Analysis device, analysis method, and program

Abstract

An analysis device according to the present invention acquires usage history information of each of a plurality of training terminals and uses information indicated by the usage history information for a period to be analyzed to analyze the similarity or dissimilarity of the modes of training with regard to the plurality of training terminals.

Description

Analytical device, analytical method, and program

[0001] The present disclosure relates to an analysis device, an analysis method, and a program.

[0002] Technologies for analyzing learning have been developed. For example, Patent Literature 1 discloses a system that analyzes students' levels of interest, understanding, and satisfaction in a lesson using lesson information such as the students' facial expressions and reactions in the lesson.

[0003] International Publication No. 2014 / 054385

[0004] The information that needs to be analyzed regarding learning is not limited to the student's level of interest, level of understanding, or level of satisfaction. The present disclosure has been made in light of this problem, and one of its purposes is to provide a new technology for analyzing learning.

[0005] The analysis device according to the present disclosure includes an acquisition means for acquiring usage history information for each of a plurality of learning terminals, and an analysis means for analyzing the similarity or dissimilarity of the learning patterns of the plurality of learning terminals using information indicated by the usage history information for the period to be analyzed.

[0006] The analysis method according to the present disclosure is executed by a computer and includes an acquisition step of acquiring usage history information for each of a plurality of learning devices, and an analysis step of analyzing the similarity or dissimilarity of learning behaviors on the plurality of learning devices using information indicated by the usage history information for a period to be analyzed.

[0007] The program of the present disclosure causes a computer to execute an acquisition step of acquiring usage history information for each of multiple learning devices, and an analysis step of analyzing the similarity or dissimilarity of learning patterns on the multiple learning devices using information indicated by the usage history information for the period being analyzed.

[0008] According to the present disclosure, new techniques for performing learning-related analysis are provided.

[0009] FIG. 1 is a diagram illustrating an overview of an analysis device. FIG. 2 is a block diagram illustrating an example of the functional configuration of an analysis device. FIG. 3 is a block diagram illustrating an example of the hardware configuration of a computer that realizes the analysis device. FIG. 4 is a flowchart illustrating an example of the flow of processing executed by the analysis device. FIG. 5 is a diagram illustrating an example of usage history information. FIG. 6 is a diagram showing changes in applications used on each target terminal. FIG. 7 is a block diagram illustrating an example of the functional configuration of an analysis device having an output unit. FIG. 8 is a diagram illustrating an example of a graph showing changes in mismatch rate over time. FIG. 9 is a second diagram illustrating an overview of an analysis device. FIG. 10 is a second diagram illustrating an example of the functional configuration of an analysis device. FIG. 11 is a second flowchart illustrating an example of the flow of processing executed by the analysis device. FIG. 12 is a diagram illustrating an example of a selection screen.

[0010] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In each drawing, the same or corresponding elements are designated by the same reference numerals, and duplicate explanations will be omitted as necessary for clarity. Furthermore, unless otherwise specified, predetermined values ​​such as predetermined values ​​and threshold values ​​are stored in advance in a storage device accessible from a device that uses the values. Furthermore, unless otherwise specified, the storage unit is composed of one or any number of storage devices.

[0011] <Overview> Fig. 1 is a diagram illustrating an example of an overview of the analysis device 2000. The operations of the analysis device 2000 shown in Fig. 1 are examples intended to facilitate understanding of the analysis device 2000. The operations that can be performed by the analysis device 2000 are not limited to the operations shown in Fig. 1.

[0012] The analysis device 2000 is used for analysis of learning using a learning terminal. The learning terminal is used by a learner 20. The learner 20 is any person who studies using a learning terminal. For example, the learning terminal is a terminal used by each student in a school class. Alternatively, for example, the learning terminal may be a terminal used by each employee in training at an organization such as a company. Note that any computer such as a tablet terminal or a PC (Personal Computer) can be used as the learning terminal. Furthermore, the learning terminal is not limited to a terminal loaned by a school or company, and may include a terminal brought by the learner 20.

[0013] The learning terminal is configured to record its usage history. The analysis device 2000 acquires usage history information 30 indicating the usage history of each learning terminal (hereinafter, target terminal 10) to be analyzed. Here, a set of target terminals 10 is also referred to as a target group 50.

[0014] The usage history information 30 of each target terminal 10 indicates, for example, a history of the number of keyboard strokes on the target terminal 10, the usage time of the target terminal 10, or the usage time of each application on the target terminal 10. Various information such as the history of keyboard strokes, the usage time of the target terminal 10, or the usage time of each application is recorded, for example, at predetermined intervals (for example, every 10 seconds, every minute, or every 5 minutes).

[0015] The keyboard referred to here is not limited to a hardware keyboard, but may also be a software keyboard.

[0016] Furthermore, the application referred to here is not limited to applications installed on the learning device (in other words, applications that can be executed by specifying an executable file). For example, a web application that can be accessed by specifying a specific URL can be used.

[0017] Here, multiple pieces of content provided on the same website may each be treated as a single application. For example, suppose a website provides content (e.g., exercises) for each subject. In this case, analysis device 2000 may treat the content for each subject as a different application.

