Technical Field
[0001] The present invention relates to a learning device, a learning method, and a
learning program for learning a model for predicting changes in a learner's skills.
Background Art
[0002] In order to make education more effective, it is important to provide education
10 that is tailored to individual learners. Such a system is called adaptive learning. To realize such
the system, computers are required to automatically provide skills tailored to each individual
learner. Specifically, it is necessary to constantly trace the state of knowledge of each learner and
provide appropriate learning according to that state of knowledge. This technology for tracing
the state of each learner's knowledge and providing appropriate information is also called as
15 knowledge tracing.
[0003] Knowledge tracing visualizes the skills of learners to grasp their learning status
in real time, predicts whether or not they will be able to solve problems, and provides optimal
problems tailored to them. For example, Patent Literature (PTL) 1 describes a test generation
server that supports effective review by closely grasping the student's own proficiency level for
20 each study content, and also generates a collection of exercise problems optimized for the
student's own proficiency level for each study content, etc.
[0004] Various types of knowledge tracing have been proposed that allow the system to
follow the learner's interactions in real time. Non Patent Literature (NPL) 1 describes a method
for real-time knowledge tracing. The method described in NPL 1 uses Recurrent Neural
25 Networks (RNN) to model student learning.
[0005] NPL 2 describes interpretable knowledge tracing with a probabilistic model with
a non-compensating item response model.
Citation List
Patent Literature
30 [0006] PTL 1: Japanese Patent Application Laid-Open No. 2012-93691
Non Patent Literature
[0007] NPL 1: Chris Piech, et al., "Deep Knowledge Tracing," Advances in Neural
Information Processing Systems 28 (NIPS 2015), 2015.
NPL 2: Hiroshi Tamano and Daichi Mochihashi, "Non-compensatory Temporal IRT with
2
Local Variational Approximation," Shingakugiho, vol. 119, no. 360, IBISML2019-31, pp. 91-98,
Jan. 2020.
Summary of Invention
Technical Problem
5 [0008] As in the test generation server described in PTL 1, generally, Artificial
Intelligence (AI) judges the learner's skills and presents appropriate problems. At first glance,
such a learning method in which the learner unilaterally solves the problems presented by the AI
may be considered efficient. However, if only the learning method in which the learner
unilaterally solves the presented problems is used, while the learner's ability to solve the asked
10 problems may improve, the learner may not acquire the ability to think independently about how
to deal with his or her own weaknesses.
[0009] Therefore, it is desirable to be able to provide a learning method that allows
learners to decide for themselves what to study while interacting with the AI, i.e. a learning
method that allows learners to use the AI proactively. To this end, it is necessary to provide
15 feedback information that enables learners to formulate their own learning plans while grasping
transition of their own skills over the long term.
[0010] For example, the test generation server described in PTL 1 displays the learning
achievement rate in three levels: “○ (circle indicating all correct answers),” “△ (triangle
indicating some incorrect answers),” and “× (cross indicating all incorrect answers),” according
20 to the ratio of the number of correct answers to the number of problems asked in a small unit.
However, since the content of the display described in PTL 1 only shows the results of correct or
incorrect answers, it is not possible to grasp the degree to which the user has fulfilled the skills
required to solve the asked problems.
[0011] The methods described in NPL 1 and NPL 2 can also be used to predict the
25 probability of solving a problem at the present time based on the estimated skills of the learner.
However, the methods described in NPL 1 and NPL 2 do not take into account the prediction of
future changes in skill as learning progresses. Ultimately, it is preferable to obtain information not
on whether or not a particular problem can be solved, but on how the skill will improve in the
future if what the learning process is continued.
30 [0012] Therefore, it is an object of the present invention to provide a learning device, a
learning method, and a learning program that can learn a model for predicting changes in
learner's long-term skills.
