition part 121 performs the process stored in the lesson record sensor information table 113 about all the sensor data in a lesson, it will notify the event detection part 122 that the process was completed.

  For example, when the event detection unit 122 receives a notification of processing completion from the acquisition unit 121, the event detection unit 122 uses the rules stored in the event detection rule table 114 to obtain information about the event from the information stored in the class record sensor information table 113. To detect. And the event detection part 122 stores the information regarding the detected event in the lesson record event table 115. FIG. In addition, when the event detection unit 122 executes a process of storing data related to one class in the class record sensor information table 113 in the class record event table 115, the event detection unit 122 notifies the event extraction unit 123 that the process is completed.

  Here, generation of a lesson record will be described with reference to FIGS. 11A to 11D. 11A to 11D are image diagrams of class record generation. In addition, in FIG. 11A-FIG. 11D, the image of the rule of event detection and the image of class record sensor information are represented. The numerical value in the rule image indicates “No.” stored in the event detection rule table 114, and the numerical value in the image of the class record sensor information is “log ID” stored in the class record sensor information table 113. Is shown.

  For example, as shown in FIG. 11A, the event detection unit 122 has a No. The rule corresponding to “1” is taken out, the data string starting from the log ID “1” indicated by the slanting left slanting line is sequentially viewed, and the data string up to the point that matches the extracted rule is extracted. Here, no. As an example, the rule corresponding to “1” is not matched with the data string starting from the log ID “1”.

  Rule No. Since “1” did not match, the event detection unit 122 next changed the No. shown by the left-downward oblique line as shown in FIG. A rule corresponding to “2” is extracted. Further, the event detection unit 122 sequentially looks at the data string starting from the log ID “1” indicated by the left-downward oblique line, and extracts the data string up to the place that matches the extracted rule. Here, as shown in FIG. For the rule corresponding to “2”, a case where the data string of the log IDs “1” to “4” indicated by the diagonally downward slant lines is taken as an example. For example, No. The event tag given to the log ID “1” conforming to the rule “2” is a “teacher question” event. Similarly, no. The event tags given to the log IDs “2” to “4” conforming to the rule “2” are “student speech” events.

  Subsequently, as illustrated in FIG. 11D, the event detection unit 122 renews the No. A rule corresponding to “1” is extracted. In addition, the event detection unit 122 sequentially looks at the data string starting from the log ID “5” indicated by the left-downward oblique line, and extracts the data string up to the point that matches the extracted rule. That is, the event detection unit 122 sequentially looks at the data string starting from the log ID “5” that is the next record of the log IDs “1” to “4” in which the event has already been detected by conforming to the rule. The data string up to the point that matches the extracted rule is extracted. In the above example, no. The case where class record sensor information that conforms to the rule “2” exists has been described, but if an event cannot be extracted even if conformance is determined for all rules, the data of the log ID “1” is stored as an event. Not detected. At this time, the event detection unit 122 then selects No. Regarding the rule corresponding to “1”, the conformity determination is performed on the data string starting from the log ID “2”. In this way, the event detection unit 122 performs matching with the rules for all class record sensor information, and associates the start time, the event, and the text with the event ID for the matched event in the class record event table 115. Store.

  For example, when the event extraction unit 123 receives a notification of processing completion from the event detection unit 122, the degree of similarity of each of the information related to the event detected by the event detection unit 122 for each information related to the event stored in the guidance plan event table 116. Is calculated. Then, the event extraction unit 123 extracts an event whose maximum similarity is equal to or greater than a predetermined threshold among the calculated similarities. Thereafter, the event extraction unit 123 stores the extracted event in the association table 117 in association with the instruction plan event ID, the instruction plan event start time, the lesson record event ID, and the lesson record event start time. In addition, when the event extracting unit 123 executes the process of storing all the extracted events in the association table 117, the event extracting unit 123 notifies the evaluation value calculating unit 124 that the process has been completed.

