JP2014115344A - Characteristic estimation method, characteristic estimation device, and characteristic estimation program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a characteristic estimation method, a characteristic estimation device, and a characteristic estimation program capable of supporting implementation for effective learning guidance.SOLUTION: In a characteristic estimation device, an estimating part 53 estimates a characteristic of a predetermined user on the basis of information at initial access timing to each of a plurality of material data by the predetermined user among access histories of users to the material data of a lecture.

Description

  The present invention relates to a characteristic estimation method, a characteristic estimation apparatus, and a characteristic estimation program.

  In recent years, systems that support learning have been provided. For example, higher education institutions such as universities have introduced a system called Learning Management System (LMS) that provides functions such as folders that store lecture data, bulletin boards, attendance management, and report reception. Yes. This learning management system is sometimes called a class support system.

  In recent years, higher education institutions have been required to provide instruction to students. There are conventional techniques that support such learning guidance. For example, Purdue University in the United States has introduced a system called “Course Signals”. Course Signals first calculates a prediction formula for predicting grades from behaviors related to learning, using behaviors and grade data related to learning in past lectures. Next, Course Signals predicts student performance for a lecture using prediction formulas from student learning behavior data during the current lecture. The learning behavior data includes the time spent in the learning support system, the number of acquired lecture material files, and the like. And Course Signals raises an alarm for students who are likely to have poor grades.

  In addition, for example, conventional technology that classifies students into several types based on past student learning history information (subjects, grades, learning time, number of questions, teaching materials used, instructors instructed, answer results, etc.) Has been proposed.

JP 2003-131549 A

“Course Signals”, [online], [searched November 27, 2012], Internet <URL: http://www.itap.purdue.edu/learning/tools/signals/>

  However, none of the conventional techniques considers what characteristics the student's behavior has, and there is a problem that effective learning guidance cannot be performed.

  An object of the present invention is to provide a characteristic estimation method, a characteristic estimation apparatus, and a characteristic estimation program that can support the implementation of effective learning instruction.

  According to an aspect of the present invention, the characteristic estimation method is based on information on the initial access timing of each of a plurality of material data by a predetermined user from among user access histories to the material data of the lecture. The process of estimating the user characteristics is executed.

  Can support the implementation of effective learning instruction.

FIG. 1 is a diagram illustrating the overall configuration of the characteristic estimation apparatus. FIG. 2 is a diagram illustrating an example of a data structure of attendance lecture information. FIG. 3 is a diagram illustrating an example of a data structure of lecture information. FIG. 4 is a diagram illustrating an example of a data configuration of access history information. FIG. 5 is a diagram illustrating an example of a data configuration of the material registration date information. FIG. 6 is a diagram illustrating an example of the data configuration of the access material number information. FIG. 7 is a diagram illustrating an example of a data configuration of common material information. FIG. 8 is a diagram illustrating an example of the data structure of the selected material information. FIG. 9 is a diagram illustrating an example of a data configuration of announcement date information. FIG. 10 is a diagram illustrating an example of a data configuration of test date information. FIG. 11 is a diagram illustrating an example of a data configuration of the lecture-specific characteristic estimation information. FIG. 12 is a diagram illustrating an example of a data configuration of student characteristic estimation information. FIG. 13 is a flowchart illustrating the procedure of the characteristic estimation process. FIG. 14 is a flowchart showing the procedure of the lecture selection process. FIG. 15 is a flowchart illustrating the procedure of the lecture determination process. FIG. 16 is a flowchart showing the procedure of the lecture material selection process. FIG. 17 is a flowchart showing a procedure of lecture-specific characteristic estimation processing. FIG. 18 is a flowchart showing the procedure of the characteristic determination process. FIG. 19 is a diagram illustrating a computer that executes a characteristic estimation program.

  Embodiments of a characteristic estimation method, a characteristic estimation apparatus, and a characteristic estimation program according to the present invention will be described below in detail with reference to the drawings. Note that the present invention is not limited to the embodiments. Each embodiment can be appropriately combined within a range in which processing contents are not contradictory.

  A system according to the first embodiment will be described. FIG. 1 is a diagram illustrating the overall configuration of the characteristic estimation apparatus. The characteristic estimation apparatus 10 is an apparatus that estimates a user's characteristics. The characteristic estimation device 10 is, for example, a computer such as a server computer. The characteristic estimation device 10 may be implemented as a single computer, or may be implemented as a cloud of a plurality of computers. In this embodiment, a case where the characteristic estimation apparatus 10 is a single computer will be described as an example.

  The characteristic estimation device 10 can communicate with other devices via a network (not shown). In the present embodiment, the learning management system 40 is introduced and operated in the characteristic estimation apparatus 10. The learning management system 40 provides various functions that support learning of users such as students. For example, the learning management system 40 provides functions such as a folder storing lecture material data, a bulletin board, attendance management, and report reception. A user such as a student uses a terminal device such as a personal computer (PC), a mobile phone, or a smartphone to access the characteristic estimation device 10 via a network and use various functions provided by the learning management system 40. To do. For example, a student acquires material data used in a lecture before or after a lecture. In addition, for example, a student registers questions and contents of questions in a lecture on a bulletin board. Also, for example, the student registers that he / she attended the lecture by accessing the learning management system 40 at the start of the lecture. Also, for example, the student submits a report by transmitting report data created for the assignment given in the lecture. The learning management system 40, when accessed by a student and using various functions, stores a student access history regarding the used function.

  In addition, the characteristic estimation apparatus 10 operates by introducing a characteristic estimation system 41 that estimates the characteristics of the user. When any student is designated as the user who estimates the characteristic, the characteristic estimation system 41 estimates the characteristic based on the access history of the specified student. For example, the characteristic estimation system 41 estimates characteristics related to student learning.

  Next, the configuration of the characteristic estimation apparatus 10 according to the first embodiment will be described. As illustrated in FIG. 1, the characteristic estimation apparatus 10 includes a communication I / F (interface) unit 20, a display unit 21, an input unit 22, a storage unit 23, and a control unit 24.

  The communication I / F unit 20 is an interface that performs communication control with another device, for example, a terminal device held by a user such as a student. The communication I / F unit 20 transmits and receives various types of information to and from other devices via a network (not shown). For example, the communication I / F unit 20 receives an access request to the learning management system 40 and the characteristic estimation system 41 from a user terminal device. As an aspect of the communication I / F unit 20, a network interface card such as a LAN card can be employed.

  The display unit 21 is a display device that displays various types of information. Examples of the display unit 21 include display devices such as a Liquid Crystal Display (LCD) and a Cathode Ray Tube (CRT). The display unit 21 displays various information.

  The input unit 22 is an input device that inputs various types of information. For example, the input unit 22 includes an input device such as a mouse or a keyboard. The input unit 22 receives an operation input from the user and inputs operation information indicating the received operation content to the control unit 24.

  The storage unit 23 is a storage device such as a hard disk, a solid state drive (SSD), or an optical disk. The storage unit 23 may be a semiconductor memory that can rewrite data, such as a random access memory (RAM), a flash memory, and a non-volatile static random access memory (NVSRAM).

