State estimation device, question recommendation device, state estimation method, question recommendation method, and program

Abstract

The present invention provides a technology that recommends, to a learner, a problem that may preferably be used in future study. The present invention includes: a correct-answer percentage prediction unit that estimates a predicted percentage of correct answers to a problem from an input vector obtained from a test result of a learner of K problems, by using a trained neural network, or from a potential variable vector obtained from the input vector that is obtained from the test result of the learner of K problems, by using a decoder of the trained neural network; and a problem selection unit that selects a problem to be recommended to the learner from problems that are candidates for selection by using a reference predicted percentage of correct answers, which is a predicted percentage of correct answers that serves as a reference for recommending the problem to be solved, and the predicated percentage of correct answers to the problems that are candidates for selection from among the K problems.

Description

[Technical Field]

[0001] The present invention relates to a technique for recommending questions to learners that they should use in their future studies. [Background technology]

[0002] Various methods have been proposed for analyzing large amounts of high-dimensional data. One such method uses a variational autoencoder (VAE) as described in Non-Patent Document 1. Here, a variational autoencoder is a neural network including an encoder and a decoder. The encoder is a neural network that converts an input vector into a latent variable vector, and the decoder is a neural network that converts the latent variable vector into an output vector. The latent variable vector is a vector whose elements are latent variables and has a lower dimension than the input vector and the output vector. By using the encoder of a variational autoencoder trained to make the input vector and output vector approximately identical, high-dimensional data to be analyzed can be converted and compressed into low-dimensional secondary data. Here, training to make the vectors approximately identical means that, ideally, it would be desirable to train them to be completely identical. However, in reality, due to limitations on training time and other factors, training must be performed to make them approximately identical. Therefore, training is performed in such a way that the data are deemed identical and the processing is terminated when a certain condition is met.

[0003] Non-Patent Document 1 discloses that if a variational autoencoder is trained to have monotonicity, the latent variables will represent abilities in categories such as "basic arithmetic and Japanese language ability," "ability to use language," and "ability to illustrate," making it easier to analyze test results. [Prior art documents] [Non-patent literature]

[0004] [Non-Patent Document 1] Masashi Hattori, Hiroshi Sawada, Takako Tonooka, Takeshi Sakata, Sanae Fujita, Tetsuo Kobayashi, Goji Kamei, and Futoshi Naya, “Feature Extraction of Learners and Problems by Analyzing Test Results Using Variational Autoencoder,” 34th Annual Conference of the Japanese Society for Artificial Intelligence, 3M1-GS-12-03, 2020. Summary of the Invention [Problem to be solved by the invention]

[0005] According to the method of Non-Patent Document 1, it is possible to obtain insights into a learner's academic ability, such as, for example, that a learner has "basic arithmetic and Japanese language ability" but is weak in "the ability to use language." However, the method of Non-Patent Document 1 is intended to analyze test results, and does not suggest what kind of problems a learner should use in future studies to improve their weak points. In other words, the method of Non-Patent Document 1 cannot recommend to a learner good problems to use in future studies.

[0006] Therefore, an object of the present invention is to provide a technique for recommending questions that are good for a learner to use in future studies. [Means for solving the problem]

[0007] In one aspect of the present invention, input information is information indicating a positive state, a negative state, or an unknown state, and an input vector is represented by two bits: a positive information bit that is 1 when the input information is information indicating a positive state and 0 when the input information is information indicating an unknown state or information indicating a negative state, and a negative information bit that is 1 when the input information is information indicating a negative state and 0 when the input information is information indicating an unknown state or information indicating a positive state. By this, K pieces of input information x1, ..., x2 (K is an integer of 2 or more) can be represented by two bits. K Let p(x) be the probability that the input information x is information indicating a positive state, and let the output vector be the K pieces of input information x1, …, x K Probabilities p(x1), …, p(x K) as elements, an encoder for calculating a latent variable vector having latent variables as elements from the input vector, and a decoder for calculating an output vector from the latent variable vector, and a loss function including a loss term that increases as the probability p(x) for the input information x decreases when the input information x is information indicating a positive state, increases as the probability p(x) for the input information x increases when the input information x is information indicating a negative state, and is approximately 0 when the input information x is information indicating an unknown state, and a recording unit that records parameters of a trained neural network that has been trained by repeating a parameter update process for updating the parameters of the encoder and decoder using the encoder of the trained neural network. K an encoder unit that calculates a latent variable vector to be estimated from an input vector to be estimated obtained from the input vector to be estimated, a decoder unit that calculates an output vector to be estimated from the latent variable vector to be estimated using a decoder of the trained neural network, and an input information X indicating an unknown state is calculated from the output vector to be estimated. k (where k satisfies 1≦k≦K) k ) Enter information X k and a state estimation unit that obtains the estimated probability that the state is positive.

[0008] In one aspect of the present invention, input information is information indicating a positive state, a negative state, or an unknown state, and an input vector is represented by two bits: a positive information bit that is 1 when the input information is information indicating a positive state and 0 when the input information is information indicating an unknown state or information indicating a negative state, and a negative information bit that is 1 when the input information is information indicating a negative state and 0 when the input information is information indicating an unknown state or information indicating a positive state. By this, K pieces of input information x1, ..., x2 (K is an integer of 2 or more) can be represented by two bits. K Let p(x) be the probability that the input information x is information indicating a positive state, and let the output vector be the K pieces of input information x1, …, x K Probabilities p(x1), …, p(x K), and includes an encoder that calculates a latent variable vector having latent variables as elements from the input vector, and a decoder that calculates an output vector from the latent variable vector, and includes a loss function that, when the input information x is information indicating a positive state, the smaller the probability p(x) for the input information x is, and, when the input information x is information indicating a negative state, the larger the probability p(x) for the input information x is, and, when the input information x is information indicating an unknown state, the larger the value is, and, when the input information x is information indicating an unknown state, the larger the value is, and, when the input information x is information indicating an unknown state, the larger the value is, and, K a decoder unit that calculates an output vector to be estimated using a decoder of the trained neural network from a latent variable vector to be estimated corresponding to an input vector to be estimated obtained from the input vector to be estimated; and k (where k satisfies 1≦k≦K) k ) Enter information X k and a state estimation unit that obtains the estimated probability that the state is positive.

