Learning tendency estimation device and method

Abstract

According to one aspect of this invention, when estimating a learning tendency of a user using a plurality of pieces of question data prepared in advance, experience data, in which experience of the user is recorded divided into a plurality of experience items, is stored in advance in a storage unit. In this state, conversion data corresponding to an answer to first question data, from among the plurality of items of question data, related to an experience item of the experience data of the user is obtained by converting the data of the experience items of the experience data in accordance with a conversion rule set in advance corresponding to the experience items. In addition, answer data of the user to second question data, among the plurality of items of question data, excluding the first question data is acquired. Learning tendency estimation data is generated by combining the answer data with the conversion data, and the learning tendency of the user is estimated on the basis of the learning tendency estimation data.

Description

Learning tendency estimation device and method

[0001] One aspect of the present invention relates to a learning tendency estimation device and method used to estimate a learning tendency of a worker when educating the worker, for example.

[0002] In recent years, with the rapid changes in society, worker reskilling, that is, acquiring or having workers acquire new skills to adapt to new occupations and jobs, has attracted significant social attention. When carrying out reskilling, a uniform educational method that does not take into account the background and motivation of the worker often does not achieve sufficient educational effectiveness. In order to improve educational effectiveness, it is necessary to understand the learning tendencies of workers and provide education that is tailored to those tendencies.

[0003] Therefore, a conventional method for analyzing students' learning tendencies using the Self-Directed Learning Readiness Scale (SDLRS) has been proposed, for example, in Non-Patent Document 1. The SDLRS proposed in Non-Patent Document 1 presents students with questions consisting of, for example, 58 items in a questionnaire format, and students respond to each question by selecting the appropriate answer from a five-point scale.

[0004] Kazuyo Matsuura, Noriko Abe, Sadako Yoshimura, Yoko Kaminari, Yumiko Masuda, Nobuko Abe, and Megumi Hama, "Development of the Japanese Version of the SDLRS: Examination of Reliability and Validity," Journal of the Japanese Society for Nursing Research, Vol. 26, No. 1, pp. 45-53, 2003

[0005] However, the method described in Non-Patent Document 1 has the problem that the subject must answer an extremely large number of questions (58 items), which places a heavy burden on the subject and takes a long time to estimate learning tendencies.

[0006] The present invention has been made in light of the above circumstances, and aims to provide a technique that reduces the burden on subjects and shortens the time required to estimate learning tendencies.

[0007] In order to solve the above-mentioned problems, one aspect of a learning tendency estimation device or estimation method according to the present invention estimates a user's learning tendency using a plurality of previously prepared question data, by storing experience data in a storage unit that describes the user's experiences divided into a plurality of experience categories. In this state, data representing the content of the experience categories included in the experience data is converted according to a conversion rule previously set for the experience category, thereby obtaining converted data corresponding to the user's answer to first question data from the plurality of question data that is related to the experience category of the user's experience data. At the same time, answer data of the user to second question data from the plurality of question data excluding the first question data is also obtained. The answer data and the converted data are then combined to generate learning tendency estimation data, and the user's learning tendency is estimated based on the learning tendency estimation data.

[0008] According to one aspect of the present invention, for a first question data set among a plurality of question data sets prepared for estimating a learning tendency, data corresponding to the user's answer can be obtained from the experience items in the experience data. Therefore, the user only needs to answer the second question data set, excluding the first question data set, thereby reducing the burden of the answering task. Furthermore, since the time required to obtain the answer data is shortened, the process of estimating a user's learning tendency can be performed efficiently.

[0009] That is, according to one aspect of the present invention, it is possible to provide a technology that can reduce the burden on the subject and shorten the time required to estimate learning tendencies.