  The storage unit 23 stores various programs that operate as an operating system (OS) executed by the control unit 24, the learning management system 40, and the characteristic estimation system 41. Furthermore, the storage unit 23 stores various data used in programs executed by the control unit 24. For example, the storage unit 23 stores attendance lecture information 60, lecture information 61, access history information 62, and material registration date information 63. In addition, the storage unit 23 stores access material number information 64, common material information 65, selected material information 66, announcement date information 67, test date information 68, lecture-specific characteristic estimation information 69, and student-specific characteristic estimation. Information 70 is stored.

  The attended lecture information 60 is data storing information indicating lectures being taken and taken for each student. In the present embodiment, information indicating a lecture that the student has already taken is stored in the attended lecture information 60, but information indicating a lecture that is currently being taken may be included. In addition, the attendance lecture information 60 may store only information indicating the lecture currently being attended. As an example, the attendance lecture information 60 is registered by the learning management system 40. As another example, the attendance lecture information 60 is referred to by the selection unit 51 described later when selecting a lecture whose behavior characteristics are easy to guess from a lecture that the user has already attended.

  FIG. 2 is a diagram illustrating an example of a data structure of attendance lecture information. As shown in FIG. 2, the attendance lecture information 60 includes items of “student ID” and “attendance lecture ID list”. The item of student ID (identification) is an area for storing information for identifying a student. The student is given an ID number for identifying each by combining numbers and letters. In the student ID item, an ID number assigned to each student is stored. The item in the lecture attendance ID list is an area for storing information indicating a lecture that has been taken by a student whose ID number is stored in the student ID item. In the lecture, identification information indicating the lecture such as a lecture name and a lecture number is defined. The item of the lecture attendance ID list stores identification information of the lecture attended by the student.

  In the example of FIG. 2, the student whose student ID is “Student 1” indicates that “Lecture 1”, “Lecture 2”, “Lecture 3”, and “Lecture 4” have been taken.

  Returning to FIG. 1, the lecture information 61 is data storing information related to a lecture. As an example, data of the lecture information 61 is registered by the learning management system 40 and the selection unit 51 described later. As another example, the lecture information 61 is referred to by the selection unit 51 described later when selecting a lecture in which a behavior characteristic easily appears.

  FIG. 3 is a diagram illustrating an example of a data structure of lecture information. As shown in FIG. 3, the lecture information 61 includes “lecture ID”, “number of students”, “type”, “number of lecture materials”, “average number of materials accessed”, “standard deviation of materials accessed”, “ Each item of “Selected Lecture”. The item of lecture ID is an area for storing lecture identification information. In the lecture ID item, lecture identification information is stored. The item of the number of students is an area for storing the number of students who have taken the lecture. The number of students field stores the number of students who have taken a lecture whose identification information is stored in the lecture ID field. The type item is an area for storing the type of lecture. In this embodiment, the type identifies whether the lecture is a selected subject or a required subject. The type item stores “selected” if the lecture whose identification information is stored in the lecture ID item is a selected subject, and stores “required” if the lecture is a required subject. The item of the number of lecture materials is an area for storing the number of material data used in the lecture. In the item of the number of lecture materials, the number of material data used in the lecture in which identification information is stored in the item of lecture ID is stored. The item “average number of access to material” is an area for storing an average value of the number of times each student has accessed the material data used in the lecture. In the item of average number of access to materials, an average value of the number of times each student has accessed the material data used in the lecture whose identification information is stored in the item of lecture ID is stored. The item of standard deviation of the number of access to materials is an area for storing the standard deviation of the number of accesses to the material data used in the lecture. The standard deviation of the number of student accesses to the material data used in the lecture in which the identification information is stored in the item of the lecture ID is stored in the item of standard deviation of the number of material accesses. The item of the selected lecture is an area for storing whether or not the lecture is easy to guess the behavior characteristic. In the selected lecture item, if the lecture whose identification information is stored in the lecture ID item is a lecture whose behavior characteristics are easy to guess, “OK” is stored, and the lecture whose identification information is stored guesses the behavior characteristics If the lecture is difficult, “NG” is stored.

  In the example of FIG. 3, the lecture with the lecture ID “Lecture 1” has the number of students “200”, is a selected subject, and the number of material data used in the lecture is “4”. Show. Also, the lecture with the lecture ID “Lecture 1” has an average value of the number of access to the material “3”, a standard deviation of the number of access to the material “1”, and the item of the selected lecture is “OK”. Indicates that the lecture is easy to guess behavioral characteristics.

  Returning to FIG. 1, the access history information 62 is data that stores a history of student access to the material data used in the lecture. In this embodiment, the access history information 62 stores the date of the first access to the material data as the history, but all the access dates may be stored. As an example, the access history information 62 is registered by the learning management system 40. As another example, the access history information 62 is referred to by the estimation unit 52 described later when estimating the announcement date and the test date. As another example, the access history information 62 is referred to by the estimation unit 53 described later when estimating characteristics.

  FIG. 4 is a diagram illustrating an example of a data configuration of access history information. As shown in FIG. 4, the access history information 62 includes items of “lecture ID”, “material ID”, “student ID”, and “first access date”. The item of lecture ID is an area for storing lecture identification information. In the lecture ID item, identification information indicating a lecture is stored. The item of material ID is an area for storing identification information of material data used in the lecture. In the material data, for example, identification information for identifying each of the file name and the material name is defined. In the item of material ID, identification information of material data used in the lecture in which the identification information is stored in the item of lecture ID is stored. The student ID item is an area for storing the ID number of the student who has accessed the material data. The student ID item stores the ID number of the student who has accessed the material data in which the identification information is stored in the material ID item. The item of the first access date is an area for storing the date when the student accessed the material data for the first time. The first access date item stores the date when the student whose ID number is stored in the student ID item accesses the material data whose identification information is stored in the material ID item for the first time.

  In the example of FIG. 4, the material data with the material ID “material 1” used in the lecture with the lecture ID “lecture 1” is the first access by the student with the student ID “student 1” to “5/2”. Indicates that

  Returning to FIG. 1, the material registration date information 63 is data storing the date when the material data used in the lecture is registered in the learning management system 40 and the material data can be accessed by the students. As an example, the material registration date information 63 is registered by the learning management system 40. As another example, the material registration date information 63 is referred to by the selection unit 51 described later when selecting material data that easily exhibits behavioral characteristics. As another example, the material registration date information 63 is referred to by the estimation unit 52 described later when estimating the announcement date and the test date.

  FIG. 5 is a diagram illustrating an example of a data configuration of the material registration date information. As shown in FIG. 5, the material registration date information 63 includes items of “lecture ID”, “material ID”, and “material registration date”. The item of lecture ID is an area for storing lecture identification information. The lecture ID item stores identification information of the lecture in which the material data is registered. The item of material ID is an area for storing identification information of material data. In the item of material ID, identification information of registered material data is stored. The material registration date item is an area for storing the date when the material data was registered. The date when the material data was registered is stored in the material registration date item.

  In the example of FIG. 5, the material data with the material ID “material 1” used in the lecture with the lecture ID “lecture 1” is registered in “5/1”.

  Returning to FIG. 1, the access material number information 64 is data that stores the number of material data accessed by each student. As an example, the access material number information 64 is registered by the selection unit 51 (to be described later) when selecting material data that easily exhibits behavioral characteristics. As another example, the access material number information 64 is referred to by the selection unit 51 described later when selecting material data in which behavioral characteristics are likely to appear.