[0018] The usage history information 30 may indicate whether or not a keyboard was pressed during each predetermined period, instead of the number of keyboard presses during each predetermined period. Furthermore, the usage history information 30 may indicate whether or not each application was used during each predetermined period, instead of the usage time of each application during each predetermined period. Furthermore, the usage history information 30 may indicate whether or not the target terminal 10 was used during each predetermined period, instead of the usage time of the target terminal 10 during each predetermined period.

[0019] The analysis device 2000 uses the usage history information 30 to analyze the similarity or dissimilarity of the learning behaviors using the target terminals 10 for the target group 50. The similarity of the learning behaviors using the target terminals 10 is expressed, for example, by the degree of agreement of the applications used in the target group 50. For example, it can be analyzed that the more common applications are used in the target terminals 10, the higher the similarity of the learning behaviors.

[0020] The dissimilarity of the learning behavior of the target terminals 10 is expressed, for example, by the degree of variation in the applications used in the target group 50. For example, it can be analyzed that the dissimilarity of the learning behavior is higher when there are fewer target terminals 10 that use common applications.

[0021] <Example of Effects> According to the analysis device 2000 of this embodiment, the similarity or dissimilarity of the learning behavior of multiple learning terminals (target terminals 10) to be analyzed is analyzed based on the usage history of the learning terminals used for learning. In this way, the analysis device 2000 applies a new technology for analyzing learning.

[0022] Analysis of the similarity or dissimilarity of learning using learning terminals can be used, for example, to evaluate whether a class is being conducted in a desirable manner. For example, it may be desirable for each student to be able to freely choose their own specific learning method in a class. This type of class style is also known as a "multi-track class."

[0023] Let's say that in a class where learning devices are used, each student is free to choose their own specific learning method. In this case, it is considered that the similarity of the learning styles using learning devices in that class is low (in other words, the dissimilarity is high). In other words, the lower the similarity of the learning styles using learning devices, the higher the probability that a multi-track class has been realized. Therefore, one way to determine whether a multi-track class has been realized in a class where learning devices are used is to determine the similarity or dissimilarity of the learning styles using learning devices.

[0024] Analysis device 2000 analyzes the similarity or dissimilarity of learning using target terminals 10 in target group 50. Therefore, by using analysis device 2000, a teacher in charge of a lesson can easily understand whether a multi-track lesson is being realized.

[0025] The analysis device 2000 of this embodiment will be described in more detail below.

[0026] 2 is a block diagram illustrating an example of the functional configuration of the analysis device 2000. The analysis device 2000 has an acquisition unit 2020 and an analysis unit 2040. The acquisition unit 2020 acquires usage history information 30 for multiple target terminals 10. The analysis unit 2040 uses the usage history information 30 to analyze the similarity or dissimilarity of learning behaviors among the multiple target terminals 10.

[0027] <Example of Hardware Configuration> Each functional component of the analytical device 2000 may be realized by hardware that realizes the functional component (e.g., a hardwired electronic circuit, etc.), or may be realized by a combination of hardware and software (e.g., a combination of an electronic circuit and a program that controls it, etc.). Below, a case where each functional component of the analytical device 2000 is realized by a combination of hardware and software will be further described.

[0028] 3 is a block diagram illustrating an example of the hardware configuration of a computer 1000 that realizes the analysis device 2000. The computer 1000 is any computer. For example, the computer 1000 is a stationary computer such as a PC or a server machine. Alternatively, the computer 1000 may be a portable computer such as a smartphone or a tablet terminal. The computer 1000 may be a dedicated computer designed to realize the analysis device 2000, or may be a general-purpose computer.

[0029] For example, by installing a predetermined application on the computer 1000, the computer 1000 realizes each function of the analysis device 2000. The application is configured with a program for realizing each functional component of the analysis device 2000. The method for acquiring the program is arbitrary. For example, the program can be acquired from a storage medium on which the program is stored. The storage medium on which the program is stored may be any storage medium such as a DVD (Digital Versatile Disk) or a USB (Universal Serial Bus) memory. Alternatively, the program can be acquired by downloading the program from a server device that manages the storage device on which the program is stored.

[0030] For example, an application for implementing the analysis device 2000 is installed on a user terminal (e.g., a PC or a tablet terminal) used by each user (e.g., a school teacher) of the analysis device 2000. In this case, the analysis device 2000 is implemented by the user terminal. Each user can use their own user terminal as the analysis device 2000.

[0031] Alternatively, for example, an application for implementing the analysis device 2000 may be installed on a server device accessed by a user terminal. In this case, the analysis device 2000 is implemented by the server device. Each user can use the analysis device 2000 by accessing the server device from their own user terminal.

[0032] The computer 1000 has a bus 1020, a processor 1040, a memory 1060, a storage device 1080, an input / output interface 1100, and a network interface 1120. The bus 1020 is a data transmission path for the processor 1040, the memory 1060, the storage device 1080, the input / output interface 1100, and the network interface 1120 to transmit and receive data to and from each other. However, the method of connecting the processor 1040 and the like to each other is not limited to bus connection.

[0033] The processor 1040 is one of various processors such as a central processing unit (CPU), a graphics processing unit (GPU), or a field-programmable gate array (FPGA). The memory 1060 is a main storage device realized using a random access memory (RAM) or the like. The storage device 1080 is an auxiliary storage device realized using a hard disk, a solid state drive (SSD), a memory card, a read only memory (ROM), or the like.