Solution to Problem
[0013] A learning device according to the present invention includes a first learning
3
means which generates a skill state sequence representing time-series changes in a learner's skill
state by machine learning using learner's learning results, and a second learning means which
learns a model in which problem characteristics that represent characteristics of problems used
by a learner for learning, user characteristics that represent characteristics of the learner, and time
5 information that represents time the learner solved the problem are explanatory variables, and the
learner's skill state represented by the skill state sequence is an objective variable.
[0014] A learning method according to the present invention, implemented by a computer,
includes generating a skill state sequence representing time-series changes in a learner's skill state
by machine learning using learner's learning results, and learning a model in which problem
10 characteristics that represent characteristics of problems used by a learner for learning, user
characteristics that represent characteristics of the learner, and time information that represents
time the learner solved the problem are explanatory variables, and the learner's skill state
represented by the skill state sequence is an objective variable.
[0015] A learning program according to the present invention, causing a computer to
15 execute a first learning process of generating a skill state sequence representing time-series
changes in a learner's skill state by machine learning using learner's learning results, and a
second learning process of learning a model in which problem characteristics that represent
characteristics of problems used by a learner for learning, user characteristics that represent
characteristics of the learner, and time information that represents time the learner solved the
20 problem are explanatory variables, and the learner's skill state represented by the skill state
sequence is an objective variable.
Advantageous Effects of Invention
[0016] According to this invention, it is possible to learn a model for predicting changes
in learner's long-term skills.
25 Brief Description of Drawings
[0017]
[FIG. 1] It depicts a block diagram showing an example of the configuration of a
learning device of the first exemplary embodiment according to the present invention.
[FIG. 2] It depicts an explanatory diagram showing an example of learning data.
30 [FIG. 3] It depicts an explanatory diagram showing an example of relating problems to
the required skills.
[FIG. 4] It depicts a flowchart showing an example of the operation by the learning
device.
[FIG. 5] It depicts a block diagram showing an example of the configuration of a
4
visualization system of an exemplary embodiment according to the present invention.
[FIG. 6] It depicts an explanatory diagram showing an example of a screen for entering
a learning plan.
[FIG. 7] It depicts an explanatory diagram showing an example of visualizing skill
5 states.
[FIG. 8] It depicts an explanatory diagram showing an example of visualizing the
probability of solving a problem.
[FIG. 9] It depicts an explanatory diagram showing an example of outputting the state of
each skill by a graph.
10 [FIG. 10] It depicts an explanatory diagram showing an example of a likelihood function
for the probability of correct answers.
[FIG. 11] It depicts an explanatory diagram representing the information of the
uncompensated model schematically.
[FIG. 12] It depicts an explanatory diagram showing an example of the process of
15 computing a threshold value.
[FIG. 13] It depicts an explanatory diagram showing an example of the process of
visualizing the results.
[FIG. 14] It depicts an explanatory diagram showing an example of the output of
recommended problems.
20 [FIG. 15] It depicts an explanatory diagram showing another example of visualizing
changes in skill state.
[FIG. 16] It depicts an explanatory diagram showing yet another example of visualizing
changes in skill state.
[FIG. 17] It depicts a flowchart showing an example of the operation by the visualization
25 device.
[FIG. 18] It depicts a block diagram showing an overview of the learning device
according to the present invention.
[FIG. 19] It depicts a schematic block diagram showing the configuration of a computer
for at least one exemplary embodiment.
30 Description of Embodiments
[0018] Hereinafter, exemplary embodiments of the present invention are described with
reference to the drawings.
[0019] Exemplary Embodiment 1.
FIG. 1 is a block diagram showing an example of the configuration of a learning device
5
of an exemplary embodiment according to the present invention. The learning device 100 of this
exemplary embodiment includes a storage unit 10, an input unit 20, a learning unit 30, and an
output unit 40.
[0020] The storage unit 10 stores various types of information, such as parameters,
5 setting information, and log data used by the learning device 100 of this exemplary embodiment
for processing. Specifically, the storage unit 10 stores learning results that indicate whether or
not a certain problem was answered correctly (hereinafter referred to as the learning
correct/incorrect log). The contents of the learning correct/incorrect log will be described later.
