System, method, and program for assisting memorization of sentence

Abstract

A learning assistance server 10 according to one embodiment of the present invention assists efficient memorization of the entire sentence. The learning assistance server 10 provides a learning assistance service to a teaching user that operates a teaching user terminal 20 and a leaning user that operates a leaning user terminal 30, the terminals being connected to be communicable via a communication network NW. The learning assistance server 10 gives the learning user a question corresponding to a divided sentence included in a plurality of divided sentences obtained by dividing a sentence to be memorized, and determines the degree of memory of the learning user for the divided sentence on the basis of information relating to the answer of the learning user to the question. Therefore, the degree of fixation of memory of the learning user for each divided sentence is managed, and consequently, the memorization of the sentence to be memorized is assisted.

Description

System, method, and program for assisting text memorization

[0001] The present invention relates to a system, a method, and a program for assisting the memorization of text.

[0002] In the past, even in daily life, there has been a need to memorize sentences such as sales pitches, classical literature, and long English texts found in textbooks, and there has been a demand for a learning support system that allows users to efficiently memorize entire sentences. For example, Patent Document 1 listed below discloses a method for encouraging memorization of sentences by masking parts of the sentences and prompting the user to input them.

[0003] Japanese Patent Application Publication No. 09-062175

[0004] However, in the conventional systems described above, users are limited to memorizing only parts of a sentence, and it is difficult for them to efficiently memorize the entire sentence. Therefore, it is desirable to provide a system that allows users to efficiently memorize the entire sentence.

[0005] One of the objects of the embodiment of the present invention is to support efficient memorization of an entire text.

[0006] A program according to one embodiment of the present invention is a program for assisting in the memorization of a sentence, and causes one or more computers to execute the following steps: asking a learning user a question corresponding to a first divided sentence contained in a plurality of divided sentences obtained by dividing a target sentence to be memorized; acquiring answer information of the learning user to the question corresponding to the first divided sentence; and determining the learning user's degree of memory for the first divided sentence based on the answer information to the question corresponding to the first divided sentence.

[0007] A system according to one embodiment of the present invention is a system for assisting in the memorization of a sentence, comprising one or more computer processors, wherein the one or more computer processors perform the steps of: presenting a learning user with a question corresponding to a first divided sentence contained in a plurality of divided sentences obtained by dividing a target sentence to be memorized; acquiring answer information of the learning user to the question corresponding to the first divided sentence; and determining the learning user's degree of memory for the first divided sentence based on the answer information to the question corresponding to the first divided sentence.

[0008] A method according to one embodiment of the present invention is a method executed by one or more computers for assisting in the memorization of a sentence, and includes the steps of: presenting a learning user with a question corresponding to a first divided sentence contained in a plurality of divided sentences obtained by dividing a target sentence to be memorized; obtaining answer information from the learning user for the question corresponding to the first divided sentence; and determining the learning user's level of memory for the first divided sentence based on the answer information to the question corresponding to the first divided sentence.

[0009] Various embodiments of the present invention support efficient memorization of entire passages.

[0010] 1 is a configuration diagram schematically showing the configuration of a network including a learning assistance server 10 according to an embodiment of the present invention. A configuration diagram schematically showing the configuration of an instructor user terminal 20. A configuration diagram schematically showing the configuration of a learner user terminal 30. A diagram illustrating an example of information managed by an instructor user information table 1511. A diagram illustrating an example of information managed by a learner user information table 1512. A diagram illustrating an example of information managed by a class information table 1513. A diagram illustrating an example of information managed by a question collection information table 1514. A diagram illustrating an example of information managed by a target sentence information table 1515. A diagram illustrating an example of information managed by a chunk information table 1516. A diagram illustrating an example of the structure of sentences and chunks to be memorized. A diagram illustrating an example of information managed by a learning plan information table 1517. A diagram illustrating an example of information managed by a memory level management table 1518. A diagram illustrating an example of a learning top screen 50. A flowchart illustrating an example of processing executed by the learning assistance server 10 in response to selection of a study button 524. A diagram illustrating an example of a question screen 60. a diagram illustrating the question screen 60 after the Confirm button 66 has been selected with the correct answer option area 644 selected on the question screen 60 illustrated in Fig. 15; a diagram illustrating the question screen 60 when the difficulty level of the question is normal mode; a diagram illustrating the question screen 60 after the Confirm button 66 has been selected with the correct answer option area 641 selected on the question screen 60 illustrated in Fig. 17; a diagram illustrating the question screen 60 when the difficulty level of the question is difficult mode; a diagram illustrating the question screen 60 after the Confirm button 66 has been selected with the correct answer option area 641 selected on the question screen 60 illustrated in Fig. 19; a diagram illustrating an example of a memory degree display screen 70.