  FIG. 6 is a diagram illustrating an example of the data configuration of the access material number information. As shown in FIG. 6, the access material number information 64 includes items of “student ID”, “number of materials”, and “determination result”. The student ID item is an area for storing a student ID number obtained by counting the number of material data. In the student ID item, a student ID number obtained by counting the number of material data is stored. The item of the number of materials is an area for storing the number of material data accessed within a predetermined first access period from the registration date. The number of material data item stores the number of material data accessed by the student whose ID number is stored in the student ID item within the first access period from the registration date. The item of the determination result is an area for storing a determination result as to whether or not the student is a serious student who accesses the material data at an early stage. In this embodiment, it is determined whether or not the student is a serious student based on the access time for the material data. In the determination result item, when the student whose ID number is stored in the student ID item is a student determined to be serious, “YES” is stored, and when the student is not determined to be serious, “ “NO” is stored.

  In the example of FIG. 6, the student ID “Student 1” has the number of material data accessed within the first access period from the registration date is “3”, and the determination result is “YES”. , Indicates that the student is determined to be serious.

  Returning to FIG. 1, the common material information 65 is data that stores a result of selecting material data in which a user's behavior characteristic is likely to appear. In the present embodiment, the material data in which the user's behavior characteristics easily appear is also referred to as “common material”. As an example, the common material information 65 is registered by a selection unit 51 (to be described later) when selecting material data of a common material in which common material behavior characteristics are likely to appear. As another example, the common material information 65 is referred to by the estimation unit 52 and the estimation unit 53 described later when estimating the characteristics of the user.

  FIG. 7 is a diagram illustrating an example of a data configuration of common material information. As shown in FIG. 7, the common material information 65 includes items of “lecture ID” and “material ID list”. The item of lecture ID is an area for storing identification information of a lecture for which common material is selected. The lecture ID item stores identification information of a lecture for which the common material is selected. The item of the material ID list is an area for storing identification information of the common material and the selected material data. The item of the material ID list stores the identification information of the common material and the selected material data for the lecture in which the identification information is stored in the item of the lecture ID.

  In the example of FIG. 7, the lecture whose identification information is “Lecture 1” indicates that the material data of “Material 1”, “Material 2”, and “Material 3” are common materials.

  Returning to FIG. 1, the selected material information 66 is data that stores the number of common materials and selected material data. As an example, the selection material information 66 is registered by the selection unit 51 described later when selecting a common material. As another example, the selection material information 66 is referred to by the estimation unit 52 and the estimation unit 53 described later when estimating the characteristics of the user.

  FIG. 8 is a diagram illustrating an example of the data structure of the selected material information. As shown in FIG. 8, the selected material information 66 includes items of “lecture ID” and “number of materials”. The item of lecture ID is an area for storing lecture identification information. The lecture ID item stores identification information of a lecture for which the common material is selected. The item of the number of materials is an area for storing the number of material data regarded as common materials. In the item of the number of materials, the number of material data set as the common material for the lecture in which the identification information is stored in the item of the lecture ID is stored.

  In the example of FIG. 8, the lecture whose identification information is “Lecture 1” indicates that the number of material data set as common material is “3”.

  Returning to FIG. 1, the announcement date information 67 is data that stores the date on which the document data is estimated to have been announced in the lecture. As an example, the announcement date information 67 is referred to by the estimation unit 52 described later when estimating the characteristics of the user. As another example, the announcement date information 67 is referred to by the estimation unit 53 described later when estimating the characteristics of the user.

  FIG. 9 is a diagram illustrating an example of a data configuration of announcement date information. As shown in FIG. 9, the announcement date information 67 has items of “lecture ID”, “material ID”, and “material announcement date”. The item of lecture ID is an area for storing lecture identification information. The lecture ID item stores identification information of a lecture that uses the material data on which the announcement date is estimated. The item of material ID is an area for storing identification information of material data. In the item of the material ID, identification information of the material data on which the announcement date is estimated is stored. The item of the material announcement date is an area for storing the estimated announcement date. In the material announcement date item, an announcement date estimated for the material data in which the identification information is stored in the material ID item is stored.

  In the example of FIG. 9, the document data whose identification information is “Lecture 1” and whose identification information is “Material 1” indicates that the estimated announcement date is “5/2”.

  Returning to FIG. 1, the test date information 68 is data storing a date on which the test is estimated to be performed in the lecture. As an example, the test date information 68 is registered by the estimation unit 52 described later when selecting material data in which behavioral characteristics are likely to appear. As another example, the test date information 68 is referred to by the estimation unit 53 described later when estimating the characteristics.

  FIG. 10 is a diagram illustrating an example of a data configuration of test date information. As shown in FIG. 10, the test date information 68 includes items of “lecture ID” and “test date”. The item of lecture ID is an area for storing lecture identification information. The lecture ID item stores identification information of a lecture whose test date is estimated. The test date item is an area for storing a test date estimated to have been tested. The test date item stores an estimated test date for a lecture whose identification information is stored in the lecture ID item.

  In the example of FIG. 10, the lecture with the identification information “Lecture 1” indicates that the estimated test date is “7/25”.

  Returning to FIG. 1, the lecture-specific characteristic estimation information 69 is data storing various data used for estimating the student characteristics for each lecture. As an example, the lecture-specific characteristic estimation information 69 is registered by the estimation unit 53 described later when estimating characteristics. As another example, the lecture-specific characteristic estimation information 69 is referred to by the estimation unit 53 described later when estimating characteristics.

  FIG. 11 is a diagram illustrating an example of a data configuration of the lecture-specific characteristic estimation information. As shown in FIG. 11, the lecture-specific characteristic estimation information 69 includes “lecture ID”, “student ID”, “number of early access materials”, “early access rate”, “number of previous access materials”, and “previous access rate”. , Each item of “estimation result”. The item of lecture ID is an area for storing lecture identification information. In the lecture ID item, identification information of a lecture in which the characteristics of the student are estimated is stored. The student ID item is an area for storing the ID number of the student whose characteristics are estimated. The student ID item stores the ID number of the student whose characteristics are estimated in the lecture in which the identification information is stored in the lecture ID item. The item of the number of early access materials is an area for storing the number of early access material data accessed early. In the early access material number item, in the lecture in which the identification information is stored in the lecture ID item, the early access material data that the student whose ID number is stored in the student ID item accessed the material data early Is stored. The item of the early access rate is an area for storing a rate of early access to the material data. The early access rate item stores the rate at which the student whose ID number is stored in the student ID item accesses the document data early in the lecture in which the identification information is stored in the lecture ID item. The The item of the number of materials accessed immediately before is an area for storing the number of material data of the last accessed data accessed immediately before the test. In the item of the number of the last access material, in the lecture in which the identification information is stored in the item of the lecture ID, the material data of the access immediately before the student whose ID number is stored in the item of the student ID accessed the data immediately before the test. Is stored. The item of the previous access rate is an area for storing a rate of access immediately before the test. The last access rate item stores the percentage of students whose ID number was stored in the student ID item in the lecture whose identification information was stored in the lecture ID item and accessed the material data immediately before the test. The The item of the estimation result is an area for storing a result of estimating the student characteristics.

