Information processing device, information processing method, and program

Abstract

To provide an information processing device, an information processing method and a program capable of easily submitting questions of appropriate difficulty corresponding to a user's learning level.SOLUTION: An information processing device comprises a processing unit configured to: identify an approximate user having an approximate proficiency trend of a plurality of questions among the plurality of users on the basis of question history information including a question history to the plurality of users and correct / incorrect determination results of submitted questions about the plurality of questions, wherein the approximate proficiency trend is approximate to a proficient trend of an object user among a plurality of users; derive a prediction accuracy rate of the object user to a prediction object question that is at least one of an unsubmitted question that has not been submitted to the object user and an incorrect question to which the object user has incorrectly answered in the past among the plurality of questions on the basis of correct / incorrect determination results of the prediction object questions of the appropriate user in the submission history information; and determine a question to be submitted to the object user among the plurality of questions on the basis of the derived prediction accuracy rate.SELECTED DRAWING: Figure 13

Description

[Technical field]

[0001] The present invention relates to an information processing device, an information processing method, and a program. [Background technology]

[0002] Conventionally, there are terminal devices that can be used for studying various subjects such as languages, and can conduct tests related to the subjects (asking questions and judging whether the answers are correct or not). In such tests, questions of a difficulty level according to the user's learning level can be presented, thereby appropriately judging the user's learning level and improving the learning effect of the test itself.

[0003] One method of presenting questions of a difficulty level according to the user's learning level is to predict the correct answer rate of questions that have not yet been presented to the user. For example, Patent Document 1 discloses a technology that analyzes the user's understanding of multiple concepts included in questions that have already been presented based on the user's own results of determining whether multiple questions are correct, and predicts the correct answer rate of questions that have not yet been presented to the user based on the analysis results. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Special Publication No. 2020-521244 Summary of the Invention [Problem to be solved by the invention]

[0005] However, the above conventional technology is based on the assumption that the degree of understanding of a concept is reflected in the correct answer rate of other questions, and therefore cannot be applied when this assumption does not hold (for example, when the question does not combine multiple concepts, such as a vocabulary test). Even if the above assumption holds, the questions are not necessarily composed of only simple combinations of concepts, so the accuracy of predicting the correct answer rate is not necessarily high. As described above, when using the conventional technology, the problems to which the method for predicting the accuracy rate can be applied are limited, and the accuracy of the prediction of the accuracy rate is not necessarily high. This poses the problem that it is not easy to conduct a test of an appropriate level of difficulty according to the user's learning level.

[0006] An object of the present invention is to provide an information processing device, an information processing method, and a program that can easily set questions of an appropriate level of difficulty according to a user's learning level. [Means for solving the problem]

[0007] In order to solve the above problems, the information processing device according to the present invention comprises: Questions were posed to multiple users Multiple issues of Correct / incorrect result To Based on the above, among the plurality of users subject A user and the above-mentioned problems Correct / incorrect result A similar user having a similar score to the target user is identified from among the plurality of users, and a similar user having a similar score to the target user is identified from among the plurality of questions. did Incorrect answers Each Against The above The prediction accuracy rate for the target users is The above Approximate user The above Derive based on the result of the correct / incorrect judgment, Derived for each of the unasked questions and the incorrectly answered questions Based on the prediction accuracy rate, From the unasked questions and the incorrectly answered questions The apparatus further comprises a processing unit for determining questions to be presented to the target user. Effect of the Invention

[0010] According to the present invention, a test of a difficulty level according to the user's learning level can be easily conducted. [Brief description of the drawings]

[0011] [Figure 1] FIG. 1 is a schematic configuration diagram of a learning support system. [Diagram 2] FIG. 2 is a block diagram showing a functional configuration of a server. [Diagram 3] FIG. 11 is a diagram showing an example of the contents of a user management DB. [Figure 4] FIG. 13 is a diagram showing an example of the contents of a dictionary DB. [Diagram 5] FIG. 13 is a diagram showing an example of the contents of a learning history DB. [Figure 6] FIG. 2 is a block diagram showing a functional configuration of a terminal device. [Figure 7] FIG. 13 is a diagram showing a dictionary screen. [Figure 8] FIG. 13 shows a difficulty level designation screen. [Figure 9] FIG. 13 is a diagram showing the relationship between the difficulty level of a vocabulary test and the predicted correct answer rate of words to be selected. [Figure 10] FIG. 13 illustrates a test screen. [Figure 11] FIG. 13 is a diagram showing an example of the contents of a question history DB. [Figure 12] FIG. 13 is a diagram showing an example of the contents of a prediction accuracy rate DB. [Figure 13] 13 is a flowchart showing a control procedure for a prediction accuracy rate calculation process. [Figure 14] 13 is a flowchart showing a control procedure of a test process. [Figure 15] FIG. 13 is a diagram showing an example of a feature vector in Modification 1. [Figure 16] FIG. 13 is a diagram showing an example of the contents of a question setting history DB according to the second modified example. [Figure 17] FIG. 11 is a diagram showing an example of the contents of a learning history DB according to Modification 2. [Figure 18] 13 is a flowchart showing a control procedure for a prediction accuracy rate calculation process according to Modification 2. [Figure 19] FIG. 11 is a diagram showing an example of a difficulty level designation screen according to Modification Example 2. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0013] <Learning support system configuration> FIG. 1 is a schematic configuration diagram of a learning support system 1 of the present embodiment. The learning support system 1 (information processing system) includes a server 10 (information processing device) and a plurality of terminal devices 20 communicably connected to the server 10 via a communication network N. The communication network N is, for example, the Internet, but is not limited thereto, and may be other networks such as a LAN (Local Area Network). At least a part of the communication path between the server 10 and the terminal devices 20 may be a wireless communication path.

[0014] The learning support system 1 provides a learning support service that supports language learning to a user who uses a terminal device 20. The terminal device 20 is, for example, a smartphone, but is not limited to this, and may be a tablet terminal, a notebook PC (personal computer), a desktop PC, or the like.

[0015] A learning application program (hereinafter, referred to as "learning application 231 (see FIG. 6)") is installed in the terminal device 20. By executing the learning application 231, the terminal device 20 cooperates with the server 10 to provide the user with various services related to language learning. For example, when the user inputs a search instruction for a word (a dictionary entry, a dictionary item) while the learning application 231 is being executed, the terminal device 20 acquires item information including the meaning of the word, example sentences, etc. from the server 10 and displays the information. In addition, the terminal device 20 can execute a word test to measure the proficiency of a word while the learning application 231 is being executed. The word test is, for example, a question in which the user answers the translation for the spelling (notation) of a word, or a question in which the user answers the spelling for the translation of a word. When executing a test, the terminal device 20 acquires a list of words to be asked and notation and translation data of each word from the server 10, asks a question to the user, and when the user inputs an answer to the question, judges whether the answer is correct or not and presents the result to the user. The above are examples of services provided by the learning support system 1, and the present invention is not limited to these.

[0016] The learning support system 1 provides learning support services to a plurality of users who each use a plurality of terminal devices 20. The server 10 manages information related to the usage status of the learning support service of each user, and provides the user with an appropriate service according to the information. For example, when analyzing the status of vocabulary tests given to a plurality of users and administering a vocabulary test to a certain user, questions of an appropriate level of difficulty according to the user's learning level are given based on the above analysis results. The method of determining the questions to be given will be described in detail later.

[0017] <Server configuration> FIG. 2 is a block diagram showing the functional configuration of the server 10. As shown in FIG. The server 10 includes a CPU 11 (Central Processing Unit), a RAM 12 (Random Access Memory), a storage unit 13, an operation unit 14, a display unit 15, a communication unit 16, and a bus 17. The components of the server 10 are connected to each other via the bus 17.