The storage unit 10 may also store each model generated by the learning unit 30, which will be
10 described later.
[0021] The learning device 100 may be configured to acquire various types of
information from other devices (e.g., storage servers) via a communication network. In this case,
the storage unit 10 may not store the information described above. The storage unit 10 is realized
by, for example, such as a magnetic disk.
15 [0022] The input unit 20 accepts input of various information used by the learning unit
30 for processing. For example, the input unit 20 may acquire various information from the
storage unit 10, or may accept input of various information acquired via a communication
network.
[0023] In this exemplary embodiment, the input unit 20 accepts the input of the learner's
20 time series of learning correct/incorrect logs as learning data indicating learning results.
Specifically, the input unit 20 accepts the input of learning data that includes data that relates
problems and the correctness or incorrectness of those problems to information that represents
the characteristics of the learner (hereinafter sometimes referred to as user characteristics).
[0024] FIG. 2 is an explanatory diagram showing an example of learning data. The
25 learning data illustrated in FIG. 2 indicates that the data relates to the correctness or
incorrectness (○, ×) for each problem for the learners, user 1 through user N. The user
characteristics, which indicate the characteristics of each user, may be maintained separately
from the learning data.
[0025] The learning unit 30 includes a first knowledge model learning unit 31 and a
30 second knowledge model learning unit 32.
[0026] The first knowledge model learning unit 31 generates time-series changes in the
state of the learner's skills (hereinafter referred to as the skill state sequence) by machine learning
using the learner's learning results. The learner's skill state is, for example, the proficiency level
of the learner's skill.
6
[0027] If the skill state sequence can be generated from the learning results, the learning
method is arbitrary. The first knowledge model learning unit 31 may, for example, generate the
skill state sequence using the method described in NPL 2. Specifically, the first knowledge
model learning unit 31 may generate as the skill state sequence the state with the maximum
5 posterior probability given the learning correct/incorrect log.
[0028] The first knowledge model learning unit 31 may also generate characteristics of
the problem used for the learning (hereinafter referred to as the problem characteristic vector).
The first knowledge model learning unit 31 may also generate, as similar to the generation of
skill state sequences, the problem characteristic vectors using the method described in NPL 2.
10 [0029] The problem characteristic vector can be generated without relying on the
learning results. For example, as described in NPL 1, a problem characteristic vector can be
generated as a vector for problem i, with the i-th entry being 1 and the other entries being 0. This
problem characteristic vector is a so-called one-hot vector ([0, ..., 1, ..., 0]) that identifies each
problem. If the problem characteristic vector can be generated in this way, the first knowledge
15 model learning unit 31 does not need to generate the problem characteristic vector.
[0030] The following is a specific description of the skill state sequence and the
problem characteristic vector when using the method described in NPL 2.
[0031] The skill state sequence in this exemplary embodiment corresponds to the state
transition probabilities in a generative model of uncompensated time-series IRT (item response
20 theory) described in NPL 2 (and initial state probabilities). Therefore, the first knowledge model
learning unit 31 may generate the skill state sequence by learning the model defined in equation
1 below. Equation 1 is a model that, given the state zj
(t) of user j at time t, transitions to the next
state zj
(t+1)
by linear transformation D. Note that zj
(t) is a random variable.
[0032]
25 [Math. 1]
𝑝(𝒛𝑗
(𝑡+1)
|𝒛𝑗
(𝑡)
) = 𝒩 (𝒛𝑗
(𝑡+1)
|𝐷𝑖(𝑗,𝑡)𝒛𝑗
(𝑡) + [
⋮
𝛽𝑘
𝑇𝒙𝑗,𝑘
(𝑡+1)
⋮
] , Γ𝑖(𝑗,𝑡+1))
𝑝(𝒛𝑗
(1)
) = 𝒩(𝒛𝑗
(1)
|𝜇0, 𝑃0)
[0033] In equation 1, Di(j, t) represents linear transformation that change states according
30 to the problem i solved by user j at time t, andΓi (j, t+1) represents Gaussian noise. The second
term on the right side is the bias term, which represents the feature of user j that can affect the
state transition.