[0034] The input / output interface 1100 is an interface for connecting the computer 1000 to an input / output device. For example, the input / output interface 1100 is connected to an input device such as a keyboard and an output device such as a display device.

[0035] The network interface 1120 is an interface for connecting the computer 1000 to a network. This network may be a LAN (Local Area Network) or a WAN (Wide Area Network).

[0036] The storage device 1080 stores programs (programs that realize the above-mentioned applications) that realize the various functional components of the analysis device 2000. The processor 1040 reads these programs into the memory 1060 and executes them to realize the various functional components of the analysis device 2000.

[0037] The analysis device 2000 may be realized by one computer 1000 or by multiple computers 1000. In the latter case, the configurations of the computers 1000 do not need to be the same, and can be different from each other.

[0038] 4 is a flowchart illustrating the flow of processing executed by the analysis device 2000. The acquisition unit 2020 acquires usage history information 30 for multiple target terminals 10 (S102). The analysis unit 2040 uses the usage history information 30 to analyze the similarity or dissimilarity of the learning patterns of the multiple target terminals 10 (S104).

[0039] <Regarding Usage History Information 30> Fig. 5 is a diagram illustrating an example of usage history information 30. The usage history information 30 is associated with a terminal identifier 40. The terminal identifier 40 indicates the identifier of the learning terminal. The usage history information 30 corresponding to the terminal identifier 40 indicates the usage history of the learning terminal identified by the terminal identifier 40.

[0040] 5, the usage history information 30 indicates a start time 31, an end time 32, a number of keystrokes 33, a terminal usage time 34, and an application usage time 35. Each record in the usage history information 30 represents a usage history for a period from the time indicated in the start time 31 of that record to the time indicated in the end time 32 of that record. For example, in the example of FIG. 5, the record in the first row of the usage history information 30 indicates a usage history for the learning terminal C1 for a period from time t1 to t2.

[0041] The number of keystrokes 33 indicates the number of keystrokes on the target terminal 10. The terminal usage time 34 indicates the usage time of the learning terminal. The application usage time 35 indicates the usage time of one or more applications. More specifically, the application usage time 35 indicates a pair of an application identifier and usage time for each of one or more applications. For example, in the example of Figure 5, the application usage time 35 in the first record indicates that the usage time of application A1 is y1 and the usage time of application A3 is y2.

[0042] <Acquisition of Usage History Information 30: S102> The acquisition unit 2020 acquires the usage history information 30 for a plurality of target terminals 10 (S102). To do so, the acquisition unit 2020 identifies the target terminals 10 (in other words, the learning terminals that are treated as target terminals 10).

[0043] There are various methods for the acquisition unit 2020 to identify the target terminal 10. For example, the acquisition unit 2020 accepts designation of conditions related to learning terminals (hereinafter, terminal conditions), and identifies each learning terminal that matches the designated terminal conditions as the target terminal 10.

[0044] For example, the terminal condition is a condition related to information that identifies a class or a lesson. When a terminal condition related to a class is specified, the acquisition unit 2020 identifies the learning terminals of each learner 20 who belongs to a class that matches the terminal condition as the target terminals 10. The class can be identified by a class identifier, such as "Class 1A."

[0045] For example, assume that information indicating the identifier of the class to which the learner 20 belongs and the identifier of the learning terminal used by the learner 20 (hereinafter referred to as learner information) is prepared in advance for each learner 20. In this case, the acquisition unit 2020 uses the learner information to identify the learner 20 who belongs to a class that matches the terminal conditions. Furthermore, the acquisition unit 2020 uses the learner information to identify the learning terminal used by the identified learner 20 as the target terminal 10.

[0046] When a terminal condition related to a class is specified, the acquisition unit 2020 identifies each learning terminal used in a class that meets the terminal condition as a target terminal 10. A class is identified by a combination of the identifier of the class instructor (such as a teacher) and the date and time, such as "Instructor: F, Date and Time: March 10, 2024, First Period." Alternatively, a class can be identified by a combination of the identifier of the class and the date and time, such as "Class: 1st Year Class A, Date and Time: March 10, 2024, First Period."

[0047] For example, for each lesson, the class, the person in charge (such as a teacher), the date and time, and the learning device used are recorded. In this case, the acquisition unit 2020 uses the record to identify lessons that meet the device conditions. Furthermore, the acquisition unit 2020 uses the record to identify each learning device used in the identified lesson as a target terminal 10.

[0048] There are various methods for the acquisition unit 2020 to acquire the usage history information 30. For example, the usage history information 30 is stored in advance in an arbitrary storage unit in a format that can be acquired by the analysis device 2000. The acquisition unit 2020 acquires the usage history information 30 by accessing the storage unit.

[0049] For example, it is assumed that information representing the usage history of each target terminal 10 is stored in a database. In this case, the acquisition unit 2020 acquires usage history information 30 for each target terminal 10 from the database.

[0050] Here, the analysis device 2000 analyzes the usage history information 30 for a specific period, such as a specific class or a specific day. Hereinafter, the specific period treated as the analysis target is also referred to as the target period. The acquisition unit 2020 may acquire usage history information 30 that includes only usage history for the target period. For example, the acquisition unit 2020 extracts, from the database described above, only information for the period included in the target period from the information of the target terminal 10, as the usage history information 30 of the target terminal 10.