[0018] The CPU 11 is a processor (processing unit) that reads and executes a server control program 131 (program) stored in the storage unit 13 and performs various arithmetic processing to control the operation of the server 10. The server 10 may have multiple processors (e.g., multiple CPUs), and the multiple processes executed by the CPU 11 of this embodiment may be executed by the multiple processors. In this case, the processing unit is configured by the multiple processors. In this case, the multiple processors may be involved in a common process, or the multiple processors may independently execute different processes in parallel.

[0019] The storage unit 13 is a non-transitory recording medium readable by the CPU 11 as a computer, and stores a server control program 131 and various data. The storage unit 13 includes a non-volatile memory such as a hard disk drive (HDD) or a solid state drive (SSD). The server control program 131 is stored in the storage unit 13 in the form of a computer-readable program code. The data stored in the storage unit 13 includes a user management DB (database) 132 (characteristic information), a dictionary DB 133, a learning history DB 134, a question history DB 135 (question history information), and a predicted correct answer rate DB 136.

[0020] FIG. 3 is a diagram showing an example of the contents of the user management DB 132. As shown in FIG. The user management DB 132 stores data related to multiple users who use the learning support service. The user management DB 132 includes characteristic information related to at least one of the attributes and characteristics of each user. One data row (record) in the user management DB 132 corresponds to one user. In the example shown in FIG. 3, the user management DB 132 has data columns for "user ID," "grade," and "desired school." A "user ID" is a unique code assigned to each user. "Grade" is the grade of the user. If the user is not a student, "general" data is registered. "School of choice" is the school of choice input in advance by the user. The user management DB 132 may further include data strings related to the attributes (gender, age, etc.) and characteristics (study time, study time zone, classification of favorite words, etc.) of the user.

[0021] FIG. 4 is a diagram showing an example of the contents of the dictionary DB 133. As shown in FIG. One data row (record) of dictionary DB 133 corresponds to one word (item) of the English-Japanese dictionary. Information included in one data row of dictionary DB 133 corresponds to "item information" related to one item. Dictionary DB 133 has data columns of "word ID", "word", and "translation". A "word ID" is a unique code assigned to the word in that data row. A "word" is the spelling of a word. "Yaku" is the Japanese translation of a word. The dictionary DB 133 may further store data relating to dictionaries other than the English-Japanese dictionary (such as an English-English dictionary).

[0022] FIG. 5 is a diagram showing an example of the contents of the learning history DB 134. As shown in FIG. The learning history DB 134 stores data related to the learning history of each user in the learning support service. The learning history DB 134 has a data block generated for each user. One data row (record) in each data block corresponds to a word searched for by the user or a word given to the user in a word test. Each data block also has data columns for "user ID", "word ID", "search date", "question date", and "correctness judgment result". The "user ID" is a common symbol with the user ID in the user management DB 132 of FIG. "Word ID" is the word ID of the word corresponding to that data row, and is a common code with the word ID in dictionary DB 133 of FIG. The "search date" is the date when the word in the data row was last searched for. Note that time information may be registered in addition to the date. "Test Date" is the date when the word in the data row was last tested in a vocabulary test. Time information may be registered in addition to the date. The "correctness judgment result" is the result of the judgment of whether the user's answer in the word test is correct or not, with "1" representing a correct answer and "0" representing an incorrect answer. For example, in the learning history DB134 shown in Figure 5, it is registered that a user with user ID "U00000" answered correctly the word with word ID "W0012" in a word test on "August 12, 2021," and then conducted a search on "August 15, 2021." Examples of the contents of the question history DB 135 and the predicted correct answer rate DB 136 will be described later.

[0023] The operation unit 14 shown in FIG. 2 includes a pointing device such as a mouse, a keyboard, and the like, and receives position inputs and key inputs from the user and outputs the operation information to the CPU 11.

[0024] The display unit 15 includes a display device such as a liquid crystal display, and performs various displays on the display device in accordance with display control signals from the CPU 11.

[0025] The communication unit 16 is configured with a network card or the like, and transmits and receives data to and from a terminal device 20 on the communication network N in accordance with a predetermined communication protocol.

[0026] <Configuration of Terminal Device 20> FIG. 6 is a block diagram showing the functional configuration of the terminal device 20. As shown in FIG. The terminal device 20 includes a CPU 21, a RAM 22, a storage unit 23, an operation unit 24, a display unit 25, an audio output unit 26, a communication unit 27, and a bus 28. The components of the terminal device 20 are connected to each other via the bus 28.

[0027] The CPU 21 is a processor (processing unit) that controls the operation of the terminal device 20 by reading and executing programs such as the learning application 231 stored in the storage unit 23 and performing various arithmetic processing. The terminal device 20 may have multiple processors (e.g., multiple CPUs), and the multiple processes performed by the CPU 21 of this embodiment may be executed by the multiple processors. In this case, the processing unit is configured by the multiple processors. In this case, the multiple processors may be involved in a common process, or the multiple processors may independently execute different processes in parallel.

[0028] The storage unit 23 is a non-transitory recording medium readable by the CPU 21 as a computer, and stores programs such as the learning application 231 and various data. The storage unit 23 includes a non-volatile memory such as a flash memory. The programs are stored in the storage unit 23 in the form of computer-readable program codes.

[0029] Operation unit 24 has a touch panel overlaid on the display screen of display unit 25, physical buttons, and the like, and receives touch operations on the touch panel and press operations on the physical buttons by the user, and outputs the operation information to CPU 21.

[0030] The display unit 25 includes a display device such as a liquid crystal display, and performs various displays on the display device in accordance with display control signals from the CPU 21 .

[0031] The audio output unit 26 has a speaker, and outputs audio such as the pronunciation of words and test question sentences in accordance with an audio output control signal from the CPU 21. The audio output unit 26 also outputs an audio signal to an external audio output device (e.g., earphones or headphones) connected via a wire or wirelessly, thereby causing the audio output device to output audio.

[0032] The communication unit 27 is configured with a communication module including an antenna and the like, and transmits and receives data to and from the server 10 on the communication network N in accordance with a predetermined communication protocol.

[0033] <Learning support system operation> Next, a description will be given of the operation of the learning support system 1. The subject of operation in the following description is the CPU 11 of the server 10 and the CPU 21 of the terminal device 20, but for convenience, the server 10 and the terminal device 20 may be described as the subject of operation below.

[0034] A user who receives a learning support service from the learning support system 1 executes the learning application 231 on the terminal device 20 and logs in to the learning support system 1. Logging in to the learning support system 1 is performed, for example, by an authentication process in which a user ID and password entered by the user and transmitted from the terminal device 20 to the server 10 are compared with a user ID and password registered in advance in the server 10. A user who has logged in to the learning support system 1 can execute various functions of the learning support service on the learning application 231.

[0035] (word search) One of the basic functions of the learning support service by the learning support system 1 is searching for words in an English-Japanese dictionary. The user can perform a predetermined operation on the learning application 231 to display on the display unit 25 a dictionary screen 40 for searching for words in an English-Japanese dictionary.

[0036] FIG. 7 is a diagram showing the dictionary screen 40. As shown in FIG. The dictionary screen 40 displays a search box 41 for specifying a word to be searched for, an item information display area 42 in which item information of the searched word is displayed, an audio playback button 43 for playing the audio of the word, and a dictionary screen exit button 44 for ending the word search. When a search is performed with the spelling of the word to be searched for input in the search box 41, the terminal device 20 requests the server 10 for item information of the word. In response to the request, the server 10 acquires item information of the specified word from the dictionary DB 133 and transmits it to the terminal device 20. The terminal device 20 displays the acquired item information in the item information display area 42. The server 10 also registers the search date on which the word was searched for in the data block corresponding to the user who performed the search in the learning history DB 134. This records the user's word search history.