(Equation 1)
7
[0034] Specifically, xj, k
(t+1) is a covariate of the state transition, and any characteristic
about the learner is used as the user characteristic. The user characteristics include, for example,
learner attributes (e.g., age, gender), motivation (interest in the subject), and the rate of forgetting
2^(-Δ/h) assumed from the time elapsed since learner j last learned a problem involving skill k
5 (where Δ is the elapsed time and h is a half-life), etc.
[0035] Other aggregate information on a result series may also be used as user
characteristics. Aggregate information may include, for example, the number of responses to five
consecutive correct answers for each skill, information indicating how quickly the user has
mastered the skill, results of previous tests, etc.
[0036] In addition, βk
T
10 is a coefficient that represents the characteristics of each skill;
for example, a large negative value is set for the coefficient of a skill that is easily forgotten. In
addition, μ0 and P0 represent the mean and variance of the Gaussian distribution of the learner's
initial state, respectively.
[0037] The vector including ai and bi included in the output probabilities described in
15 NPL 2 corresponds to the problem characteristic vector in this exemplary embodiment. Note that
ai is a vector representing the identification power (slope) of each skill in problem i, and bi is
difficulty of problem i. Therefore, the first knowledge model learning unit 31 may generate the
problem characteristic vector by learning the model defined in equation 2 below. Qi(j, t), k in
equation 2 indicates the correspondence between problem i and skill k, and becomes 1 if skill k is
20 needed to solve problem i and 0 if it is not needed.
[0038]
[Math. 2]
𝑝(𝑦𝑗
(𝑡) = 1|𝑧𝑗
(𝑡)
) = ∏ 𝜎 (𝑎𝑖(𝑗,𝑡),𝑘(𝑧𝑗,𝑘
(𝑡) − 𝑏𝑖(𝑗,𝑡),𝑘))
𝑄𝑖(𝑗,𝑡),𝑘
𝑘
25 [0039] Specifically, the first knowledge model learning unit 31 may generate the
problem characteristic vector as shown in equation 3 below. For example, if problem 1 requires
skills 1 and 2, the first knowledge model learning unit 31 may generate the characteristic vector
that sets entries except for a1, a2, b1, and b2 to 0 for the vector indicated the following equation 3.
[0040]
30 [Math. 3]
[⋯ , 𝑎𝑘, ⋯ , ⋯ , 𝑏𝑘, ⋯ ]
identification power difficulty
(slope)
35
(Equation 2)
(Equation 3)
8
[0041] When generating the skill state sequences and the problem characteristic vectors
using the method described in NPL 2, a table relating problems to required skills (problem skill
correspondence table) should be prepared in advance during learning. FIG. 3 is an explanatory
diagram showing an example of relating problems to the required skills. The example shown in
5 FIG. 3 shows an example of relating problems to the skills required to solve them in a tabular
format. As illustrated in FIG. 3, there may be one, two or more skills required for each problem.
The relating problems to required skills is set in advance by the user or others.
[0042] Thus, the first knowledge model learning unit 31 may generate, as the problem
characteristic vector, a vector including the identification power and difficulty of the problem
10 ([..., ak, ..., ..., bk, ...]).
[0043] Otherwise, the first knowledge model learning unit 31 may generate a skill state
sequence using, for example, the method described in NPL 1. The skill state sequence in this
exemplary embodiment corresponds to the vector yt of predicted probabilities of the time series
described in NPL 1. The yt described in NPL 1 is a vector of length equal to the number of
15 problems, where each entry represents the probability that the learner will answer the problem
correctly. Thus, the first knowledge model learning unit 31 may generate the vector yt of
predicted probabilities of the time series as the skill state sequence.