[0010] FIG. 1 is a block diagram showing an example of the hardware configuration of a learning tendency estimation device according to an embodiment of the present invention. FIG. 2 is a block diagram showing an example of the software configuration of a learning tendency estimation device according to an embodiment of the present invention. FIG. 3 is a flowchart showing an example of the processing procedure and processing content of a learning tendency estimation process executed by a control unit of the learning tendency estimation device shown in FIG. 2. FIG. 4 is a flowchart showing an example of the processing procedure and processing content of an experience data conversion process and a data combination process in the learning tendency estimation process shown in FIG. 3. FIG. 5 is a diagram showing an example of experience data registered in advance for a subject. FIG. 6 is a diagram showing an example of learning tendency estimation data obtained by combining response data and experience conversion data.

[0011] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0012] [One embodiment] (Configuration example) The learning tendency estimation device SV is configured by a personal computer used by, for example, an administrator who provides education. Note that the learning tendency estimation device SV may also be configured by a server computer located on the web or on the cloud.

[0013] 2 and 3 are block diagrams showing an example of the hardware and software configurations of a learning tendency estimation device SV according to an embodiment of the present invention.

[0014] The learning tendency estimation device SV includes a control unit 1 that uses a hardware processor such as a central processing unit (CPU). A storage unit having a program storage unit 2 and a data storage unit 3, and an input / output interface unit (hereinafter referred to as input / output I / F unit) 4 are connected to the control unit 1 via a bus 5.

[0015] The input / output I / F unit 4 has, for example, a communication interface function, and transmits and receives information data to and from a user terminal (not shown) and an administrator terminal (not shown) under the control of the control unit 1, using a communication protocol defined by the Internet, for example.

[0016] The user terminal is a terminal such as a personal computer or a smartphone used by a user whose learning tendency is to be estimated, such as a worker or a student. The administrator terminal is a personal computer used by an administrator who provides education, for example.

[0017] The program storage unit 2 is configured, for example, by combining a non-volatile memory such as a HDD (Hard Disk Drive) or SSD (Solid State Drive) as a storage medium that can be written to and read at any time, with a non-volatile memory such as a ROM (Read Only Memory), and stores application programs necessary for executing various processes related to one embodiment of the present invention, in addition to middleware such as an OS (Operating System).

[0018] The data storage unit 3 is, for example, a combination of a non-volatile memory such as an HDD or SSD as a storage medium that can be written to and read from at any time, and a volatile memory such as a RAM (Random Access Memory), and its storage area is provided with a response data storage unit 31, an experience data storage unit 32, and a combined data storage unit 33.

[0019] The response data storage unit 31 stores the questionnaire response data sent from the user terminal of the user whose learning tendency is to be estimated, in association with the user's identification information (subject ID).

[0020] The experience data storage unit 32 stores experience data representing the past work experience of the user whose learning tendency is to be estimated, in association with the user ID.

[0021] The combined data storage unit 33 stores combined data, which is generated for each user and combines the answer data with data converted from the experience data, in association with the user ID as learning tendency estimation data.

[0022] The control unit 1 includes a questionnaire response acquisition processing unit 11, an experience data conversion processing unit 12, a data combination processing unit 13, and a learning tendency estimation and output processing unit 14 as processing units according to an embodiment of the present invention.

[0023] The processing units 11 to 14 are all realized by causing a hardware processor in the control unit 1 to execute an application program stored in the program storage unit 2. Note that some or all of the processing units 11 to 14 may be realized using hardware such as an LSI (Large Scale Integration) or an ASIC (Application Specific Integrated Circuit).

[0024] The survey response acquisition processing unit 11 acquires the user's response data to the survey sent from the user terminal via the input / output I / F unit 4, and stores the acquired response data in the response data storage unit 31 in association with the user ID of the respondent.

[0025] The questionnaire response acquisition processing unit 11 may have a function of storing questionnaire question data in advance, for example, in the response data storage unit 31, and transmitting the data to the user terminal of the user whose learning tendency is to be estimated.