[0051] The target period is, for example, specified by a user of the analysis device 2000. Alternatively, for example, the target period may be determined by the analysis device 2000. For example, as described above, assume that a terminal condition related to a class is specified to identify the target terminal 10. In this case, the acquisition unit 2020 identifies the period from the start time to the end time of the class that matches the specified terminal condition as the target period.

[0052] <Analysis Process: S104> The analysis unit 2040 uses the usage history information 30 to analyze the similarity or dissimilarity of the learning behaviors of the multiple target terminals 10 (S104). The similarity and dissimilarity of the learning behaviors of the target terminals 10 will be described below.

[0053] <<Similarity of Learning Behavior Using Target Terminal 10>> The similarity of learning behavior in the target terminal 10 can be expressed, for example, by the degree of agreement between application usage behaviors in the target terminal 10. For example, it can be said that the application usage behaviors are consistent between multiple target terminals 10 that use the same application. On the other hand, it can be said that the application usage behaviors are inconsistent between multiple target terminals 10 that use different applications. Note that it can also be considered that the application usage behaviors are consistent between multiple target terminals 10 that do not use an application.

[0054] The application here preferably refers to an application used for learning. Therefore, for example, the analysis unit 2040 identifies a target application used on each target terminal 10 from applications belonging to a specific group (hereinafter, target applications).

[0055] 6 is a diagram showing changes in applications used on each target terminal 10. In this example, the target group 50 is made up of ten target terminals 10, namely, learning terminals C1 to C10. The target period is divided into eight partial periods P1 to P8.

[0056] In Figure 6, cell (i,j) represents the application used on learning device Cj during partial period Pi with a pattern corresponding to that application. Note that cell (i,j) being white indicates that the application was not used on learning device Cj during partial period Pi.

[0057] For example, in partial period P1, no application is used in any of the target terminals 10. Next, in partial period P2, no application is used in learning terminals C1 to C6, while application A1 is used in learning terminals C7 to C10.

[0058] For example, the analysis unit 2040 calculates the consistency rate of the usage patterns of the applications in the target group 50 for each partial period obtained by dividing the target period into multiple periods. The consistency rate of the usage patterns of the applications is calculated using, for example, the following formula (1). Ei represents the match rate in the partial period Pi. Dn represents the number of target terminals 10 in which the target application was not used in the partial period Pi, expressed as a ratio to the total number of target terminals 10. B represents the set of target applications. Dk represents the number of target terminals 10 in which target application k was used in the partial period Pi, expressed as a ratio to the total number of target terminals 10.

[0059] Here, the analysis unit 2040 may correct the match rate of the application usage mode so that the minimum possible value is 0 and the maximum possible value is 1. The corrected match rate is called a corrected match rate. The corrected match rate is expressed, for example, by the following equation (2). CEi represents the corrected match rate for sub-period i, and m represents the total number of target terminals 10.

[0060] Here, the length of the partial period Pi may be fixed in advance, may be specified by a user of the analysis apparatus 2000, or may be automatically determined by the analysis apparatus 2000. For example, assume that the number of partial periods included in the target period is predetermined. In this case, the length of the partial period can be automatically determined based on the length of the target period and the number of partial periods.

[0061] Here, during one partial period, multiple target applications may be used on one target terminal 10. Therefore, for each target terminal Cj, it is preferable that the analysis unit 2040 selects one of the multiple target applications used during the partial period Pi as the target application to be used in calculating the match rate for the partial period Pi.

[0062] For example, the analysis unit 2040 selects the target application that was used for the longest time among the target applications used on the target terminal Cj during the partial period Pi. Alternatively, for example, the analysis unit 2040 selects the target application with the highest priority among the target applications used on the target terminal Cj during the partial period Pi. In the latter case, a priority is determined in advance for each target application.

[0063] <<Dissimilarity of Learning Behavior Using Target Terminal 10>> The dissimilarity of learning behavior in the target terminal 10 can be expressed, for example, by the degree of variation in usage behavior of the target application in the target terminal 10. The degree of variation in usage behavior of the target application in the target terminal 10 can also be expressed as the degree to which the usage behavior of the application in the target terminal 10 does not match (hereinafter, mismatch rate).

[0064] Here, it can be said that the higher the above-mentioned match rate, the lower the mismatch rate. Therefore, for example, the analysis unit 2040 calculates the mismatch rate using the following formula (3). The discrepancy rate Ni represents the discrepancy rate in the subperiod Pi. In equation (3), the discrepancy rate is the reciprocal of the concordance rate.

[0065] Alternatively, for example, the mismatch rate may be calculated using equation (4). The mismatch rate Ni in equation (4) is 1 minus the corrected match rate.

[0066] <Output of Analysis Results: S106> The analysis device 2000 preferably outputs the results of the analysis performed by the analysis unit 2040. The information output here is called result information. The functional configuration unit that generates and outputs the result information is called an output unit.

[0067] Fig. 7 is a block diagram illustrating an example of the functional configuration of an analysis device 2000 having an output unit. In the example of Fig. 7, the analysis device 2000 has an output unit 2060. The output unit 2060 generates result information 60 representing the results of the analysis by the analysis unit 2040, and outputs the generated result information 60.

[0068] Various types of information are indicated in the result information 60. For example, the result information 60 indicates index values ​​(hereinafter referred to as match rates, etc.) such as a match rate, a corrected match rate, or a mismatch rate calculated by the analysis unit 2040. When a match rate, etc. is calculated for each of a plurality of partial periods as described above, the analysis unit 2040 may include a table, graph, etc. showing changes in the match rate, etc. over time.