[0011] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In each drawing, the same reference numerals may be used to designate the same or similar components.

[0012] FIG. 1 is a schematic diagram illustrating the configuration of a network including a learning assistance server 10 according to one embodiment of the present invention. As shown in the figure, the learning assistance server 10 is communicatively connected to an instructor user terminal 20 and a learner user terminal 30 via a communication network NW such as the Internet. While only one instructor user terminal 20 and one learner user terminal 30 are illustrated in FIG. 1 , the learning assistance server 10 is communicatively connected to multiple instructor user terminals 20 and multiple learner user terminals 30. The learning assistance server 10 provides learning assistance services to an instructor user who operates the instructor user terminal 20 and a learner user who operates the learner user terminal 30. The learning assistance service has a function for assisting in memorization of text. The learning assistance server 10 is an example of a device that implements all or part of the system of the present invention.

[0013] First, we will explain the hardware configuration of the learning assistance server 10. The learning assistance server 10 is configured as a general computer, and as shown in Figure 1, it includes a computer processor 11, a main memory 12, an input / output I / F 13, a communication I / F 14, and a storage (storage device) 15, and these components are electrically connected via a bus or the like (not shown).

[0014] The computer processor 11 is configured with a CPU, GPU, FPGA, or the like, or a circuit including any of them, and loads various programs stored in the storage 15, etc., into the main memory 12 and executes various instructions included in the programs. The main memory 12 is configured with, for example, a DRAM, etc.

[0015] The input / output I / F 13 includes various input / output devices for exchanging information with an operator, etc. The input / output I / F 13 includes, for example, information input devices such as a keyboard and a pointing device (e.g., a mouse, a touch panel, etc.), audio input devices such as a microphone, and image input devices such as a camera. The input / output I / F 13 also includes an image output device such as a display, and an audio output device such as a speaker.

[0016] The communication I / F 14 is implemented as hardware such as a network adapter, various communication software, or a combination of these, and is configured to enable wired or wireless communication via a communication network NW or the like.

[0017] The storage 15 is configured, for example, by a magnetic disk or a flash memory. The storage 15 stores various programs including an operating system, various data, and the like. For example, as shown in FIG. 1 , the storage 15 has various tables 151 that store various information. The storage 15 also stores, for example, a server-side program 40 according to an embodiment of the present invention. The program 40 is a program that causes the learning assistance server 10 to function as all or part of a system for providing learning assistance services. At least a portion of the server-side program 40 can be configured to be executed on the instructor user terminal 20 side or the learner user terminal 30 side via an instructor user terminal side program 42 or a learner user terminal side program 44, which will be described later.

[0018] In this embodiment, the learning assistance server 10 may be configured using a plurality of computers each having the above-described hardware configuration. For example, the learning assistance server 10 may be configured by one or a plurality of server devices.

[0019] The learning assistance server 10 configured in this manner functions as a web server and an application server, and executes various processes in response to requests from the instructor user terminal side program 42 or the learner user terminal side program 44 installed in the instructor user terminal 20 or the learner user terminal 30, respectively, and transmits screen data (e.g., HTML data) and control data according to the results of the processes to the instructor user terminal 20 or the learner user terminal 30. The instructor user terminal 20 or the learner user terminal 30 outputs a web page or other screen based on the received data.

[0020] Next, we will explain the hardware configuration of the training user terminal 20. The training user terminal 20 is configured as a general computer, and as shown in Fig. 2, includes a computer processor 21, a main memory 22, an input / output I / F 23, a communication I / F 24, and a storage (storage device) 25, and these components are electrically connected via a bus or the like (not shown).

[0021] The computer processor 21 is configured by a CPU, a GPU, an FPGA, or the like, or a circuit including any of them, and loads various programs stored in the storage 25 or the like into the main memory 22 and executes various instructions included in the programs. The main memory 22 is configured by, for example, a DRAM or the like.

[0022] The input / output I / F 23 includes various input / output devices for exchanging information with an operator, etc. The input / output I / F 23 includes, for example, information input devices such as a keyboard and a pointing device (e.g., a mouse, a touch panel, etc.), audio input devices such as a microphone, and image input devices such as a camera. The input / output I / F 23 also includes an image output device such as a display, and an audio output device such as a speaker.