[0009] In one aspect of the present invention, input information is information indicating a positive state, a negative state, or an unknown state, and an input vector is represented by two bits: a positive information bit that is 1 when the input information is information indicating a positive state and 0 when the input information is information indicating an unknown state or information indicating a negative state, and a negative information bit that is 1 when the input information is information indicating a negative state and 0 when the input information is information indicating an unknown state or information indicating a positive state. By this, K pieces of input information x1, ..., x2 (K is an integer of 2 or more) can be represented by two bits. K Let p(x) be the probability that the input information x is information indicating a positive state, and let the output vector be the K pieces of input information x1, …, x K Probabilities p(x1), …, p(x K) as elements, an encoder that calculates a latent variable vector having latent variables as elements from the input vector, and a decoder that calculates an output vector from the latent variable vector, and a loss function that updates the parameters of the encoder and decoder using a loss term that takes a larger value the smaller the probability p(x) for the input information x when the input information x is information indicating a positive state, a larger value the larger the probability p(x) for the input information x when the input information x is information indicating a negative state, and a loss term that takes a larger value the larger the probability p(x) for the input information x when the input information x is information indicating an unknown state, and is approximately 0 when the input information x is information indicating an unknown state, and a recording unit that records the parameters of the trained neural network that has been trained, and a recording unit that records the parameters of the trained neural network that has been trained, and a recording unit that records the test results X of the K input information for K problems, and a recording unit that records the test results X of the learner for the ... k (k=1, ..., K) using the trained neural network to calculate an output vector, and k ) (k=1, ..., K), and obtains the probability corresponding to the candidate question to be recommended to the learner as a predicted correct answer rate of the candidate question to be recommended to the learner; i_1 , …, p i_M (where M is an integer between 1 and K, and i m (m=1, …, M) is 1≦i m ≦K, and i m and i m’ (m ≠ m') are different from each other) are selected from the K questions i1, ..., i M The standard predicted correct answer rate is the standard predicted correct answer rate for recommending problems to be solved, and the standard predicted correct answer rate and the K problems i1, ..., i are used as the selection candidate for the problem to be recommended to the learner. M Prediction accuracy rate p i_1 , …, p i_M Using the problem i1, …, i M Question i to recommend to the learner from m_1 , …, i m_N and a question selection unit for selecting:

[0010] In one aspect of the present invention, input information is information indicating a positive state, a negative state, or an unknown state, and an input vector is represented by two bits: a positive information bit that is 1 when the input information is information indicating a positive state and 0 when the input information is information indicating an unknown state or information indicating a negative state, and a negative information bit that is 1 when the input information is information indicating a negative state and 0 when the input information is information indicating an unknown state or information indicating a positive state. By this, K pieces of input information x1, ..., x2 (K is an integer of 2 or more) can be represented by two bits. K Let p(x) be the probability that the input information x is information indicating a positive state, and let the output vector be the K pieces of input information x1, …, x K Probabilities p(x1), …, p(x K ) as elements, an encoder that calculates a latent variable vector having latent variables as elements from the input vector, and a decoder that calculates an output vector from the latent variable vector, and a loss function that updates the parameters of the encoder and decoder using a loss function including a loss term that, when the input information x is information indicating a positive state, is larger the smaller the probability p(x) for the input information x, when the input information x is information indicating a negative state, is larger the larger the probability p(x) for the input information x, and is approximately 0 when the input information x is information indicating an unknown state, and a recording unit that records the parameters of the decoder of the trained neural network that has been trained by repeating a parameter update process; and a recording unit that records the parameters of the decoder of the trained neural network that has been trained by repeating a parameter update process using a loss function including a loss term that, when the input information x is information indicating a positive state, is larger the larger the probability p(x) for the input information x, and is approximately 0 when the input information x is information indicating an unknown state, and a recording unit that records the parameters of the decoder of the trained neural network that has been trained; and a recording unit that records the test results X of the learner for the K problems, k (k=1, ..., K) using the decoder of the trained neural network to calculate an output vector from the latent variable vector corresponding to the input vector obtained from k ) (k=1, ..., K), and obtains the probability corresponding to the candidate question to be recommended to the learner as a predicted correct answer rate of the candidate question to be recommended to the learner; i_1 , …, pi_M (where M is an integer between 1 and K, and i m (m=1, …, M) is 1≦i m ≦K, and i m and i m’ (m ≠ m') are different from each other) are selected from the K questions i1, ..., i M The standard predicted correct answer rate is the standard predicted correct answer rate for recommending problems to be solved, and the standard predicted correct answer rate and the K problems i1, ..., i are used as the selection candidate for the problem to be recommended to the learner. M Prediction accuracy rate p i_1 , …, p i_M Using the problem i1, …, i M Question i to recommend to the learner from m_1 , …, i m_N and a question selection unit for selecting: [Effects of the Invention]

[0011] According to the present invention, it is possible to recommend to a learner questions that would be good to use in future studies. [Brief explanation of the drawings]

[0012] [Figure 1] FIG. 10 is a diagram showing an example of an input vector representing a test result of a learner. [Figure 2] FIG. 1 is a block diagram showing the configuration of a neural network learning device 100. [Figure 3] 3 is a flowchart showing the operation of the neural network learning device 100. [Figure 4] FIG. 2 is a block diagram showing the configuration of a state estimation device 200. [Figure 5] 4 is a flowchart showing the operation of the state estimating device 200. [Figure 6] FIG. 2 is a block diagram showing the configuration of a state estimation device 201. [Figure 7] 4 is a flowchart showing the operation of the state estimation device 201. [Figure 8]FIG. 3 is a block diagram showing the configuration of a question recommendation device 300. [Figure 9] 10 is a flowchart showing the operation of the question recommendation device 300. [Figure 10] FIG. 2 is a diagram illustrating an example of the functional configuration of a computer that realizes each device according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0013] Hereinafter, embodiments of the present invention will be described in detail. Components having the same functions are given the same numbers, and duplicated explanations will be omitted.

[0014] Before describing each embodiment, the notation used in this specification will be explained.

[0015] ^ (caret) represents a superscript, e.g., x y^z Yes z is a superscript to x, and x y^z Yes z is a subscript to x. Also, _ (underscore) represents a subscript. For example, x y_z Yes z is a superscript to x, and x y_z Yes z is a subscript to x.

[0016] In addition, the superscripts "^" and "~" such as ^x and ~x for a certain letter x should be written directly above the "x", but due to restrictions on the notation in the specification, they are written as ^x and ~x.

[0017] <Technical background> Here, we will explain a learning method for a neural network used in an embodiment of the present invention. The neural network in the embodiment of the present invention is a neural network that includes an encoder that calculates a latent variable vector from an input vector and a decoder that calculates an output vector from the latent variable vector.

[0018] The input vector, encoder, output vector, and loss function in the embodiment of the present invention will be described below.

[0019] (1: input vector) In an embodiment of the present invention, an input vector is a vector representing multiple pieces of input information. Here, input information is information indicating one of a positive state, a negative state, and an unknown state. Examples of input vectors and input information are described below. In the previous example of analyzing test results, a learner's test result for each question can generally be one of three possible outcomes: correct, incorrect, or no answer. Here, no answer refers to a case where the learner has not yet taken a question, such as when the learner has taken Japanese and arithmetic tests but not science and social studies tests, and therefore no answer exists for that question. Therefore, in the example of analyzing test results, the test results for each question of the learner can be represented as input information by representing the test results for each question of the learner as a positive state, a negative state, or an unknown state, respectively, so that the test results for multiple questions of the learner can be represented as an input vector. Another example is the analysis of information acquired by multiple sensors. Using a sensor that detects the presence or absence of a specific situation, two types of information can be obtained: information indicating that the situation has been detected (i.e., detected) and information indicating that the situation has not been detected (i.e., not detected). However, when collecting and analyzing information acquired by multiple sensors via a communication network, it is possible that, due to loss of communication packets, it may not be possible to obtain information indicating that a specific situation has been detected or not detected for any of the sensors, and neither information may be obtained (i.e., the situation is unknown). Therefore, in this example, the detection results of each sensor, detected, not detected, and the situation is unknown, can be represented as a positive state, negative state, and unknown state, respectively, as input information for each sensor, thereby allowing the detection results of multiple sensors to be represented as an input vector.