[0037] (test) The learning support service by the learning support system 1 can conduct the above-mentioned word test. In the following, a word test in which a translation is given for the spelling (notation) of a word will be described as an example. In the word test of this embodiment, words to be asked (hereinafter, referred to as "question words") are selected from among words included as items in the dictionary DB 133, which the user has not searched for in the past, and which have never been asked in past word tests (unasked questions). When the user issues an instruction to execute a vocabulary test on the learning application 231, first, a difficulty level designation screen 50 for designating the difficulty level of the vocabulary test is displayed on the display unit 25.

[0038] FIG. 8 is a diagram showing the difficulty level designation screen 50. As shown in FIG. The difficulty level selection screen 50 displays a difficulty level selection button 51 for selecting the difficulty level of the vocabulary test, a test start button 52 for starting the vocabulary test, etc. In this embodiment, the difficulty level selection button 51 allows the user to select one of five levels of difficulty, ranging from the least difficult "Level 1" to the most difficult "Level 5."

[0039] When the user selects the test start button 52 with the difficulty level specified by the difficulty level specification button 51, the terminal device 20 requests the server 10 to provide a list of test words of the specified difficulty level (hereinafter, referred to as the "test word list"). In response to the request, the server 10 obtains test words of the specified difficulty level for the user from the dictionary DB 133 to generate a test word list. The predicted correct answer rate DB 136 in the storage unit 13 of the server 10 stores information on the predicted correct answer rate of the user for words that have never been given to the user in past word tests. The server 10 extracts test words of the specified difficulty level based on the predicted correct answer rate. Specifically, as shown in FIG. 9, when the specified difficulty level is "Level 5," question words are selected from among words with a predicted accuracy rate of 0.0 or more and less than 0.2; when the specified difficulty level is "Level 4," question words are selected from among words with a predicted accuracy rate of 0.2 or more and less than 0.4; when the specified difficulty level is "Level 3," question words are selected from among words with a predicted accuracy rate of 0.4 or more and less than 0.6; when the specified difficulty level is "Level 2," question words are selected from among words with a predicted accuracy rate of 0.6 or more and less than 0.8; and when the specified difficulty level is "Level 1," question words are selected from among words with a predicted accuracy rate of 0.8 or more and less than 1.0.

[0040] The number of words to be included in the question word list, i.e., the number of words to be given in one word test, is preset by settings and is 10 in this embodiment. The server 10 creates a question word list by selecting 10 words with a predicted accuracy rate corresponding to the specified difficulty level, and transmits the list to the terminal device 20. When the terminal device 20 acquires the question word list, it transitions the display screen on the display unit 25 to a test screen 60 for taking the word test.

[0041] FIG. 10 is a diagram showing the test screen 60. As shown in FIG. The test screen 60 displays a question word 61, a text box 62 for inputting a translation as an answer, an answer button 63, and the like. The question word 61 is one word included in the application word list. The user can answer the question by inputting a translation of the question word 61 in the text box 62 and selecting the answer button 63. When the user has completed the answer to one question word 61, the next question word 61 included in the question word list is displayed, and the user can continue to answer. When the user has completed the answers to all (10 in this embodiment) question words 61, the correct / incorrect judgment results of all the question words 61 are displayed on the display unit 25. Alternatively, the correct / incorrect judgment result of the question word 61 may be displayed each time an answer is given to one question word 61.

[0042] The server 10 also records the words added to the test word list in the learning history DB 134 as words that have been tested. That is, in the learning history DB 134, in a data block corresponding to the user who took the word test, a data row for the word added to the test word list is added, and the test date is registered. Also, the result of the correctness judgment for each test word is registered. This records the history of words being tested for the user, and the history of the correctness judgment results.

[0043] (Calculation method for prediction accuracy rate) Next, a method for calculating the prediction accuracy rate will be described. The server 10 executes a prediction accuracy calculation process for calculating the prediction accuracy rate of untested words in the word test for all users (multiple users) at a predetermined frequency (for example, about once a month). In this embodiment, untested words (untested questions) correspond to the "prediction target questions" for which the prediction accuracy rate is calculated.

[0044] In the prediction accuracy rate calculation process, first, data on the question history including whether or not each word has been posed to each user for all words registered in the dictionary DB 133 (in other words, all questions (multiple questions) in the word test) and the results of the correct / incorrect judgment of the posed words are collected and registered in the question history DB 135. The correct / incorrect judgment results of the posed words are calculated by tallying up the correct / incorrect judgment results of tests conducted within a recent specified period (e.g., within the past three months). If a word has been posed multiple times within the specified period, the correct / incorrect judgment result from the last time it was posed is used.

[0045] FIG. 11 is a diagram showing an example of the contents of the question history DB 135. As shown in FIG. One data row (record) of the question history DB 135 corresponds to one user. The question history DB 135 has data rows in the number corresponding to all users (here, 30,000 users with user IDs U00000 to U29999). Also, one data string (column) of the question history DB 135 corresponds to one word. The question history DB 135 has data strings in the number corresponding to all words registered in the dictionary DB 133 (here, it is assumed that the number of words is 3000 words with word IDs W0000 to W2999).

[0046] The data corresponding to each word in each data row is either "0", "1", or "null (no data)". A "0" indicates that the word has been asked at least once within the most recent specified period to the user corresponding to that data row, and the correctness judgment result the last time the word was asked was "incorrect." A "1" indicates that the word has been asked at least once within the most recent specified period to the user corresponding to that data row, and the result of the accuracy judgment the last time the word was asked was "correct." "Null" indicates that the word has never been posed to the user corresponding to that data row in the past. In this way, the question history DB 135 includes information on the question setting status (presence or absence of question setting history) and the correct / incorrect judgment results for all words to all users.

[0047] Next, for each user, similar users who have similar word mastery tendencies are identified from among all other users based on the question setting status and the correct / incorrect judgment results in the question setting history DB 135. Here, a collaborative filtering technique is used.

[0048] Specifically, first, a feature vector is specified for one target user who is the target for identifying a similar user, and for each of all other users (hereinafter, referred to as "comparison users"). The feature vector is a vector (here, a vector consisting of the elements) that contains data of words that have been posed to both the target user and the comparison user (i.e., words whose values ​​are "0" or "1" in the data rows of the target user and the comparison user) from the data of the total number of words in the data rows of the question history DB135 (3000 data in FIG. 11).

[0049] For example, let us take the case where there are 10 words in total, and the data for these words corresponding to a target user and a comparison user is as follows ("-" represents "null"). Target user: 01--01110- Comparison user: 101--01-1- In this case, the data for the first, second, sixth, seventh, and ninth words, which have all been posed to the target user and comparison user, are treated as elements of the feature vector, and feature vector a corresponding to the target user and feature vector b corresponding to the comparison user are identified as follows: Feature vector a=(0,1,1,1,0) Feature vector b=(1,0,0,1,1)

[0050] Next, the cosine similarity between the feature vectors of the target user and the comparison user is calculated using the following formula.

[0051]

number

[0052] The closer the cosine similarity is to "1", the more similar the characteristics (here, word mastery tendencies) of the target user and the comparison user are. This cosine similarity is calculated for a target user and all remaining comparison users. Data group D1 in FIG. 11 shows the calculation results of cosine similarity between the user with user ID "U00000" as the target user and all other comparison users. Depending on the number of words for which at least one of the users has "null," the number of dimensions of the feature vector may be reduced, making it impossible to compare proficiency trends using cosine similarity with the desired accuracy. Therefore, users whose feature vectors have a number of dimensions less than a specified number may be excluded from the extraction of similar users.

