JP7643143B2 - Information processing device, information processing method, and program - Google Patents

Description

The present invention relates to an information processing device, an information processing method , and a program.

In recent years, systems for providing learning support to learners have been developed. For example, Patent Document 1 discloses a learning support program that supports learners in executing and recording their learning plans.

Patent No. 6572412

However, the invention of Patent Document 1 merely stores the learner's learning plan (target learning outcome data) in advance and cannot automatically create target learning outcome data.

In one aspect, the objective is to provide an information processing device etc. capable of automatically creating appropriate target learning outcome data for learners.

According to one aspect, an information processing device includes a first acquisition unit that acquires, in a time series, learning outcome data for each unit period that indicates a learning outcome of a learner in a first period; a first output unit that inputs the time series learning outcome data acquired by the first acquisition unit into a learning model that has learned a relationship between the learning outcome data for each unit period and target learning outcome data that is a learning outcome for each unit period necessary for achieving a goal in the first period and thereafter, and outputs target learning outcome data for each unit period in time series; and a second acquisition unit that acquires actual learning outcome data of the learner when the unit period has elapsed. The first output unit outputs the target learning outcome data for each unit period. The system further comprises a judgment unit which outputs learning outcome data and actual learning outcome data acquired by the second acquisition unit in a manner that allows comparison between the learning outcome data and the actual learning outcome data acquired by the second acquisition unit and the target learning outcome data output by the first output unit, and a second output unit which outputs an alert message when the judgment unit judges that the target has not been achieved, and the first output unit inputs learning outcome data, which is the learning outcome data acquired by the first acquisition unit plus the learning outcome data acquired by the second acquisition unit, into the learning model, and outputs the target learning outcome data for each unit period.

On one hand, it is possible to automatically create appropriate target learning outcome data for learners.

FIG. 1 is an explanatory diagram showing an overview of a learning outcome prediction system. FIG. 2 is a block diagram showing an example of the configuration of a server. FIG. 2 is an explanatory diagram illustrating an example of a record layout of a training data DB. 1 is an explanatory diagram showing an example of a record layout of a learning model management DB and a learner DB. FIG. 2 is a block diagram showing a configuration example of a terminal. FIG. 1 is an explanatory diagram of a learning outcome prediction model. FIG. 10 is an explanatory diagram illustrating an example of training data. 13 is a flowchart showing the steps of a process for generating a learning outcome prediction model. 13 is a flowchart showing a processing procedure for outputting target learning outcome data. 10 is a flowchart showing a processing procedure for performing a process of determining whether a goal has been achieved. FIG. 13 is an explanatory diagram showing an example of a display screen of a graph showing target learning outcome data. FIG. 11 is a block diagram showing an example of the configuration of a server according to a second embodiment. 11 is an explanatory diagram showing an example of a record layout of an assignment DB and a progress DB. 13 is a flowchart showing a processing procedure for outputting a task to be studied together with target learning outcome data. 13 is a flowchart showing the procedure of a subroutine for identifying a task to be studied. FIG. 13 is an explanatory diagram showing an example of a display screen of a graph showing target learning outcome data and assignments.

The present invention will be described in detail below with reference to drawings showing an embodiment of the invention.

(Embodiment 1)
The first embodiment relates to a form in which target learning outcome data for each unit period after the first period is output (predicted) using artificial intelligence (AI) based on learning outcome data for each unit period that indicates the learning outcome of a learner in the first period. Fig. 1 is an explanatory diagram showing an overview of a learning outcome prediction system. The system of this embodiment includes an information processing device 1 and an information processing terminal 2, and each device transmits and receives information via a network N such as the Internet.

The information processing device 1 is an information processing device that processes, stores, and transmits/receives various types of information. The information processing device 1 is, for example, a server device, a personal computer, or a general-purpose tablet PC (personal computer). In this embodiment, the information processing device 1 is a server device, and for the sake of simplicity, will be referred to as server 1 below.

The information processing terminal 2 is a terminal device that accepts and transmits past learning outcome data, and receives and displays target learning outcome data. The information processing terminal 2 is, for example, an information processing device such as a smartphone, a mobile phone, a wearable device such as an Apple Watch (registered trademark), a tablet, or a personal computer terminal. For the sake of brevity, the information processing terminal 2 will be read as terminal 2 below.

The server 1 according to this embodiment acquires learning outcome data for each unit period in a time series that indicates the learning outcome of the learner in the first period. The server 1 inputs the acquired time series learning outcome data into a learning model that has learned the relationship between the learning outcome data for each unit period in the first period and the target learning outcome data, which is the learning outcome for each unit period necessary to achieve the goal in the first period and thereafter, and outputs the target learning outcome data for each unit period in the first period and thereafter in chronological order. The learning model will be described later. The server 1 transmits the output time series target learning outcome data to the terminal 2.

When the server 1 determines that the unit period has elapsed, it acquires the learner's actual learning outcome data from the terminal 2. The server 1 determines whether or not the goal has been achieved based on the acquired actual learning outcome data and the target learning outcome data output from the learning model. When the server 1 determines that the goal has not been achieved, it sends an alert message to the terminal 2 indicating that the goal has not been achieved.

Figure 2 is a block diagram showing an example of the configuration of the server 1. The server 1 includes a control unit 11, a storage unit 12, a communication unit 13, an input unit 14, a display unit 15, a reading unit 16, and a large-capacity storage unit 17. Each component is connected by a bus B.

The control unit 11 includes a processor such as a CPU (Central Processing Unit), MPU (Micro-Processing Unit), and GPU (Graphics Processing Unit), and performs various information processing, control processing, and the like related to the server 1 by reading and executing the control program 1P stored in the storage unit 12. The control program 1P can be deployed so as to be executed on a single computer or at one site, or distributed across multiple sites and on multiple computers interconnected by a communications network. Although the control unit 11 is described in FIG. 2 as being a single processor, it may also be a multiprocessor.