  Here, in the present embodiment, the student's characteristic for learning is estimated based on the early access rate and the previous access rate. In the present embodiment, for example, when the early access rate is equal to or greater than the previous access rate, the first type is estimated, and when the early access rate is lower than the previous access rate, the second type is estimated. The first type is a type in which learning is planned because the early access rate is equal to or greater than the previous access rate. In the present embodiment, the first mold is also referred to as a “knack type”. The second type is a type in which learning is performed immediately before the test because the early access rate is lower than the previous access rate. In this embodiment, the second mold is also referred to as “immediate mold”. In addition, the name which shows a 1st type | mold and a 2nd type | mold is not limited to this, As long as each characteristic is expressed, any may be sufficient. For example, the first type may be referred to as a “plan type”. Further, the second mold may be referred to as a “deadline mold” or the like.

  In the guess result item, if it is inferred to be a trick type (first type), it is stored as “trick type”, and if it is inferred to be the immediately preceding type (second type), it is stored as “previous type”. The

  In the example of FIG. 11, in the lecture whose identification information is “Lecture 1”, the student whose ID number is “Student 1” has the number of early access materials “3” and the early access rate “1.0”. Indicates that there is. In addition, in the lecture whose identification information is “Lecture 1”, the student whose ID number is “Student 1” has the previous access number as “0”, the previous access rate as “0”, and the guess result is "Type".

  Returning to FIG. 1, the student-specific characteristic estimation information 70 is data that stores various types of data used to estimate student characteristics. As an example, the student-specific characteristic estimation information 70 is registered by the estimation unit 53 described later when estimating characteristics. As another example, the student-specific characteristic estimation information 70 is referred to by the estimation unit 53 described later when estimating characteristics.

  FIG. 12 is a diagram illustrating an example of a data configuration of student characteristic estimation information. As shown in FIG. 12, the student-specific characteristic estimation information 70 includes items of “student ID”, “number of knack-type lectures”, “number of immediately preceding lectures”, and “estimation”. The student ID item is an area for storing the ID number of the student whose characteristics are estimated. In the student ID item, the ID number of the student whose characteristics are estimated is stored. The item of “number of lectures” is an area for storing the number of lectures estimated to be of the “knack” type. In the item of “number of lectures”, the number of lectures estimated to be of the “knack” type for the student whose ID number is stored in the item of student ID is stored. The item of the number of immediately preceding lectures is an area for storing the number of lectures estimated to be the immediately preceding type. In the item of the number of immediately preceding lectures, the number of lectures presumed to be the immediately preceding type is stored for the student whose ID number is stored in the item of student ID. The guess item is an area for storing a guess result obtained by guessing a student's learning characteristic from a guess result of each lecture. In the present embodiment, it is estimated whether the characteristic relating to the student's learning is a stubborn type or a previous type. In the guess item, if it is estimated to be a trick type, it is stored as “trick type”, and if it is estimated as a previous type, “previous type” is stored.

  In the example of FIG. 12, the student whose ID number is “Student 1” has “3” as the number of lectures that are estimated to be a trick, and “0” as the number of lectures that are estimated as the immediately preceding type. Indicates that the result is a “trick” type.

  Returning to FIG. 1, the control unit 24 is a device that controls the characteristic estimation apparatus 10. As the control unit 24, an electronic circuit such as a central processing unit (CPU) or a micro processing unit (MPU), or an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA) can be employed. The control unit 24 has an internal memory for storing programs defining various processing procedures and control data, and executes various processes using these. The control unit 24 operates as various systems by operating various programs, and functions as various processing units. For example, in the control unit 24, the learning management system 40 and the characteristic estimation system 41 operate.

  The learning management system 40 provides various functions that support learning of users such as students. The learning management system 40 provides functions such as a folder storing lecture material data, a bulletin board, attendance management, and report reception, for example. The learning management system 40 manages various data used for the provided functions. For example, the learning management system 40 registers and manages the identification information of the lecture taken for each student in the attendance lecture information 60. In addition, the learning management system 40 registers and manages the number of students attending the lecture, the type of lecture, and the number of material data used in the lecture in the lecture information 61 for each lecture. In addition, the learning management system 40 manages the material data for each lecture, for example, divided into folders. When the lecture material data is registered by a lecturer or the like, the date when the material data is registered is the material registration date. Register and manage information 63. In addition, the learning management system 40 stores a student access history for each material data of each lecture. Then, the learning management system 40 totals the number of accesses made by each student to the material data, obtains the average value of each student's access, and the standard deviation of the number of accesses, and registers and manages it in the lecture information 61. . In addition, when the material data is accessed by a student, the learning management system 40 registers and manages the access date accessed for the first time in the access history information 62 for each material data.

  The characteristic estimation system 41 provides a function for estimating the characteristics of the user from the access history related to the material data stored in the access history information 62. The characteristic estimation system 41 includes a reception unit 50, a selection unit 51, an estimation unit 52, an estimation unit 53, and an output unit 54.

  The reception unit 50 performs various receptions. For example, the reception unit 50 receives the designation of the user who estimates the characteristics. For example, the accepting unit 50 displays a designation screen for designating a student on a terminal device of an instructor who performs learning guidance, such as a lecturer, and accepts designation of a student as a user who estimates characteristics from the designation screen.

  The selection unit 51 performs various selections. For example, the selection unit 51 selects a lecture whose behavior characteristics are easy to guess from the lectures already taken by the user designated by the reception unit 50 stored in the attended lecture information 60. Here, lectures with a high degree of freedom in student behavior tend to give a characteristic of student behavior because of their independence. Lectures with a high degree of freedom of behavior of students include, for example, lectures with a large number of students, lectures of elective subjects, and lectures in which actual student behavior is diverse. Lectures with a large number of students tend to be characterized by the behavior of students because it is difficult for the instructor to closely observe and teach. In addition, in the elective courses, students do not necessarily have to acquire credits, and it is up to the student to decide whether to take the courses, so the behavioral characteristics of the students are likely to appear. Lectures with diverse student behavior tend to give a distinctive character of student behavior because each student behaves differently. Lectures with a variety of student behaviors have a large coefficient of variation (standard deviation / average value) in the number of accesses to the lecture material data because the students have different times to access the material data of the lecture. In this embodiment, based on the coefficient of variation of the number of accesses to the lecture material data, it is determined whether the student's behavior is various.

  The selection unit 51 selects a lecture with a high degree of freedom of behavior of students as a lecture that makes it easy to guess behavioral characteristics. For example, the selection unit 51 refers to the attended lecture information 60 and identifies the lecture that the user designated by the reception unit 50 has taken. Then, for each identified lecture, the selection unit 51 refers to the lecture information 61 and divides the standard deviation of the number of access to the material by the average value of the number of access to the material to calculate the variation coefficient of the access number. Then, the selection unit 51 has a lecture in which the number of participants is a predetermined number or more from each lecture that the user has taken, is a selected subject, and the variation coefficient of the number of access to the document data is a predetermined constant value or more. Select. The fixed number and the fixed value may be fixed values, or may be set to an arbitrary value by an administrator who manages the characteristic estimation device 10, and may be changed according to the number of students who can take a lecture, for example. . Further, the fixed number and the fixed value may be adjustable from the outside. In this embodiment, for example, the fixed number is set to 100 and the fixed value is set to 0.2. For example, the selection unit 51 selects a lecture having 100 or more students, a selected subject, and a coefficient of variation of the number of access to the material data of 0.2 or more.