[0023] The communication I / F 24 is implemented as hardware such as a network adapter, various communication software, or a combination thereof, and is configured to realize wired or wireless communication via a communication network NW or the like.

[0024] The storage 25 is configured, for example, by a magnetic disk or flash memory. The storage 25 stores various programs including an operating system, various data, and the like. The programs stored in the storage 25 can be downloaded and installed from an application market, etc. The storage 25 also stores the instructor user terminal-side program 42 described above. The program 42 can be configured as a web browser or other application (e.g., an application for instructor users of a learning support service), and can be configured to execute at least a portion of the server-side program 40, as described above.

[0025] In this embodiment, the training user terminal 20 may be configured as a smartphone, a tablet terminal, a personal computer, or the like.

[0026] A teaching user operating the teaching user terminal 20 configured in this manner can use the learning support services provided by the learning support server 10 by communicating with the learning support server 10 via the teaching user terminal side program 42 installed in the storage 25.

[0027] Next, we will explain the hardware configuration of the learner user terminal 30. Like the above-mentioned instructor user terminal 20, the learner user terminal 30 is configured as a general computer, and as shown in Fig. 3, it includes a computer processor 31, a main memory 32, an input / output I / F 33, a communication I / F 34, and a storage (storage device) 35, and these components are electrically connected via a bus or the like (not shown).

[0028] The storage 35 stores the above-mentioned learner terminal-side program 44. The program 44 may be configured as a web browser or other application (e.g., an application for a learner of a learning support service) and may be configured to execute at least a part of the server-side program 40, as described above. In this embodiment, the learner terminal 30 may be configured as a smartphone, a tablet terminal, a personal computer, or the like.

[0029] A learning user operating a learning user terminal 30 configured in this manner can use the learning support services provided by the learning support server 10 by communicating with the learning support server 10 via the learning user terminal side program 44 installed in the storage 35.

[0030] Next, we will explain the functions of the learning assistance server 10 configured as above. As shown in Figure 1, the computer processor 11 of the learning assistance server 10 is configured to function as a management function control unit 112 and a learning management unit 114 by executing instructions included in a program (e.g., at least a part of the server-side program 40) loaded into the main memory 12.

[0031] The management function control unit 112 is configured to execute various processes related to the control of the management functions of the learning support service. For example, the management function control unit 112 transmits screen data and control data of various screens related to the management functions to the instructor user terminal 20 or the learner user terminal 30, executes various processes in response to operation input by the user via the screens output on the instructor user terminal 20 or the learner user terminal 30, and transmits screen data and control data according to the results of the processes to the instructor user terminal 20 or the learner user terminal 30. The management functions controlled by the management function control unit 112 include, for example, login processing (user authentication) and management of user information.

[0032] The learning management unit 114 is configured to execute various processes related to the management of learning performed by the learner. For example, the learning management unit 114 transmits screen data and control data of various screens related to learning management to the instructor user terminal 20 or the learner user terminal 30, executes various processes in response to operation input by the user via the screen output on the instructor user terminal 20 or the learner user terminal 30, and transmits screen data and control data according to the results of the processes to the instructor user terminal 20 or the learner user terminal 30.

[0033] In this embodiment, the learning management unit 114 is configured to present the learner with questions corresponding to the divided sentences (first divided sentences) included in the divided sentences obtained by dividing the target sentence to be memorized. For example, the learning management unit 114 transmits information regarding questions corresponding to each of the divided sentences to the learner terminal 30. Note that presenting questions may be any process that causes the questions to be displayed on the learner terminal, and may be, for example, a process of transmitting the divided sentences to the learner as information for displaying questions corresponding to the divided sentences on the learner terminal, or a process of displaying questions corresponding to the divided sentences on the learner terminal. Furthermore, if the target sentence includes a portion that is not to be memorized, the divided sentences are sentences generated by dividing the portion to be memorized.

[0034] The learning management unit 114 is also configured to acquire answer information of the learner to the questions posed. For example, the learning management unit 114 receives answer information regarding the answer entered by the learner via a screen displayed on the learner terminal 30 from the learner terminal 30. The answer information may include the content of the answer and / or the result of the answer (correct or incorrect).

