QUESTION RECOMMENDATION APPARATUS, QUESTION RECOMMENDATION METHOD, AND PROGRAM
Provided is a technique for recommending a question suitable for use in future study to a learner. Included are, setting a first latent variable vector as a latent variable vector obtained from an input vector obtained from test results of a learner of K questions using an encoder of a learned neural network, a first decoder unit that calculates a first predicted correct answer rate vector from the first latent variable vector using a decoder of the learned neural network, a latent variable vector generation unit that generates a second latent variable vector by a predetermined method from the first latent variable vector, a second decoder unit that calculates a second predicted correct answer rate vector from the second latent variable vector using the decoder of the learned neural network, and a question selection unit that preferentially selects an element having a larger value from elements of a vector obtained by subtracting the first predicted correct answer rate vector from the second predicted correct answer rate vector, and obtains a question corresponding to the index of the selected element as a question to be recommended to the learner.
1 . A question recommendation apparatus comprising:
setting input information as information indicating one of a positive state, a negative state, or an unknown state,
setting an input vector as a vector obtained from K pieces (K is an integer of 2 or more) of the input information x 1 , . . . , x K by expressing the input information using two bits of a positive information bit set to 1 in a case where the input information is information indicating the positive state, or set to 0 in a case where the input information is information indicating the unknown state or information indicating the negative state, and a negative information bit set to 1 in a case where the input information is information indicating the negative state, or set to 0 in a case where the input information is information indicating the unknown state or information indicating the positive state,
setting p(x) as a probability that the input information x is information indicating the positive state,
setting an output vector as a vector having probabilities p(x 1 ), . . . , p(x K ) for the K pieces of input information x 1 , . . . , x K as elements,
a processing circuitry configured to record a parameter of a learned neural network, including an encoder that calculates a latent variable vector having a latent variable as an element from the input vector and a decoder that calculates an output vector from the latent variable vector, that has been learned by repeating parameter update processing of uprating parameters of the encoder and the decoder so that the latent variable vector has monotonicity with respect to the input vector, using a loss function including a loss term that has a larger value as the probability p(x) for the input information x is smaller in a case where the input information x is information indicating the positive state, has a larger value as the probability p(x) for the input information x is larger in a case where the input information x is information indicating the negative state, and is substantially 0 in a case where the input information x is information indicating the unknown state;
setting the K pieces of input information as test results of K questions, and setting the positive state, the negative state, and the unknown state as a correct answer, a wrong answer, and no answer, respectively,
setting a first latent variable vector as a latent variable vector calculated from an input vector obtained from the test results of a learner of the K questions by using an encoder of the learned neural network or a latent variable vector corresponding to the input vector,
calculate an output vector (hereinafter referred to as a first predicted correct answer rate vector) from the first latent variable vector using a decoder of the learned neural network;
generate, as a second latent variable vector, a vector obtained by replacing at least one element of elements of the first latent variable vector with a value larger than a value of the element in a case where the monotonicity is monotonic increase, or a vector obtained by replacing at least one element of the elements of the first latent variable vector with a value smaller than the value of the element in a case where the monotonicity is monotonic decrease;
calculate an output vector (hereinafter referred to as a second predicted correct answer rate vector) from the second latent variable vector using the decoder of the learned neural network; and
generate a vector obtained by subtracting the first predicted correct answer rate vector from the second predicted correct answer rate vector as a difference vector, preferentially select an element having a larger value from elements of the difference vector, and obtain a question corresponding to an index of the selected element as a question to be recommended to the learner.
2 . The question recommendation apparatus according to claim 1 , wherein
the processing circuitry generates, as the second latent variable vector, a vector obtained by replacing an element having a minimum value of the elements of the first latent variable vector with a value larger than the minimum value of the element in the case where the monotonicity is monotonic increase, or a vector obtained by replacing an element having a maximum value of the elements of the first latent variable vector with a value smaller than the maximum value of the element in the case where the monotonicity is monotonic decrease.