[0044] Also, as described above, the one-hot vector described in NPL 1 corresponds to
the problem characteristic vector in this exemplary embodiment. Specifically, it can be generated
20 as a vector for problem i, with the i-th entry being 1 and the other entries being 0. Thus, as the
problem characteristic vector, a one-hot vector identifying each problem ([ 0, ..., 1, ..., 0]) may be
generated in advance. In this case, the first knowledge model learning unit 31 does not need to
generate the problem characteristic vector.
[0045] The methods for generating the skill state sequences and the problem
25 characteristic vectors using the methods described in NPL 1 and NPL 2 were described above.
However, methods for generating the skill state sequences and the problem characteristic vectors
are not limited to the learning methods described in NPL 1 and NPL 2.
[0046] The second knowledge model learning unit 32 generates a model that predicts
the future skill state of the learner by machine learning using the skill state sequence and the
30 problem characteristic vector. Specifically, the second knowledge model learning unit 32 learns a
model in which the problem characteristics, user characteristics, and time information are
explanatory variables and the user skill state is an objective variable.
[0047] The skill states can be acquired from the skill state sequence generated by the
first knowledge model learning unit 31. The problem characteristics may also be acquired from
9
the problem characteristic vector generated by the first knowledge model learning unit 31, or
from information (e.g., a one-hot vector) generated in any manner based on problems. The user
characteristics are the same as those used by the first knowledge model learning unit 31 for
learning. The time information is information that represents the time that the learner solved the
5 problem. The form of the time information is arbitrary and can be, for example, time information
expressed in the form of YYYYMMDDHHMM, or the elapsed time from a certain time t-1 to t,
etc.
[0048] For example, using the method described in NPL 2, the first knowledge model
learning unit 31 may generate a skill state sequence that maximizes the posterior probability as
the skill state sequence. Specifically, with the obtained specific values of user j's results yj
(1) 10 , ...,
yj
(Tj) indicated by the learning correct/incorrect log, the first knowledge model learning unit 31
should find the value of zj
(t) (state variable) that maximizes the posterior probability up to t = 1,
..., T, as illustrated below.
[0049]
15 [Math. 4]
P (𝑧𝑗
(𝑡)
|𝑦𝑗
(1)
, … , 𝑦𝑗
(𝑇𝑗
)
)
[0050] The form of the model learned by the second knowledge model learning unit 32
is arbitrary, and the second knowledge model learning unit 32 may, for example, learn RNN,
20 which is often used in the prediction of time-series data. For RNN, general RNN, LSTM (Long
short-term memory), or GRU (Gated Recurrent Unit), etc. may also be used.
[0051] The learning of the model to perform knowledge tracing is generally performed
using the learner's correct/incorrect data (the learning correct/incorrect log), as in the learning
performed by the first knowledge model learning unit 31. On the other hand, the second
25 knowledge model learning unit 32 in this exemplary embodiment learns models for knowledge
tracing without directly using the learner's correct/incorrect data, and therefore, the model
learned by the second knowledge model learning unit 32 can be referred to as a knowledge
tracing model without correct/incorrect data.
[0052] By using the model learned in this way, a learner with the characteristics
30 indicated by the user characteristics can predict changes in the state of a skill when selects
(solves) a problem at a certain time. This makes it possible, for example, to predict the timeseries changes in the state of skills for a future learning plan generated by the learner on his/her
own initiative, if he/she executes the learning plan.
10
[0053] The output unit 40 outputs the model (knowledge tracing model without
correct/incorrect data) generated by the second knowledge model learning unit 32. The output
unit 40 may store the generated model in the storage unit 10 or may store the generated model in
another storage medium (not shown) via a communication network.
5 [0054] The input unit 20, the learning unit 30 (more specifically, the first knowledge
model learning unit 31 and the second knowledge model learning unit 32) and the output unit 40
are realized by a computer processor (e.g., CPU (Central Processing Unit), GPU (Graphics
Processing Unit)) that operates according to a program (learning program).