[0035] The learning management unit 114 is also configured to determine the learning user's memory level for the corresponding segmented sentence based on the acquired answer information. The memory level can also be considered a parameter that indicates the degree of memory retention, and for example, increases when the answer is correct and decreases when the answer is incorrect. Note that it is sufficient to manage the learning user's memory level for each segmented sentence, and the learning user's memory level for the segmented sentences may be managed by associating a memory level with each segmented sentence, or by associating a memory level with each parameter corresponding to each segmented sentence.

[0036] In this way, the learning assistance server 10 in this embodiment presents the learner with questions corresponding to the divided sentences contained in the multiple sentences into which the target sentence to be memorized is divided, and determines the learner's degree of memory for the divided sentences based on the learner's answer information to the questions, thereby managing the learner's degree of retention of each divided sentence and, as a result, supporting memorization of the target sentence. In other words, the learning assistance server 10 supports efficient memorization of the entire sentence.

[0037] The learning management unit 114 may be configured to determine the learning user's memory level for the corresponding target sentence based on the learning user's memory level for each of the multiple segmented sentences. This configuration enables management of the memory level for the target sentence in addition to the memory levels for the segmented sentences.

[0038] In this embodiment, the memorability of multiple sub-division elements (including sentences, phrases, or words) obtained by further dividing a divided sentence may be determined in the same manner as for the divided sentence. That is, the learning management unit 114 may be configured to ask the learner a question corresponding to the sub-division element (first sub-division element), obtain the learner's answer information for the question, and determine the learner's memorability of the sub-division element based on the answer information. In this case, the learner's memorability of the corresponding divided sentence may be determined based on the learner's memorability of each of the multiple sub-division elements. This configuration enables management of the memorability of the sub-division elements in addition to the memorability of the divided sentence.

[0039] The learning management unit 114 may be configured to determine the learning user's memory level for a segmented sentence based on the learning user's memory level for a segmented sentence that is similar to the segmented sentence (e.g., another segmented sentence). Such a configuration allows for a more appropriate determination of the memory level.

[0040] The learning management unit 114 may also be configured to determine the difficulty level of questions corresponding to the segmented sentences to be posed to the learning user based on the learning user's memory for the segmented sentences. For example, the higher the memory level, the higher the difficulty level of the corresponding questions. Furthermore, the difficulty levels of multiple questions corresponding to multiple segmented sentences to be posed to the learning user may be determined collectively based on the learning user's memory for the target sentence. This configuration enables questions of an appropriate difficulty level to be posed based on the learning user's memory for the sentences.

[0041] The learning management unit 114 may also be configured to determine the frequency with which questions corresponding to a segmented sentence are to be presented to the learning user based on the learning user's memory for the segmented sentence. For example, the higher the memory level, the lower the frequency with which the corresponding question is presented. This configuration enables questions to be presented at an appropriate frequency based on the memory level of the sentence.

[0042] The learning management unit 114 may also be configured to determine whether questions corresponding to each of the subdivision elements into which the subdivision element is further divided should be presented to the learning user based on the learning user's memory for the subdivision element. For example, if the learning user's memory for the subdivision element is within a predetermined range, it may be determined that questions corresponding to the subdivision element should be presented to the learning user. This configuration enables appropriate presentation of questions corresponding to the subdivision elements.

[0043] The learning management unit 114 may also be configured to present to the learner a predetermined screen that displays the target sentence in a manner based on the memorability of each of the multiple divided sentences (e.g., by transmitting screen data and control data for the predetermined screen to the learner terminal 30). For example, the predetermined screen displays each divided sentence in an appearance (e.g., background color, foreground color, character color, and shape (including character font), etc.) based on its memorability. This configuration helps the learner intuitively understand the memorability of the target sentence.

[0044] The predetermined screen may be configured to display the multiple sentence segments, each with an appearance based on the corresponding memorability, in order within the target sentence. For example, the predetermined screen may display the target sentence by displaying the multiple sentence segments in colors (e.g., background, foreground, or text colors) corresponding to the memorability of each of the multiple sentence segments in order within the target sentence. This configuration helps the learner easily understand the memorability of the target sentence.

[0045] The predetermined screen may be configured to display a graphic (e.g., a graph) based on the memorability of each of the multiple divided sentences in addition to the target sentence. For example, the predetermined screen may display the target sentence in association with a graphic indicating the memorability of the target sentence based on the memorability of each of the multiple divided sentences in the target sentence. This configuration helps the learning user easily understand the memorability of the target sentence.