  The selection unit 51 stores “OK” in the selected lecture item of the lecture information 61 for the selected lecture and the lecture whose behavior characteristics are easy to guess among the lectures that the user has taken. In addition, the selection unit 51 stores “NG” in the selected lecture item of the lecture information 61 for the lecture that has not been selected among the lectures that the user has taken. Thus, in the example of FIG. 3, “Lecture 1”, “Lecture 2”, and “Lecture 3” are selected as lectures whose behavior characteristics are easy to guess, and “OK” is stored in the item of the selected lecture. In addition, “lecture 4” and “lecture 5” which are not selected and lectures whose behavior characteristics are easy to guess store “NG” in the selected lecture item.

  Moreover, the selection part 51 selects the material data which a user's action characteristic tends to appear. For example, the selection unit 51 selects material data in which a user's behavior characteristic is likely to appear from each material data used in the lecture for each lecture in which the behavior characteristic is easy to guess. For example, the selection unit 51 identifies a lecture in which “OK” is stored in the selected lecture item of the lecture information 61 among the lectures already taken by the user stored in the attended lecture information 60. Then, the selection unit 51 obtains each material data to be used in the lecture with reference to the material registration date information 63 for each identified lecture, and selects the material data in which the user's behavior characteristic easily appears from each material data. . There are two types of material data used in the lecture: high importance and low importance. The less important material data is difficult for students who can access the material data to access the material data, so it is difficult to estimate the characteristics. Therefore, the selection unit 51 selects highly important material data. Here, the highly important material data is accessed by a serious student from a relatively early stage. Therefore, in the present embodiment, a serious student is estimated, and the material data accessed by the estimated serious student in common is selected as highly important material data. For example, the selection unit 51 counts the number of material data accessed within a predetermined first access period from the registration date of the material data for each student. The first access period may be a fixed value, or may be set to an arbitrary value by an administrator who manages the characteristic estimation device 10. The first access period may be adjustable from the outside. In this embodiment, for example, the first access period is set to one week. For each student, the selection unit 51 counts the number of material data accessed within one week from the registration date. The selection unit 51 stores the number of material data aggregated for each student in the item of the number of materials in the access material number information 64.

  Then, the selection unit 51 extracts the first ratio of students in descending order of the number of the totaled document data. The first ratio may be a fixed value, or may be set to an arbitrary value by an administrator who manages the characteristic estimation device 10. Further, the first ratio may be changed according to the number of lecture attendees, for example. The first ratio may be adjustable from the outside. In this embodiment, for example, the first ratio is 10%. The selection unit 51 extracts 10% of students in descending order of the number of material data accessed within the first access period from the registration date. In this embodiment, this extracted student is a student who is assumed to be serious.

  The selection unit 51 stores “YES” in the item of the determination result of the access material number information 64 for the extracted student among the students. Further, the selection unit 51 stores “NO” in the item of the determination result of the access material number information 64 for the students other than the extracted students. In the example of FIG. 6, “Student 1” and “Student 2” have a large number of material data within one week from the registration date to access, and are extracted as serious students. “YES” is stored.

  Then, the selection unit 51 identifies the material data that the second or higher percentage of the extracted students accesses within the predetermined second access period from the date of registration of the material data, and uses the material in common. Select as material. This second ratio may be a fixed value, or may be set to an arbitrary value by an administrator who manages the characteristic estimation device 10. Further, the second ratio may be changed according to the number of lecture attendees, for example. The second ratio may be adjustable from the outside. In the present embodiment, for example, the second ratio is 80%. The second access period may also be a fixed value, and may be set to an arbitrary value by an administrator who manages the characteristic estimation device 10. The second access period may be adjustable from the outside. In this embodiment, for example, the second access period is set to one week which is the same as the first access period. The selection unit 51 selects, as a common material, material data that more than 80% of the extracted students access within one week from the date of registration of the material data.

  The selection unit 51 stores the identification information of the common material and the selected material data in the item of the material ID list of the common material information 65 for each lecture. In the example of FIG. 7, the lecture data of “Course 1” stores the material data of “Material 1”, “Material 2”, and “Material 3” as common materials. The selection unit 51 stores the common material and the number of selected material data in the item of the number of materials of the selected material information 66 for each lecture. In the example of FIG. 8, “3” is stored as the number of material data for the lecture “Course 1” as common material.

  The estimation unit 52 performs various estimations. For example, the estimation unit 52 estimates the announcement date when the material was announced and the test date when the lecture test was performed. Here, the material data may be registered before being used in the lecture. In addition, document data for multiple lectures may be registered at one time. For this reason, the date when the document data was registered is not necessarily the date when the document data was announced to the student at the lecture. Therefore, for example, the estimation unit 52 estimates the announcement date when the material data was announced in the lecture and the test date when the lecture test was performed for the common material and the selected material data. Based on the student access history stored by the learning management system 40, the estimation unit 52 obtains a change over time in the access rate of the user with respect to the common material and the selected material data. Then, the estimation unit 52 estimates the announcement date when the material was announced in the lecture and the test date on which the lecture test was performed from the change in the access rate. For example, the estimation unit 52 estimates the date when the access rate first becomes equal to or greater than a predetermined first threshold as the announcement date. In addition, the estimation unit 52 estimates the next weekday after the date when the access rate after the elapse of a certain period or more from the estimated announcement date has finally reached a predetermined second threshold or more as the test date. The first threshold value and the second threshold value may be fixed values, or may be set to arbitrary values by an administrator who manages the characteristic estimation device 10. Moreover, you may change this 1st threshold value and 2nd threshold value according to the number of students of a lecture, for example. Further, the first threshold value and the second threshold value may be adjustable from the outside. In this embodiment, for example, both the first threshold value and the second threshold value are 50%.

  The estimation unit 52 stores the estimated announcement date of each material data in the material announcement date item of the announcement date information 67. In the example of FIG. 9, in the lecture of “Course 1”, “Document 1” is announced to “5/2”, “Document 2” is announced to “5/9”, and “Document 3” is “5 / 16 "indicates that the estimation was announced. The estimation unit 52 stores the estimated test date of the lecture in the test date item of the test date information 68. In the example of FIG. 10, the lecture “Course 1” indicates that “7/25” is estimated as the test date.

  The estimation unit 53 performs various estimations. For example, the estimation unit 53 estimates the characteristics of the user specified by the reception unit 50 based on the information on the initial access timing of each of the plurality of material data by the user. For example, the estimation unit 53 counts the number of early access material data that was accessed for the first time within the first period from the announcement date for each material data selected for the common material for each lecture in which behavioral characteristics can be easily estimated. To do. In addition, for each lecture in which behavior characteristics can be easily estimated, the estimation unit 53 determines the number of material data of the last access for the first time within the second period immediately before the test date for each material data selected as the common material. Count. The first period and the second period may be fixed values, and may be set to arbitrary values by an administrator who manages the characteristic estimation apparatus 10. Further, the first period and the second period may be adjustable from the outside. In this embodiment, for example, both the first period and the second period are set to one week. The estimation unit 53 counts the number of material data for early access and the number of material data for the last access for each common material and each selected material data for each lecture for which behavioral characteristics can be easily estimated.