[0069] 8 is a diagram illustrating an example of a graph showing the change in mismatch rate over time. In the example of FIG. 8, the result information 60 includes a graph 70 showing the change in mismatch rate over time. In this graph, the target period is divided into 15 partial periods. Therefore, the graph 70 shows a line 80 connecting the mismatch rates calculated for each of the 15 partial periods.

[0070] It is preferable that the result information 60 further includes information for identifying the target group 50 and the target period. For example, in FIG. 8 , the result information 60 indicates the name of the teacher in charge, F, and the date and time of the lesson, which is the first period on March 10, 2024. According to this information, it can be seen that the target group 50 is a collection of learning terminals that satisfy the condition "used in a lesson taught by teacher F in the first period on March 10, 2024." In other words, each target terminal 10 included in the target group 50 is a learning terminal of a learner 20 who took a lesson taught by teacher F in the first period on March 10, 2024.

[0071] The result information 60 may be output in any manner. For example, the output unit 2060 may store the result information 60 in any storage unit. Alternatively, the output unit 2060 may output the result information 60 to any display device, causing the display device to display the contents of the result information 60. Alternatively, the analysis device 2000 may transmit the result information 60 to another device (for example, a terminal used by a user of the analysis device 2000).

[0072] [Embodiment 2] Fig. 9 is a second diagram illustrating an overview of an analysis device 2000. The operation of the analysis device 2000 shown in Fig. 9 is an example intended to facilitate understanding of the analysis device 2000. The operations that can be performed by the analysis device 2000 are not limited to the operations shown in Fig. 9.

[0073] The analysis device 2000 of the second embodiment determines one or more candidate periods (i.e., the aforementioned target periods) to be used in the analysis process for learning using the target terminal 10. Hereinafter, the candidate target periods are also referred to as candidate periods. The candidate period is, for example, a period during which the target terminal 10 is estimated to have been used for learning.

[0074] Specifically, the analysis device 2000 accepts the specification of conditions (hereinafter, "period conditions") to be used in determining the candidate period. The period conditions include at least conditions related to the content of the usage history information 30. The analysis device 2000 determines, as the candidate period, a period for which the period conditions are satisfied.

[0075] The analysis device 2000 performs an analysis process on learning using the target terminal 10 for at least one candidate period using the usage history information 30. If multiple candidate periods have been determined, for example, the analysis device 2000 accepts an input to select one or more of the candidate periods, and performs an analysis process on the usage history information 30 for each selected candidate period. However, as will be described later, the selection of a candidate period may not be required.

[0076] Here, the analysis process performed by the analysis device 2000 of embodiment 2 is not limited to the process of analyzing the similarity or dissimilarity of learning patterns on the target terminal 10 described in embodiment 1. For example, the analysis process is a process of analyzing changes in the number of keystrokes over time. The changes in the number of keystrokes over time can be analyzed by unit of learning terminal, class, school, or the like. The number of keystrokes in a group such as a class or school can be expressed as a statistical value (such as an average value) for the group. Another example of the analysis process is an analysis of the proportion of usage time of each application in a specific time period. The proportion of usage time of each application can be expressed, for example, by a pie chart.

[0077] <Example of Action and Effect> According to the analysis device 2000 of this embodiment, candidate periods to be analyzed for learning using a learning terminal are automatically determined based on conditions related to the content of the usage history of the learning terminal, etc. Therefore, by using the analysis device 2000, it is possible to more easily determine the period to be analyzed for learning using a learning terminal.

[0078] An example of a situation where automatically determining candidate periods for analysis is useful is when class schedules are dynamic. When class schedules are static (i.e., fixed), classes are held on the same days and times each week. For example, science classes are held every Monday in the third period and every Thursday in the fourth period.

[0079] In contrast, when class schedules are flexible, the days and times of classes are not fixed. For example, a situation may arise where "this week, science classes were held on Monday, third period, and Thursday, fourth period, but next week, science classes will be held on Tuesday, first period, and Friday, second period." Furthermore, the schedule for the next week may not have been decided the previous week.

[0080] In this situation where class schedules are constantly changing, let's say a teacher wants to analyze the classes he or she taught. In this case, it is difficult to specify the days of the week and dates and times that the teacher will teach in advance in the analysis device. Furthermore, if the teacher has to manually set the period to be analyzed, analyzing classes becomes a heavy burden for the teacher.

[0081] In this regard, the analysis device 2000 automatically determines the period during which the class is estimated to have been held as the candidate period, thereby reducing the burden of analyzing the class.

[0082] The analysis device 2000 of the second embodiment will be described in further detail below.

[0083] <Example of Functional Configuration> FIG. 10 is a second diagram illustrating an example of the functional configuration of the analysis device 2000. In FIG. 10 , the analysis device 2000 includes an acquisition unit 2020, a period determination unit 2080, and an analysis unit 2040. The acquisition unit 2020 of the second embodiment, like the acquisition unit 2020 of the first embodiment, acquires usage history information 30 for each target terminal 10. The period determination unit 2080 determines a period for which a period condition is satisfied as a candidate period. The analysis unit 2040 performs an analysis process related to learning using the target terminal 10 using the usage history information 30 for at least one candidate period. The analysis process performed by the analysis unit 2040 of the second embodiment may be the same as or different from the analysis process performed by the analysis unit 2040 of the first embodiment.