[0053] Based on the calculated cosine similarity of the data group D1, a similar user who has a tendency to master words similar to that of the target user is identified. For example, among a plurality of users, a comparison user whose cosine similarity is equal to or greater than a reference value (eg, 0.5 or greater) may be identified as a similar user to the target user. Alternatively, a predetermined reference number (for example, the top 10) of comparison users selected from a plurality of users in descending order of cosine similarity may be specified as similar users to the target user. Alternatively, a predetermined standard percentage (for example, "top 5%) of comparison users selected from a plurality of users in descending order of cosine similarity may be specified as similar users to the target user. In the example of Figure 11, three comparison users selected in order of largest cosine similarity are determined as approximate users, and three users with user IDs "U00001" to "U00003" (their cosine similarities are shown in area A) are identified as approximate users.

[0054] Next, for words that have not been given to the target user (colored parts in FIG. 11, i.e., three words with word IDs "W0002" to "W0004"), the prediction accuracy rate of the target user (area C in FIG. 11) is calculated (derived) based on the data of the correct / incorrect judgment status of the approximate users (area B in FIG. 11). Specifically, for each word that has not been given, the average correct answer rate of the identified multiple approximate users is calculated and used as the prediction accuracy rate of the target user. For example, for a word with a word ID of "W0002" in FIG. 11, the correct / incorrect judgment results of the three approximate users are all "1" (correct answer), so the prediction accuracy rate is calculated as "1". Also, for a word with a word ID of "W0003", one of the three approximate users is "1" (correct answer) and two are "0" (incorrect answer), so the prediction accuracy rate is calculated as "0.33". In addition, for the word with the word ID "W0003", one of the three approximate users answered "1" (correct answer), one answered "0" (incorrect answer), and one answered "null" (not asked), so the predicted accuracy rate is calculated as "0.50".

[0055] In this manner, a data group D2 of predicted correct answer rates for all words that have not yet been posed to the target user is generated. In this embodiment, even if a word has not been posed to the target user, if the target user has already searched for the word, it is not included in the question, so the prediction accuracy rate of the searched word is set to "null". Therefore, in this embodiment, among the words that have not been posed, words that have not been searched correspond to "prediction target questions". However, this is not limited to this, and the unposed words may be included in the question regardless of whether or not there is a search history. In this case, even for words with a search history, the unposed words are set as "prediction target questions", and the prediction accuracy rate is calculated and registered in the data group D2. The data group D1 and the data group D2 generated in the process of deriving the predicted accuracy rate may be included in the question setting history DB135, or may be stored in a storage area of ​​the storage unit 13 other than the question setting history DB135.

[0056] Thereafter, the remaining users are treated as target users, and similar users are identified and the prediction accuracy is derived in the same manner as described above. A data group D2 of the prediction accuracy for each user is registered in the prediction accuracy DB 136.

[0057] FIG. 12 is a diagram showing an example of the contents of the prediction accuracy rate DB 136. As shown in FIG. One data row in the prediction accuracy rate DB136 corresponds to one user, and each data column corresponding to multiple words registers the prediction accuracy rate (value of data group D2 in FIG. 11) for the word of the user. Also, words that have already been posed to the user corresponding to the data row and words that have already been searched are set to "null." As described above, the prediction accuracy rate in the prediction accuracy rate DB136 is used in the process of selecting a word with a prediction accuracy rate according to a specified difficulty level.

[0058] (Control procedure for prediction accuracy calculation process) Next, a control procedure for a prediction accuracy rate calculation process for calculating a prediction accuracy rate will be described. FIG. 13 is a flowchart showing a control procedure for the prediction accuracy rate calculation process. As described above, the prediction accuracy rate calculation process is executed at a predetermined frequency, such as once a month.

[0059] When the prediction accuracy rate calculation process is started, the CPU 11 of the server 10 acquires the result data of the word test of all users (step S101). Here, the CPU 11 acquires the words that have been given as a test and the correct / incorrect judgment results for the words from the data block of each user in the learning history DB 134, and registers the contents in the test history DB 135.

[0060] The CPU 11 assigns 0 to a variable N that indicates the ordinal number of a user (step S102). Hereinafter, the Nth user (in this embodiment, N ranges from 0 to 29999) will be referred to as "user N."

[0061] The CPU 11 determines whether the variable N is less than the total number of users (step S103). If it is determined that the variable N is less than the total number of users ("YES" in step S103), the CPU 11 calculates the cosine similarity between the user N (target user) and each of the other users (comparison users) and generates a data group D1 shown in FIG. 11 (step S104).

[0062] The CPU 11 extracts a predetermined reference number of users in descending order of cosine similarity, and identifies them as similar users of the user N (step S105). Note that, as described above, the method of identifying similar users based on cosine similarity is not limited to this.

[0063] The CPU 11 assigns 0 to a variable M that indicates the ordinal number of a word (step S106). Hereinafter, the Mth word (in this embodiment, M ranges from 0 to 2999) will be referred to as "word M."

[0064] The CPU 11 determines whether the variable M is less than the total number of words (step S107). If it is determined that the variable M is less than the total number of words ("YES" in step S107), the CPU 11 determines whether the user N has already searched for the word M (step S108). Here, the CPU 11 determines that the user N has already searched for the word M if a search date is registered in the data row of the word M in the data block of the user N in the learning history DB 134.

[0065] If it is determined that the word M has not been searched for by the user N ("NO" in step S108), the CPU 11 determines whether the word M has been quizzed to the user (step S109). Here, the CPU 11 determines that the word M has been quizzed to the user N if the quiz date is registered in the data row of the word M in the data block of the user N in the learning history DB 134.

[0066] When it is determined that the word M has not been given to the user N ("NO" in step S109), the CPU 11 calculates the average correct answer rate of the similar users for the word M as the predicted correct answer rate of the word M (step S110).

[0067] On the other hand, if it is determined in step S108 that the user has already searched for word M ("YES" in step S108), or if it is determined in step S109 that word M has already been posed to the user ("YES" in step S109), CPU 11 sets the predicted accuracy rate for word M to "null" (step S111). In addition, in the case where untested words that have already been searched are also included in the test, the determination step of step S108 is omitted.

[0068] When step S110 or step S110 ends, the CPU 11 registers the calculation result of the prediction accuracy rate in the prediction accuracy rate DB 136 (step S112).

[0069] CPU 11 increments variable M (step S113) and returns the process to step S107. If it is determined in step S107 that variable M has reached the total number of words ("NO" in step S107), CPU 11 increments variable N (step S114) and returns the process to step S103. If it is determined in step S103 that variable N has reached the total number of users ("NO" in step S103), CPU 11 ends the prediction accuracy rate calculation process.

[0070] (Test process control procedure) Next, a control procedure for the test process for carrying out the word test will be described. FIG. 14 is a flowchart showing a control procedure of the test process. In FIG. 14, the test process executed by the CPU 21 of the terminal device 20 and the test process executed by the CPU 11 of the server 10 are shown side by side.

[0071] When the test process is started, the CPU 21 of the terminal device 20 causes the display unit 25 to display the difficulty level designation screen 50 (step S201).

[0072] The CPU 21 determines whether or not an operation to specify the difficulty level has been performed (an operation to select the test start button 52 while the difficulty level specification button 51 in FIG. 8 is selected) (step S202), and if it is determined that such an operation has not been performed ("NO" in step S202), executes step S202 again. If it is determined that an operation to specify the difficulty level has been performed ("YES" in step S202), the CPU 21 requests the server for a question word list of the specified difficulty level (step S203). Here, the CPU 21 transmits a request signal for the question word list to the server 10.