The storage unit 12 includes memory elements such as RAM (Random Access Memory) and ROM (Read Only Memory), and stores the control program 1P or data required for the control unit 11 to execute processing. The storage unit 12 also temporarily stores data required for the control unit 11 to execute arithmetic processing. The communication unit 13 is a communication module for performing communication-related processing, and transmits and receives information to and from the terminal 2 via the network N.

The input unit 14 is an input device such as a mouse, keyboard, touch panel, or button, and outputs received operation information to the control unit 11. The display unit 15 is a liquid crystal display or an organic EL (electroluminescence) display, etc., and displays various information according to instructions from the control unit 11.

The reading unit 16 reads the portable storage medium 1a, which may be a CD (Compact Disc)-ROM or a DVD (Digital Versatile Disc)-ROM. The control unit 11 may read the control program 1P from the portable storage medium 1a via the reading unit 16 and store it in the mass storage unit 17. The control unit 11 may also download the control program 1P from another computer via a network N or the like and store it in the mass storage unit 17. The control unit 11 may also read the control program 1P from the semiconductor memory 1b.

The mass storage unit 17 includes a recording medium such as a hard disk drive (HDD) or a solid state drive (SSD). The mass storage unit 17 includes a learning outcome prediction model 171, a training data DB (database) 172, a learning model management DB 173, and a learner DB 174.

The learning outcome prediction model 171 is a predictor that predicts (outputs) target learning outcome data for each unit period after the first period based on the learning outcome data for each unit period in the first period, and is a trained learning model generated by machine learning. The training data DB 172 stores training data for constructing (creating) the learning outcome prediction model 171. The learning model management DB 173 stores information related to trained learning models. The learner DB 174 stores information related to learners.

In this embodiment, the memory unit 12 and the large-capacity memory unit 17 may be configured as an integrated memory device. The large-capacity memory unit 17 may also be configured from multiple memory devices. Furthermore, the large-capacity memory unit 17 may be an external memory device connected to the server 1.

Server 1 may be executed on a single computer, or may be executed in a distributed manner on multiple computers, or may be executed in a distributed manner on virtual machines.

Figure 3 is an explanatory diagram showing an example of a record layout of training data DB172. Training data DB172 includes a training ID column, an input column, an output column, a subject column, a learning level column, and a target level column.

The training ID column stores a unique ID of the training data to identify each training data. The input column stores learning outcome data for each unit period in the first period. The output column stores target learning outcome data for each unit period after the first period. The learning outcome is a numerical value quantified based on the amount of learning by the learner (e.g., the number of problems solved or the study time). For example, the input column may store the number of problems for each unit period (e.g., one month) in the first period, and the output column may store the target number of problems for each unit period (e.g., one month) after the first period. Details of the learning outcome will be described later.

The subject column stores the subject to be studied (e.g., Japanese, mathematics, or social studies). The learning level column stores the learning level of the learner (e.g., academic ability deviation score). The target level column stores the target level to be reached by the learner. The target level to be reached may be an entrance exam for high school or university, or the school of the learner's choice, etc.

FIG. 4 is an explanatory diagram showing an example of the record layout of the learning model management DB 173 and the learner DB 174.
The learning model management DB 173 includes a model ID column, a learning model column, a type column, and a generation date and time column. The model ID column stores a uniquely specified learning model ID to identify each trained learning outcome prediction model 171. The learning model column stores a file of the trained learning outcome prediction model 171.

The type column stores the type of learning model. The type may be classified, for example, by the subject being studied, or by the learning level of the learner (e.g., academic ability deviation score), or further, by a combination of subject and learning level. Types classified based on subject include, for example, "Japanese model", "mathematics model", or "social studies model". Types classified based on learning level include, for example, "deviation score 50 model" or "deviation score 55 model". Types classified based on a combination of subject and learning level include, for example, "Japanese deviation score 50 model" or "mathematics deviation score 50 model". The creation date and time column stores date and time information when the learning model was created.

Learner DB174 includes a learner ID column, a period column, an actual learning outcome column, and a target learning outcome column. The learner ID column stores a unique learner ID to identify each learner. The period column stores a period corresponding to the learning outcome data. The period may be in monthly units such as one month, or in weekly units such as one week, and is not limited thereto. The actual learning outcome column stores actual learning outcome data for each period. The target learning outcome column stores target learning outcome data for each period.

Note that the storage format of each DB described above is just an example, and other storage formats are also possible as long as the relationships between data are maintained.

Figure 5 is a block diagram showing an example of the configuration of terminal 2. Terminal 2 includes a control unit 21, a storage unit 22, a communication unit 23, an input unit 24, and a display unit 25. Each component is connected by a bus B.

The control unit 21 includes an arithmetic processing device such as a CPU or MPU, and performs various information processing, control processing, etc. related to the terminal 2 by reading and executing the control program 2P stored in the memory unit 22. Note that while FIG. 5 describes the control unit 21 as a single processor, it may also be a multi-processor. The memory unit 22 includes memory elements such as RAM and ROM, and stores the control program 2P or data, etc. required for the control unit 21 to execute processing. The memory unit 22 also temporarily stores data, etc. required for the control unit 21 to execute arithmetic processing.

The communication unit 23 is a communication module for performing communication-related processing, and transmits and receives information to and from the server 1 via the network N. The input unit 24 may be a keyboard, a mouse, or a touch panel integrated with the display unit 25. The display unit 25 is a liquid crystal display or an organic EL display, etc., and displays various information according to instructions from the control unit 21.

Next, a process for outputting target learning outcome data for each unit period after the first period based on the learning outcome data for each unit period in the first period will be described. In this embodiment, the target learning outcome data is output (predicted) using the learning outcome prediction model 171.

Figure 6 is an explanatory diagram of the learning outcome prediction model 171. In this embodiment, the server 1 performs machine learning to learn the relationship between the learning outcome data for each unit period in the first period and the target learning outcome data for each unit period after the first period, and generates (creates) the learning outcome prediction model 171.

For example, the learning outcome prediction model 171 is a neural network generated by deep learning, and is a Seq2Seq (Sequence to Sequence) which is a type of RNN (Recurrent Neural Network). The learning outcome prediction model 171 has an input layer that accepts input of learning outcome data for each unit period in the first period, an intermediate layer that performs calculations based on the input data, and an output layer that outputs target learning outcome data for each unit period after the first period based on the calculation results in the intermediate layer.