[0026] The experience data conversion processing unit 12 sequentially reads, for each user, data relating to a plurality of experience items included in the user's experience data stored in the experience data storage unit 32. Then, for each of the read experience item data, data that can be converted into quantitative data is converted into quantitative data corresponding to the user's answer using a predetermined conversion formula pre-defined for the experience item. Furthermore, for experience item data that cannot be converted into quantitative data, the experience data conversion processing unit 12 converts the experience item data into data representing the relative positional relationship of the target user's learning tendency among all users, or data representing the data type of the experience item. The converted data is then stored in the experience data storage unit 32 in place of the data before conversion of the experience item. An example of the experience item data conversion process will be described in the operation example.

[0027] The data combination processing unit 13 combines, for each user to be estimated, the response data stored in the response data storage unit 31 with the converted data of the experience items stored in the experience data storage unit 32, and stores the combined data in the combined data storage unit 33 as data for estimating learning tendencies, in association with the user ID.

[0028] The learning tendency estimation / output processing unit 14 reads the combined data for each user from the combined data storage unit 33, estimates the user's learning tendency based on the read combined data, and transmits information representing the estimated learning tendency from the input / output I / F unit 4 to the administrator terminal or the corresponding user terminal.

[0029] (Example of Operation) Next, an example of operation of the learning tendency estimation device SV configured as above will be described.

[0030] FIG. 3 is a flowchart showing an example of the overall processing procedure and processing contents executed by the control unit 1 of the learning tendency estimation device SV.

[0031] (1) Registration of Experience Data Prior to the user learning tendency estimation process, the administrator acquires data representing multiple experience items related to the work history or learning history of each user to be estimated, such as a worker or a student, and then transmits the acquired history information together with a registration request from the administrator terminal to the learning tendency estimation device SV.

[0032] In response to this, when the control unit 1 of the learning tendency estimation device SV receives the registration request from the administrator terminal, it receives the history information transmitted from the administrator terminal together with the registration request via the input / output I / F unit 4. Then, the control unit 1 stores the received history information in the experience data storage unit 32 as experience data representing the user's past experiences in association with the user ID.

[0033] 5 shows an example of user experience data stored in the experience data storage unit 32. This example shows a case where history information including values ​​expressed on a five-point scale for multiple experience items such as work history indicating the types of work performed in the past, the number of qualifications obtained, whether the work performed was routine or non-routine, and the number of training sessions attended, for users A and B, who are employed, is registered as experience data.

[0034] The learning tendency estimation device SV may acquire the user's history information directly from the user's own user terminal and store it in the experience data storage unit 32 .

[0035] (2) Acquisition of Questionnaire Response Data: For example, suppose a request to acquire learning tendencies of a target user is input from an administrator terminal. In response to this, in step S1, the control unit 1 of the learning tendency estimation device SV first executes a process to acquire questionnaire response data from the target user under the control of the questionnaire response acquisition processing unit 11 as follows.

[0036] That is, the user to be estimated selects a corresponding level from, for example, five levels of options for each question and inputs the numerical value in response to the questionnaire question data sent in advance from the learning tendency estimation device SV or distributed by the administrator on his / her own user terminal. Then, when the process of inputting answers to all questions is completed, the results are transmitted as questionnaire response data from his / her own user terminal to the learning tendency estimation device SV.

[0037] In response to this, the control unit 1 of the learning tendency estimation device SV receives the questionnaire response data transmitted from the user terminal of each user to be estimated via the input / output I / F unit 4 under the control of the questionnaire response acquisition processing unit 11. Then, the questionnaire response acquisition processing unit 11 stores the received questionnaire response data in the response data storage unit 31 in association with the user ID of the user who responded.

[0038] Incidentally, the questionnaire question data includes multiple question items (for example, 58 items defined in the SDLRS) prepared to estimate the user's learning tendencies, but excludes question items that are related to the experience items in the user's experience data, i.e., question items (first question items) that can convert the data of the experience items included in the user's experience data into data equivalent to the user's answers, and only includes question items (second question items) that evaluate the user's internal tendencies that cannot be converted from the experience data.