[0073] When the CPU 11 of the server 10 receives the request signal for the question word list, the CPU 11 refers to the data row corresponding to the user (target user) currently taking the test in the predicted accuracy rate DB 136, and extracts words with a predicted accuracy rate (see FIG. 9) corresponding to the specified difficulty level (step S301). The CPU 11 also generates data for a question word list including a predetermined number of the extracted words (10 in this embodiment) and data on the spelling and translation of each word, and transmits the data to the terminal device 20 (step S302).

[0074] When the CPU 21 of the terminal device 20 receives the question word list, it displays the test screen 60 on the display unit 25 and starts the word test (step S204). Here, the CPU 21 displays one of the words included in the question word list on the test screen 60 and accepts the user's input of a translation answer in the text box 62. When the answer button 63 is selected with the translation input, it compares it with the translation data in the question word list to determine whether it is correct or not. Thereafter, this process is performed for all words included in the question word list. When the user has provided answers for all the words, the CPU 21 displays the results of the correctness determination for all the words on the display unit 25.

[0075] The CPU 21 determines whether the word test has been completed (whether the correct / incorrect result has been displayed) (step S205). If the CPU 21 determines that the word test has not been completed ("NO" in step S205), it executes step S205 again, and if the CPU 21 determines that the word test has been completed ("YES" in step S205), it ends the test process.

[0076] Meanwhile, the CPU 11 of the server 10 registers the question date in the learning history DB 134 for the words included in the question word list transmitted in step S302 (step S303). This records the question history of the words for the user. Also, in the data row corresponding to the user currently taking the test in the prediction accuracy rate DB 136, the data corresponding to the questioned word is changed to "null" (step S304). This prevents the words that have already been asked from being extracted as question words in the next test and thereafter. When step S304 ends, the CPU 11 ends the test process.

[0077] <Variation 1> Next, a first modified example of the above embodiment will be described. This modified example is different from the above embodiment in the method of identifying similar users, but is otherwise similar to the above embodiment. The following describes the differences from the above embodiment.

[0078] In the above embodiment, the result of the judgment of the correctness of the questioned words in the question history DB 135 (question history information) is used as the feature vector of the user used for calculating the cosine similarity. In contrast, in this modified example, the similar user is identified based on the result of the judgment of the correctness of the question history DB 135 and the feature information related to at least one of the attributes and characteristics of each user included in the user management DB 132.

[0079] FIG. 15 is a diagram showing an example of a feature vector in the first modification. In FIG. 15, in the data row corresponding to the user, in addition to the contents of the question history DB 135, data columns of the grade and the desired school in the user management DB 132 are added. Specifically, data columns corresponding to the categories of "grade" such as "first year of high school", "second year of high school", etc., and the categories of "desired school" such as "University A", "University B", etc. are added. Then, the data column of the category to which each user corresponds is set to "1", and the data column of the category to which the user does not correspond is set to "null". In this modified example, a feature vector a including data of the question history DB 135 and the user management DB 132 as elements is used. For the elements corresponding to the categories of "grade" and "desired school", only the categories in which both the target user and the comparison user are set to "1" are incorporated into the elements of the feature vector, and the categories in which at least one of the target user and the comparison user is set to "null" are not incorporated into the elements of the feature vector. According to this method, comparison users whose "grade" or "desired school" categories match those of the target user, i.e., comparison users who share attributes and characteristics with the target user, will have a large cosine similarity and will be more likely to be identified as similar users.

[0080] Note that the feature information of a user can also be used to identify a similar user without being incorporated into the elements of the feature vector. For example, the cosine similarity may be calculated using a feature vector whose elements are only the correct / incorrect results from the question history DB135, and then a correction may be made to increase the cosine similarity depending on the degree of match between the feature information of the target user and the comparison user. Furthermore, users whose characteristic information coincidence rate is equal to or lower than a predetermined value may be excluded from the extraction of similar users.

[0081] <Variation 2> Next, a second modification of the above embodiment will be described. In the above embodiment, the question to be posed to the target user is determined according to the prediction accuracy rate from among words that have not yet been posed to the target user. However, even if the word has already been posed, there may be a meaning or advantage in re-posing the word to the target user that has been answered incorrectly. This is because re-posing the word can confirm the learning effect and promote the consolidation of learning.

[0082] Therefore, in this modified example, in addition to words that have not been asked yet (unasked questions), words that have been asked in the past to the target user and that the target user has answered incorrectly (incorrect questions) are also considered as "predicted questions" and the prediction accuracy rate is calculated. Then, from among the predicted questions including unasked questions and incorrect questions, questions to be asked to the target user are determined according to the prediction accuracy rate. Furthermore, in this modified example, even words that have been searched for in the past by the target user are considered as questions to be asked. This is because words in incorrectly answered questions are often searched for study purposes after being asked. However, this is not limited to this, and in this modified example, words that have been searched for in the past may also be excluded from questions to be asked. The other points are the same as those of the above embodiment. The points of difference from the above embodiment will be described below. Modification 2 may be combined with Modification 1.

[0083] FIG. 16 is a diagram showing an example of the contents of the question setting history DB 135 according to the second modification. In this modified example, the target user is assumed to be a user with a user ID of "U00000". Similar users to the target user are assumed to be three users with user IDs of "U00001" to "U00003" (their cosine similarities are shown in area A), as in the above embodiment. For words not yet given to the target user (words with word IDs of "W0002" and "W2995" in FIG. 16), the prediction accuracy rate is calculated using the same method as in the above embodiment.

[0084] In this modified example, the prediction accuracy rate is also calculated for words that were previously given to the target user and that the target user answered incorrectly (i.e., words for which the correct / incorrect judgment result is "0"; in FIG. 16, words with word IDs "W2996" and "W2998"). For questions that were answered incorrectly, the prediction accuracy rate (area C in FIG. 16) of the target user is calculated (derived) based on the data of the correct / incorrect judgment status of the approximate users (area B in FIG. 16). That is, the average accuracy rate of the approximate users is regarded as the prediction accuracy rate of the target user. Specifically, for the word with the word ID "W2996", one of the three approximate users answered "1" (correct answer) and two answered "0" (incorrect answer), so the prediction accuracy rate is calculated as "0.33". In addition, for the word with the word ID "W2998", one of the three approximate users answered "1" (correct answer), one answered "0" (incorrect answer), and one answered "null" (not asked), so the predicted accuracy rate is calculated as "0.50".

[0085] In addition, when deriving the predicted accuracy rate for a question with an incorrect answer, the predicted accuracy rate may be the average correct answer rate of the approximate users and the target user instead of the average correct answer rate of only the approximate users. In this case, in FIG. 16, for a word with a word ID of "W2996", one of four people, including the three approximate users and the target user, is "1" (correct answer) and three are "0" (incorrect answer), so the predicted accuracy rate is calculated as "0.25". In addition, for a word with a word ID of "W2998", one of the four people is "1" (correct answer), two are "0" (incorrect answer), and one is "null" (not asked), so the predicted accuracy rate is calculated as "0.33".

[0086] In this modification, the predicted correct answer rate of the prediction target question (unasked question and incorrectly answered question) is calculated for all users. In addition, in this modification, the predicted correct answer rate calculated for each user is registered in the learning history DB 134.