The input layer has a number of neurons that receive input of learning outcome data for each unit period in the first period. Each neuron receives input of learning outcome data for each unit period in chronological order.

The intermediate layer is composed of multiple neurons called LSTM (Long short-term memory) blocks. Each neuron in the intermediate layer performs calculations based on the learning outcome data input to the corresponding neuron in the input layer. In the LSTM block, calculations are performed while referring to the calculation results in the previous LSTM block (neuron), i.e., the calculation results based on the learning outcome data that appears immediately before. In this way, the learning outcome prediction model 171 predicts the target learning outcome data for each unit period from the first period onwards based on the chronological order.

The output layer has a number of neurons that sequentially output target learning outcome data for each unit period from the first period onwards in chronological order. Each neuron predicts the target learning outcome data to be output for each unit period based on the results of calculations performed by the corresponding neurons in the intermediate layer.

As shown in Figure 6, neural networks related to Seq2Seq are classified into networks that function as encoders and networks that function as decoders. The label <SOS (Start of String)> is a reserved word that indicates the beginning of data during learning or prediction processing. The label <EOS (End of String)> is a reserved word that indicates the end of data during learning or prediction processing.

The Encoder accepts input of time-series learning outcome data for each unit period in the first period and performs calculations in the intermediate layer. Based on the time-series learning outcome data input to the Encoder, the Decoder sequentially outputs target learning outcome data for each unit period after the first period in chronological order.

As shown in the figure, the Encoder accepts input of time-series learning outcome data for each unit period in the first period, and performs calculations in the intermediate layer. The unit period may be a month, such as one month, or a week, such as one week, and is not particularly limited. Note that in this embodiment, an example of a month unit will be described. For example, the learning outcome data for April, May, June, and July may be input to the Encoder in chronological order.

The Decoder predicts the target learning outcome data for each unit period from the first period onwards based on the time series learning outcome data input into the Encoder.

For example, when learning outcome data from April to July is input into the Encoder in chronological order, the Decoder first predicts the target learning outcome data for August after July. The Decoder predicts the target learning outcome data for August, inputs the predicted target learning outcome data for August into the next LSTM block, and predicts the target learning outcome data for September. The Decoder repeats this process, sequentially predicting the target learning outcome data from October onwards, and finally predicts the target learning outcome data for each unit period. For example, learning outcome data from April to July can be input into the learning outcome prediction model 171, and target learning outcome data from August to March of the following year can be output.

Note that Seq2Seq is an example of the learning outcome prediction model 171, and the server 1 may generate other neural networks, such as a Transformer, as the learning outcome prediction model 171. Furthermore, the learning outcome prediction model 171 is not limited to a neural network, and may be a model based on other learning algorithms, such as a decision tree, a random forest, or an SVM (Support Vector Machine).

For example, the server 1 generates a learning outcome prediction model 171 using training data stored in the training data DB 172. The training data is a combination of learning outcome data for each unit period in a first period, which is associated with target learning outcome data for each unit period after the first period. The training data is generated based on a large amount of learning outcome data collected from learners who have passed the exam. The training data may also be data that has been manually created separately.

Figure 7 is an explanatory diagram showing an example of training data. Figure 7 includes a learning outcome graph 13a. The learning outcome graph 13a is a graph showing the learning outcome data of a learner for each specified period (e.g., monthly). The horizontal axis of the graph indicates the learning period of the learner (e.g., April to February of the following year). The vertical axis of the graph indicates the amount of learning, which is one type of learning outcome data. For example, the amount of learning is the number of tasks completed by a learner within a specified period, or the amount of time the learner spent studying within a specified period. Note that the learning outcome is not limited to the amount of learning, and may be quantified based on other indicators related to learning outcome (e.g., scores).

Furthermore, learning outcomes may be quantified by combining the amount of learning and the difficulty level. The difficulty level is set, for example, for each level of correct answer rate for tasks. For example, a task with a correct answer rate of 0-20% may be set to a difficulty level of "5," a task with a correct answer rate of 21-40% may be set to a difficulty level of "4," a task with a correct answer rate of 41-60% may be set to a difficulty level of "3," a task with a correct answer rate of 61-80% may be set to a difficulty level of "2," and a task with a correct answer rate of 81-100% may be set to a difficulty level of "1."

The learning outcome can be quantified, for example, by the product of the difficulty level and the amount of learning. When the amount of learning is set to "10 questions" for a task of difficulty level "5," the learning outcome is 50 (5 x 10), and when the amount of learning is set to "10 questions" for a task of difficulty level "4," the learning outcome is 40 (4 x 10). The learning outcome may be quantified based on any calculation formula.

Based on the learner's learning outcome data, training data can be created by combining the period and the amount of learning. As shown in the figure, the learning outcome data of successful candidate Mr. A from April to February of the following year is displayed on the learning outcome graph 13a. Ten sets of training data can be created from Mr. A's learning outcome data from April to February of the following year. Specifically, the first set of training data is created with the learning outcome data from April as input data and the learning outcome data from May to February of the following year as output data. Next, the second set of training data is created with the learning outcome data from April and May as input data and the learning outcome data from June to February of the following year as output data. Based on such combinations of learning outcome data, finally, a tenth set of training data is created with the learning outcome data from April to January of the following year as input and the learning outcome data from February of the following year as output.

In this way, multiple sets of training data can be generated from the learning outcome data of one successful candidate (a learner who has achieved his or her goal). Therefore, training data for learning can be generated for the learning outcome prediction model 171 using the learning outcome data of many successful learners.

Next, returning to FIG. 6, the generation process of the learning outcome prediction model 171 will be described in detail. The server 1 inputs learning outcome data (input data) for each unit period in the first training period to the learning outcome prediction model 171 in chronological order, and obtains target learning outcome data (output data) for each unit period after the first period from the output layer. The server 1 compares the correct output data contained in the training data with the output data output from the learning outcome prediction model 171, and optimizes various parameters such as weights used in calculations in the intermediate layer so that the two are close to each other.