[0020] The input vector has the following characteristics:

[0021] [Feature 1] The input vector is a vector consisting of a group of positive information bits and a group of negative information bits.

[0022] Below, we will explain using an example of analyzing test results. The test results of a learner are represented using two bits: a positive information bit, where 1 indicates a correct answer and 0 indicates no answer or an incorrect answer, and a negative information bit, where 1 indicates an incorrect answer and 0 indicates no answer or a correct answer. In this way, x (1) sk , x (0) sk are respectively the positive information bits and negative information bits for the test result of the kth question of the sth learner, and the input vector representing the test results of the K questions of the sth learner is the set of positive information bits {x (1) s1 , x (1) s2 , …, x (1) sK} and negative information bits {x (0) s1 , x (0) s2 , …, x (0) sK}. Figure 1 shows an example of an input vector that represents a learner's test results. Here, Q1, …, Q K represents the first problem, …, Kth problem, and N1, …, N S represents the first learner, ..., Sth learner, the rows represent a list of pairs of positive and negative information bits for all learners for each question, and the columns represent a list of positive and negative information bits for all questions for each learner. For example, the input vector for the second learner is a vector consisting of positive and negative information bits {1, 0, ..., 1, 0} and negative information bits {0, 0, ..., 0, 1}. The test result for the second question for the second learner is no answer, as both the positive and negative information bits are 0.

[0023] (2: Encoder) The encoder according to the embodiment of the present invention has the following features.

[0024] [Feature 2] The first layer of the encoder (i.e., the layer that inputs the input vector) is a layer that obtains intermediate information from the positive and negative information bits contained in the input vector so that elements of the input vector that correspond to input information indicating an unknown state do not affect the encoder output.

[0025] Below, we will explain using an example of analyzing test results. s1 , q s2 , …, q sH} is the intermediate information set of the sth learner, which is the output of the first layer of the encoder, and the intermediate information q sh is obtained by the following formula:

number

[0026] If the test result of the kth question of the sth student is correct, then x (1) sk =1, x (0) sk = 0, the two weight parameters w (1) hk , w (0) hk Of w (1) hk Only reacts, and w (0) hk If the test result of the sth learner on the kth question is incorrect, then x (1) sk =0, x (0) sk = 1, the two weights w (1) hk, w (0) hk Of w (0) hk Only reacts, and w (1) hk Furthermore, if the test result of the sth learner on the kth question is no answer, then x (1) sk =0, x (0) sk = 0, the two weight parameters w (1) hk , w (0) hk are both insensitive. Note that "sensitive" means that the weight parameters are updated during learning and that the weight parameters have an effect when the trained encoder is used, while "insensitive" means that the weight parameters are not updated during learning and that the weight parameters have no effect when the trained encoder is used. Therefore, by using equation (1), intermediate information can be obtained that affects the encoder output when the input information is either information indicating a correct answer or information indicating an incorrect answer, but does not affect the encoder output when the input information is information indicating no answer. Note that the neural network from the second layer onwards of the encoder generates intermediate information group {q s1 , q s2 , …, q sH} to the latent variable vector Z s Any method may be used as long as it calculates the above.

[0027] (3: output vector) The output vector in the embodiment of the present invention has the following characteristics.

[0028] [Feature 3] If p(x) is the probability that the input information x is information indicating a positive state, the output vector is a set of K pieces of input information x1, ..., x K Probability p(x1) , …, p(x K ) is a vector with elements.

[0029] Therefore, using the example of analyzing the test results, the decoder generates a latent variable vector Zs The input is the probability that the sth learner will correctly answer the kth question, p sk A probability vector P with elements s =(p s1 , p s2 , …, p sK ) as the output vector.

[0030] (4: Loss function) The loss function in the embodiment of the present invention has the following characteristics.

[0031] [Feature 4] The loss function includes a loss term that does not consider input information indicating no response to be a loss.

[0032] Below, we will explain using an example of analyzing test results. The loss L for the kth problem of the sth learner is sk x (1) sk If =1 (i.e., the test result is correct), then -log(p sk ) and x (0) sk If =1 (i.e., the test result is incorrect), then -log(1-p sk ) and x (1) sk =0, x (0) sk = 0 (i.e., the test result is no answer), the loss L for all questions of all learners is set to 0. sk The term L related to the reconstruction error is calculated by the following formula, which represents the sum of RC The loss function includes

number

[0033] First Embodiment Neural network training device 100 uses training data to train parameters of a neural network to be trained. Here, the neural network to be trained includes an encoder that calculates a latent variable vector from an input vector and a decoder that calculates an output vector from the latent variable vector. The neural network parameters include weight parameters and bias parameters of the encoder, and weight parameters and bias parameters of the decoder.

[0034] The input information is assumed to be information indicating a positive state, a negative state, or an unknown state. The input vector represents the input information using two bits: a positive information bit that is 1 when the input information indicates a positive state and 0 when the input information indicates an unknown state or a negative state, and a negative information bit that is 1 when the input information indicates a negative state and 0 when the input information indicates an unknown state or a positive state. By representing the input information using two bits, K (K is an integer equal to or greater than 2) pieces of input information x1, …, x K Therefore, the input vector is a vector whose elements are 0 or 1. Also, let p(x) be the probability that the input information x is information indicating a positive state, and the output vector is a vector obtained by dividing K pieces of input information x1, ..., x K Probabilities p(x1), …, p(x K ) as elements. A latent variable vector is a vector whose elements are latent variables.

[0035] As explained in the <Technical Background>, the first layer of the encoder is x (1) sk , x (0) sk The input information x of the sth training data kThe positive and negative information bits for the input vector are used, and H intermediate information q s1 , …, q sH The intermediate information q sh As expressed in equation (1), is a value obtained by adding together the values ​​obtained by multiplying each positive information bit by a weight parameter and the values ​​obtained by multiplying each negative information bit by a weight parameter, and then adding the value of the bias parameter.

[0036] The neural network training device 100 will be described below with reference to FIGS. 2 and 3. FIG. 2 is a block diagram showing the configuration of the neural network training device 100. FIG. 3 is a flowchart showing the operation of the neural network training device 100. As shown in FIG. 2, the neural network training device 100 includes an initialization unit 110, a training unit 120, a termination condition determination unit 130, and a recording unit 190. The recording unit 190 is a component that appropriately records information necessary for the processing of the neural network training device 100. The recording unit 190 records, for example, initialization data used to initialize the neural network. Here, the initialization data refers to the initial values ​​of the neural network parameters, such as the initial values ​​of the weight parameters and bias parameters of the encoder and the initial values ​​of the weight parameters and bias parameters of the decoder. The recording unit 190 may also record training data in advance. Note that the training data is input to the encoder and is therefore provided as an input vector. In the example of analyzing test results, the training data would be test results of multiple questions for multiple learners.

[0037] The operation of the neural network learning device 100 will be described with reference to FIG.

[0038] In S110, the initialization unit 110 performs initialization processing of the neural network using the initialization data. Specifically, the initialization unit 110 sets an initial value for each parameter of the neural network.