  In the calculation of the similarity by the event extraction unit 123, for example, “similarity = α × text similarity + β × time similarity” is obtained. Here, α and β indicate weights. The text similarity indicates the similarity between “text” included in the teaching plan event table 116 and “text” included in the lesson record event table 115. As the text similarity, as one aspect, a method such as the number of matching by summing up the frequency of words appearing in each text is used. The similarity of time indicates the similarity between “time distribution (start time)” included in the instruction plan event table 116 and “start time” included in the lesson record event table 115. The similarity of time is calculated as “1 / | start time included in class record event table 115−time allocation included in teaching plan event table 116” as one aspect. Note that | * | represents the absolute value of *.

  Here, the correspondence between the teaching plan event and the class recording event will be described with reference to FIGS. 12A to 12D. 12A to 12D are image diagrams of correspondence between the teaching plan event and the class recording event. 12A to 12D show an image of the data string of the teaching plan event table 116 and an image of the data string of the lesson record event table 115. The numerical value in the image of the guidance plan event indicates the “guidance plan event ID” stored in the guidance plan event table 116. The numerical value in the image of the lesson record event indicates the “lesson record event ID” stored in the lesson record event table 115.

  For example, as illustrated in FIG. 12A, the event extraction unit 123 compares the event of the teaching plan event ID “1” indicated by the left-downward oblique line with all the class recording events indicated by the left-downward oblique line. Then, as illustrated in FIG. 12B, the event extraction unit 123 has the same event as the instruction plan event ID “1” indicated by the left-slanting diagonal line, and the class record event ID “1” indicated by the left-slanting diagonal line. , “4” and “7” events are extracted as association candidates. Subsequently, the event extraction unit 123 calculates the similarity between the event with the teaching plan event ID “1” and the extracted class record event IDs “1”, “4”, and “7”. Here, as shown in FIG. 12C, the similarity between the event of the teaching plan event ID “1” indicated by the right-downward oblique line and the event of the lesson record event ID “1” indicated by the downward-rightward oblique line is maximized. Take the case as an example.

  Thereafter, as shown in FIG. 12C, the event extraction unit 123 determines that the similarity between the instruction plan event ID “1” indicated by the right-downward diagonal line and the lesson record event ID “1” indicated by the right-downward diagonal line is a predetermined threshold value. It is determined whether it is above. At this time, when the event extraction unit 123 determines that the similarity is equal to or greater than a predetermined threshold, the guidance plan event ID “1”, the guidance plan event start time, the lesson record event ID “1”, and the lesson record The event start time is associated with each other and stored in the association table 117. If the event extraction unit 123 determines that the similarity is less than the predetermined threshold or if there is no lesson recording event having the same event as the instruction plan event, the event extraction unit 123 sets “NULL” in the association table 117. Store.

  Then, as illustrated in FIG. 12D, the event extraction unit 123 displays the event of the teaching plan event ID “2” indicated by the left-downward oblique line and the event after the class record event ID “2” indicated by the downward-leftward oblique line. The comparison is performed and the association is executed as described above. That is, the event extraction unit 123 compares the events for the records after the associated records, and stores the same events having the highest similarity in the association table 117. At this time, the event extraction unit 123 stores a lesson record event ID if the maximum similarity is equal to or greater than a predetermined threshold, and stores a NULL value if there is no event less than or equal to the predetermined threshold. In the above example, the data string after the associated class recording event is associated, that is, the case where the change of the order of events in time series is not considered. About this, it is good also as implementing the process of matching also with respect to the data string of the lesson record event from which the correlation was taken. Thereby, the event extraction part 123 can be matched also with respect to the event which is not teaching according to the guidance plan in time series. However, the event extraction unit 123 sets the correspondence by changing the predetermined threshold or adjusting the weight of the similarity calculation formula for data that is associated in such a way that the order is changed in time series. Execute the process.

  For example, when the evaluation value calculation unit 124 receives a notification of processing completion from the event extraction unit 123, the degree of coincidence between events corresponding to each of the teaching plan event ID and the class recording event ID stored in the association table 117 The evaluation value of the teaching plan indicating is calculated. In calculating the evaluation value, as one aspect, an event recall rate and a time score are calculated. In calculating the event recall rate and time score, information such as the start time stored in the class record event table 115 and the instruction plan event table 116 and the number of records in the instruction plan event table 116 and the association table 117 are used. The Then, the evaluation value calculation unit 124 calculates the evaluation score as, for example, “γ × event reproduction rate + δ × time score”. Here, γ and δ indicate weights. Thereafter, the evaluation value calculation unit 124 stores the calculated evaluation score in the instruction plan sharing DB 118.

