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 skill visualization
device, a skill visualization method, and a skill visualization program that can visualize changes
in learner's long-term skills.
Solution to Problem
[0013] A skill visualization device according to the present invention includes a learning
3
plan input unit which accepts input of a learning plan, which is information that lists problems a
learner plans to solve in time series, a state estimation unit which estimates a learner's skill state
at each future point in time when each problem scheduled in the learning plan is solved in time
series, and a state visualization unit which visualizes the learner's skill state at each estimated
5 time point.
[0014] A skill visualization method according to the present invention includes accepting
input of a learning plan, which is information that lists problems a learner plans to solve in time
series, estimating a learner's skill state at each future point in time when each problem scheduled
in the learning plan is solved in time series, and visualizing the learner's skill state at each estimated
10 time point.
[0015] A skill visualization program according to the present invention, causing a
computer to execute a learning plan input process of accepting input of a learning plan, which is
information that lists problems a learner plans to solve in time series, a state estimation process
of estimating a learner's skill state at each future point in time when each problem scheduled in
15 the learning plan is solved in time series, and a state visualization process of visualizing the
learner's skill state at each estimated time point.
Advantageous Effects of Invention
[0016] According to this invention, it is possible to visualize changes in learner's longterm skills.
20 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.
25 [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
30 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
states.
4
[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.
5 [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
10 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.
15 [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
20 device.
[FIG. 18] It depicts a block diagram showing an overview of the skill visualization 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.
25 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
30 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,
setting information, and log data used by the learning device 100 of this exemplary embodiment
5
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
5 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.
10 [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
15 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
20 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
25 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.
30 [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
posterior probability given the learning correct/incorrect log.
6
[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.
5 [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
10 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
15 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]
20 [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
25 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.
[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,
30 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
(where Δ is the elapsed time and h is a half-life), etc.
(Equation 1)
7
[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
5 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
10 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
15 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
20 [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]
25 [Math. 3]
[⋯ , 𝑎𝑘, ⋯ , ⋯ , 𝑏𝑘, ⋯ ]
identification power difficulty
(slope)
30
[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
35 FIG. 3 shows an example of relating problems to the skills required to solve them in a tabular
(Equation 2)
(Equation 3)
8
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
5 ([..., 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
10 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.

Claims
1. A skill visualization device comprising:
a learning plan input unit which accepts input of a learning plan, which is information
5 that lists problems a learner plans to solve in time series;
a state estimation unit which estimates a learner's skill state at each future point in time
when each problem scheduled in the learning plan is solved in time series; and
a state visualization unit which visualizes the learner's skill state at each estimated time
point.
10
2. The skill visualization device according to claim 1,
wherein the state visualization unit visualizes learner's skills assumed at a specified
point in time for each skill required to solve a target problem.
15 3. The skill visualization device according to claim 1 or 2,
wherein the state visualization unit relates a proficiency level of the learner's skills
assumed at a specified point in time to a threshold value indicating the proficiency level of skills
required to solve a target problem to visualize.
20 4. The skill visualization device according to any one of claims 1 to 3,
wherein the state visualization unit relates the proficiency level of the learner's skills
assumed at a specified point in time to a threshold value indicating the proficiency level of the
skills required to solve a problem included in a target group to visualize.
25 5. The skill visualization device according to any one of claims 1 to 4,
wherein the state visualization unit visualizes time-series one or more changes in a skill
state.
6. The skill visualization device according to any one of claims 1 to 5,
30 wherein the state visualization unit visualizes a probability of correct answer at a specified
point in time for each problem.
7. The skill visualization device according to any one of claims 1 to 6,
wherein the state visualization unit outputs candidate problems that require a specified
26
skill ordered according to a degree to which the skill is required, and related with an assumed
learner's skill.
8. The skill visualization device according to any one of claims 1 to 7,
5 wherein the state estimation unit estimates the changes in the skill state using a prediction
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 is an objective variable.
10. A skill visualization method comprising:
accepting input of a learning plan, which is information that lists problems a learner plans
to solve in time series;
20 estimating a learner's skill state at each future point in time when each problem scheduled
in the learning plan is solved in time series; and
visualizing the learner's skill state at each estimated time point.
12. A program storage medium that stores a skill visualization program causing a computer
to execute:
30 a learning plan input process of accepting input of a learning plan, which is information
that lists problems a learner plans to solve in time series;
a state estimation process of estimating a learner's skill state at each future point in time
when each problem scheduled in the learning plan is solved in time series; and
a state visualization process of visualizing the learner's skill state at each estimated time
27
point.