[0039] In S120, the learning unit 120 receives training data as input, performs a process of updating each parameter of the neural network using the training data (hereinafter referred to as parameter update process), and outputs the neural network parameters along with information (e.g., the number of times the parameter update process has been performed) necessary for the termination condition determination unit 130 to determine the termination condition. The learning unit 120 uses a loss function to train the neural network, for example, by backpropagation. That is, in each parameter update process, the learning unit 120 performs a process of updating each parameter of the encoder and decoder so as to reduce the loss function.

[0040] The loss function is the term L related to the reconstruction error in Eq. (2). RC In other words, the loss function includes a loss term that takes a larger value as the probability p(x) for the input information x decreases when the input information x is information indicating a positive state, a larger value as the probability p(x) for the input information x increases when the input information x is information indicating a negative state, and is approximately 0 when the input information x is information indicating an unknown state.

[0041] In S130, the termination condition determination unit 130 receives as input the neural network parameters output in S120 and information necessary to determine the termination condition, and determines whether the termination condition, which is a condition for terminating learning, is satisfied (for example, whether the number of times the parameter update process has been performed has reached a predetermined number of repetitions).If the termination condition is satisfied, the neural network parameters obtained in the last S120 execution are output as the parameters of the trained neural network and the process is terminated.On the other hand, if the termination condition is not satisfied, the process returns to S120.

[0042] According to an embodiment of the present invention, it is possible to train a neural network including an encoder and a decoder that can estimate the state of input information that indicates an unknown state as a probability, thereby making it possible to train a neural network that predicts the probability that a learner will correctly answer a question that has not yet been attempted.

[0043] Second Embodiment In this embodiment, a state estimation device that estimates the state of input information indicating an unknown state using a trained neural network trained using the first embodiment will be described. Here, the trained neural network is a network in which input information is information indicating any one of a positive state, a negative state, and an unknown state, and an input vector is represented by two bits: a positive information bit that is 1 when the input information is information indicating a positive state and 0 when the input information is information indicating an unknown state or information indicating a negative state, and a negative information bit that is 1 when the input information is information indicating a negative state and 0 when the input information is information indicating an unknown state or information indicating a positive ... network in which K pieces of input information x1, ..., x2 (K is an integer of 2 or more) are represented by two bits. K Let p(x) be the probability that the input information x is information indicating a positive state, and let the output vector be the K pieces of input information x1, …, x K Probabilities p(x1), …, p(x K ) as elements, an encoder that calculates a latent variable vector having latent variables as elements from the input vector, and a decoder that calculates an output vector from the latent variable vector, and the neural network is trained by repeatedly updating the parameters of the encoder and decoder using a loss function including a loss term that increases as the probability p(x) for the input information x decreases when the input information x indicates a positive state, increases as the probability p(x) for the input information x increases when the input information x indicates a negative state, and is approximately 0 when the input information x indicates an unknown state.

[0044] The state estimation device 200 will be described below with reference to Figs. 4 and 5. Fig. 4 is a block diagram showing the configuration of the state estimation device 200. Fig. 5 is a flowchart showing the operation of the state estimation device 200. As shown in Fig. 4, the state estimation device 200 includes an encoder unit 210, a decoder unit 220, a state estimation unit 230, and a recording unit 290. The recording unit 290 is a component that appropriately records information necessary for the processing of the state estimation device 200. The recording unit 290 records, for example, parameters of a trained neural network.

[0045] The operation of the state estimating device 200 will be described with reference to FIG.

[0046] In S210, the encoder 210 outputs K pieces of input information X1, . . . , X K The input vector to be estimated obtained from is used as input, and a latent variable vector to be estimated is calculated from the input vector to be estimated using the encoder of the trained neural network, and is output.

[0047] In S220, the decoder unit 220 receives the latent variable vector to be estimated calculated in S210 as input, and calculates and outputs an output vector to be estimated from the latent variable vector to be estimated using the decoder of the trained neural network.

[0048] In S230, the state estimation unit 230 receives the output vector to be estimated calculated in S220 as an input, and calculates input information X k (where k satisfies 1≦k≦K) k ) and obtain the probability p(X k ) Enter information X k is output as the estimated probability that is in the positive state.

[0049] According to an embodiment of the present invention, it is possible to estimate the state of input information indicating an unknown state as a probability, which makes it possible to predict, for example, the probability that a learner will correctly answer a question that the learner has not yet attempted from among a plurality of questions, based on the test results of a question that the learner has already attempted from among the plurality of questions.

[0050] Third Embodiment In some cases, analysis of the test results of a learner to be estimated has been completed, and a latent variable vector indicating the ability of the learner has already been obtained. Therefore, in this embodiment, a state estimation device is described that estimates the state of input information indicating an unknown state using a latent variable vector as an input. In other words, this embodiment differs from the first embodiment in that the input vector is different.

[0051] The state estimation device 201 will be described below with reference to Figs. 6 and 7. Fig. 6 is a block diagram showing the configuration of the state estimation device 201. Fig. 7 is a flowchart showing the operation of the state estimation device 201. As shown in Fig. 6, the state estimation device 201 includes a decoder unit 220, a state estimation unit 230, and a recording unit 290. The recording unit 290 is a component that appropriately records information necessary for the processing of the state estimation device 201. The recording unit 290 records, for example, decoder parameters of a trained neural network.

[0052] The operation of the state estimating device 201 will be described with reference to FIG.

[0053] In S220, the decoder unit 220 receives K pieces of input information X1, ..., X K The latent variable vector to be estimated, which is calculated from the input vector to be estimated using the encoder of the trained neural network, is used as input, and the output vector to be estimated is calculated from the latent variable vector to be estimated using the decoder of the trained neural network, and is output.

[0054] In S230, the state estimation unit 230 receives the output vector to be estimated calculated in S220 as an input, and calculates input information X k (where k satisfies 1≦k≦K) k ) and obtain the probability p(X k ) Enter information X k is output as the estimated probability that is in the positive state.

[0055] According to an embodiment of the present invention, for input information indicating an unknown state, it is possible to estimate the state of the input information as a probability. As a result, it is possible to predict, for example, the probability that a learner will correctly answer a question out of a plurality of questions that the learner has not attempted, based on the latent variable vector of the learner to be estimated obtained from the test results of a question out of a plurality of questions that the learner has attempted.

[0056] <Fourth embodiment> In this embodiment, a problem recommendation device is described that recommends problems to be solved by a target learner using the state estimation device 200 / 201. Here, K pieces of input information in the state estimation device 200 / 201 are the test results of K problems, and a positive state, a negative state, and an unknown state are respectively defined as a correct answer, an incorrect answer, and no answer.

[0057] The question recommendation device 300 will be described below with reference to Figs. 8 and 9. Fig. 8 is a block diagram showing the configuration of the question recommendation device 300. Fig. 9 is a flowchart showing the operation of the question recommendation device 300. As shown in Fig. 8, the question recommendation device 300 includes a correct answer rate prediction unit 310, a question selection unit 320, and a recording unit 390. The recording unit 390 is a component that appropriately records information necessary for the processing of the question recommendation device 300.

[0058] The operation of the question recommendation device 300 will be described with reference to FIG.