[0039] For example, the second set of questions assessing the user's internal tendencies, which cannot be converted from experiential data, include "Learning is fun," "I am responsible for my own learning, not others," "I like to think about the future," and "I am better at self-study than many other people," and all of these questions are included in the survey question data.

[0040] In contrast, an example of a first question item that can be converted from user experience data into data equivalent to a user's answer is "I don't want to tackle problems that do not have a single correct answer." This question item can be converted into data equivalent to a user's answer based on the user's past work experience, for example, whether the work style was mostly "non-routine" or "routine." Therefore, estimation target data representing learning tendencies corresponding to this first question item is excluded from the questionnaire question data.

[0041] (3) Conversion of Experience Data After the process of acquiring the questionnaire response data is completed, in step S2, the control unit 1 of the learning tendency estimation device SV sequentially reads, for each user to be estimated, data on multiple experience items included in the experience data of the user to be estimated from the experience data storage unit 32 under the control of the experience data conversion processing unit 12. Then, the control unit 1 converts the read data on each experience item into data corresponding to the user's response as follows.

[0042] Figure 4 is a flowchart showing an example of the processing procedure and processing content of a series of processes from converting experience data to estimating the user's learning tendency, which are executed by the control unit 1 of the learning tendency estimation device SV. Steps S10 to S20 in Figure 4 represent the experience data conversion processing executed by the experience data conversion processing unit 12.

[0043] That is, in step S11, the experience data conversion processing unit 12 first selects one of the multiple experience items included in the experience data from the experience data storage unit 32 and reads data representing the content of that item. For example, if the experience items are represented by ID(Ij) (j = 0 to M), the experience data conversion processing unit 12 selects one of the M experience items in ascending order of j and reads the data. Then, in step S12, the experience data conversion processing unit 12 determines whether the data of the selected experience item Ij can be converted into a level value, which is quantitative data. Whether conversion into a level value is possible can be determined, for example, by an administrator determining in advance whether a conversion formula can be set for the experience item Ij and assigning a flag or the like indicating the result to each item Ij.

[0044] (3-1) When Conversion to Level Values ​​is Possible: It is assumed that the empirical data conversion processing unit 12 determines in step S12 that conversion to level values ​​is possible. In this case, in step S13, the empirical data conversion processing unit 12 converts the data of the empirical item Ij into a level value, which is quantitative data, using a conversion formula previously set for the empirical item Ij.

[0045] The conversion formula is expressed as y=f(x), for example, where Y is an arbitrary question item, x is data of experience item X of the experience data corresponding to this question item Y, and y is a score value corresponding to the user's answer converted from the question item Y. This conversion formula is stored in advance in the experience data storage unit 32 in association with each experience item Dj.

[0046] An example of the conversion process to quantitative data will be described below. If the data for the experience item Ij relates to the "type of tool that the target user has used in work," this data can be converted into level values, which are quantitative data. In this case, the experience data conversion processing unit 12 first counts the number of users who have used the tool for each tool type, based on the experience data of all users stored in the experience data storage unit 32.

[0047] Next, the experience data conversion processing unit 12 classifies the number of users of the tool into multiple stages using a threshold value, and assigns a score to each stage. Since the fewer users of a tool, the more advanced the skills required, the higher the score is assigned. For example, for a certain tool type, if there are 100 or more users, the score is assigned as 1 point, if there are 30 to 99 users, the score is assigned as 2 points, and if there are less than 30 users, the score is assigned as 3 points.

[0048] Next, the experience data conversion processing unit 12 sets the score set as described above as a quantitative level value for each tool type that the target user has used, instead of the user's answer, for each user.

[0049] Next, in step S14, the experience data conversion processing unit 12 replaces the data of the experience item Ij of the experience data with the level value set for each user, and then in step S15, stores the level value of each user in the experience data storage unit 32.