  Specifically, for an event recall rate that is one of the evaluation values, the evaluation value calculation unit 124 acquires the number of records in the guidance plan event table 116 and the number of records that have been handled in the association table 117, and these It is calculated by obtaining the ratio of. That is, the guidance plan includes only major events, and an actual class includes digressions that are not included in the guidance plan, so more events occur than the guidance plan. From this, the evaluation value calculation unit 124 calculates “number of records matched in the correspondence table 117 / number of records in the teaching plan event table 116” as the event recall rate.

  Here, calculation of a time score, which is one of evaluation values, will be described with reference to FIGS. 13A to 13C. 13A to 13C show an image of the data string of the teaching plan event table 116 and an image of the data string of the lesson record event table 115. Further, the shift pattern listed below is a pattern of time information difference between a teaching plan event and a class recording event. For example, one lesson time is determined to be 45 minutes.

  FIG. 13A is a diagram for explaining a shift pattern when time is left. Specifically, in FIG. 13A, the event of the last record in the chronological order of the teaching plan event table 116 corresponds to the arbitrary record of the lesson record event table 115, and the lesson record event by the time when the lesson ends. An example where is further present is shown. That is, the evaluation value calculation unit 124 matches the guidance plan event ID of the last record in the time series of the guidance plan event table 116 with the guidance plan event ID of the last record in the time series of the association table 117. Judge that. In this way, in the deviation pattern when time is left, the evaluation value calculation unit 124 sets the time score to “1 / (lesson time-correspondence table 117 corresponding to the last record lesson record event in time series”. Start time) ”. If the denominator is “0” in the time score calculation formula, the time score is calculated as “1”. Moreover, although FIG. 13A is a shift pattern when time is left, it is a pattern that is similarly applied even when a lesson is performed on time.

  FIG. 13B is a diagram for explaining a shift pattern when time is insufficient. Specifically, in FIG. 13B, an event of an arbitrary record in the teaching plan event table 116 corresponds to an event of the last record in the time series of the class recording event table 115, and all teaching is performed by the time of class end. An example in which a plan event could not be performed is shown. That is, the evaluation value calculation unit 124 determines that the above determination condition illustrated in FIG. 13A is not satisfied. In addition, the evaluation value calculation unit 124 includes the lesson record event ID of the last record in the time series of the lesson record event table 115, and the lesson record event ID of the last record in the time series, which is supported in the association table 117. Are determined to match. As described above, in the deviation pattern when time is insufficient, the evaluation value calculation unit 124 sets the time score to “1 / (Class hours-correspondence table 117 in time series corresponding to the last record instruction plan”. Event start time) ”.

  FIG. 13C is a diagram illustrating a shift pattern when the schedule is not met from the middle. Specifically, FIG. 13C shows an example in which the correspondence between the event in the record in the teaching plan event table 116 and the record in the lesson record event table 115 cannot be taken. That is, the example illustrated in FIG. 13C is a case where neither the pattern determination condition illustrated in FIG. 13A nor the pattern determination condition illustrated in FIG. 13B is met. In this way, in the shift pattern when the schedule is not met from the middle, the evaluation value calculation unit 124 calculates the time score as “0” by regarding the evaluation value as being out of target. As described above, the evaluation value calculation unit 124 determines the shift pattern, extracts the last record in time series corresponding to the correlation table 117 according to the determined shift pattern, and determines the shift pattern according to the shift pattern. Calculate the time score. In the above example, the case where the start time is compared with respect to the time lag has been described, but the comparison may be made based on the end time. At this time, the information processing apparatus 100 can calculate the evaluation value with higher accuracy by further providing an end time item in each of the class record event table 115, the teaching plan event table 116, and the association table 117. . In the above example, the case where the time score is set to “0” in the pattern of FIG. 13C has been described. However, the types (for example, the importance level of events) and the number of remaining events of the teaching plan event and the class recording event are described. The time score may be calculated according to the (ratio) condition. Alternatively, the time score may be calculated according to the condition of the difference between the lesson time and the start time of the last record associated with the lesson time.