[0059] In S310, the correct answer rate prediction unit 310 calculates the test results X of the learners to whom the K questions are to be recommended. k(k=1, …, K) is used as an input, and an output vector (hereinafter referred to as a predicted accuracy vector) is calculated from the input vector using a trained neural network. The element p(X k ) (k=1, ..., K), the correct answer rate prediction unit 310 selects a probability corresponding to input information indicating no answer, and outputs the selected probability as the predicted correct answer rate of the learner for questions that the learner has not yet attempted. The correct answer rate prediction unit 310 can be configured using, for example, the state estimation device 200. An example of configuring the correct answer rate prediction unit 310 using the state estimation device 201 will be described later.

[0060] In S320, the question selection unit 320 selects questions i1, ..., i that the learner to be recommended has not yet taken. M (where M is an integer between 1 and K, and i m (m=1, …, M) is 1≦i m ≦K, and i m and i m’ (m ≠ m') are different from each other) i_1 , …, p i_M and the predicted correct answer rate that is the standard for recommending questions to be solved (hereinafter referred to as the standard predicted correct answer rate). M The predicted correct answer rate of the learner p i_1 , …, p i_M Using the problem i1, …, i M Question i to recommend to the target learner from m_1 , …, i m_N is selected and output. The standard predicted correct answer rate can be set to, for example, 0.5. This example is based on the idea that questions for which the predicted correct answer rate of the recommended learner is close to 0 are too difficult for the learner, questions for which the predicted correct answer rate of the learner is close to 1 are too easy for the learner, and questions for which the predicted correct answer rate of the learner is close to 0.5 will likely lead to an improvement in the learner's academic ability if the learner makes an effort to solve them.

[0061] The question selection unit 320 selects, for example, questions i1, ..., i2 that the learner to be recommended has not yet taken. M From this, the predicted correct answer rate p i_m (m=1, …, M) is a question that is included in a predetermined range including the standard predicted correct answer rate. m_1 , …, i m_N The predetermined range including the reference prediction accuracy rate may be, for example, 0.5, and may be in the range from 0.4 to 0.6.

[0062] In addition, the question selection unit 320 selects questions i1, ..., i2 that have not been taken by the learner to be recommended. M From this, the predicted correct answer rate p i_m (m=1, …, M) is the problem i that is recommended to the learner with priority given to the problem that is close to the standard predicted correct answer rate. m_1 , …, i m_N Specifically, the question selection unit 320 may select questions i1, ..., i M From this, the predicted correct answer rate p i_m N questions are selected in order from the smallest absolute value of the difference between (m=1, ..., M) and the standard predicted accuracy rate.

[0063] The reference prediction accuracy rate, the predetermined range including the reference prediction accuracy rate, and the number N of questions to be selected may be recorded in advance by the recording unit 390, or may be received by an input unit (not shown) as desired input values ​​by the user of the question recommendation device 300.

[0064] Furthermore, for example, even if a question has already been taken by the learner to be recommended, if it has been a long time since the question was taken, it may be included as a selection candidate for the question to be recommended. In other words, the question selection unit 320 may include not only questions that the learner to be recommended has not yet taken, but also one or more questions that the learner has taken, in the selection candidate for the question to be recommended, i1, ..., i M For this purpose, the correct answer rate prediction unit 310 may include the element p(X k)(k=1, …, K) M For example, if all questions are to be included in the selection candidates for questions to be recommended, regardless of whether the learner to be recommended has already taken the test, the correct answer rate prediction unit 310 may select the probability corresponding to all elements p(X k ) (k=1, ..., K) of the test results X k (k=1, …, K) is used as an input, and an output vector (predicted accuracy vector) is calculated from the input vector using a trained neural network. The element p(X k ) (k=1, ..., K), the probability corresponding to the question of the selection candidate to be recommended to the learner is selected, and the selected probability is output as the predicted correct answer rate of the learner for the selection candidate question of the question of the selection candidate to be recommended to the learner. Also, in S320, the question selection unit 320 selects the question i1, ..., i M (where M is an integer between 1 and K, and i m (m=1, …, M) is 1≦i m ≦K, and i m and i m’ (m ≠ m') are different from each other) i_1 , …, p i_M and the predicted correct answer rate (baseline predicted correct answer rate) that is the standard for recommending problems to be solved. The base predicted correct answer rate and the K problems i1, ..., i are used as inputs. M The predicted correct answer rate of the learner p i_1 , …, p i_M Using the problem i1, …, i M Question i to recommend to the target learner from m_1 , …, i m_N Then, the question selection unit 320 selects and outputs questions i1, ..., i2 from the K questions as selection candidates to be recommended to the learner. M From the above, the predicted accuracy rate p i_m(m=1, …, M) is a question that is included in a predetermined range including the standard predicted correct answer rate. m_1 , …, i m_N Alternatively, the question selection unit 320 may select questions i1, ..., i2 as selection candidates for questions to be recommended to the learner from among the K questions. M From the above, the predicted accuracy rate p i_m (m=1, …, M) is the problem i that is recommended to the learner with priority given to the problem that is close to the standard predicted correct answer rate. m_1 , …, i m_N It may be selected as.

[0065] Furthermore, for example, an input vector may be used in which the test result is "No answer" for questions that the recommended learner actually answered correctly, or an input vector may be used in which the test result is "No answer" for questions that the recommended learner actually answered incorrectly. Specifically, an input vector may be used in which the test results are "No answer" for a predetermined number of questions, starting with the question answered correctly and the question answered incorrectly by the recommended learner, in descending order of the difference between the predicted correct answer rate and the value indicating the actual correct answer, or an input vector may be used in which the test result is "No answer" for questions for which the difference is greater than or equal to a predetermined threshold. The above input vectors can be generated by the same operation as the question recommendation device 300. That is, from a vector representing the actual test results of the learner to be recommended, the predicted correct answer rates for questions answered correctly and questions answered incorrectly by the learner to be recommended are obtained using an operation similar to that of the correct answer rate prediction unit 310 of the question recommendation device 300. Then, using an operation similar to that of the question selection unit 320 of the question recommendation device 300, the difference between the predicted correct answer rate and 1 for questions answered correctly and the difference between the predicted correct answer rate and 0 for questions answered incorrectly are calculated. A predetermined number of questions are selected in descending order of the calculated difference, and an input vector is generated for the selected questions indicating that the test result is "No Answer." Alternatively, questions for which the calculated difference is greater than or equal to a predetermined threshold are selected, and an input vector is generated for the selected questions indicating that the test result is "No Answer." This allows questions that the learner to be recommended happens to answer correctly or happens to answer incorrectly to remain viable as recommended questions. Similarly, an input vector indicating that the test result is "No Answer" can be used for questions that have been taken by the learner to be recommended a considerable amount of time ago. This allows questions to be recommended in a way that encourages the learner to be recommended to study again.

[0066] (Variation) The state estimation device 201 may be used instead of the state estimation device 200 to configure the correct answer rate prediction unit 310. In this case, the correct answer rate prediction unit 310 predicts the test results X kThe latent variable vector calculated from the input vector obtained from (k=1, …, K) using the encoder of the trained neural network is used as input, and the output vector (prediction accuracy vector) is calculated from the latent variable vector using the decoder of the trained neural network, and the element p(X k ) (k=1, ..., K), the probability corresponding to the input information indicating no answer is selected, and the selected probability is output as the predicted correct answer rate of the learner for the questions that the learner has not yet taken. Alternatively, the correct answer rate prediction unit 310 may use the test results X k The latent variable vector calculated from the input vector obtained from (k=1, …, K) using the encoder of the trained neural network is used as input, and the output vector (prediction accuracy vector) is calculated from the latent variable vector using the decoder of the trained neural network, and the element p(X k ) (k=1, …, K), the probability corresponding to the candidate question to be recommended to the learner is selected, and the selected probability is output as the predicted correct answer rate for the candidate question to be recommended to the learner.