[0084] <Example of Hardware Configuration> The hardware configuration of the analysis apparatus 2000 of the second embodiment is, for example, represented in Fig. 3 , similar to the hardware configuration of the analysis apparatus 2000 of the first embodiment. However, the storage device 1080 of the second embodiment stores a program that realizes each functional component of the analysis apparatus 2000 of the second embodiment.

[0085] 11 is a second flowchart illustrating the flow of processing executed by the analysis device 2000. The acquisition unit 2020 acquires the usage history information 30 for each target terminal 10 (S202). The content of the processing executed in S202 is the same as the content of the processing executed in S102 described above.

[0086] The period determination unit 2080 receives the designation of the period condition (S204). The period determination unit 2080 determines a period for which the period condition is satisfied as a candidate period (S206). The analysis unit 2040 executes an analysis process related to learning using the target terminal 10 for at least one candidate period using the usage history information 30 (S208).

[0087] <Specifying Period Condition: S204> The period determination unit 2080 receives the specification of the period condition (S204). As described above, the period condition includes at least a condition related to the content of the usage history information 30.

[0088] For example, the candidate period is a period during which learning is presumed to have been performed using the target terminal 10. Therefore, for example, the period condition is specified as a condition that is presumed to be satisfied by the usage history information 30 when learning is performed using the target terminal 10.

[0089] The period condition related to the content of the usage history information 30 includes, for example, a condition related to the number of keystrokes on the target terminal 10. The condition related to the number of keystrokes is, for example, a condition related to the lower limit of the statistical value (average value, minimum value, median value, etc.) of the number of keystrokes in the target group 50. Such a condition is, for example, "the average number of keystrokes in the target group 50 is equal to or greater than n."

[0090] The condition regarding the number of keystrokes may be expressed by a lower limit of the number of keystrokes and the percentage of target terminals 10 that have recorded a number of keystrokes equal to or greater than the lower limit. Such a condition may be, for example, "q1% or more of the target terminals 10 have n or more keystrokes."

[0091] In addition, for example, the period condition regarding the content of the usage history information 30 includes a condition regarding an application. The condition regarding an application is expressed, for example, by the percentage of target terminals 10 that used a specific application. Such a condition is, for example, "application A1 was used in q2% or more of the target terminals 10."

[0092] Here, the type of application may be specified instead of the identifier of the application, thereby making it possible to specify the proportion of target terminals 10 that have used a specific type of application as a period condition.

[0093] Another example of a period condition related to the content of the usage history information 30 is a condition related to whether or not the target terminal 10 was used. The condition related to whether or not the target terminal 10 was used is expressed by the percentage of the target terminal 10 that was used. Such a condition is, for example, "q3% or more of the target terminals 10 were used."

[0094] Note that "the target terminal 10 was being used" means "the learner 20 to whom the target terminal 10 was assigned was studying using the target terminal 10." Therefore, the "condition regarding the proportion of target terminals 10 that were being used" can also be expressed as "a condition regarding the proportion of learners 20 who were studying using the target terminal 10."

[0095] Here, the period condition may include a condition related to other than the content of the usage history information 30. The period condition related to other than the content of the usage history information 30 is, for example, a condition related to the length of the candidate period. The condition related to the length of the candidate period may include, for example, a condition related to the lower limit of the length of the candidate period, a condition related to the upper limit of the length of the candidate period, or both of these.

[0096] In addition, for example, the period condition may include a condition regarding the start date, end date, or both of the period to be detected as a candidate period (hereinafter referred to as the detection period). For example, assume that the condition "start date: January 1, 2024, end date: January 31, 2024" is given. In this case, from the detection period from January 1, 2024 to January 31, 2024, a period that satisfies the other conditions included in the period condition is determined as the candidate period.

[0097] There are various methods by which the period determination unit 2080 can accept the specification of the period condition. For example, the period determination unit 2080 provides the user of the analysis device 2000 with an input screen on which the period condition can be specified. The period determination unit 2080 treats the content of the input on the input screen as the period condition. Alternatively, for example, information representing the period condition may be stored in advance in a storage unit accessible from the analysis device 2000. Here, the period condition may differ for each of multiple users. Therefore, for example, the period condition may be stored in the storage unit in association with a user identifier.

[0098] For example, the period determination unit 2080 determines whether the storage unit stores a period condition corresponding to the user currently using the analysis device 2000. If the storage unit does not store a period condition corresponding to this user, the period determination unit 2080 provides the user with the above-mentioned input screen. The period determination unit 2080 associates the user's identifier with the period condition specified on the input screen and stores them in the storage unit.

[0099] On the other hand, if the period condition corresponding to the user is stored in the storage unit, the period determination unit 2080 provides the user with an input screen in which the period condition is already displayed in the input area. If the period condition does not need to be changed, the user finishes specifying the period condition without changing the content of the input area. On the other hand, if the period condition needs to be changed, the user changes the content of the input area and then finishes specifying the period condition. If the period condition is changed, the period determination unit 2080 updates the period condition stored in the storage unit.

[0100] In this way, by presenting the previously specified period conditions to the user, the user can easily maintain or change the period conditions.