[Sensor information acquisition processing according to Embodiment 1]
Next, sensor information acquisition processing according to the first embodiment will be described with reference to FIG. FIG. 14 is a flowchart illustrating an example of a flow of sensor information acquisition processing according to the first embodiment.

  For example, as shown in FIG. 14, when the information processing apparatus 100 receives sensor data from the terminals 10a to 10n (Yes in step S101), the information processing apparatus 100 converts the text in the audio file or image file included in the received data into text. (Step S102). Note that, when the sensor data is not received (No at Step S101), the information processing apparatus 100 is in a state of waiting for reception of the sensor data.

  And the information processing apparatus 100 calculates the start time and end time which show the elapsed time of a lesson from the time information contained in the received data (step S103). Subsequently, the information processing apparatus 100 acquires the sensor type and the person ID from the user profile table 112 based on the sensor ID included in the received data (step S104). Thereafter, the information processing apparatus 100 stores the text, start time, end time, sensor type, and person ID in the class record sensor information table 113 in association with the log ID (step S105).

[Class recording process according to Example 1]
Next, the lesson recording process according to the first embodiment will be described with reference to FIG. FIG. 15 is a flowchart illustrating an example of a lesson recording process according to the first embodiment.

  For example, as illustrated in FIG. 15, the information processing apparatus 100 installs start pointers at the heads of the class record sensor information table 113 and the event detection rule table 114 (step S <b> 201). Then, the information processing apparatus 100 extracts one rule from the position of the start pointer in the event detection rule table 114 (step S202). Subsequently, when there is a rule (Yes at Step S203), the information processing apparatus 100 determines whether or not there is a data string that meets the rule condition in the data string starting from the start pointer position of the lesson record sensor information table 113. Is determined (step S204).

  At this time, if the information processing apparatus 100 determines that there is a data string that matches the rule condition (Yes in step S204), the information processing apparatus 100 stores the event tag corresponding to the matched condition in the lesson record event table 115 (step S204). S205). Then, the information processing apparatus 100 shifts the position of the start pointer in the lesson record sensor information table 113 to the next record in the adapted data string (step S206). Subsequently, the information processing apparatus 100 returns the start pointer to the top of the event detection rule table 114 (step S207). Thereafter, the information processing apparatus 100 determines whether there is a record after the start pointer of the lesson record sensor information table 113 (step S208).

  At this time, if there is no record (No at Step S208), the information processing apparatus 100 ends the process. Further, when there is a record (Yes at Step S208), the information processing apparatus 100 executes the process at Step S202. In addition, when there is no rule in step S203 (No in step S203), the information processing apparatus 100 shifts the position of the start pointer in the lesson record sensor information table 113 to the next record (step S209), and then in step S207. Execute the process. If the information processing apparatus 100 determines in step S204 that there is no data string that matches the rule condition (No in step S204), the information processing apparatus 100 shifts the position of the start pointer in the event detection rule table 114 to the next record. (Step S210).

[Association Processing According to Embodiment 1]
Next, the association process according to the first embodiment will be described with reference to FIG. FIG. 16 is a flowchart illustrating an example of a flow of association processing according to the first embodiment.

  For example, as illustrated in FIG. 16, the information processing apparatus 100 installs a start pointer at the head of the class recording event table 115 and the teaching plan event table 116 (step S <b> 301). Then, the information processing apparatus 100 reads one record at the position of the start pointer from the guidance plan event table 116 and extracts a corresponding event (step S302). Subsequently, the information processing apparatus 100 determines whether or not there is a record at the position of the start pointer in the lesson recording event table 115 (step S303).