[0046] Furthermore, the learning management unit 114 can be configured to present to the learning user a question corresponding to the next segment (second segment) that follows the segment in the target text as the question following the segment. This configuration makes it possible to present questions in accordance with the order of the segments in the target text.

[0047] In this embodiment, the question corresponding to the divided sentence may be configured as a multiple-choice question in which a correct answer option is selected from a plurality of options. For example, the question may be configured as a question including a plurality of options corresponding to the divided sentence.

[0048] In this case, the question text may be displayed so that character strings corresponding to the divided sentences are recognizable. For example, a question corresponding to a divided sentence may be configured to include a question text that prompts the user to select a specific divided sentence according to the order of the divided sentences in the target sentence, one correct answer option that displays the specific divided sentence, and one or more incorrect answer options that display sentences different from the specific divided sentence. In this case, the divided sentences corresponding to the correct answer option are displayed so that they are recognizable (e.g., semi-transparently) in the question text. This configuration allows the learner to select the correct answer option while recognizing the divided sentences, thereby supporting learning for learners who have a low memory for the target sentence.

[0049] Furthermore, for example, a question corresponding to a divided sentence may include questions corresponding to each of a plurality of sub-segmented elements into which the divided sentence is further divided. For example, a question corresponding to a divided sentence may be configured to include a question sentence that prompts a user to select a specific divided sentence according to the order of the multiple divided sentences in the target sentence, correct answer choices that display sub-segmented elements into which the specific divided sentence is further divided, and incorrect answer choices that display elements (e.g., sentences, phrases, or words) different from the sub-segmented elements. This configuration helps a learner memorize the divided sentences through answers to questions corresponding to the sub-segmented elements.

[0050] Furthermore, for example, a question corresponding to a segmented sentence may be configured to include a question sentence that prompts the user to select the first character or character string of a specific segmented sentence according to the order of the segments in the target sentence, a correct answer option that displays the first character or character string, and an incorrect answer option that displays a character or character string different from the first character or character string. This configuration supports learning for a learner who has a high degree of memory for the target sentence.

[0051] In this embodiment, the segmentation of the target sentence into multiple segmented sentences may be performed by the learning assistance server 10. For example, the learning management unit 114 may be configured to segment the acquired target sentence into multiple segmented sentences through predetermined natural language processing. In this case, information (prompts) including instructions for segmenting the target sentence into multiple segmented sentences may be input to a large-scale language model, and the multiple segmented sentences may be acquired from information output by the large-scale language model. Such large-scale language models include, for example, GPT-4 provided by OpenAI, Inc. in the United States. This configuration enables automatic segmentation of the target sentence.

[0052] Next, a specific example of one aspect of the learning assistance server 10 of this embodiment having such functions will be described. First, in this example, information managed by each table included in the various tables 151 will be described.

[0053] 4 illustrates information managed by the training user information table 1511 in this example. The training user information table 1511 in this example manages information related to training users who train learning users, and as shown in the figure, manages information such as "basic information" including the name etc., and a "learning organization ID" identifying the learning organization to which the training user belongs (works), in association with a "training user ID" that identifies the individual training user.

[0054] 5 illustrates information managed by the learning user information table 1512. The learning user information table 1512 in this example manages information related to learning users, and as shown in the figure, manages information such as "basic information" including the name and the like, and a "learning organization ID" identifying the learning organization to which the learning user belongs, in association with a "learning user ID" that identifies an individual learning user.

[0055] 6 illustrates information managed by the class information table 1513 in this example. The class information table 1513 in this example manages information related to "classes," which are units for managing multiple learner users as a group, and as shown in the figure, manages information such as a "training user ID" that identifies the corresponding (responsible) training user, "available problem set information" that is information about problem sets available in this class, and "associated learner information" that is information about learner users belonging to this class, in association with a "class ID" that identifies an individual class. The available problem set information includes a problem set ID that identifies each of the multiple available problem sets. The associated learner information includes a learner user ID that identifies each of the multiple learner users belonging to the class.

[0056] In this example, the class is set by the instructor user. Specifically, the instructor user generates the class, selects the learners to belong to the class, and sets the problem sets available for the class via a screen (not shown) output on the instructor user terminal 20.

[0057] 7 illustrates information managed by the problem set information table 1514. In this example, the problem set information table 1514 manages information related to problem sets available for use in the learning support service, and as shown in the figure, manages information such as "name" in association with a "problem set ID" that identifies an individual problem set.