[0087] FIG. 17 is a diagram showing an example of the contents of the learning history DB 134 according to the second modification. In the learning history DB 134 shown in FIG. 17, the data block for each user includes data rows (records) corresponding to all words. In addition, each data block has a data column of "prediction accuracy rate", and the calculated prediction accuracy rate is registered in this data column. By referring to the learning history DB 134 in FIG. 17, the prediction accuracy rate for unasked questions and the prediction accuracy rate for incorrectly answered questions can be distinguished and obtained. In detail, the prediction accuracy rate in a data row in which the data columns of "asked date" and "correct / incorrect judgment result" are "null (no data)" can be determined to be the prediction accuracy rate for unasked questions. In addition, the prediction accuracy rate in a data row in which the "correct / incorrect judgment result" is "0 (incorrect answer)" can be determined to be the prediction accuracy rate for incorrectly answered questions. Note that the prediction accuracy rate is not calculated for words in which the "correct / incorrect judgment result" is "1 (correct answer)".

[0088] As in the above embodiment, the predicted accuracy rate may be registered in the predicted accuracy rate DB 136 instead of the learning history DB 134. In this case, for example, a second database in which only the predicted accuracy rates of incorrectly answered questions for each user are registered may be generated separately from a first database (the same database as the predicted accuracy rate DB 136 shown in FIG. 12) in which only the predicted accuracy rates of unasked questions for each user are registered. This allows the predicted accuracy rates for unasked questions and the predicted accuracy rates for incorrectly answered questions to be registered in a distinguishable state.

[0089] Next, a prediction accuracy rate calculation process according to the second modification will be described. FIG. 18 is a flowchart showing a control procedure of a prediction accuracy rate calculation process according to the second modification. FIG. 18 corresponds to a flowchart of the prediction accuracy rate calculation process shown in FIG. 13 in which step S108 is deleted, step S115 is added, and step S112 is changed to step S112a.

[0090] Steps S101 to S107 in FIG. 18 are the same as steps S101 to S107 in FIG. 13. In step S107, if it is determined that the variable M is less than the total number of words ("YES" in step S107), the CPU 11 determines whether or not the word M has been posed to the user (step S109). If it is determined that the word M has been posed to the user ("YES" in step S109), the CPU 11 refers to the question history DB 135 and determines whether or not the user N has correctly answered the question on the word M (step S115). If it is determined that the user N has correctly answered the question on the word M ("YES" in step S115), the CPU 11 determines that the word M is not a prediction target question and sets the prediction accuracy rate for the word M to "null" (step S111).

[0091] If it is determined that user N has answered the question about word M incorrectly ("NO" in step S115), or if it is determined in step S109 that word M has not yet been posed to the user ("NO" in step S109), CPU 11 determines that word M is the question to be predicted, and calculates the average correct answer rate of similar users for word M as the predicted correct answer rate for word M (step S110).

[0092] When step S110 or step S110 ends, the CPU 11 registers the calculation result of the prediction accuracy rate in the learning history DB 134 (step S112a). Note that, as described above, the calculation result of the prediction accuracy rate may be registered in the prediction accuracy rate DB 136. The subsequent processing is similar to that in the flowchart of FIG.

[0093] The flowchart of the test process in this modified example is basically the same as the flowchart of the test process in the above embodiment shown in FIG. However, the difficulty level specification screen 50 displayed in step S201 of FIG. 14 may accept a specification of the proportion of unasked questions and incorrectly answered questions to be posed.

[0094] FIG. 19 is a diagram showing an example of a difficulty level designation screen 50 according to the second modification. The difficulty level selection screen 50 shown in FIG. 19 corresponds to the difficulty level selection screen 50 shown in FIG. 8 to which a text box 53 for specifying the percentage of each of unasked questions and incorrectly answered questions is added. By selecting the start test button 52 with a number between "0" and "100" entered in the text box 53, a plurality of questions are asked so that the number of unasked questions and incorrectly answered questions meets the specified percentage. When a number is entered in one of the text boxes 53 for unasked questions and incorrectly answered questions, a number may be automatically entered in the other text box 53 so that the sum of the numbers in the two text boxes 53 becomes "100".

[0095] Note that the difficulty level designation screen 50 may be provided with a difficulty level designation button 51 for unasked questions and a difficulty level designation button 51 for incorrectly answered questions, and the CPU 11 may receive designations of a first difficulty level for unasked questions and a second difficulty level for incorrectly answered questions, respectively. In this case, the CPU 11 determines, based on the predicted correct answer rates for unasked questions and incorrectly answered questions, unasked questions corresponding to the designated first difficulty level and incorrectly answered questions corresponding to the designated second difficulty level as questions to be presented to the target user.

[0096] In this modified example, both unasked questions and incorrectly answered questions are set as questions, but the present invention is not limited to this, and only incorrectly answered questions may be set as questions to be predicted. In this case, only incorrectly answered questions may be set as prediction target questions, and the prediction accuracy rate may be calculated only for incorrectly answered questions.

[0097] <Effects> As described above, the server 10 as an information processing device according to the present embodiment has the CPU 11 as a processing unit. Based on the question history DB 135 (question history information) including the presence or absence of a history of questions being posed to multiple users and the result of the correct / incorrect judgment of questions that have already been posed, the CPU 11 identifies a similar user who has a similar tendency to master multiple questions to a certain target user among the multiple users, derives the prediction accuracy rate of the target user for a prediction target question that is at least one of an unasked question that has not been posed to the target user and an incorrect question that the target user has answered incorrectly in the past, based on the correct / incorrect judgment result of the prediction target question of the similar user, and determines a question to be posed to the target user among the multiple questions based on the derived prediction accuracy rate. In this way, the method using the result of the correct / incorrect judgment of the similar user can derive the predicted correct answer rate of the target user for the prediction target question (unasked question and / or wrongly answered question) easily and with high accuracy, compared to the conventional technology that derives the predicted correct answer rate from the analysis result of the target user's own understanding of the concept. Therefore, based on the derived predicted correct answer rate, questions of appropriate difficulty according to the user's learning level can be easily posed. For example, in a word test, it is possible to predict and pose words that the user does not remember, thereby efficiently improving academic ability. In addition, by posing questions with a low predicted correct answer rate for learning, the user can practice and master the questions that the similar user with a similar learning level got wrong, thereby securing an advantage over the competing users. In addition, since the approximate users are selected to reflect the academic ability of the target user at that time, it is possible to derive a predicted correct answer rate at that time for questions that the target user has answered incorrectly in the past, which reflects the target user's improvement in academic ability. Therefore, it is possible to re-ask incorrectly answered questions at an appropriate time according to the predicted correct answer rate, and to effectively study the incorrectly answered questions. In addition, since the prediction accuracy rate of the target user is derived based on the result of the correct / incorrect judgment of the similar user after identifying the similar user, there is no need to analyze the content of the question in order to derive the prediction accuracy rate. Therefore, the above method can be applied to any type of question.

[0098] Furthermore, the CPU 11 identifies a plurality of approximate users and sets the average correct answer rate of the plurality of approximate users for the question to be predicted as the prediction correct answer rate, thereby improving the accuracy of the prediction correct answer rate.

[0099] Furthermore, the CPU 11 identifies a similar user by a cosine similarity derived based on a feature vector whose elements include the results of correct / incorrect judgments on a plurality of questions of the target user and a vector whose elements include the results of correct / incorrect judgments on a plurality of questions of each of the other users. This makes it possible to identify a similar user by a simple method that uses the results of correct / incorrect judgments on a plurality of questions of each user.

[0100] Furthermore, the CPU 11 identifies, among the multiple users, a user whose cosine similarity is equal to or greater than a reference value as a similar user. This makes it possible to identify a similar user whose learning tendency similarity with the target user is equal to or greater than a certain level.

[0101] In addition, the CPU 11 identifies a reference number or a reference ratio of users selected in descending order of cosine similarity from among the multiple users as similar users. This makes it possible to identify a certain number of similar users who have a high degree of similarity in learning tendency with the target user.