  At this time, if the information processing apparatus 100 determines that there is a record (Yes at Step S303), the information processing apparatus 100 extracts all records having the same event type as the event extracted at Step S302 from the class record event table 115 (Step S304). ). When the same event type exists (Yes at step S305), the information processing apparatus 100 calculates the similarity by comparing the time and text of the teaching plan event table 116 and the lesson recording event table 115. The largest one is selected (step S306). Subsequently, the information processing apparatus 100 determines whether or not the similarity is equal to or greater than a predetermined threshold (step S307).

  At this time, when the degree of similarity is equal to or greater than the predetermined threshold (Yes in step S307), the information processing apparatus 100 regards that the association is established and associates the information of the instruction plan event table 116 and the lesson recording event table 115 with the association table. It is stored in 117 (step S308). Then, the information processing apparatus 100 shifts the start pointer of the lesson record event table 115 to the record next to the associated record (step S309). Subsequently, the information processing apparatus 100 ends the process when the next event does not exist in the instruction plan event table 116 (No in step S310). Further, when there is a next event in the guidance plan event table 116 (Yes at Step S310), the information processing apparatus 100 moves the position of the start pointer of the guidance plan event table 116 to the next record (Step S311). The process of step S302 is executed.

  If the information processing apparatus 100 determines in step S303 that there is no record (No in step S303), the information processing apparatus 100 stores a NULL value in the class record event ID of the association table 117 (step S312). Execute the process. If the same event type does not exist in step S305 (No in step S305), the information processing apparatus 100 stores a NULL value in the class record event ID of the association table 117 (step S312), and the process of step S310 Execute. Further, when the similarity is less than the predetermined threshold in Step S307 (No in Step S307), the information processing apparatus 100 stores a NULL value in the class record event ID of the association table 117 (Step S312), and Step S310. Execute the process.

[Event Recall Rate Calculation Processing According to Embodiment 1]
Next, the event reproduction rate calculation process according to the first embodiment will be described with reference to FIG. FIG. 17 is a flowchart illustrating an example of a flow of an event reproduction rate calculation process according to the first embodiment.

  For example, as illustrated in FIG. 17, the information processing apparatus 100 acquires the number of records in the guidance plan event table 116 (step S401). Then, the information processing apparatus 100 acquires the number of records for which the correspondence table 117 has been matched (step S402). Subsequently, the information processing apparatus 100 calculates the ratio of the number of records as an event recall rate (step S403). Note that the order of steps S401 and S402 may be reversed.

[Time Score Calculation Processing According to Example 1]
Next, the time score calculation process according to the first embodiment will be described with reference to FIG. FIG. 18 is a flowchart illustrating an example of a flow of time score calculation processing according to the first embodiment.

  For example, as illustrated in FIG. 18, the information processing apparatus 100 determines a shift pattern (step S501). Then, the information processing apparatus 100 calculates a time score according to the shift pattern (step S502).

[Effects of Example 1]
As described above, the information processing apparatus 100 evaluates the degree of coincidence of events by associating an instruction plan serving as an index of lesson progress and a lesson record of a lesson performed using the instruction plan with each event unit. Since it is calculated as a value, the teaching plan can be evaluated. In other words, since the information processing apparatus 100 evaluates the teaching plan by associating the teaching plan with the actual lesson in units of events, the information processing apparatus 100 is compared with the conventional technology that evaluates only the actual teaching material or associates each phrase. Thus, the evaluation of the teaching plan can be realized more suitably.

  Although the embodiments of the information processing apparatus 100 disclosed in the present application have been described so far, the present invention may be implemented in various different forms other than the embodiments described above. Therefore, different embodiments in (1) application, (2) configuration, and (3) program will be described.

(1) Application An example of an application that supports guidance plan creation using the guidance plan sharing DB data created in the first embodiment will be described with reference to FIG. FIG. 19 is a diagram illustrating a screen example of a guidance plan creation support application.

  For example, as shown in FIG. 19, in the guidance plan creation support application, when a unit name is input by a teacher or the like, the guidance plan related to the input unit name is displayed and output with an evaluation score. Then, in the guidance plan creation support application, when an arbitrary guidance plan is selected, a preview of the selected guidance plan is displayed and output. Further, in the guidance plan creation support application, when dragging and dropping from the selected guidance plan, editing is possible in the guidance plan editing area. The edited teaching plan is used in class. It is also possible to link the instruction plans reused in this way, store them in the instruction plan DB, and integrate the evaluation scores and output them by an application for supporting the instruction plan creation.