3 . The question recommendation apparatus according to claim 1 , wherein
setting i 1 , . . . , i M (where M is an integer of 1 or more and K or less, i m (m=1, . . . , M) satisfies 1≤i m ≤K, and i m and i m′ (m≠m′) are different from each other) as indexes of the elements of the first latent variable vector whose values are replaced, setting z i_1 , . . . , z i_M as values of the elements i 1 , . . . , and i M of the first latent variable vector, and setting as a median value of a latent variable value range, and
the processing circuitry generates, as the second latent variable vector, a vector obtained by replacing an element of the first latent variable vector whose index i m satisfies z i_m <μ with z i_m +(μ−z i_m )/2 in the case where the monotonicity is monotonic increase, or a vector obtained by replacing an element of the first latent variable vector whose index i m satisfies μ<z i_m with z i_m −(z i_m −μ)/2 in the case where the monotonicity is monotonic decrease.
4 . The question recommendation apparatus according to claim 1 , wherein
the processing circuitry selects a predetermined number of elements in descending order of values of the elements from among the elements of the difference vector.
5 . The question recommendation apparatus according to claim 1 , wherein
the processing circuitry selects an element having a value larger than, or larger than or equal to a predetermined value from among the elements of the difference vector.
6 . A question recommendation method comprising:
setting input information as information indicating one of a positive state, a negative state, or an unknown state;
setting an input vector as a vector obtained from K pieces (K is an integer of 2 or more) of the input information x 1 , . . . , x K by expressing the input information using two bits of a positive information bit set to 1 in a case where the input information is information indicating the positive state, or set to 0 in a case where the input information is information indicating the unknown state or information indicating the negative state, and a negative information bit set to 1 in a case where the input information is information indicating the negative state, or set to 0 in a case where the input information is information indicating the unknown state or information indicating the positive state;
setting p(x) as a probability that the input information x is information indicating the positive state;
setting an output vector as a vector having probabilities p(x 1 ), . . . , p(x K ) for the K pieces of input information x 1 , . . . , x K as elements;
setting the K pieces of input information as test results of K questions, and setting the positive state, the negative state, and the unknown state as a correct answer, a wrong answer, and no answer, respectively,
setting a first latent variable vector as a latent variable vector calculated from an input vector obtained from the test results of a learner of the K questions by using an encoder of the learned neural network or a latent variable vector corresponding to the input vector,
a first decoder step of, by a question recommendation apparatus including a processing circuitry configured to record a parameter of a learned neural network, including an encoder that calculates a latent variable vector having a latent variable as an element from the input vector and a decoder that calculates an output vector from the latent variable vector, that has been learned by repeating parameter update processing of uprating parameters of the encoder and the decoder so that the latent variable vector has monotonicity with respect to the input vector, using a loss function including a loss term that has a larger value as the probability p(x) for the input information x is smaller in a case where the input information x is information indicating the positive state, has a larger value as the probability p(x) for the input information x is larger in a case where the input information x is information indicating the negative state, and is substantially 0 in a case where the input information x is information indicating the unknown state, calculating an output vector (hereinafter referred to as a first predicted correct answer rate vector) from the first latent variable vector using a decoder of the learned neural network;
a latent variable vector generation step of, by the question recommendation apparatus, generating, as a second latent variable vector, a vector obtained by replacing at least one element of elements of the first latent variable vector with a value larger than a value of the element in a case where the monotonicity is monotonic increase, or a vector obtained by replacing at least one element of the elements of the first latent variable vector with a value smaller than the value of the element in a case where the monotonicity is monotonic decrease;
a second decoder step of, by the question recommendation apparatus, calculating an output vector (hereinafter referred to as a second predicted correct answer rate vector) from the second latent variable vector using the decoder of the learned neural network; and
a question selection step of, by the question recommendation apparatus, generating a vector obtained by subtracting the first predicted correct answer rate vector from the second predicted correct answer rate vector as a difference vector, preferentially selecting an element having a larger value from elements of the difference vector, and obtaining a question corresponding to an index of the selected element as a question to be recommended to the learner.
7 . A non-transitory computer-readable storage medium which stores a program for causing a computer to function as the question recommendation apparatus according to claim 1 .