As a result, the server 1 generates (constructs) a learning outcome prediction model 171. The server 1 stores the generated learning outcome prediction model 171 in the learning model management DB 173. In this embodiment, the server 1 predicts the target learning outcome data for each unit period using the above-mentioned learning outcome prediction model 171, and outputs the target learning outcome data for each unit period after the first period in chronological order for the learning outcome data for each unit period in the first period.

Figure 8 is a flowchart showing the steps of the process for generating the learning outcome prediction model 171. The process for generating the learning outcome prediction model 171 by performing machine learning will be described with reference to Figure 8.

The control unit 11 of the server 1 acquires multiple pieces of training data from the training data DB 172 of the mass storage unit 17, in which learning outcome data for each unit period in the first period is associated with target learning outcome data for each unit period after the first period (step S101). Based on the acquired learning outcome data for each unit period in the first period and the target learning outcome data for each unit period after the first period, the control unit 11 generates a learning outcome prediction model 171 that uses the learning outcome data for each unit period in the first period as input and outputs the target learning outcome data for each unit period after the first period (step S102).

For example, the learning outcome prediction model 171 is a neural network related to Seq2Seq, which receives time-series learning outcome data for each unit period in a first period as input, and outputs time-series target learning outcome data for each unit period after the first period. The control unit 11 sequentially inputs the learning outcome data for each unit period in the first period to the learning outcome prediction model 171 in chronological order, and sequentially outputs the target learning outcome data for each unit period after the first period in chronological order. The control unit 11 compares the output target learning outcome data for each unit period with the correct target learning outcome data included in the training data, and optimizes various parameters of the intermediate layer so that the two are similar to each other, thereby generating the learning outcome prediction model 171.

The control unit 11 stores the generated learning outcome prediction model 171 in the learning model management DB 173 of the mass storage unit 17 (step S103), and ends the series of processes. Specifically, the control unit 11 assigns a model ID to the generated learning outcome prediction model 171, and stores the file and generation date and time of the learning outcome prediction model 171 as a single record in the learning model management DB 173 in association with the assigned model ID.

In addition, a learning outcome prediction model 171 can be generated for each subject being studied. Specifically, the server 1 obtains training data for each subject from the training data DB 172. For example, when a learning outcome prediction model 171 for Japanese is generated, the server 1 may extract multiple pieces of training data corresponding to the subject "Japanese" from the training data DB 172. The server 1 generates the learning outcome prediction model 171 using the extracted training data. Note that the process of generating the learning outcome prediction model 171 is the same as the process described above, and therefore a description thereof will be omitted.

The server 1 stores the generated learning outcome prediction model 171 in the learning model management DB 173. Specifically, the server 1 assigns a model ID to the generated learning outcome prediction model 171, and stores the file, model type, and generation date and time of the learning outcome prediction model 171 in association with the assigned model ID in the learning model management DB 173 as a single record.

In addition, a learning outcome prediction model 171 can be generated for each learning level of a learner. Specifically, the server 1 acquires training data for each learning level of a learner from the training data DB 172. The learning level is, for example, an academic ability deviation value. For example, when a learning outcome prediction model 171 for a deviation value of 50 is generated, the server 1 may extract multiple pieces of training data corresponding to the learning level of "deviation value 50" from the training data DB 172. The server 1 generates the learning outcome prediction model 171 using the extracted training data, and stores the generated learning outcome prediction model 171 in the learning model management DB 173.

In addition, a learning outcome prediction model 171 can be generated for each target level of the learner. The target level is a level higher than the current learning level (e.g., academic ability deviation value). Specifically, the server 1 acquires training data from the training data DB 172 for each target level of the learner. For example, when a learning outcome prediction model 171 for a target deviation value of 55 is generated, the server 1 may extract multiple pieces of training data corresponding to the target level of "deviation value 55" from the training data DB 172. The server 1 generates the learning outcome prediction model 171 using the extracted training data, and stores the generated learning outcome prediction model 171 in the learning model management DB 173.

Furthermore, the learning outcome prediction model 171 can be generated by combining a subject and a learning level, or a subject and a target level to be achieved. For example, when a learning outcome prediction model 171 for a Japanese language deviation score 50 model is generated, the server 1 may extract multiple pieces of training data corresponding to the subject "Japanese language" and the learning level "deviation score 50" from the training data DB 172. The server 1 generates the learning outcome prediction model 171 using the extracted training data, and stores the generated learning outcome prediction model 171 in the learning model management DB 173.

Next, we will explain how to use the generated learning outcome prediction model 171.

The server 1 inputs the learning outcome data for each unit period in the first period to the learning outcome prediction model 171, and outputs the target learning outcome data for each unit period after the first period in chronological order. The server 1 stores the target learning outcome data for each unit period output from the learning outcome prediction model 171 in the learner DB 174, in association with the learner ID.

Based on the target learning outcome data for each unit period, the server 1 generates a graph showing the target learning outcome data for the unit period. The server 1 transmits the generated graph to the terminal 2. The terminal 2 receives the graph transmitted from the server 1 and displays the received graph on the screen. Note that the display format of the target learning outcome data is not limited to a graph format and may be, for example, a text or table format.

The server 1 may transmit the target learning outcome data to the terminal 2 without generating a graph showing the target learning outcome data. In this case, the terminal 2 may generate a graph based on the target learning outcome data transmitted from the server 1.

In addition, it is possible to determine whether or not the goal has been achieved based on the target learning outcome data output from the learning outcome prediction model 171. Specifically, the server 1 determines whether or not a unit period (e.g., one month) has passed. If the server 1 determines that the unit period has passed, it transmits to the terminal 2 a request to obtain the learner's actual learning outcome data for that unit period.

In response to a request to acquire actual learning outcome data sent from the server 1, the terminal 2 acquires the actual learning outcome data for the unit period. For example, the terminal 2 may accept input of the learning outcome data for the unit period. Alternatively, the terminal 2 may acquire the learning outcome data for the unit period through, for example, an e-learning system (e-Learning) that provides assignments (questions, etc.).