(2) Configuration Regarding information (eg, information stored in the event detection rule table 114) including processing procedures, control procedures, specific names, various data, parameters, and the like shown in the above documents and drawings, It can be changed arbitrarily unless otherwise specified.

  Each component of the illustrated information processing apparatus 100 is functionally conceptual and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or a part thereof may be functionally or physically distributed or arbitrarily distributed in arbitrary units according to various burdens or usage conditions. Can be integrated. For example, the acquisition unit 121 may execute processing using sensor data received in advance without receiving sensor data from the terminals 10a to 10n. In addition, the acquisition unit 121 not only determines who's behavior using the user profile table 112 with a fixed user for each terminal, but uses, for example, voice authentication of voice data obtained from sensor data. You may judge. In addition, after the lesson when all sensor acquisitions are completed, the process may be sequentially performed during the class, instead of performing the process in batches.

  In addition, in the text conversion performed by the acquisition unit 121, the speech recognition dictionary may be created using the appearance words as a dictionary based on the data in the instruction plan event table 116. That is, since the teaching plan is created before the lesson is performed, a dictionary can also be created in advance, thereby improving the accuracy of voice recognition. The association may be corrected by a UI (User Interface) that can be viewed and corrected on the teacher's terminal screen. At this time, if the event is corrected, it may be added to the event detection rule table 114 based on the sensor information at that time.

  In addition, the list of the class record event table 115 and the class record sensor information table 113 may be browsed on the teacher's terminal screen, and a UI that can access corresponding parts of raw data such as voice corresponding to the selected data is used. You may do it. At this time, the lesson record sensor information table 113 may hold a pointer to the audio raw data, and the lesson record event table 115 may hold a pointer to the lesson record sensor information table 113. As a result, when it is considered that the result of the voice recognition is not accurate, the voice at the corresponding portion can be immediately accessed and the correction can be easily performed.

(3) Program The various processes of the information processing apparatus described in the above embodiments can be realized by executing a program prepared in advance on a computer system such as a personal computer or a workstation. Therefore, in the following, an example of a computer that executes a teaching plan evaluation program having the same function as the information processing apparatus described in the above embodiment will be described with reference to FIG. FIG. 20 is a diagram illustrating a computer that executes a teaching plan evaluation program.

  As shown in FIG. 20, a computer 1000 includes a CPU (Central Processing Unit) 1100, a ROM (Read Only Memory) 1200, an HDD (Hard Disk Drive) 1300, and a RAM (Random Access Memory) 1400. These units 1000 to 1400 are connected via a bus 1500.

  The ROM 1200 stores in advance a teaching plan evaluation program that exhibits the same functions as the acquisition unit 121, the event detection unit 122, the event extraction unit 123, and the evaluation value calculation unit 124 described in the first embodiment. . That is, as shown in FIG. 20, the ROM 1200 stores a teaching plan evaluation program 1200a. Note that the program 1200a may be separated as appropriate. Then, the CPU 1100 reads the program 1200a from the ROM 1200 and executes it. Further, the HDD 1300 is provided with an event detection rule 1300a and a guidance plan event 1300b. The event detection rule 1300a corresponds to the event detection rule table 114 shown in FIG. The guidance plan event 1300b corresponds to the guidance plan event table 116 shown in FIG.

  Then, the CPU 1100 reads out the event detection rule 1300a and the instruction plan event 1300b and stores them in the RAM 1400. Further, the CPU 1100 executes the guidance plan evaluation program using the event detection rule data 1400a and the guidance plan event data 1400b stored in the RAM 1400. Note that all the data stored in the RAM 1400 may not always be stored in the RAM 1400, and only the data required for processing may be stored in the RAM 1400. Note that the instruction plan evaluation program does not necessarily have to be stored in the ROM 1200 from the beginning.