  Then, the estimation unit 53 calculates the early access rate by dividing the number of material data for early access by the number of material data that is stored as common material and stored in the selected material information 66. In addition, the estimation unit 53 calculates the previous access rate by dividing the number of material data of the previous access by the number of material data determined as the common material.

  The estimation unit 53 estimates the characteristic in the lecture from the early access rate and the previous access rate for each lecture for which it is easy to guess the behavior characteristic. For example, when the early access rate is equal to or greater than the previous access rate, the estimation unit 53 estimates the knack type. Further, when the early access rate is lower than the immediately preceding access rate, the estimating unit 53 estimates the immediately preceding type.

  For each lecture, the estimation unit 53 stores the number of early access material data, the early access rate, the number of material data for previous access, the previous access rate, and the estimation results for the user students in the lecture-specific characteristic estimation information 69. To do. In the example of FIG. 11, in the lecture “Course 1”, “Student 1” has an early access number of materials “3”, an early access rate of “1.0”, and an immediately preceding access material number of “Student 1”. “0”, the immediately preceding access rate is “0”, and the estimation result is “trick”.

  The estimation unit 53 aggregates the estimation results of characteristics for each lecture stored in the lecture-specific characteristic estimation information 69 for each user's student. For example, the estimation unit 53 aggregates the number of lectures estimated to be “trick” and the number of lectures estimated to be “immediately before” for the user students. If the number of trick-type lectures is larger than the number of previous-type lectures, the guessing unit 53 guesses the user as a trick-type lecture, and if the number of trick-type lectures is not larger than the number of previous-type lectures, Guess the user as the last type.

  The estimation unit 53 stores the number of lectures estimated to be “trick”, the number of lectures estimated to be “immediately before”, and the estimation result of user characteristics in the student-specific characteristic estimation information 70. To do. In the example of FIG. 12, the number of lectures that are estimated to be a trick type is “3”, the number of lectures that is estimated to be a previous type is “0”, and the estimation result is “a trick type”. .

  The output unit 54 performs various outputs. For example, the output unit 54 outputs image information for displaying the estimation result of the characteristic of the user on the terminal device of the leader, and displays the estimation result on the terminal device of the leader. For example, the output unit 54 displays whether the user is the “trick type” or the “immediate type”. Note that the output unit 54 may display other information. For example, the output unit 54 may display the number of lectures estimated as “trick” and the number of lectures estimated as “immediately before”. The output unit 54 may display a characteristic estimation result for each lecture.

  Since the instructor can grasp the characteristics of the user from the display content, the instructor can perform effective learning instruction.

  Thus, since the characteristic estimation apparatus 10 estimates a user's characteristic based on the information of the first access time with respect to the lecture material data, it can support effective learning guidance. In addition, the characteristic estimation apparatus 10 can estimate the characteristics of the user from the information of the first access time, and does not need to register additional information for estimating the characteristics. Can do.

  Next, the flow of the characteristic estimation process in which the characteristic estimation apparatus 10 according to the present embodiment estimates the characteristics of the user based on the access time of the user's material data will be described. FIG. 13 is a flowchart illustrating the procedure of the characteristic estimation process. This characteristic estimation process is executed, for example, at a timing when the user who estimates the characteristic is specified by the reception unit 50.

  As illustrated in FIG. 13, the selection unit 51 performs a lecture selection process of selecting a lecture whose behavior characteristics are easy to guess from lectures that the user designated by the reception unit 50 has taken (S10). By this lecture selection process, a lecture with a high degree of freedom of action is selected as a lecture that is easy to guess behavioral characteristics.

  Then, the selection unit 51 determines whether or not a lecture material selection process to be described later is completed for all selected lectures (S11). When the lecture material selection process is completed for all lectures (Yes at S11), the process proceeds to S15 described later.

  On the other hand, when the lecture material selection process has not been completed for all the lectures (No in S11), the selection unit 51 selects a lecture for which the lecture material selection process has not been completed (S12). Then, the selection unit 51 performs a lecture material selection process of selecting material data in which the user's behavior characteristics are likely to appear from the selected lecture material data (S13). By this lecture material selection process, for each lecture, material data that easily shows the behavioral characteristics of the user is selected from the lecture material data that makes it easy to guess the behavioral characteristics.

  The estimation unit 53 performs lecture-specific characteristic estimation processing for estimating the characteristics of the user specified by the reception unit 50 from the history of access to the selected material data of the selected lecture (S14). The process proceeds to S11. By the characteristic estimation process for each lecture, the characteristics of the user in the selected lecture are estimated.

  The estimation unit 53 performs a characteristic determination process for determining the characteristics of the user from the estimation results of the characteristics of the user in each lecture with a high degree of freedom of behavior of the student (S15). By this characteristic determination process, the characteristic of the user specified by the reception unit 50 is determined from the characteristic determination result in each lecture. The output unit 54 outputs the characteristic determined by the characteristic determination process (S16), and ends the process.

  Next, the flow of the lecture selection process according to the present embodiment will be described. FIG. 14 is a flowchart showing the procedure of the lecture selection process. This lecture selection process is executed from S10 of the characteristic estimation process shown in FIG.

  The selection unit 51 reads out identification information of a lecture taken by the user designated by the reception unit 50 from the attended lecture information 60 (S20). The selection unit 51 determines whether or not a lecture determination process, which will be described later, has been completed for all lectures whose identification information has been read (S21). When the lecture determination process is completed for all lectures (Yes at S21), the process proceeds to S24 described later.

  On the other hand, when the lecture determination process has not been completed for all the lectures (No in S21), the selection unit 51 selects a lecture for which the lecture determination process has not been completed (S22). And the selection part 51 performs the lecture determination process which determines the ease of guessing the action characteristic of the selected lecture (S23), and transfers to above-mentioned S21 after completion | finish of a process. For the lecture whose behavior characteristics are easy to guess by this lecture determination process, OK is stored in the selected lecture item of the lecture information 61.

  On the other hand, the selection unit 51 selects a lecture in which OK is stored in the selected lecture item of the lecture information 61 as a lecture whose behavior characteristics are easy to guess (S24), and the processing shifts to a caller of the lecture selection process.

  Next, the flow of the lecture determination process according to the present embodiment will be described. FIG. 15 is a flowchart illustrating the procedure of the lecture determination process. This lecture determination process is executed from S23 of the lecture selection process shown in FIG.

  Based on the lecture-specific characteristic estimation information 69, the selection unit 51 determines whether or not the number of students who have selected the lecture is a certain number or more (S30). If the number of students is not equal to or greater than a certain number (No at S30), the process proceeds to S35 described later.

  When the number of students is equal to or greater than a certain number (Yes at S30), the selection unit 51 determines whether or not the selected lecture is a selected subject (S31). If the selected lecture is not a selected subject (No at S31), the process proceeds to S35 described later.

  If the selected lecture is a selected subject (Yes at S31), the selection unit 51 calculates the coefficient of variation by dividing the standard deviation of the number of accesses to the lecture material data by the average value (S32). Then, the selection unit 51 determines whether or not the calculated variation coefficient is a certain value or more (S33). If the calculated coefficient of variation is not equal to or greater than a certain value (No at S33), the process proceeds to S35 described later.