An e-learning system is a system in which learning is digitized and students use computers, tablets, smartphones, etc. to learn over a network such as the Internet. By studying the tasks provided on the e-learning system, students can record their learning outcome data in the e-learning system.

The terminal 2 transmits the learner ID and the actual learning outcome data for the acquired unit period to the server 1. The server 1 receives the learner ID and the actual learning outcome data transmitted from the terminal 2. The server 1 stores the received actual learning outcome data for the unit period in the learner DB 174. The server 1 acquires the target learning outcome data for the unit period from the learner DB 174 based on the received learner ID. The server 1 transmits the acquired target learning outcome data to the terminal 2. The terminal 2 displays the target learning outcome data for the unit period transmitted from the server 1 on the screen together with the actual learning outcome data.

The server 1 compares the actual learning outcome data for the unit period with the target learning outcome data for the unit period. For example, if the learning outcome data is the amount of learning (e.g., the number of tasks solved), the server 1 may compare the actual amount of learning with the target amount of learning.

When the server 1 determines that the actual amount of learning is equal to or greater than the target amount of learning, it determines that the goal has been achieved. Conversely, when the server 1 determines that the actual amount of learning is less than the target amount of learning, it determines that the goal has not been achieved. When the server 1 determines that the goal has not been achieved, it sends an alert message to the terminal 2 indicating that the goal has not been achieved. The terminal 2 receives the alert message sent from the server 1 and displays the received alert message on the screen.

Figure 9 is a flowchart showing the processing steps when outputting target learning outcome data. The control unit 21 of the terminal 2 accepts the subjects to be studied via the input unit 24 (step S251). The control unit 21 accepts input of the learner's learning level (e.g., academic achievement deviation score) via the input unit 24 (step S252). The control unit 21 transmits the accepted subjects and learning level to the server 1 via the communication unit 23 (step S253).

The control unit 11 of the server 1 receives the subject and learning level sent from the terminal 2 via the communication unit 13 (step S151). The control unit 11 identifies a learning outcome prediction model 171 based on the received subject and learning level (step S152). Specifically, the control unit 11 identifies the learning outcome prediction model 171 by acquiring the learned learning outcome prediction model 171 corresponding to the received subject and learning level from the learning model management DB 173 of the mass storage unit 17.

Note that, although FIG. 9 describes the process of identifying the learning outcome prediction model 171 based on the subject and learning level, this is not limited to this. For example, the server 1 may identify the learning outcome prediction model 171 based on either the subject or the learning level.

Note that once the above-mentioned processes (steps S251 to S253 and steps S151 to S152) have been performed, the process can be omitted from the next time.

The control unit 21 acquires learning outcome data for each unit period (e.g., one month) in the first period (e.g., April to June) (step S254). By the processing of step S254, learning outcome data corresponding to the learning level accepted in the processing of step S252 is acquired. The control unit 21 transmits the acquired learning outcome data to the server 1 via the communication unit 23 (step S255). For example, the control unit 21 accepts input of learning outcome data for each unit period in the first period via the input unit 24, and transmits the accepted learning outcome data to the server 1.

The control unit 11 of the server 1 receives the learning outcome data sent from the terminal 2 via the communication unit 13 (step S153). The control unit 11 acquires target learning outcome data using the identified learning outcome prediction model 171 (step S154). Specifically, the control unit 11 inputs the learning outcome data for each unit period in the first period in chronological order to the identified learning outcome prediction model 171, and outputs the target learning outcome data for each unit period after the first period in chronological order (for example, the target learning outcome data for July to February of the following year).

The control unit 11 transmits the acquired target learning outcome data for each unit period after the first period to the terminal 2 via the communication unit 13 (step S155). The control unit 21 of the terminal 2 receives the target learning outcome data transmitted from the server 1 via the communication unit 23 (step S256). The control unit 21 displays the received target learning outcome data on the display unit 25 (step S257) and ends the process.

Figure 10 is a flowchart showing the processing steps when performing the goal achievement determination process. The control unit 11 of the server 1 determines whether or not a unit period (e.g., one month) has elapsed (step S111). If the control unit 11 determines that the unit period has not elapsed (NO in step S111), it waits. If the control unit 11 determines that the unit period has elapsed (YES in step S111), it sends a request to obtain actual learning outcome data for the unit period to the terminal 2 via the communication unit 13 (step S112).

The control unit 21 of the terminal 2 receives the request to acquire the actual learning outcome data sent from the server 1 via the communication unit 23 (step S211). In response to the received acquisition request, the control unit 21 accepts input of the actual learning outcome data for the unit period via the input unit 24 (step S212). The control unit 21 transmits the learner ID and the accepted actual learning outcome data to the server 1 via the communication unit 23 (step S213). The control unit 11 of the server 1 receives the learner ID and actual learning outcome data sent from the terminal 2 via the communication unit 13 (step S113).

The control unit 11 acquires the target learning outcome data for the unit period from the learner DB 174 in the mass storage unit 17 based on the received learner ID (step S114). The control unit 11 transmits the acquired target learning outcome data to the terminal 2 via the communication unit 13 (step S115). The control unit 21 of the terminal 2 receives the target learning outcome data transmitted from the server 1 via the communication unit 23 (step S214). The control unit 21 displays the actual learning outcome data and the target learning outcome data for the unit period on the display unit 25 (step S215).

The control unit 11 of the server 1 compares the actual learning outcome data with the acquired target learning outcome data and determines whether the goal has been achieved (step S116). If the control unit 11 determines that the goal has been achieved (YES in step S116), it ends the process. If the control unit 11 determines that the goal has not been achieved (NO in step S116), it sends an alert message indicating that the goal has not been achieved to the terminal 2 via the communication unit 13 (step S117).

The control unit 21 of the terminal 2 receives the alert message sent from the server 1 through the communication unit 23 (step S216). The control unit 21 displays the received alert message on the display unit 25 (step S217) and ends the process. Note that the process of determining whether or not the goal has been achieved based on the actual learning outcome data and the target learning outcome data may be performed on the terminal 2 side.