  For example, the program is stored in a “portable physical medium” such as a flexible disk (FD), a CD-ROM, a DVD disk, a magneto-optical disk, or an IC card inserted into the computer 1000. Then, the computer 1000 may read and execute the program from these. Further, the program is stored in “another computer (or server)” connected to the computer 1000 via a public line, the Internet, a LAN, a WAN, or the like. Then, the computer 1000 may read and execute the program from these.

DESCRIPTION OF SYMBOLS 100 Information processing apparatus 110 Storage part 111 Sensor data 112 User profile table 113 Class record sensor information table 114 Event detection rule table 115 Class record event table 116 Instruction plan event table 117 Correlation table 118 Instruction plan sharing DB
DESCRIPTION OF SYMBOLS 120 Control part 121 Acquisition part 122 Event detection part 123 Event extraction part 124 Evaluation value calculation part

Claims (6)

For each event performed by a teacher or student in a class, an event detection rule storage unit that stores a rule for detecting the event from sensor data ;
For each event held in a class according to the guidance plan, a guidance plan event storage unit that stores at least the contents of the event;
An acquisition unit for acquiring sensor data indicating the behavior of a teacher or student performed in a class ;
Using the rules stored in the event detection rule storage unit, an event detection unit for detecting an event corresponding to the rule from the sensor data acquired by the acquisition unit;
Calculating a similarity of the contents of the event detected the a lesson plan event storage unit in the storage event in said event detecting unit, for each detected event, the maximum and becomes the similarity is equal to or greater than the predetermined threshold event An event extraction unit that extracts from the instruction plan event storage unit ;
An evaluation value calculation unit that calculates an evaluation value using at least a ratio of the number of events extracted by the event extraction unit and the number of events stored in the instruction plan event storage unit. Information processing device. The evaluation value calculation unit corresponds to an event that is final in time series among the events extracted by the event extraction unit and an event that is final in time series among events stored in the instruction plan event storage unit. In this case, the evaluation value of the teaching plan is calculated by further using the predetermined total time of the lesson and time information of the event that is final in time series among the events extracted by the event extraction unit. The information processing apparatus according to claim 1. The evaluation value calculation unit, when an event that is final in time series among events extracted by the event extraction unit corresponds to an event that is final in time series among events detected by the event detection unit, The time that was originally scheduled for the event stored in the instruction plan event storage unit corresponding to the total time of the predetermined class and the event that is final in time series among the events extracted by the event extraction unit further by using the information processing apparatus according to claim 1, characterized in that to calculate the evaluation value of the lesson plan. The event extraction unit includes text information or time information related to the event corresponding to the rule detected from the sensor data by the event detection unit for each text information or time information related to the event stored in the instruction plan event storage unit. The information processing apparatus according to claim 1, wherein the similarity is calculated. Obtain sensor data indicating the behavior of teachers or students in class ,
For each event performed by a teacher or student in a class, an event corresponding to the rule is obtained from the acquired sensor data using a rule stored in an event detection rule storage unit that stores a rule for detecting the event from the sensor data. Detect
For each event to be executed in classes along the lesson plan to calculate the events stored in the lesson plan event storage unit for storing at least the content of the event, the similarity of the contents of said detected event,
Among the calculated similarities, an event whose maximum similarity is a predetermined threshold or more is extracted from the instruction plan event storage unit ,
A guidance plan evaluation program that causes a computer to execute a process of calculating an evaluation value using at least a ratio between the number of extracted events and the number of events stored in the guidance plan event storage unit. A teaching plan evaluation method executed by a computer,
Obtain sensor data indicating the behavior of teachers or students in class ,
For each event performed by a teacher or student in a class, an event corresponding to the rule is obtained from the acquired sensor data using a rule stored in an event detection rule storage unit that stores a rule for detecting the event from the sensor data. Detect
For each event to be executed in classes along the lesson plan to calculate the events stored in the lesson plan event storage unit for storing at least the content of the event, the similarity of the contents of said detected event,
Among the calculated similarities, an event whose maximum similarity is a predetermined threshold or more is extracted from the instruction plan event storage unit ,
An evaluation value is calculated by using at least a ratio between the number of extracted events and the number of events stored in the instruction plan event storage unit.

Images