  If the calculated coefficient of variation is greater than or equal to a certain value (Yes at S33), the selection unit 51 stores OK in the selected lecture item of the lecture information 61 (S34), and the process proceeds to the caller of the lecture determination process. On the other hand, in the case of negative determination in S30, S31, and S33 described above, the selection unit 51 stores NG in the selected lecture item of the lecture information 61 (S35), and the process proceeds to the caller of the lecture determination process.

  Next, the flow of the lecture material selection process according to the present embodiment will be described. FIG. 16 is a flowchart showing the procedure of the lecture material selection process. This lecture material selection process is executed from S13 of the characteristic estimation process shown in FIG.

  The selection unit 51 totals the number of material data accessed within the first period from the registration date of the material data for each student (S40). Then, the selection unit 51 extracts the first proportion of students in descending order of the number of material data accessed within the first period from the registration date (S41). Then, the selection unit 51 obtains the material data that the second or higher percentage of the extracted students access within the second period from the registration date of the material data, and uses the material data as the common material. Select (S42), and the process proceeds to the caller of the lecture material selection process.

  Next, the flow of lecture-specific characteristic estimation processing according to the present embodiment will be described. FIG. 17 is a flowchart showing a procedure of lecture-specific characteristic estimation processing. This lecture-specific characteristic estimation process is executed from S14 of the characteristic estimation process shown in FIG.

  The estimation unit 52 estimates the date of announcement for each common document (S50). For example, the estimation unit 52 obtains a change over time in the access rate of the user for each common material based on the access history information 62. Then, for each common material, the estimation unit 52 estimates the date when the access rate first becomes equal to or higher than the first threshold as the date of announcement of the common material.

  The estimation unit 52 estimates the test date of the lecture (S51). For example, the estimation unit 52 estimates the next weekday after the date when the access rate after the elapse of a certain period or more from the estimated announcement date has finally reached the second threshold or more as the test date.

  If the first access time of the common material is within the first period from the announcement date for each common material, the estimation unit 52 determines that the material data was accessed early and within the second period immediately before the test date. If there is, it is determined as the material data accessed immediately before the test (S52). Then, the estimation unit 52 counts the number of material data accessed early and the number of material data accessed immediately before the test (S53).

  The estimation unit 53 calculates an early access rate in which the first access is performed within the first period from the announcement date and a previous access rate in which the first access is performed within the second period immediately before the test date (S54). ). For example, the estimation unit 53 calculates the early access rate by dividing the number of material data accessed immediately before the test stored in the lecture-specific characteristic estimation information 69 by the number of lecture materials stored in the lecture information 61. . In addition, the estimation unit 53 divides the number of material data accessed immediately before the test stored in the lecture-specific characteristic estimation information 69 by the number of lecture materials stored in the lecture information 61 to calculate a previous access rate. .

  The estimation unit 53 determines whether the early access rate is equal to or higher than the previous access rate (S55). If the early access rate is equal to or greater than the previous access rate (Yes at S55), the estimation unit 53 estimates that it is a knack type (first type) (S56), and the process proceeds to the caller of the lecture-specific characteristic estimation process. On the other hand, when the early access rate is lower than the previous access rate (No at S55), the estimation unit 53 estimates the previous type (second type) (S57), and the process shifts to the caller of the lecture-specific characteristic estimation process. To do.

  Next, the flow of the characteristic determination process according to the present embodiment will be described. FIG. 18 is a flowchart showing the procedure of the characteristic determination process. This characteristic determination process is executed from S15 of the characteristic estimation process shown in FIG.

  The estimation unit 53 adds up the number of lectures determined to be a trick type and the number of lectures determined to be the previous type for the user specified by the reception unit 50 (S70). The estimation unit 53 compares the number of lectures determined to be a trick type with the number of lectures determined to be a previous type, and the number of lectures determined to be a trick type is greater than the number of lectures determined to be a previous type. It is determined whether or not (S71). When the number of trick-type lectures is larger than the number of previous-class lectures (Yes in S71), the estimation unit 53 estimates the user designated by the reception unit 50 as a trick-type (S72), and performs characteristic determination processing. Processing moves to the caller. On the other hand, when the number of trick-type lectures is not greater than the number of previous-class lectures (No in S71), the estimation unit 53 estimates the user designated by the reception unit 50 as the previous type (S73), and the characteristics. The process moves to the caller of the determination process.

  As described above, the characteristic estimation apparatus 10 estimates the characteristics of the user based on the information on the first access times of the plurality of material data by the user among the user's access history to the material data of the lecture. . Thereby, the characteristic estimation apparatus 10 can support implementation of effective learning instruction.

  Moreover, the characteristic estimation apparatus 10 calculates | requires the time-dependent change of the user's access rate with respect to material data based on an access history. The characteristic estimation apparatus 10 estimates the announcement date when the material was announced in the lecture and the test date on which the lecture test was performed from the change in the access rate. The characteristic estimation device 10 estimates the characteristics of the user based on whether the first access time to the document data is within a predetermined first period from the announcement date or within a predetermined second period immediately before the test date. Thus, the characteristic estimation apparatus 10 can estimate the user's characteristics with high accuracy by estimating the announcement date and the test date to estimate the user's characteristics.

  In addition, the characteristic estimation device 10 uses a plurality of document data, and the early access rate in which the first access is performed within the first period from the announcement date and the first access is performed within the second period immediately before the test date. The previous access rate is calculated. When the early access rate is equal to or higher than the access rate, the characteristic estimation device 10 estimates the first type (knock type), and when the early access rate is lower than the previous access rate, the characteristic estimation device 10 estimates the second type (immediate type). To do. Thus, the characteristic estimation apparatus 10 can estimate a user's characteristic accurately by estimating a user's characteristic using several document data.

  Moreover, the characteristic estimation apparatus 10 estimates the date when the access rate first becomes equal to or greater than the predetermined first threshold as the announcement date. The characteristic estimation device 10 estimates the next weekday after the date when the access rate after the elapse of a certain period or more from the announcement date finally becomes a predetermined second threshold or more as the test date. Thereby, the characteristic estimation apparatus 10 can estimate the announcement date and the test date with high accuracy.

  Moreover, the characteristic estimation apparatus 10 selects a lecture in which the user's characteristic is likely to appear. The characteristic estimation apparatus 10 estimates a user's characteristic based on the user's first access time to the selected lecture material data. Thereby, the characteristic estimation apparatus 10 can estimate a user's characteristic accurately.

  Moreover, the characteristic estimation apparatus 10 selects material data in which a user's behavior characteristic is likely to appear. The characteristic estimation device 10 estimates the characteristic based on the user's initial access time to the selected material data. Thereby, the characteristic estimation apparatus 10 can estimate a user's characteristic accurately.

  Although the embodiments related to the disclosed apparatus have been described so far, the disclosed technology may be implemented in various different forms other than the above-described embodiments. Therefore, another embodiment included in the present invention will be described below.

  For example, in the above-described embodiment, a case has been described in which whether the user characteristic is the stubby type or the immediately preceding type is described, but the disclosed apparatus is not limited to this. Other characteristics may be inferred. Further, the characteristics may be estimated in more stages.