[0050] For example, when trying to obtain data equivalent to a user's response to "learning tendencies toward learning programming" from the user's experience data, if the job category among the experience items included in the user's experience data is defined as "jobs that normally use programming," "jobs that require IT skills other than programming," and "other," then it is possible to assign a level to these job categories by setting 3 points, 2 points, and 1 point, respectively.

[0051] (3-2) When the experience item Ij cannot be converted into a level value and the number of users to be estimated is equal to or greater than a threshold value: As a result of the determination in step S12, it is assumed that the data of the selected experience item Ij is determined to be data that is difficult to level. In this case, the experience data conversion processing unit 12 first determines in step S17 whether the number of users to be estimated is equal to or greater than a threshold value α (α is an arbitrary constant). Then, when it is determined that the number of users to be estimated is equal to or greater than the threshold value α, the experience data conversion processing unit 12 vectorizes the data of the experience item Ij in step S18.

[0052] For example, taking the work history data of a user to be estimated as an example, the experience data conversion processing unit 12 creates a vector for each user to be estimated, where "1" indicates that the user has experience in a job type defined in the work history data, and "0" indicates that the user has not experienced that job. In the example shown in Fig. 5, the vector of user A, who has experience in both clerical and sales jobs, is: Vector = (Clerical, Technical, Sales, Other) = (1, 0, 1, 0) Furthermore, the vector of user B, who has only experience in technical jobs, is: Vector = (Clerical, Technical, Sales, Other) = (0, 1, 0, 0)

[0053] Next, in step S19, the experience data conversion processing unit 12 clusters each estimation target user using the created vector and assigns a cluster ID to each user. In other words, in this case, the data of the experience item Ij is not converted into quantitative data, but is converted into qualitative data, such as an ID representing an occupation category that indicates the user's tendency for experience in the occupation. In other words, it is converted into data indicating the relative position of the target user's occupation experience among all users. Finally, in step S21, the experience data conversion processing unit 12 replaces the data of the experience item Ij with the cluster ID for each user, and stores the result in the experience data storage unit 32 in step S15.

[0054] (3-3) When the experience item Ij cannot be converted into a level value and the number of users to be estimated is less than the threshold value: Assume that the number of users to be estimated does not meet the threshold value α in step S17. In this case, the experience data conversion processing unit 12 assigns an ID representing the type of data to the data for each type of data of the experience item Ij in step S22. That is, in this case too, the data of the experience item Ij is not converted into quantitative data, but is converted into an ID representing a data category, which is qualitative data. Finally, in step S23, the experience data conversion processing unit 12 replaces the data of the experience item Ij with the data type ID for each user, and stores the result in the experience data storage unit 32 in step S15.

[0055] (3-4) Repeated Control of Conversion Process When any of the conversion processes (3-1), (3-2), and (3-3) described above is completed, the experience data conversion processing unit 12 determines in step S16 whether j in the experience item ID (Ij) has become j=M. In other words, it determines whether the selection of all experience items Ij has been completed.

[0056] If the result of this determination is that there are still unselected experience items remaining, the experience data conversion processing unit 12 returns to step S10, selects the next unselected experience item Ij in step S11, and executes the conversion process again in steps S10 to S20. Thereafter, the experience data conversion processing unit 12 repeatedly executes the above conversion process for each selected experience item Ij.

[0057] (4) Combining Response Data and Estimation Data After the conversion process of the data of all experience items Ij included in the experience data is completed, the control unit 1 of the learning tendency estimation device SV subsequently executes, in step S3, a process of combining the response data and the converted data for each estimation target user under the control of the data combination processing unit 13 as follows.

[0058] That is, first, in step S30, the data combination processing unit 13 reads converted data for each experience item Ij for each user to be estimated from the experience data storage unit 32. Then, in step S31, the data combination processing unit 13 combines the read converted data with the questionnaire response data of the user to be estimated stored in the response data storage unit 31. Then, the combined data is stored in the combined data storage unit 33 in association with the user ID.