[0102] Furthermore, the CPU 11 identifies similar users based on the question history DB 135 and the user management DB 132 (characteristic information) including at least one of the attributes and characteristics of a plurality of users. This makes it possible to more appropriately identify similar users, and further improve the accuracy of the prediction accuracy rate of the target user.

[0103] In addition, the CPU 11 accepts a specification of the difficulty level of the questions to be presented to the target user, and determines the questions to be presented to the target user based on the prediction accuracy rates of the multiple prediction target questions, the questions having the prediction accuracy rate corresponding to the specified difficulty level. This makes it possible to present questions of an appropriate difficulty level according to the user's learning level and the specified difficulty level.

[0104] In addition, in the second modification, when deriving the predicted accuracy rate for the incorrectly answered questions, the CPU 11 may use the average correct answer rate of the incorrectly answered questions of the approximate user and the target user as the predicted accuracy rate. It can be said that the incorrectly answered questions are questions that the target user is likely to answer incorrectly. Therefore, by using the average correct answer rate of the approximate user and the target user instead of the average correct answer rate of only the approximate user, the average correct answer rate can be adjusted in a more appropriate direction, that is, in a lower direction. This can further improve the accuracy of the predicted accuracy rate.

[0105] In addition, in the second modification, the CPU 11 accepts a specification of the ratio of unasked questions and the ratio of incorrectly answered questions among the questions to be presented to the target user, and determines questions to be presented to the target user based on the prediction accuracy rates of a plurality of prediction target questions so that the number of unasked questions and incorrectly answered questions to be presented is the specified ratio. This allows unasked questions and incorrectly answered questions to be presented at the ratio desired by the user.

[0106] Furthermore, the information processing method executed by CPU11 and CPU21 as computers of learning support system 1 as an information processing system in this embodiment identifies a similar user from among the multiple users who has a similar tendency to master multiple problems to a certain target user among the multiple users, based on question history DB135 (question history information) which includes whether or not multiple questions have been posed to multiple users and the correct / incorrect results of questions that have already been posed, derives a prediction accuracy rate for the target user for a prediction target question, which is at least one of an unasked question that has not been posed to the target user and a wrong question that the target user has answered incorrectly in the past, based on the correct / incorrect results of the prediction target question of the similar user, and determines which of the multiple questions to be posed to the target user based on the derived prediction accuracy rate. According to this, compared to the conventional technology that derives the prediction accuracy rate from the analysis result of the target user's own understanding of the concept, etc., it is possible to easily and highly accurately derive the prediction accuracy rate of the target user for the prediction target question (unasked question and / or incorrectly answered question). Therefore, based on the derived prediction accuracy rate, it is possible to easily pose a question of appropriate difficulty according to the learning level of the user. In addition, it is possible to reassign the incorrectly answered question at an appropriate timing that reflects the target user's improvement in academic ability, and to effectively study the incorrectly answered question. In addition, after identifying the approximate user, the prediction accuracy rate of the target user is derived based on the correctness judgment result of the approximate user, so there is no need to analyze the content of the question to derive the prediction accuracy rate. Therefore, the above method can be applied to any type of question.

[0107] Furthermore, the server control program 131 as a program according to this embodiment causes the CPU 11 as a computer provided in the server 10 as an information processing device to execute the following processes: identifying a similar user from among the multiple users who has a similar tendency to master multiple problems to a certain target user among the multiple users, based on a question history DB 135 (question history information) including the presence or absence of a history of questions being posed to multiple users for multiple questions and the correct / incorrect judgment results for questions that have already been posed; deriving the target user's prediction accuracy rate for a prediction target question, which is at least one of an unasked question that has not been posed to the target user among the multiple questions and an incorrect question that the target user has answered incorrectly in the past, based on the correct / incorrect judgment results for the prediction target question of the similar user; and determining which question from the multiple questions to be posed to the target user, based on the derived prediction accuracy rate. According to this, compared to the conventional technology that derives the prediction accuracy rate from the analysis result of the target user's own understanding of the concept, etc., it is possible to easily and highly accurately derive the prediction accuracy rate of the target user for the prediction target question (unasked question and / or incorrectly answered question). Therefore, based on the derived prediction accuracy rate, it is possible to easily pose a question of appropriate difficulty according to the learning level of the user. In addition, it is possible to reassign the incorrectly answered question at an appropriate timing that reflects the target user's improvement in academic ability, and to effectively study the incorrectly answered question. In addition, after identifying the approximate user, the prediction accuracy rate of the target user is derived based on the correctness judgment result of the approximate user, so there is no need to analyze the content of the question to derive the prediction accuracy rate. Therefore, the above method can be applied to any type of question.

[0108] <Other> The description of the above embodiment is merely an example of the information processing device, the information processing method, and the program according to the present invention, and the present invention is not limited to this. For example, a part or all of the processes executed by the server 10 in the above embodiment may be executed by the terminal device 20. When the calculation of the prediction accuracy rate and the selection of questions based on the prediction accuracy rate are executed by the CPU 21 of the terminal device 20, the terminal device 20 corresponds to the "information processing device."

[0109] In addition, the question presented to the user is exemplified as a question for asking the translation or spelling of a word in a vocabulary test, but the present invention is not limited to this and may be any question that can be judged as correct or incorrect. Therefore, the question presentation method of the above embodiment can be applied to any type of question (e.g., memorization questions, written questions, and listening questions using the audio output unit 26 of the terminal device 20) in any subject (e.g., mathematics, Japanese, etc.). In addition, the present invention is not limited to questions in school education, but may also be applied to questions in qualification tests at driving schools, questions in quiz games, etc.

[0110] In the above embodiment, the user specifies the difficulty level of the questions on the difficulty level specification screen 50, but the present invention is not limited to this. The CPU 11 of the server 10 may extract questions according to a predetermined difficulty level setting. For example, words that are estimated to be highly unlikely to be remembered by the user (words whose prediction accuracy rate is equal to or less than a predetermined value) may be extracted, or conversely, words that are estimated to be highly likely to be remembered by the user (words whose prediction accuracy rate is equal to or more than a predetermined value) may be extracted for the purpose of confirming the user's understanding. In these cases, the display of the difficulty level specification screen 50 is omitted.

[0111] In the above description, an example has been disclosed in which the HDD or SSD of the storage unit 13 is used as a computer-readable medium for the program according to the present invention, but the present invention is not limited to this example. As other computer-readable media, information recording media such as flash memory and CD-ROM can be applied. In addition, a carrier wave can also be applied to the present invention as a medium for providing data of the program according to the present invention via a communication line.

[0112] Furthermore, the detailed configurations and operations of the components of the learning support system 1, the server 10, and the terminal device 20 in the above embodiment may of course be modified as appropriate without departing from the spirit of the present invention.