[0055] For example, the program is stored in the storage unit 10, the processor reads the
10 program, and may operate as the input unit 20, the learning unit 30 (more specifically, the first
knowledge model learning unit 31 and the second knowledge model learning unit 32), and the
output unit 40 according to the program. The functions of the input unit 20, the learning unit 30
(more specifically, the first knowledge model learning unit 31 and the second knowledge model
learning unit 32), and the output unit 40 may be provided in a SaaS (Software as a Service)
15 format.
[0056] The input unit 20, the learning unit 30 (more specifically, the first knowledge
model learning unit 31 and the second knowledge model learning unit 32) and the output unit 40
may each be realized in dedicated hardware. In addition, some or all of each component of each
device may be realized by general-purpose or dedicated circuits (circuitry), processors, etc. or a
20 combination of these. They may be configured by a single chip or by multiple chips connected
via a bus. Part or all of each component of each device may be realized by a combination of the
above-mentioned circuits, etc. and a program.
[0057] In the case where some or all of each component of the input unit 20, the
learning unit 30 (more specifically, the first knowledge model learning unit 31 and the second
25 knowledge model learning unit 32) and the output unit 40 are realized by multiple information
processing devices, circuits, etc., the multiple information processing devices, circuits, etc. may
be arranged in a centralized or distributed arrangement. For example, the information processing
devices and circuits, etc. may be realized as client-server systems, cloud computing systems, etc.,
each of which is connected via a communication network.
30 [0058] Next, the operation of the learning device 100 of this exemplary embodiment
will be described. FIG. 4 is a flowchart showing an example of the operation by the learning
device 100 of this exemplary embodiment. The learning unit 30 (more specifically, the first
knowledge model learning unit 31) generates a skill state sequence by machine learning using
the learning results (step S11). Then, the learning unit 30 (more specifically, the second
11
knowledge model learning unit 32) learns a model that uses the problem characteristics, user
characteristics, and time information as explanatory variables and the learner's skill states as
objective variables (step S12).
[0059] As described above, in this exemplary embodiment, the first knowledge model
5 learning unit 31 generates a skill state sequence by machine learning using the learning results,
and the second knowledge model learning unit 32 learns a model in which the problem
characteristics, user characteristics, and time information are explanatory variables and the
learner's skill state is an objective variable. Thus, a model that predicts changes in the learner's
long-term skills can be learned.
10 [0060] For example, the method described in NPL 2 learns a knowledge tracing model
based on the learner's time-series learning correct/incorrect logs. In other words, the model
described in NPL 2 is not suitable for long-term prediction because the correct/incorrect results
of solving problems are required as learning data.
[0061] On the other hand, in this exemplary embodiment, the second knowledge model
15 learning unit 32 learns a model in which the problem characteristics, user characteristics, and
time information are explanatory variables and the learner's skill state is an objective variable.
This makes it possible to make long-term predictions about the learner.
[0062] Exemplary Embodiment 2.
Next, a second exemplary embodiment of this invention will be described. The second
20 exemplary embodiment describes a method for visualizing changes in the state of a learner's skills
based on a learning plan. The learning plan in this exemplary embodiment is information that
represents which problems the learner plans to solve, when and in what order, and is information
that lists the problems the learner plans to solve in time series. This exemplary embodiment
describes a method for visualizing how the state of one's skills will change once which problems
25 are solved and when.
[0063] In the following description, the method of estimating changes in the state of
skills using the model learned in the first exemplary embodiment and visualizing the results of
the estimation will be described as appropriate. However, the method of estimating changes in
the state of skills is not limited to the method using the model learned in the first exemplary
30 embodiment.