[0101] <Determining Candidate Periods: S206> The analysis unit 2040 determines, as candidate periods, periods that satisfy the period condition (S204). Specifically, the analysis unit 2040 identifies one or more periods that satisfy the period condition using the multiple pieces of usage history information 30 acquired for the target group 50. The one or more periods identified here are determined as candidate periods.

[0102] Here, there may be multiple candidate periods separated by short blank periods, such as "10:15-10:20" and "10:21-10:40." In such a case, the period obtained by concatenating these multiple candidate periods may be the period during which learning was performed using the target terminal 10.

[0103] Therefore, for example, the analysis unit 2040 may concatenate multiple candidate periods and treat them as a single candidate period. For example, assume that a lower limit value for the time interval between two candidate periods is predetermined. In this case, the analysis unit 2040 determines whether the interval between two chronologically adjacent candidate periods is equal to or greater than the lower limit value. If the interval between the two candidate periods is less than the lower limit value, the analysis unit 2040 concatenates the two candidate periods into a single candidate period. On the other hand, if the interval between the two candidate periods is equal to or greater than the lower limit value, the analysis unit 2040 does not concatenate the two candidate periods.

[0104] The lower limit value of the interval between candidate periods may be determined in common for all users, or may be specified by each user.

[0105] <Execution of Analysis Process: S208> The analysis unit 2040 executes the analysis process for at least one candidate period (S208). For example, the analysis unit 2040 executes the analysis process for each of all candidate periods, treating the candidate period as a target period.

[0106] Alternatively, for example, the analysis unit 2040 may accept a selection of a candidate period by the user. In this case, the analysis unit 2040 provides the user with a selection screen from which the candidate period can be selected. The analysis unit 2040 performs analysis processing by treating the candidate period selected by the user as the target period. Note that the user may select one or more candidate periods.

[0107] The analysis unit 2040 may prioritize the candidate periods based on a predetermined rule and present the prioritized candidate periods to the user. There are various methods for prioritizing the candidate periods. For example, suppose the period condition is a condition regarding the proportion of target terminals 10 that satisfy a condition regarding some index, such as the number of keystrokes. In this case, the analysis unit 2040 assigns priorities to the candidate periods in descending order of the proportion.

[0108] For example, suppose the period condition is "the number of keystrokes is n or more in 60% or more of the target terminals 10." Then, suppose candidate period 1, candidate period 2, and candidate period 3 are determined as candidate periods that satisfy the period condition.

[0109] Here, in candidate period 1, the number of keystrokes is assumed to be n or more in 70% of the target terminals 10. In candidate period 2, the number of keystrokes is assumed to be n or more in 62% of the target terminals 10. Furthermore, in candidate period 3, the number of keystrokes is assumed to be n or more in 80% of the target terminals 10.

[0110] In this case, the analysis unit 2040 assigns the first priority to candidate period 3, the second priority to candidate period 1, and the third priority to candidate period 2.

[0111] 12 is a diagram illustrating an example of a selection screen. The selection screen 90 shows three candidate periods in order of priority. The candidate periods are selected using check boxes. In this example, multiple candidate periods can be selected.

[0112] 12, the detection period to be detected as a candidate period is only one day, January 15, 2024. Therefore, the year and month are omitted from the display of the candidate period.

[0113] Here, an upper limit may be set for the number of candidate periods to be included in the selection screen. In this case, it is preferable that the analysis unit 2040 prioritizes candidate periods with higher priorities before including them in the selection screen. For example, assume that the upper limit for the number of candidate periods is three. In this case, the analysis unit 2040 includes candidate periods with first to third priorities in the selection screen. Here, the upper limit for the number of candidate periods may be specified by the user of the analysis device 2000, or may be a fixed number determined in advance.

[0114] <Result Output> Similar to the analysis device 2000 of embodiment 1, the analysis device 2000 of embodiment 2 preferably outputs result information 60. The manner in which the result information 60 is output in embodiment 2 is similar to the manner in which the result information 60 is output in embodiment 1.

[0115] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0116] Each drawing is merely an example for describing one or more embodiments. Each drawing may not relate to only one particular embodiment, but may also relate to one or more other embodiments. As will be understood by those skilled in the art, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings to create, for example, an embodiment not explicitly shown or described. Not all features or steps shown in any one drawing are necessary to describe an exemplary embodiment, and some features or steps may be omitted. The order of steps described in any drawing may be changed as appropriate.

[0117] In the present disclosure, a program includes a set of instructions (or software code) that, when loaded into a computer, causes the computer to perform one or more functions described in the embodiments. The program may be stored in a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, computer-readable medium or tangible storage medium includes random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technology, CD-ROM, digital versatile disc (DVD), Blu-ray disc or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage device. The program may also be transmitted on a transitory computer-readable medium or communication medium. By way of example and not limitation, transitory computer-readable medium or communication medium includes electrical, optical, acoustic, or other forms of propagated signals.