[0113] Although the embodiments of the present invention have been described, the scope of the present invention is not limited to the above-described embodiments, but includes the scope of the invention described in the claims and its equivalents. The inventions described in the claims originally attached to this application are set forth below. The claim numbers in the appended claims are the same as those in the claims originally attached to this application. [Additional Notes] <Claim 1> Identifying a similar user from among the plurality of users who has a similar tendency to master the plurality of problems to a certain target user based on question history information including whether or not the plurality of problems have been set to the plurality of users and the results of determining whether the questions have been set; Derive a prediction accuracy rate of the target user for a prediction target question that is at least one of an unasked question that has not been posed to the target user and an incorrect question that the target user has answered incorrectly in the past, based on the correct / incorrect judgment result of the prediction target question of the approximate user in the question setting history information; A processing unit is provided for determining a question to be presented to the target user from among the plurality of questions based on the derived prediction accuracy rate. 23. An information processing apparatus comprising: <Claim 2> The processing unit includes: Identifying a plurality of said proximate users; The average accuracy rate of the question to be predicted of the plurality of approximate users is defined as the prediction accuracy rate. 2. The information processing device according to claim 1, <Claim 3> The information processing device according to claim 1 or 2, characterized in that the processing unit identifies the similar user by a cosine similarity derived based on a vector whose elements include the correct / incorrect judgment results of the plurality of questions of the target user and a vector whose elements include the correct / incorrect judgment results of the plurality of questions of each of the other users. <Claim 4> 4. The information processing apparatus according to claim 3, wherein the processing unit specifies, from among the plurality of users, a user whose cosine similarity is equal to or greater than a reference value as the similar user. <Claim 5> 4. The information processing apparatus according to claim 3, wherein the processing unit specifies, as the approximate users, a reference number or a reference ratio of users selected from the plurality of users in descending order of the cosine similarity. <Claim 6> 3. The information processing device according to claim 1, wherein the processing unit identifies the similar users based on the question history information and feature information including at least one of attributes and characteristics of the multiple users. <Claim 7> The processing unit includes: Accepting a specification of the difficulty level of questions to be presented to the target user; Based on the prediction accuracy rates of the plurality of prediction target questions, a question having a prediction accuracy rate corresponding to a specified level of difficulty is determined as a question to be presented to the target user. 3. The information processing device according to claim 1, wherein the information processing device is a computer. <Claim 8> The information processing device according to claim 1, characterized in that, when deriving the predicted accuracy rate for the incorrectly answered question, the processing unit sets an average correct answer rate for the incorrectly answered question of the approximate user and the target user as the predicted accuracy rate. <Claim 9> The processing unit includes: Accepting designation of the proportion of the unassigned questions and the proportion of the incorrectly answered questions to be posed to the target user; Based on the prediction accuracy rates of the plurality of prediction target questions, questions to be presented to the target user are determined so that the unasked questions and the incorrectly answered questions have a specified ratio. 3. The information processing device according to claim 1, wherein the information processing device is a computer. <Claim 10> An information processing method executed by a computer of an information processing system, comprising: Identifying a similar user from among the plurality of users who has a similar tendency to master the plurality of problems to a certain target user based on question history information including whether or not the plurality of problems have been set to the plurality of users and the results of determining whether the questions have been set; Derive a prediction accuracy rate of the target user for a prediction target question that is at least one of an unasked question that has not been posed to the target user and an incorrect question that the target user has answered incorrectly in the past, based on the correct / incorrect judgment result of the prediction target question of the approximate user in the question setting history information; determining a question to be posed to the target user from among the plurality of questions based on the derived prediction accuracy rate; Presenting the determined problem to the target user 23. An information processing method comprising: <Claim 11> A computer provided in the information processing device A process of identifying a similar user who has a tendency to master the plurality of problems similar to a certain target user among the plurality of users, based on question history information including whether or not the plurality of problems have been set to the plurality of users and a result of determining whether the questions have been set; A process of deriving a prediction accuracy rate of the target user for a prediction target question that is at least one of an unasked question that has not been asked to the target user and an incorrect answer question that the target user has answered incorrectly in the past, based on the correct / incorrect judgment result of the prediction target question of the similar user in the question setting history information; A process of determining a question to be presented to the target user from among the plurality of questions based on the derived prediction accuracy rate. A program characterized by executing the above. [Explanation of symbols]

[0114] 1. Learning support system (information processing system) 10 Server (information processing device) 11 CPU (processing unit) 12 RAM 13 Storage section 131 Server Control Program 132 User Management DB 133 Dictionary DB 134 Learning History DB 135 Question History DB 136 Prediction accuracy rate DB 14 Control section 15 Display 16 Communications Department 17 Bus 20 Terminal Equipment 21 CPU 23 Memory section 231 Learning Apps 24 Control section 25 Display section 26 Audio output section 27 Communications Department 28 Bus 40 Dictionary screen 50 Difficulty selection screen 60 Test Screen N Communication Network

Claims

1. Based on the results of a judgment of correctness of a plurality of questions given to a plurality of users, a similar user whose results of judgment of correctness of the plurality of questions are similar to those of a target user among the plurality of users is identified from the plurality of users; Derive a predicted correct answer rate of the target user for each of the unasked questions that have not been posed to the target user and the incorrect answer questions that the target user has answered incorrectly in the past, based on the correct / incorrect judgment result of the similar user; A question to be presented to the target user is determined from among the unasked questions and the incorrectly answered questions based on the predicted correct answer rates derived for each of the unasked questions and the incorrectly answered questions. An information processing device comprising a processing unit.

2. The processing unit: Based on the predicted correct answer rates derived for each of the unasked questions and the incorrectly answered questions, a question to be presented to the target user among the unasked questions and a question to be presented to the target user among the incorrectly answered questions are determined. The information processing device according to claim 1 .

3. The processing unit: The unasked question, the predicted correct answer rate of which derived for the unasked question corresponds to a specified predicted correct answer rate, and the incorrectly answered question, the predicted correct answer rate of which derived for the incorrectly answered question corresponds to a specified predicted correct answer rate, are determined as questions to be presented to the target user. The information processing device according to claim 2 .

4. The processing unit: Accepting a specification of the difficulty level of questions to be presented to the target user; Based on the predicted correct answer rate corresponding to the specified difficulty level, a question to be presented to the target user from among the unassigned questions and a question to be presented to the target user from among the incorrectly answered questions are determined. The information processing device according to claim 3 .

5. The processing unit: Accepting at least one of a ratio of the unassigned questions to be posed to the target user and a ratio of the incorrectly answered questions; Based on the predicted correct answer rates derived for each of the unasked questions and the incorrectly answered questions, the number of questions to be posed to the target user is determined so that the number of questions to be posed for at least one of the unasked questions and the incorrectly answered questions is equal to the accepted ratio. The information processing device according to claim 1 .

6. The processing unit: Based on the received ratio, a ratio of the unassigned questions and a ratio of the incorrectly answered questions among the questions to be posed to the target user are identified; Based on the predicted correct answer rates derived for each of the unasked questions and the incorrectly answered questions, questions to be presented to the target user among the unasked questions and questions to be presented to the target user among the incorrectly answered questions are determined so that the number of the unasked questions and the incorrectly answered questions is the specified ratio. The information processing device according to claim 5 .

7. The computer in the information processing system Based on the results of a correct / incorrect judgment of a plurality of questions posed to a plurality of users, a similar user whose correct / incorrect judgment results of the plurality of questions are similar to those of a target user among the plurality of users is identified from the plurality of users; Derive a predicted correct answer rate of the target user for each of the unasked questions that have not been posed to the target user and the incorrect answer questions that the target user has answered incorrectly in the past, based on the correct / incorrect judgment result of the similar user; A question to be presented to the target user is determined from among the unasked questions and the incorrectly answered questions based on the predicted correct answer rates derived for each of the unasked questions and the incorrectly answered questions. An information processing method for performing processing.

8. A computer provided in the information processing device Based on the results of a correct / incorrect judgment of a plurality of questions posed to a plurality of users, a similar user whose correct / incorrect judgment results of the plurality of questions are similar to those of a target user among the plurality of users is identified from the plurality of users; Derive a predicted correct answer rate of the target user for each of the unasked questions that have not been posed to the target user and the incorrect answer questions that the target user has answered incorrectly in the past, based on the correct / incorrect judgment result of the similar user; A question to be presented to the target user is determined from among the unasked questions and the incorrectly answered questions based on the predicted correct answer rates derived for each of the unasked questions and the incorrectly answered questions. A program that executes a process.

Images