[0064] FIG. 5 is a block diagram showing an example of the configuration of a
visualization system of an exemplary embodiment according to the present invention. The
visualization system 1 of this exemplary embodiment includes a learning device 100 and a
visualization device 200. Since the contents of the learning device 100 of this exemplary
12
embodiment are the same as those of the learning device 100 of the first exemplary embodiment,
a detailed description is omitted. It should be noted that the storage unit 10 included in the
learning device 100 of the first exemplary embodiment may be provided in a different device
from the learning device 100.
5 [0065] The visualization device 200 acquires the model learned by the learning device
100 (i.e., the knowledge tracing model without correct/incorrect data). If the information used by
the visualization device 200 for processing (e.g., the above knowledge tracing model without
correct/incorrect data, etc.) is stored in a storage device (e.g., the storage unit 10) provided in a
device other than the learning device 100, the visualization device 200 may not be connected to
10 the learning device 100.
[0066] The visualization device 200 includes a learning plan input unit 210, a state
estimation unit 220, and a state visualization unit 230.
[0067] The learning plan input unit 210 accepts input of learning plans. The learning
plan input unit 210 may, for example, display an input screen for the learning plans on a display
15 device (not shown) and accept input of the learning plans interactively from the learner. FIG. 6 is
an explanatory diagram showing an example of a screen for entering a learning plan. The
learning plan input unit 210 may display an input screen 211 in calendar format, as illustrated in
FIG. 6, and accept learning plans input by the learner via an appropriate input interface (e.g.,
touch panel, pointing device, keyboard, etc.).
20 [0068] The display device may be provided in the visualization device 200, and may be
realized in a device different from the visualization device 200 connected via a communication
line. In addition, the learning plan input unit 210 may also accept input of a learning plan
recorded in a file or the like.

Claims
1. A learning device comprising:
a first learning means which generates a skill state sequence representing time-series
5 changes in a learner's skill state by machine learning using learner's learning results; and
a second learning means which learns a model in which problem characteristics that
represent characteristics of problems used by a learner for learning, user characteristics that
represent characteristics of the learner, and time information that represents time the learner solved
the problem are explanatory variables, and the learner's skill state represented by the skill state
10 sequence is an objective variable.
2. The learning device according to claim 1,
wherein the first learning means generates states that maximize a posterior probability
under given learning results as the skill state sequence.
15
3. The learning device according to claim 1,
wherein the first learning means generates a vector of time-series prediction probabilities
as the skill state sequence.
20 4. The learning device according to any one of claims 1 to 3,
wherein the first learning means performs machine learning using learning results that
relates problems and correctness or incorrectness of those problems to the user characteristics that
represent the characteristics of the learner as the learning results.
25 5. The learning device according to any one of claims 1 to 4,
wherein the second learning means learns a recurrent neural network as the model.
6. A learning method implemented by a computer, comprising:
generating a skill state sequence representing time-series changes in a learner's skill state
30 by machine learning using learner's learning results; and
learning a model in which problem characteristics that represent characteristics of
problems used by a learner for learning, user characteristics that represent characteristics of the
learner, and time information that represents time the learner solved the problem are explanatory
variables, and the learner's skill state represented by the skill state sequence is an objective
25
variable.
7. The learning method implemented by the computer according to claim 6, further
comprising:
5 generating states that maximize a posterior probability under given learning results as
the skill state sequence.
8. The learning method implemented by the computer according to claim 6, further
comprising:
10 generating a vector of time-series prediction probabilities as the skill state sequence.
9. A program storage medium that stores a learning program causing a computer to execute:
a first learning process of generating a skill state sequence representing time-series
changes in a learner's skill state by machine learning using learner's learning results; and
15 a second learning process of learning a model in which problem characteristics that
represent characteristics of problems used by a learner for learning, user characteristics that
represent characteristics of the learner, and time information that represents time the learner solved
the problem are explanatory variables, and the learner's skill state represented by the skill state
sequence is an objective variable.
20
10. The program storage medium according to claim 9,
wherein the learning program causes the computer to generate states that maximize a
posterior probability under given learning results as the skill state sequence, in the first learning
process.