Figure 11 is an explanatory diagram showing an example of a display screen for a graph showing target learning outcome data. The screen includes a type selection combo box 11a and a graph display field 11b. The type selection combo box 11a is a combo box for selecting the type of learning model. The graph display field 11b is a display field for displaying a graph showing the target learning outcome data.

When the terminal 2 receives a selection operation in the type selection combo box 11a, it transmits the selected type of learning model and the time-series learning outcome data for each unit period in the first period (e.g., learning outcome data from April to May) to the server 1. The server 1 receives the type of learning model and the time-series learning outcome data transmitted from the terminal 2. Based on the received type of learning model, the server 1 retrieves the corresponding trained learning outcome prediction model 171 from the learning model management DB 173.

The server 1 inputs the received learning outcome data for each unit period in the first period in chronological order into the acquired learning outcome prediction model 171, and outputs the target learning outcome data for each unit period after the first period (for example, the target learning outcome data from June to February of the following year) in chronological order. The server 1 generates a graph showing the target learning outcome data based on the output chronological target learning outcome data. The server 1 transmits the generated graph to the terminal 2.

The terminal 2 receives the graph sent from the server 1 and displays the received graph in the graph display field 11b. As shown in the figure, a vertical bar graph showing the relationship between learning outcome data and time period is displayed in the graph display field 11b. The horizontal axis of the vertical bar graph indicates the time period (e.g., April to February of the following year). The vertical axis of the vertical bar graph indicates the learning outcome data (e.g., the amount of learning). The broken line indicates the progress of the learning outcome data, which includes the already-learned learning outcome data and the target learning outcome data.

When actual learning outcome data is acquired, the actual learning outcome data can be displayed on a graph together with the target learning outcome data. For example, when terminal 2 acquires actual learning outcome data for June, it transmits the acquired actual learning outcome data to server 1. Server 1 receives the actual learning outcome data transmitted from terminal 2, and reflects the received actual learning outcome data on a graph.

The server 1 resends the graph reflecting the actual learning outcome data to the terminal 2. The terminal 2 receives the graph resent from the server 1 and displays it in the graph display field 11b. As shown in the figure, for the learning outcome in June, the vertical bar of the actual learning outcome data (actual value) and the vertical bar of the target learning outcome data (target value) are displayed simultaneously on the graph.

The graph can be updated based on the actual learning outcome data. Specifically, the server 1 inputs the learning outcome data, which is the target learning outcome data output from the learning outcome prediction model 171 plus the actual learning outcome data sent from the terminal 2, into the learning outcome prediction model 171, and outputs the target learning outcome data for each unit period in chronological order.

The server 1 updates the graph showing the target learning outcome data based on the output time-series target learning outcome data for each unit period. The server 1 resends the updated graph to the terminal 2. The terminal 2 receives the graph resent from the server 1 and displays the received graph in the graph display field 11b.

Note that while Figure 11 shows a vertical bar graph, this is not limiting and other graph formats may also be used.

In this embodiment, the process of generating the learning outcome prediction model 171 for goal achievement (passing) has been described, but the present invention is not limited to this. For example, a learning outcome prediction model 171 for goal non-achievement (fail) may be generated. Specifically, the server 1 performs machine learning to learn the relationship between the learning outcome data for each unit period in the first period of the learner who has not achieved the goal and the target learning outcome data for each unit period after the first period, and generates the learning outcome prediction model 171 for goal non-achievement. The minimum target learning outcome data for achieving the goal (passing) can be obtained using the learning outcome prediction model 171 for goal non-achievement.

It may also be possible to generate learning outcome prediction models 171 for other tests, including language tests such as TOEIC (registered trademark), certification tests (e.g., the Test of Practical English Proficiency), qualification tests, or promotion tests.

According to this embodiment, it is possible to predict the target learning outcome data for each unit period after the first period using the learning outcome prediction model 171.

According to this embodiment, by creating a learning outcome prediction model 171 for each subject being studied, it is possible to predict target learning outcome data for each subject.

According to this embodiment, by creating a learning outcome prediction model 171 for each learner's learning level or goal level, it is possible to predict appropriate target learning outcome data according to the learner's current situation or goal.

According to this embodiment, it is possible to determine whether or not a goal has been achieved based on the actual learning outcome data and the target learning outcome data predicted by the learning outcome prediction model 171.

According to this embodiment, if it is determined that the goal has not been achieved, an alert message is output, making it possible to encourage the learner to study toward the goal.

(Embodiment 2)
The second embodiment relates to a form in which tasks to be studied in order to achieve a goal are output together with target learning outcome data predicted from the learning outcome prediction model 171. Note that a description of the contents that overlap with the first embodiment will be omitted.

Figure 12 is a block diagram showing an example of the configuration of the server 1 of the second embodiment. Contents that overlap with those in Figure 2 are given the same reference numerals and will not be described. The large-capacity storage unit 17 stores an assignment DB 175 and a progress DB 176. The assignment DB 175 stores assignments that should be studied in order to achieve a goal, according to the target learning outcome data. The progress DB 176 stores the progress status of the assignments studied by the learner.

FIG. 13 is an explanatory diagram showing an example of the record layout of the assignment DB 175 and the progress DB 176.
The assignment DB 175 includes an assignment ID column, a subject column, a learning level column, an assignment name column, a thumbnail image column, a page column, and an assignment number column. The assignment ID column stores a unique assignment ID to identify each assignment. The subject column stores the subject of the assignment. The learning level column stores the learning level (e.g., academic ability deviation value). The assignment name column stores the name of the assignment. The thumbnail image column stores thumbnail images of the assignment. The page column stores the page of the assignment. The assignment number column stores the number of assignments corresponding to the page of the assignment.

The progress DB176 includes a learner ID column, a subject column, a month column, an actual learning outcome column, and an assignment ID column. The learner ID column stores a unique learner ID to identify each learner. The subject column stores the subject being studied. The month column stores the month in which the learner studied. The actual learning outcome column stores actual learning outcome data for each month. The assignment ID column stores an assignment ID that identifies the assignment.