[0059] For example, when the combined data of a user Li to be estimated is defined as vector data x = (x, x, ..., x), the combined data x is generated by combining questionnaire response data (quantitative data) x to x, data xi(k+1) to x obtained by converting experiential data into quantitative data, and qualitative data (such as category numbers) xi(l+1) to x obtained from the experiential data.

[0060] 6 shows an example of the combined data of users A and B generated by the combining process. In this example, the answer data is expressed as quantitative data because the user selects the answer that applies to them from a five-level list, for example. The data converted from the experience data is also expressed as quantitative data consisting of level values. Note that the qualitative data converted from the experience data is not shown in the example of FIG. 6.

[0061] (5) Estimation of learning tendency and output of prediction result Finally, in step S4 (step S32 in FIG. 5 ), the control unit 1 of the learning tendency estimation device SV, under the control of the learning tendency estimation / output processing unit 14, performs a process of estimating a learning tendency from the combined data, for example, as follows.

[0062] That is, when the learning tendency estimation / output processing unit 14 wants to estimate the learning tendency of, for example, a "specific digital tool A," it compares the score Pu assigned to the combined data of the user to be estimated with the reference score Pa of tool A, and estimates that users for whom Pa >> Pu may have a low aptitude for learning tool A.

[0063] Furthermore, when the combined data includes response data represented by quantitative data, quantitative data converted from empirical data, and data that cannot be converted from empirical data to quantitative data and has been converted to qualitative data, the control unit 1 of the learning tendency estimation device SV, under the control of the learning tendency estimation / output processing unit 14, in step S4 (step S32 in FIG. 5 ), performs a process of estimating a learning tendency from the combined data using a method capable of calculating the distance between vectors that contain a mixture of quantitative and qualitative variables. One example of such a method is the Gower distance.

[0064] That is, for example, the item information of users Li and Lj are respectively vectorized as xi and xj and expressed as follows:

[0065] xi = (xi1, xi2, ..., xip) xj = (xj1, xj2, ..., xjp).

[0066] Then, the distance between these two vectors is calculated. For example, when the Gower distance is used, the Gower distance Dij is defined as follows:

[0067]

[0068] Next, if the k-th variable is quantitative data, the k-th variable is transformed using the following formula: where Rk indicates the range of the k-th variable.

[0069]

[0070] On the other hand, if the kth variable is qualitative data, the kth variable is transformed using the following formula:

[0071]

[0072] The combined data converted as described above is then clustered, and a label representing the learning tendency is assigned to each cluster.

[0073] (6) Output of Learning Tendency Estimation Data In step S32, the control unit 1 of the learning tendency estimation device SV, under the control of the learning tendency estimation / output processing unit 14, transmits the estimated learning tendency estimation data autonomously or in response to a request from the administrator or the user from the input / output I / F unit 4 to, for example, the administrator terminal or the user terminal of the user to be estimated. Note that the estimated learning tendency estimation data may be stored in a predetermined storage area in the data storage unit 3 in association with the user ID.

[0074] (Effects) As described above, in one embodiment, a plurality of questions used to estimate a user's learning tendency are divided into a first set of questions related to the user's experience data and a second set of questions excluding the first set of questions. Quantitative data representing the user's answers to the second set of questions is then acquired from the user terminal, and the experience data is converted in accordance with a predetermined conversion rule to obtain converted data corresponding to the answers to the first set of questions. The answer data and the converted data are then combined to generate composite data for estimating the learning tendency, and the user's learning tendency is estimated based on the generated composite data.

[0075] Therefore, for the first question item among the multiple questions prepared for estimating learning tendencies that is related to an experience item in the user's experience data, data corresponding to the user's answer can be obtained from the experience item in the experience data. As a result, the user only needs to answer the second question item, excluding the first question item, thereby reducing the burden of the answering work. Furthermore, since the time required to obtain the answer data is shortened, it is possible to efficiently perform the process of estimating the user's learning tendencies.