[0067] According to the embodiment of the present invention, it is possible to recommend to a learner to whom recommendation is made that problems that would be good for future study be used as problems to be solved.

[0068] <Additional Notes> The processing of each unit of each of the above-mentioned devices may be realized by a computer, in which case the processing content of the functions that each device should have is described by a program. Then, by loading this program into the recording unit 2020 of the computer 2000 shown in Fig. 10 and operating the arithmetic processing unit 2010, the input unit 2030, the output unit 2040, the auxiliary recording unit 2025, etc., the processing functions of each of the above-mentioned devices are realized on the computer.

[0069] The device of the present invention may, for example, be a single hardware entity, having an input unit capable of inputting signals from outside the hardware entity, an output unit capable of outputting signals to outside the hardware entity, a communication unit to which a communication device (e.g., a communication cable) can be connected for communication with outside the hardware entity, a CPU (which may also include a central processing unit, cache memory, registers, etc.) as an arithmetic processing unit, RAM and ROM as memories, an external storage device such as a hard disk, and buses connecting these input unit, output unit, communication unit, CPU, RAM, ROM, and external storage device so as to enable data exchange. If necessary, the hardware entity may also be provided with a device (drive) capable of reading and writing to a recording medium such as a CD-ROM. An example of a physical entity equipped with such hardware resources is a general-purpose computer.

[0070] The external storage device of the hardware entity stores the programs required to realize the above-mentioned functions and the data required for processing these programs (the programs may be stored in a ROM, which is a read-only storage device, for example, instead of an external storage device). Data obtained by processing these programs is stored in RAM, the external storage device, etc. as appropriate.

[0071] In the hardware entity, each program stored in an external storage device (or ROM, etc.) and data required for processing each program are loaded into memory as needed, and interpreted, executed, and processed by the CPU as appropriate. As a result, the CPU realizes predetermined functions (each component represented as the above, "... unit," "... means," etc.). In other words, each component in the embodiments of the present invention may be configured by a processing circuitry.

[0072] As described above, when the processing functions of the hardware entities (apparatuses of the present invention) described in the above embodiments are realized by a computer, the processing contents of the functions that the hardware entities should have are described by a program. Then, by executing this program on a computer, the processing functions of the hardware entities are realized on the computer.

[0073] The program describing the processing contents can be recorded on a computer-readable recording medium, such as a non-transitory recording medium, specifically a magnetic recording device, an optical disk, or the like.

[0074] The program may be distributed, for example, by selling, transferring, lending, etc. a portable recording medium such as a DVD or CD-ROM on which the program is recorded. Furthermore, the program may be stored in a storage device of a server computer, and then transferred from the server computer to another computer via a network, thereby distributing the program.

[0075] A computer that executes such a program, for example, first stores the program recorded on a portable recording medium or transferred from a server computer in its own non-transitory storage device, the auxiliary storage unit 2025. Then, when executing a process, the computer loads the program stored in its own non-transitory storage device, the auxiliary storage unit 2025, into the storage unit 2020 and executes processing in accordance with the loaded program. Alternatively, as another execution mode of this program, the computer may load the program directly from a portable recording medium into the storage unit 2020 and execute processing in accordance with the program. Furthermore, each time a program is transferred from a server computer to this computer, the computer may execute processing in accordance with the received program. Alternatively, the server computer may not transfer the program to this computer, but may instead execute the processing function by issuing an execution instruction and obtaining the results, thereby executing the above-described processing through a so-called ASP (Application Service Provider) type service. Note that the program in this embodiment includes information used for processing by a computer that is equivalent to a program (such as data that is not a direct instruction to a computer but has properties that define computer processing).

[0076] Furthermore, in this embodiment, the device is configured by executing a predetermined program on a computer, but at least a part of the processing contents may be realized by hardware.

[0077] The present invention is not limited to the above-described embodiment, and various modifications can be made without departing from the spirit of the present invention.

Claims

1. The input information is information indicating a positive state, a negative state, or an unknown state, The input vector is represented by two bits: a positive information bit that is 1 when the input information indicates a positive state and 0 when the input information indicates an unknown state or a negative state, and a negative information bit that is 1 when the input information indicates a negative state and 0 when the input information indicates an unknown state or a positive state. By representing the input information using two bits, K pieces of input information x (K is an integer equal to or greater than 2) can be represented. 1 , …, x K Let be the vector obtained from Let p(x) be the probability that the input information x is information indicating a positive state, The output vector is calculated by dividing the K input information x 1 , …, x K Probability p(x 1 ), …, p(x K ) is a vector with elements, a recording unit that records the parameters of the trained neural network that has been trained by repeating a parameter update process that updates the parameters of the encoder and decoder using a loss function that includes an encoder that calculates a latent variable vector having latent variables as elements from an input vector and a decoder that calculates an output vector from the latent variable vector, the loss function including a loss term that increases as the probability p(x) for the input information x decreases when the input information x is information indicating a positive state, a loss term that increases as the probability p(x) for the input information x increases when the input information x is information indicating a negative state, and a loss term that is approximately 0 when the input information x is information indicating an unknown state; Using the encoder of the trained neural network, K pieces of input information X 1 , …, X K an encoder unit that calculates a latent variable vector to be estimated from an input vector to be estimated obtained from a decoder unit that calculates an output vector to be estimated from the latent variable vector to be estimated using a decoder of the trained neural network; From the output vector to be estimated, input information X indicating an unknown state is k (where k satisfies 1≦k≦K) k ) Enter information X k a state estimation unit that obtains the estimated probability that the state is positive; A state estimator including:

2. The input information is information indicating a positive state, a negative state, or an unknown state, The input vector is represented by two bits: a positive information bit that is 1 when the input information indicates a positive state and 0 when the input information indicates an unknown state or a negative state, and a negative information bit that is 1 when the input information indicates a negative state and 0 when the input information indicates an unknown state or a positive state. By representing the input information using two bits, K pieces of input information x (K is an integer equal to or greater than 2) can be represented. 1 , …, x K Let be the vector obtained from Let p(x) be the probability that the input information x is information indicating a positive state, The output vector is calculated by dividing the K input information x 1 , …, x K Probability p(x 1 ), …, p(x K ) is a vector with elements, a recording unit that records the decoder parameters of the trained neural network that has been trained by repeating a parameter update process that updates the parameters of the encoder and the decoder using a loss function that includes an encoder that calculates a latent variable vector having latent variables as elements from an input vector and a decoder that calculates an output vector from the latent variable vector, the loss function including a loss term that increases as the probability p(x) for the input information x decreases when the input information x is information indicating a positive state, increases as the probability p(x) for the input information x increases when the input information x is information indicating a negative state, and is approximately 0 when the input information x is information indicating an unknown state; K pieces of input information X 1 , …, X K a decoder unit that calculates an output vector to be estimated using a decoder of the trained neural network from a latent variable vector to be estimated corresponding to an input vector to be estimated obtained from From the output vector to be estimated, input information X indicating an unknown state is k (where k satisfies 1≦k≦K) k ) Enter information X k a state estimation unit that obtains the estimated probability that the state is positive; A state estimator including:

3. The input information is information indicating a positive state, a negative state, or an unknown state, The input vector is represented by two bits: a positive information bit that is 1 when the input information indicates a positive state and 0 when the input information indicates an unknown state or a negative state, and a negative information bit that is 1 when the input information indicates a negative state and 0 when the input information indicates an unknown state or a positive state. By representing the input information using two bits, K pieces of input information x (K is an integer equal to or greater than 2) can be represented. 1 , …, x K Let be the vector obtained from Let p(x) be the probability that the input information x is information indicating a positive state, The output vector is calculated by dividing the K input information x 1 , …, x K Probability p(x 1 ), …, p(x K ) is a vector with elements, a recording unit that records the parameters of the trained neural network that has been trained by repeating a parameter update process that updates the parameters of the encoder and decoder using a loss function that includes an encoder that calculates a latent variable vector having latent variables as elements from an input vector and a decoder that calculates an output vector from the latent variable vector, the loss function including a loss term that increases as the probability p(x) for the input information x decreases when the input information x is information indicating a positive state, a loss term that increases as the probability p(x) for the input information x increases when the input information x is information indicating a negative state, and a loss term that is approximately 0 when the input information x is information indicating an unknown state; Let K input information be the test results for K questions, and let the positive state, negative state, and unknown state be the correct answer, incorrect answer, and no answer, respectively. Test results for learners for K questions X k (k=1, ..., K) using the trained neural network to calculate an output vector, and k ) (k=1, ..., K), and obtains the probability corresponding to a question in the selection candidate set of questions to be recommended to the learner as a predicted correct answer rate for the question in the selection candidate set of questions to be recommended to the learner. p i_1 , …, p i_M (where M is an integer between 1 and K, and i m (m=1, …, M) is 1≦i m ≦K, and i m and i m’ (m ≠ m') are different from each other) to be recommended to the learner from among the K questions. 1 , …, i M The predicted correct answer rate is the standard predicted correct answer rate for recommending problems to be solved. The reference predicted correct answer rate and the selection candidate question i of the questions recommended to the learner from among the K questions 1 , …, i M Prediction accuracy rate p i_1 , …, p i_M Using this, problem i 1 , …, i M Question i to recommend to the learner from m_1 , …, i m_N a problem selection section for selecting A problem recommendation device including:

4. The input information is information indicating a positive state, a negative state, or an unknown state, The input vector is represented by two bits: a positive information bit that is 1 when the input information indicates a positive state and 0 when the input information indicates an unknown state or a negative state, and a negative information bit that is 1 when the input information indicates a negative state and 0 when the input information indicates an unknown state or a positive state. By representing the input information using two bits, K pieces of input information x (K is an integer equal to or greater than 2) can be represented. 1 , …, x K Let be the vector obtained from Let p(x) be the probability that the input information x is information indicating a positive state, The output vector is calculated by dividing the K input information x 1 , …, x K Probability p(x 1 ), …, p(x K ) is a vector with elements, a recording unit that records the decoder parameters of the trained neural network that has been trained by repeating a parameter update process that updates the parameters of the encoder and the decoder using a loss function that includes an encoder that calculates a latent variable vector having latent variables as elements from an input vector and a decoder that calculates an output vector from the latent variable vector, the loss function including a loss term that increases as the probability p(x) for the input information x decreases when the input information x is information indicating a positive state, increases as the probability p(x) for the input information x increases when the input information x is information indicating a negative state, and is approximately 0 when the input information x is information indicating an unknown state; Let K input information be the test results for K questions, and let the positive state, negative state, and unknown state be the correct answer, incorrect answer, and no answer, respectively. Test results for learners for K questions X k (k=1, ..., K) using the decoder of the trained neural network to calculate an output vector from the latent variable vector corresponding to the input vector obtained from k ) (k=1, ..., K), and obtains the probability corresponding to a question in the selection candidate set of questions to be recommended to the learner as a predicted correct answer rate for the question in the selection candidate set of questions to be recommended to the learner. p i_1 , …, p i_M (where M is an integer between 1 and K, and i m (m=1, …, M) is 1≦i m ≦K, and i m and i m’ (m ≠ m') are different from each other) to be recommended to the learner from among the K questions. 1 , …, i M The predicted correct answer rate is the standard predicted correct answer rate for recommending problems to be solved. The reference predicted correct answer rate and the selection candidate question i of the questions recommended to the learner from among the K questions 1 , …, i M Prediction accuracy rate p i_1 , …, p i_M Using this, problem i 1 , …, i M Question i to recommend to the learner from m_1 , …, i m_N a problem selection section for selecting A problem recommendation device including:

5. 5. The problem recommendation device according to claim 3, Questions recommended to the learner i m_1 , …, i m_N contains only questions that the learner has not yet attempted. A problem recommendation device characterized by:

6. 5. The problem recommendation device according to claim 3, The question selection unit selects question i from the K questions as a selection candidate for a question to be recommended to the learner. 1 , …, i M From the above, the predicted accuracy rate p i_m (m=1, …, M) is a question that is included in a predetermined range including the standard predicted correct answer rate, and is recommended to the learner. m_1 , …, i m_N Select as A problem recommendation device characterized by:

7. 5. The problem recommendation device according to claim 3, The question selection unit selects question i from the K questions as a selection candidate for a question to be recommended to the learner. 1 , …, i M From the above, the predicted accuracy rate p i_m (m=1, …, M) is the problem i that is recommended to the learner with priority given to problems that are close to the standard predicted correct answer rate. m_1 , …, i m_N Select as A problem recommendation device characterized by:

8. The input information is information indicating a positive state, a negative state, or an unknown state, The input vector is represented by two bits: a positive information bit that is 1 when the input information indicates a positive state and 0 when the input information indicates an unknown state or a negative state, and a negative information bit that is 1 when the input information indicates a negative state and 0 when the input information indicates an unknown state or a positive state. By representing the input information using two bits, K pieces of input information x (K is an integer equal to or greater than 2) can be represented. 1 , …, x K Let be the vector obtained from Let p(x) be the probability that the input information x is information indicating a positive state, The output vector is calculated by dividing the K input information x 1 , …, x K Probability p(x 1 ), …, p(x K ) is a vector with elements, The state estimation device includes an encoder that calculates a latent variable vector having latent variables as elements from an input vector and a decoder that calculates an output vector from the latent variable vector, and the loss function includes a loss term that, when input information x is information indicating a positive state, increases as the probability p(x) for the input information x decreases, when input information x is information indicating a negative state, increases as the probability p(x) for the input information x increases, and is approximately 0 when input information x is information indicating an unknown state. The state estimation device includes a recording unit that records parameters of a trained neural network that has undergone training by repeating a parameter update process that updates the parameters of the encoder and decoder using a loss function that includes a loss term that, when input information x is information indicating a positive state, increases as the probability p(x) for the input information x increases, and is approximately 0 when input information x is information indicating an unknown state. 1 , …, X K an encoder step of calculating a latent variable vector to be estimated from an input vector to be estimated obtained from a decoder step in which the state estimation device calculates an output vector to be estimated from the latent variable vector to be estimated using a decoder of the trained neural network; The state estimation device extracts input information X indicating an unknown state from the estimation target output vector. k (where k satisfies 1≦k≦K) k ) Enter information X k a state estimation step in which the estimated probability of being in a positive state is obtained; A state estimation method including:

9. The input information is information indicating a positive state, a negative state, or an unknown state, The input vector is represented by two bits: a positive information bit that is 1 when the input information indicates a positive state and 0 when the input information indicates an unknown state or a negative state, and a negative information bit that is 1 when the input information indicates a negative state and 0 when the input information indicates an unknown state or a positive state. By representing the input information using two bits, K pieces of input information x (K is an integer equal to or greater than 2) can be represented. 1 , …, x K Let be the vector obtained from Let p(x) be the probability that the input information x is information indicating a positive state, The output vector is calculated by dividing the K input information x 1 , …, x K Probability p(x 1 ), …, p(x K ) is a vector with elements, The state estimation device includes an encoder that calculates a latent variable vector having latent variables as elements from an input vector and a decoder that calculates an output vector from the latent variable vector, and the loss function includes a loss term that, when the input information x is information indicating a positive state, increases as the probability p(x) for the input information x decreases, when the input information x is information indicating a negative state, increases as the probability p(x) for the input information x increases, and is approximately 0 when the input information x is information indicating an unknown state. The state estimation device includes a recording unit that records the decoder parameters of the trained neural network that has undergone training by repeating a parameter update process that updates the parameters of the encoder and the decoder using a loss function that includes a loss term that, when the input information x is information indicating a positive state, increases as the probability p(x) for the input information x increases, and is approximately 0 when the input information x is information indicating an unknown state. 1 , …, X K a decoder step of calculating an output vector to be estimated using a decoder of the trained neural network from a latent variable vector to be estimated corresponding to an input vector to be estimated obtained from The state estimation device extracts input information X indicating an unknown state from the estimation target output vector. k (where k satisfies 1≦k≦K) k ) Enter information X k a state estimation step in which the estimated probability of being in a positive state is obtained; A state estimation method including:

10. The input information is information indicating a positive state, a negative state, or an unknown state, The input vector is represented by two bits: a positive information bit that is 1 when the input information indicates a positive state and 0 when the input information indicates an unknown state or a negative state, and a negative information bit that is 1 when the input information indicates a negative state and 0 when the input information indicates an unknown state or a positive state. By representing the input information using two bits, K pieces of input information x (K is an integer equal to or greater than 2) can be represented. 1 , …, x K Let be the vector obtained from Let p(x) be the probability that the input information x is information indicating a positive state, The output vector is calculated by dividing the K input information x 1 , …, x K Probability p(x 1 ), …, p(x K ) is a vector with elements, The problem recommendation device includes an encoder that calculates a latent variable vector having latent variables as elements from an input vector, and a decoder that calculates an output vector from the latent variable vector, and the problem recommendation device includes a loss function that, when the input information x is information indicating a positive state, the smaller the probability p(x) for the input information x, the larger the value; when the input information x is information indicating a negative state, the larger the value for the probability p(x) for the input information x, and the loss function that is approximately 0 when the input information x is information indicating an unknown state, and the problem recommendation device includes a recording unit that records the parameters of the trained neural network that has undergone training, and the problem recommendation device sets K pieces of input information as test results for K problems, and sets a positive state, a negative state, and an unknown state as correct answers, incorrect answers, and no answer, respectively, and calculates the test results X of the learner for the K problems. k (k=1, ..., K) using the trained neural network to calculate an output vector, and k ) (k=1, ..., K), and obtain the probability corresponding to the question of the selection candidate of the question to be recommended to the learner as the predicted correct answer rate of the question of the selection candidate of the question to be recommended to the learner. The problem recommendation device is i_1 , …, p i_M (where M is an integer between 1 and K, and i m (m=1, …, M) is 1≦i m ≦K, and i m and i m’ (m ≠ m') are different from each other) to be recommended to the learner from among the K questions. 1 , …, i M The standard predicted correct answer rate is the predicted correct answer rate that is the standard for recommending problems to be solved, and the standard predicted correct answer rate and the problem i of the selection candidate for the problem to be recommended to the learner among the K problems are 1 , …, i M Prediction accuracy rate p i_1 , …, p i_M Using this, problem i 1 , …, i M Question i to recommend to the learner from m_1 , …, i m_N a problem selection step of selecting Problem recommendation methods including.

11. The input information is information indicating a positive state, a negative state, or an unknown state, The input vector is represented by two bits: a positive information bit that is 1 when the input information indicates a positive state and 0 when the input information indicates an unknown state or a negative state, and a negative information bit that is 1 when the input information indicates a negative state and 0 when the input information indicates an unknown state or a positive state. By representing the input information using two bits, K pieces of input information x (K is an integer equal to or greater than 2) can be represented. 1 , …, x K Let be the vector obtained from Let p(x) be the probability that the input information x is information indicating a positive state, The output vector is calculated by dividing the K input information x 1 , …, x K Probability p(x 1 ), …, p(x K ) is a vector with elements, The problem recommendation device includes an encoder that calculates a latent variable vector having latent variables as elements from an input vector, and a decoder that calculates an output vector from the latent variable vector, and the problem recommendation device includes a loss function that, when the input information x is information indicating a positive state, the smaller the probability p(x) for the input information x, the larger the value; when the input information x is information indicating a negative state, the larger the value for the probability p(x) for the input information x, and the loss function that is approximately 0 when the input information x is information indicating an unknown state, and the problem recommendation device includes a recording unit that records the decoder parameters of the trained neural network that has undergone training by repeating a parameter update process that updates the parameters of the encoder and the decoder using the loss function. The problem recommendation device sets K pieces of input information as test results for K problems, and treats a positive state, a negative state, and an unknown state as correct answers, incorrect answers, and no answer, respectively, and calculates the test results X of the learner for the K problems. k (k=1, ..., K) using the decoder of the trained neural network to calculate an output vector from the latent variable vector corresponding to the input vector obtained from k ) (k=1, ..., K), and obtain the probability corresponding to the question of the selection candidate of the question to be recommended to the learner as the predicted correct answer rate of the question of the selection candidate of the question to be recommended to the learner. The problem recommendation device is i_1 , …, p i_M (where M is an integer between 1 and K, and i m (m=1, …, M) is 1≦i m ≦K, and i m and i m’ (m ≠ m') are different from each other) to be recommended to the learner from among the K questions. 1 , …, i M The standard predicted correct answer rate is the predicted correct answer rate that is the standard for recommending problems to be solved, and the standard predicted correct answer rate and the problem i of the selection candidate for the problem to be recommended to the learner among the K problems are 1 , …, i M Prediction accuracy rate p i_1 , …, p i_M Using this, problem i 1 , …, i M Question i to recommend to the learner from m_1 , …, i m_N a problem selection step of selecting Problem recommendation methods including.

12. A program for causing a computer to function as either the state estimation device according to claim 1 or 2 or the question recommendation device according to claim 3 or 4.

Images