Figure 14 is a flowchart showing the processing steps when outputting tasks to be studied together with target learning outcome data. Note that in Figure 14, an example is described in which the target learning outcome data is the number of tasks to be completed, but the same can be applied to other types of learning outcome data.

The control unit 21 of the terminal 2 accepts input of the subjects to be studied by the learner and the learning level of the learner through the input unit 24 (step S231). The control unit 21 transmits the accepted subjects and learning level to the server 1 through the communication unit 23 (step S232). The control unit 11 of the server 1 receives the subjects and learning level transmitted from the terminal 2 through the communication unit 13 (step S131).

The control unit 11 identifies the learning outcome prediction model 171 based on the received subject and learning level (step S132). Specifically, the control unit 11 identifies the learning outcome prediction model 171 by acquiring the learned learning outcome prediction model 171 corresponding to the received subject and learning level from the learning model management DB 173 of the mass storage unit 17.

Note that once the above-mentioned processes (steps S231 to S232 and steps S131 to S132) have been performed, the process can be omitted from the next time.

When the control unit 21 receives input of actual learning outcome data for the target period (e.g., April to June) through the input unit 24 (step S233), it transmits the received actual learning outcome data to the server 1 through the communication unit 23 (step S234). The actual learning outcome data includes the problem ID and the number of solved problems. Note that when an e-learning system that provides problems is used, the control unit 21 may obtain the actual learning outcome data for the target period recorded on the e-learning system.

The control unit 11 of the server 1 receives the actual learning outcome data for the target period sent from the terminal 2 via the communication unit 13 (step S133). The control unit 11 stores the received actual learning outcome data in the progress DB 176 of the mass storage unit 17 (step S134). Specifically, the control unit 11 stores the number of answers for the target period (e.g., June) and the assignment ID in the progress DB 176 in association with the assignment ID.

The control unit 11 acquires the target learning outcome data of the learner (step S135). Specifically, the control unit 11 inputs the received learning outcome data for the target period (e.g., April to June) into the identified learning outcome prediction model 171, and acquires the target learning outcome data for each unit period after the target period. The control unit 11 may also acquire the target learning outcome data of the learner stored in the learner DB 174 based on the learner ID.

The control unit 11 executes a subroutine for identifying tasks to be studied in order to achieve the goal, based on the acquired target learning outcome data (step S136). The subroutine for identifying tasks to be studied will be described later.

The control unit 11 transmits the acquired target learning outcome data and information about the assignment identified according to the target learning outcome data to the terminal 2 via the communication unit 13 (step S137). The information about the assignment includes, for example, the assignment ID, the assignment name, the thumbnail image, the assignment page, and the number of assignments corresponding to the assignment page.

The control unit 21 of the terminal 2 receives the target learning outcome data and information on the assignments sent from the server 1 via the communication unit 23 (step S235). The control unit 21 displays the actual learning outcome data for the target period together with the received target learning outcome data and information on the assignments on the display unit 25 (step S236), and ends the process.

Figure 15 is a flowchart showing the processing steps of a subroutine for identifying tasks to be studied. The control unit 11 of the server 1 extracts the task ID of the corresponding task from the task DB 175 of the mass storage unit 17 based on the subject and learning level (step S11). The control unit 11 obtains the task ID of the task that the learner has completed studying (study-completed task) from the progress DB 176 of the mass storage unit 17 based on the learner ID (step S12).

Based on the acquired completed task ID, the control unit 11 extracts the task IDs of tasks that the learner has not studied (unlearned tasks) from the task DB 175 (step S13). Based on the extracted unlearned task IDs and the target learning outcome data, the control unit 11 extracts the task IDs of tasks to be studied from the task DB 175 (step S14). The extraction is performed, for example, in ascending order of task IDs until the total number of tasks reaches the target learning outcome. Based on the extracted task IDs of the tasks to be studied, the control unit 11 acquires information about the tasks to be studied from the task DB 175 (step S15). The control unit 11 ends the subroutine for identifying tasks to be studied and returns.

Figure 16 is an explanatory diagram showing an example of a display screen of a graph showing target learning outcome data and tasks. Note that the same reference numerals are used for the contents that overlap with Figure 11, and the description will be omitted. The screen includes a task display field 12a and a progress display field 12b. The task display field 12a is a display field that displays the name and thumbnail image of the task identified according to the target learning outcome data. The progress display field 12b is a display field that displays the progress status of the task. Note that the progress display field 12b may be a progress bar that indicates the progress status, or may be a text field for displaying progress information including the progress rate, etc.

The terminal 2 transmits to the server 1 the type of learning model selected in the type selection combo box 11a and the time-series learning outcome data for each unit period in the first period. The server 1 receives the type of learning model and the time-series learning outcome data transmitted from the terminal 2. The server 1 acquires the corresponding trained learning outcome prediction model 171 from the learning model management DB 173 based on the received type of learning model.

The server 1 inputs the received learning outcome data for each unit period in the first period (e.g., April to May) in chronological order into the acquired learning outcome prediction model 171, and outputs the target learning outcome data for each unit period after the first period in chronological order. The server 1 generates a graph showing the target learning outcome data based on the output chronological target learning outcome data.

The server 1 identifies the tasks to be studied in order to achieve the goal, based on the subject corresponding to the type of learning model and the output target learning outcome data. Note that the process of identifying the tasks to be studied is similar to the process in FIG. 15, so a description is omitted. As shown in the figure, "Chart-style Basics p.33-35 Problems 1-5" and "Mathematics Problem Collection p121-123 Problems 1-9" are identified.

The server 1 calculates the progress rate of each task based on the number of tasks extracted from the task DB 175 and the number of tasks for which learning has been completed obtained from the progress DB 176. When an E-learning system that provides tasks is used, the server 1 may obtain the tasks to be studied and the progress status of the tasks (e.g., the percentage of correct answers or the progress rate) recorded on the E-learning system. The server 1 transmits the generated graph, information on each task to be studied in order to achieve the goal, and the progress rate of each task to the terminal 2.