[0076] [Other Embodiments] (1) In one embodiment, a case has been described in which a conversion process is performed on all of the multiple experience items included in the experience data, and the converted data is combined with the response data to estimate the user's learning tendency. However, this is not limited to this. For example, a conversion process may be performed only on items among the multiple experience items included in the experience data that can be converted into level values, which are quantitative data, and the converted quantitative data may be combined with the response data to estimate the user's learning tendency.

[0077] (2) The various processing functions of the learning tendency estimation device, their processing procedures and processing contents, the types of users, the types and contents of questions, the structure of experience data, etc. can be modified and implemented in various ways without departing from the spirit of this invention.

[0078] Although the embodiments of the present invention have been described in detail above, the above description is merely an example of the present invention in every respect. It goes without saying that various improvements and modifications can be made without departing from the scope of the present invention. In other words, when implementing the present invention, specific configurations according to the embodiments may be appropriately adopted.

[0079] In short, this invention is not limited to the above-described embodiments, and in the implementation stage, the components can be modified and embodied without departing from the spirit of the invention. Furthermore, various inventions can be formed by appropriately combining multiple components disclosed in the above-described embodiments. For example, some components may be omitted from all the components shown in the embodiments. Furthermore, components from different embodiments may be appropriately combined.

[0080] SV...Learning tendency estimation device 1...Control unit 2...Program storage unit 3...Data storage unit 4...Input / output I / F unit 5...Bus 11...Survey response acquisition processing unit 12...Experience data conversion processing unit 13...Data combination processing unit 14...Learning tendency estimation / output processing unit 31...Response data storage unit 32...Experience data storage unit 33...Combined data storage unit

Claims

1. A learning tendency estimation device that estimates a user's learning tendency using a plurality of pre-prepared question data, comprising: a storage unit that stores experience data in which the user's experience is divided into a plurality of experience items; a first processing unit that obtains conversion data corresponding to an answer to first question data having relevance to the experience items of the user's experience data among the plurality of question data by converting data representing the content of the experience items included in the experience data according to a pre-set conversion rule corresponding to the experience items; a second processing unit that obtains the user's answer data for second question data excluding the first question data among the plurality of question data; a third processing unit that combines the answer data and the conversion data to generate learning tendency estimation data; and a fourth processing unit that estimates the user's learning tendency based on the learning tendency estimation data.

2. The first processing unit of claim 1 comprises: a processing unit that determines whether data representing the content of the experience items included in the experience data can be converted into quantitative data; and a processing unit that, when it is determined that the data can be converted into quantitative data, converts the data representing the content of the experience items into the quantitative data and uses the converted quantitative data as data corresponding to the answer to the first question data.

3. The first processing unit of claim 2 comprises: a processing unit that determines whether the number of users is equal to or greater than a pre-set threshold when it is determined that the data cannot be converted into quantitative data; and a processing unit that, when it is determined that the number of users is equal to or greater than the threshold, clusters a plurality of the users based on the data representing the content of the experience items and uses identification information representing the result of the clustering as data corresponding to the answer of the user to the experience item.

4. A learning tendency estimation method in which an information processing apparatus performs a process of estimating a user's learning tendency using a plurality of pre-prepared question data, the method including: a process of acquiring experience data in which the user's experience is divided into a plurality of experience items and storing the experience data in a storage unit; a process of obtaining conversion data corresponding to an answer to first question data having a relevance to the experience items of the user's experience data among the plurality of question data by converting data representing the content of the experience items included in the experience data according to a conversion rule preset corresponding to the experience items; a process of acquiring the user's answer data for second question data excluding the first question data among the plurality of question data; a process of generating learning tendency estimation data by combining the answer data and the conversion data; and a process of estimating the user's learning tendency based on the learning tendency estimation data.

Images