[0118] Some or all of the above embodiments can be described as, but are not limited to, the following supplementary notes. (Supplementary Note 1) An analysis device having: acquisition means for acquiring usage history information for each of a plurality of learning terminals; and analysis means for analyzing the similarity or dissimilarity of learning behaviors on the plurality of learning terminals using information indicated by the usage history information for a period to be analyzed. (Supplementary Note 2) The analysis device described in Supplementary Note 1, wherein the analysis means calculates the degree of agreement between application usage behaviors on the plurality of learning terminals as an index value representing the similarity, or calculates the degree of variation in application usage behaviors on the plurality of learning terminals as an index value representing the dissimilarity. (Supplementary Note 3) The analysis device described in Supplementary Note 2, wherein the analysis means calculates an index value representing the similarity or an index value representing the dissimilarity for each of a plurality of partial periods included in the period to be analyzed. (Supplementary Note 4) The analysis device according to Supplementary Note 3, wherein the analysis means uses the usage history information to identify one or more combinations of the learning terminals that used the same application during the partial period, and calculates an index value representing the similarity or an index value representing the dissimilarity based on the number of learning terminals included in each combination. (Supplementary Note 5) The analysis device according to Supplementary Note 3, comprising output means for outputting information representing the change over time in the index value representing the similarity or the index value representing the dissimilarity calculated for each partial period. (Supplementary Note 6) The analysis device according to any one of Supplements 1 to 5, comprising period determination means for determining the period to be analyzed based on conditions related to the content of the usage history information and the content of the usage history information. (Supplementary Note 7) The analysis device according to Supplementary Note 6, wherein the conditions related to the content of the usage history information include a condition related to the number of keystrokes on the learning terminal, a condition related to the use of an application on the learning terminal, or a condition related to whether the learning terminal is used. (Supplementary Note 8) The analysis device according to any one of Supplementary Notes 1 to 5, wherein each of the plurality of learning terminals is a computer used by a learner who has taken the same class.(Supplementary Note 9) An analysis method executed by a computer, comprising: an acquisition step of acquiring usage history information for each of a plurality of learning terminals; and an analysis step of analyzing the similarity or dissimilarity of learning behaviors on the plurality of learning terminals using information indicated by the usage history information for a period to be analyzed. (Supplementary Note 10) A program that causes a computer to execute: an acquisition step of acquiring usage history information for each of a plurality of learning terminals; and an analysis step of analyzing the similarity or dissimilarity of learning behaviors on the plurality of learning terminals using information indicated by the usage history information for a period to be analyzed.

[0119] Some or all of the elements (e.g., configurations and functions) described in Supplementary Notes 2 to 8 that are dependent on Supplementary Note 1 may also be dependent on Supplementary Notes 9 and 10 in the same dependency relationship as Supplementary Notes 2 to 8. Some or all of the elements described in any Supplementary Note may be applied to various hardware, software, recording means for recording software, systems, and methods.

[0120] This application claims priority based on Japanese Patent Application No. 2024-050687, filed March 27, 2024, the disclosure of which is incorporated herein in its entirety by reference.

[0121] 10 Target terminal 20 Learner 30 Usage history information 31 Start time 32 End time 33 Number of keystrokes 34 Terminal usage time 35 Application usage time 40 Terminal identifier 50 Target group 60 Result information 70 Graph 80 Line 90 Selection screen 1000 Computer 1020 Bus 1040 Processor 1060 Memory 1080 Storage device 1100 Input / output interface 1120 Network interface 2000 Analysis device 2020 Acquisition unit 2040 Analysis unit 2060 Output unit 2080 Period determination unit 3000 Classification device

Claims

1. An analysis device having: an acquisition means for acquiring usage history information for each of a plurality of learning devices; and an analysis means for analyzing the similarity or dissimilarity of learning patterns on the plurality of learning devices using information indicated by the usage history information for the period to be analyzed.

2. The analysis device of claim 1, wherein the analysis means calculates the degree of similarity in the usage patterns of applications on the multiple learning terminals as an index value representing the similarity, or calculates the degree of variation in the usage patterns of applications on the multiple learning terminals as an index value representing the dissimilarity.

3. The analysis device according to claim 2, wherein the analysis means calculates an index value representing the similarity or an index value representing the dissimilarity for each of a plurality of partial periods included in the period to be analyzed.

4. The analysis device described in claim 3, wherein the analysis means uses the usage history information to identify one or more combinations of learning terminals that used the same application during the partial period, and calculates an index value representing the similarity or an index value representing the dissimilarity based on the number of learning terminals included in each combination.

5. The analysis device according to claim 3, further comprising output means for outputting information representing a change over time in the index value representing the similarity or the index value representing the dissimilarity calculated for each of the partial periods.

6. An analysis device according to any one of claims 1 to 5, further comprising a period determination means for determining the period to be analyzed based on conditions relating to the content of the usage history information and the content of the usage history information.

7. The analysis device described in claim 6, wherein the conditions regarding the content of the usage history information include conditions regarding the number of keystrokes on the learning terminal, conditions regarding the use of applications on the learning terminal, or conditions regarding whether or not the learning terminal is used.

8. An analysis device according to any one of claims 1 to 5, wherein each of the plurality of learning terminals is a computer used by a learner who has taken the same class.

9. An analysis method executed by a computer, comprising: an acquisition step of acquiring usage history information for each of a plurality of learning terminals; and an analysis step of analyzing the similarity or dissimilarity of learning patterns on the plurality of learning terminals using information indicated by the usage history information for the period to be analyzed.

10. A program that causes a computer to execute an acquisition step of acquiring usage history information for each of a plurality of learning devices, and an analysis step of analyzing the similarity or dissimilarity of learning patterns on the plurality of learning devices using information indicated by the usage history information for the period to be analyzed.