The terminal 2 receives the graphs, information about each assignment (e.g., assignment ID, assignment name, thumbnail image, assignment page, etc.), and the progress rate of each assignment sent from the server 1. The terminal 2 displays the received graphs in the graph display area 11b, displays the assignment thumbnail image, assignment name (e.g., Chart-Style Basics), and assignment page (e.g., p. 33-35 Problems 1-5) in the assignment display area 12a, and displays the progress status in the progress display area 12b. Note that the graph display is the same as in FIG. 11, so a description is omitted.

Furthermore, when actual learning outcome data (for example, June) is acquired, the actual learning outcome data is displayed on a graph together with the target learning outcome data. Note that the display process of the actual learning outcome data and the target learning outcome data is the same as that in FIG. 11, and therefore a description thereof will be omitted. In this case, the server 1 recalculates the progress rate of the assignment based on the number of completed answers stored in the progress DB 176 and the number of completed answers included in the actual learning outcome data, based on the assignment ID. The server 1 displays the calculated progress rate of the assignment in the progress display column 12b.

In this embodiment, by simultaneously outputting the target learning outcome data and the tasks that should be studied in order to achieve the goal, it is possible to suggest tasks of an appropriate level of difficulty.

In this embodiment, the target learning outcome data and the progress status of the tasks to be studied are output simultaneously, making it possible to grasp the learning status of the learner.

The embodiments disclosed herein are illustrative in all respects and should not be considered limiting. The scope of the present invention is indicated by the claims, not by the meaning described above, and is intended to include all modifications within the scope and meaning equivalent to the claims.

1. Information processing device (server)
REFERENCE SIGNS LIST 11 Control unit 12 Memory unit 13 Communication unit 14 Input unit 15 Display unit 16 Reading unit 17 Large-capacity memory unit 171 Learning outcome prediction model 172 Training data DB
173 Learning model management DB
174 Learner DB
175 Issue DB
176 Progress DB
1a Portable storage medium 1b Semiconductor memory 1P Control program 2 Information processing terminal (terminal)
21 Control unit 22 Memory unit 23 Communication unit 24 Input unit 25 Display unit 2P Control program

Claims (10)

a first acquisition unit that acquires, in time series, learning outcome data for each unit period that indicates the learning outcome of the learner in a first period;
a first output unit that inputs the time-series learning outcome data acquired by the first acquisition unit into a learning model that has learned the relationship between the learning outcome data for each unit period and target learning outcome data, which is a learning outcome for each unit period necessary for achieving a goal after the first period, and outputs the target learning outcome data for each unit period in chronological order ;
a second acquisition unit that acquires actual learning outcome data of the learner when the unit period has elapsed;
The first output unit outputs the target learning outcome data for each unit period and the actual learning outcome data acquired by the second acquisition unit in a manner that allows comparison between the target learning outcome data for each unit period and the actual learning outcome data acquired by the second acquisition unit;
moreover,
a determination unit that determines whether or not the goal has been achieved based on the actual learning outcome data acquired by the second acquisition unit and the target learning outcome data output by the first output unit;
a second output unit that outputs an alert message when the determination unit determines that the target has not been achieved;
The first output unit inputs the learning outcome data obtained by adding the learning outcome data acquired by the second acquisition unit to the learning model, and outputs the target learning outcome data for each unit period.
Information processing device. The information processing apparatus according to claim 1 , wherein the learning result is a numerical value quantified according to an amount of learning. The learning model is created for each subject to be studied,
The information processing device according to claim 1 , wherein the first acquisition unit acquires learning outcome data corresponding to a subject of the learning model. The learning model is created for each learning level of the learner,
The information processing device according to claim 1 , wherein the first acquisition unit acquires learning outcome data corresponding to a learning level of the learning model. 5. The information processing apparatus according to claim 1, wherein the learning model is created for each target level of the learner. The information processing device according to claim 1 , wherein the first output unit outputs a graph showing the target learning outcome data for each unit period. a third acquisition unit that acquires a learning level of the learner,
an identification unit that identifies a task to be studied in order to achieve the goal from the tasks associated with each learning level acquired by the third acquisition unit according to the target learning outcome data output by the first output unit;
The information processing device according to claim 1 , further comprising: a third output unit that outputs the task identified by the identification unit together with the target learning outcome data output by the first output unit. a fourth acquisition unit that acquires a progress status of the task studied by the learner,
The information processing device according to claim 7 , wherein the third output unit outputs the progress status acquired by the fourth acquisition unit together with the target learning outcome data output by the first output unit. Acquire learning outcome data for each unit period in time series, which indicates the learning outcome of the learner in the first period;
inputting the acquired time-series learning outcome data into a learning model that has learned the relationship between the learning outcome data for each unit period and target learning outcome data, which is a learning outcome for each unit period necessary for achieving the goal after the first period, and outputting the target learning outcome data for each unit period in chronological order;
When the unit period has elapsed, actual learning outcome data of the learner is acquired;
outputting the target learning outcome data for each unit period and the acquired actual learning outcome data in a manner that allows comparison;
Determine whether the goal has been achieved based on the acquired actual learning outcome data and the output target learning outcome data;
If it is determined that the goal has not been achieved, an alert message will be output.
The acquired learning outcome data is added to the acquired learning outcome data, and the acquired learning outcome data is input into the learning model, and the target learning outcome data for each unit period is output.
An information processing method in which processing is performed by a computer. Acquire learning outcome data for each unit period in time series, which indicates the learning outcome of the learner in the first period;
inputting the acquired time-series learning outcome data into a learning model that has learned the relationship between the learning outcome data for each unit period and target learning outcome data, which is a learning outcome for each unit period necessary for achieving the goal after the first period, and outputting the target learning outcome data for each unit period in chronological order;
When the unit period has elapsed, actual learning outcome data of the learner is acquired;
outputting the target learning outcome data for each unit period and the acquired actual learning outcome data in a manner that allows comparison;
Determine whether the goal has been achieved based on the acquired actual learning outcome data and the output target learning outcome data;
If it is determined that the goal has not been achieved, an alert message will be output.
The acquired learning outcome data is added to the acquired learning outcome data, and the acquired learning outcome data is input into the learning model, and the target learning outcome data for each unit period is output.
A program that causes a computer to carry out processing.

Images