  In the above-described embodiment, the case where the announcement date and the test date are estimated and the user characteristics are estimated from the timing of the first access to the announcement date and the test date has been described, but the disclosed apparatus is not limited thereto. Any estimation method may be used as long as the characteristics can be estimated. For example, the estimation unit 53 may estimate the characteristics of the user from the time of the first access to the lecture period. As an example, the estimation unit 53 divides the lecture period into a plurality of periods and totals the number of initial accesses for each period, estimates that the user who has made the initial access from an early period is a trick, and the late period It may be assumed that the user who is accessing for the first time is the immediately preceding type.

  For example, in the above-described embodiment, a case where the selection unit 51 selects a lecture with a large number of students, a lecture with a selected subject, and a lecture with a variety of actual student behaviors as a lecture that is easy to guess the behavior characteristics. However, the disclosed apparatus is not limited to this. Any method may be used as long as a lecture in which a user's behavior characteristic is likely to appear can be selected. For example, the selection unit 51 selects a lecture that satisfies any one or two of a lecture that is easy to guess behavioral characteristics, a lecture that has a large number of students, and a lecture of selected subjects as a lecture that easily guesses behavioral characteristics. Also good.

  For example, in the above-described embodiment, a case where the selection unit 51 guesses a serious student and selects material data that is commonly accessed by the estimated serious student as highly important material data will be described. However, the disclosed apparatus is not limited to this. As long as material data having high importance can be selected, any selection method may be used. For example, the selection unit 51 may select material data accessed by more than a predetermined percentage of students taking a lecture as highly important material data.

  For example, in the above-described embodiment, a case has been described in which, when a student whose property is to be estimated is specified by the reception unit 50, the property is estimated for the specified student, but the disclosed apparatus is not limited thereto. For example, the characteristics of all students may be periodically estimated by batch processing or the like.

  For example, in the above-described embodiment, the case has been described in which the characteristics of the student are estimated from the access history with respect to the material data in the lecture that the student has taken, but the disclosed apparatus is not limited thereto. For example, the student's characteristics may be estimated from the access history to the material data in the lecture that the student is taking.

  For example, in the above embodiment, the case where the learning management system 40 and the characteristic estimation system 41 are operated on the characteristic estimation apparatus 10 has been described, but the disclosed apparatus is not limited to this. For example, the learning management system 40 and the characteristic estimation system 41 may operate on different devices.

  Further, each component of each illustrated apparatus is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific state 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 loads or usage conditions. Can be integrated and configured. For example, the receiving unit 50, the selection unit 51, the estimation unit 52, the estimation unit 53, and the output unit 54 illustrated in FIG. 1 may be appropriately integrated or divided. Each processing function performed by each processing unit may be realized in whole or in part by a CPU and a program that is analyzed and executed by the CPU, or may be realized by hardware using wired logic. .

[Characteristic estimation program]
The various processes described in the above embodiments can also 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 system that executes a program having the same function as in the above embodiment will be described. FIG. 19 is a diagram illustrating a computer that executes a characteristic estimation program.

  As illustrated in FIG. 19, the computer 300 includes a CPU 310, a read only memory (ROM) 320, a hard disk drive (HDD) 330, and a random access memory (RAM) 340. These units 310 to 340 are connected via a bus 400.

  The ROM 320 stores in advance a characteristic estimation program 320a that exhibits the same function as each processing unit of the above embodiment. For example, the characteristic estimation program 320a that exhibits the same functions as the reception unit 50, selection unit 51, estimation unit 52, estimation unit 53, and output unit 54 of the above-described embodiment is stored. Note that the characteristic estimation program 320a may be separated as appropriate.

  Various data are stored in the HDD 330. For example, the HDD 330 stores various data used for OS and characteristic estimation.

  Then, the CPU 310 reads out and executes the characteristic estimation program 320a from the ROM 320, thereby executing the same operation as each processing unit of the embodiment. That is, the characteristic estimation program 320a performs the same operations as the reception unit 50, selection unit 51, estimation unit 52, estimation unit 53, and output unit 54 of the embodiment.

  Note that the above-described characteristic estimation program 320a is not necessarily stored in the ROM 320 from the beginning. The characteristic estimation program 320a may be stored in the HDD 330.

  For example, a program is stored in a “portable physical medium” such as a flexible disk (FD), a compact disk read only memory (CD-ROM), a digital versatile disk (DVD), a magneto-optical disk, or an IC card inserted into the computer 300. Remember. Then, the computer 300 may read and execute the program from these.

  Furthermore, the program is stored in “another computer (or server)” connected to the computer 300 via a public line, the Internet, a LAN, a WAN, or the like. Then, the computer 300 may read and execute the program from these.

DESCRIPTION OF SYMBOLS 10 Characteristic estimation apparatus 23 Memory | storage part 24 Control part 40 Learning management system 41 Characteristic estimation system 50 Reception part 51 Selection part 52 Estimation part 53 Estimation part 54 Output part 60 Attendance lecture information 61 Lecture information 62 Access history information 63 Document registration date information 64 Number of access materials 65 Common material information 66 Selected material information 67 Announcement date information 68 Test date information 69 Lecture-specific characteristic estimation information 70 Student-specific characteristic estimation information

Claims (8)

Computer
Executing a process of estimating the characteristics of the predetermined user based on information on the first access time of each of a plurality of material data by a predetermined user out of the user's access history to the lecture material data A method for estimating characteristics. Computer
Based on the access history, a change in the access rate of the user with respect to the material data is obtained over time, and the announcement date when the material was announced in the lecture and the test date on which the test of the lecture was performed are estimated from the change in the access rate. Perform further processing,
The inferring process determines the characteristics of the predetermined user based on whether the first access time to the document data is within a predetermined first period from the announcement date or within a predetermined second period immediately before the test date. The characteristic estimation method according to claim 1, wherein estimation is performed. The presuming process uses a plurality of document data, and the early access rate in which the first access was made within the first period from the announcement date and the first access within the second period immediately before the test date. When the early access rate is equal to or higher than the previous access rate, the first type is estimated. When the early access rate is lower than the previous access rate, the second type is calculated. The method for estimating characteristics according to claim 2, wherein the characteristics are estimated. The estimating process estimates a date when the access rate first becomes equal to or greater than a predetermined first threshold as an announcement date, and the access rate after a certain period of time has elapsed from the announcement date for a predetermined second threshold. The method for estimating characteristics according to claim 2 or 3, wherein the next weekday after the above date is estimated as a test day. Computer
Perform further processing to select lectures where user characteristics are likely to appear,
5. The method according to claim 1, wherein the estimating process estimates a characteristic of the predetermined user based on an initial access time of the predetermined user to the selected lecture material data. The characteristic estimation method as described in any one. Computer
Perform further processing to select document data in which user behavior characteristics are likely to appear,
The said estimating process estimates a user's characteristic based on the predetermined access time of the said predetermined | prescribed user with respect to the selected document data. The claim 1 characterized by the above-mentioned. Characteristics estimation method. Of the access history of the user with respect to the lecture material data, based on the information on the initial access time of each of the plurality of material data by the predetermined user, an estimation unit for estimating the characteristics of the predetermined user,
The characteristic estimation apparatus characterized by having. On the computer,
Executing a process of estimating the characteristics of the predetermined user based on information on the first access time of each of a plurality of material data by a predetermined user out of the user's access history to the lecture material data Characteristic estimation program characterized by

Images