[0058] The learning support service in this example includes a collection of questions aimed at memorizing text, such as a collection of questions for memorizing sales pitches, English texts, etc. For example, a collection of questions for memorizing sales pitches includes questions corresponding to each of a plurality of sales pitches.

[0059] 8 illustrates information managed by the target sentence information table 1515 in this example. The target sentence information table 1515 in this example manages information related to the target sentences to be memorized, and as shown in the figure, manages information such as a "question set ID" that identifies the question set containing the target sentence, the "target sentence," and "question content information" that is information related to the content of the questions related to the target sentence, in association with a "target sentence ID" that identifies an individual target sentence.

[0060] 9 illustrates information managed by the chunk information table 1516 in this example. The chunk information table 1516 in this example manages information about multiple chunks (divided sentences or re-divided elements) into which a memorization target sentence is divided, and as shown, manages information such as a "parent target sentence / chunk ID" that identifies a parent target sentence or chunk, an "order" that indicates the order of multiple chunks that have the same target sentence or chunk as a parent, and "chunk content information" that is information about the content of sentences, phrases, words, etc. included in a chunk, in association with a "chunk ID" that identifies each individual chunk. Note that because each individual chunk is uniquely determined by the combination of the parent target sentence and the order, chunks may be managed by the parent target sentence ID and the order instead of the chunk ID.

[0061] In this example, each target sentence included in a workbook designed for memorization is associated with multiple chunks into which the sentence is divided. FIG. 10 illustrates the structure of the sentence and chunks to be memorized. In the example of FIG. 10, the sentence S (an English sentence) to be memorized is divided into two chunks C1 and C2. Chunk C1 is further divided into seven child chunks C11-C17, and chunk C2 is further divided into eight child chunks C21-C28. In this example, there are three levels of hierarchy for the sentence, chunks, and child chunks to be memorized. The chunk information table 1516 manages the parent-child relationships between the target sentences and chunks, as well as the order (sorting) between the chunks. In this example, the division of the sentence into chunks and child chunks is performed by the operator of the learning support service. Note that the hierarchy of the sentence, chunks, and child chunks to be memorized does not have to be three levels, and may be two levels, or four or more levels.

[0062] 11 illustrates information managed by the learning plan information table 1517 in this example. The learning plan information table 1517 in this example manages information related to learning plans set for classes, and as shown in the figure, manages information such as "study period" in association with a combination of a "class ID" that identifies an individual class and a "problem set ID" that identifies an individual problem set. The problem set is selected from multiple problem sets available for the corresponding class.

[0063] In this example, the study plan is set by the instructor who teaches the corresponding class. Specifically, the combination of the class and the workbook, and the corresponding study period (study start date and study end date) are set via a screen (not shown) output on the instructor user terminal 20.

[0064] 12 illustrates information managed by the memory level management table 1518 in this example. The memory level management table 1518 in this example manages the memory level of a learning user for a target sentence and chunk (including child chunks), and as shown in the figure, manages information such as "memory level" in association with a combination of a "learning user ID" that identifies an individual learning user and a "target sentence / chunk ID" that identifies an individual target sentence or chunk. In this example, memory level is set to a value between 0 and 100, with the higher the value, the higher the memory level.

[0065] The information managed by each table in this example has been described above. Next, the processing executed by the learning assistance server 10 and the screens output on the instructor user terminal 20 or the learner user terminal 30 will be described.

[0066] 13 shows an example of a learning top screen 50 output on the learning user terminal 30. As shown in the figure, the screen 50 has a problem set list display area 52 that displays a list of problem sets (identified by referencing the learning plan information table 1517) currently available (included in the learning period) for the class to which the corresponding learning user belongs, and a back button 54. In the problem set list display area 52, a plurality of individual display areas 521, each corresponding to an individual problem set, are arranged vertically.

[0067] As shown in the figure, the individual display area 521 displays the image and name of the corresponding problem set, and also has a progress indicator 522 that indicates the progress of studying the problem set, a study button 524, and a memory level button 526. In this example, the progress of studying is calculated based on the memory levels of multiple target sentences included in the problem set; for example, the higher the memory level of each target sentence, the greater the progress.

[0068] The study button 524 is an object for starting study of the corresponding problem set. FIG. 14 is a flowchart illustrating a process executed by the learning assistance server 10 in response to selection of the study button 524. As shown in the figure, the learning assistance server 10 first determines a target sentence to be posed from among a plurality of target sentences included in the corresponding problem set (step S100). For example, each of a plurality of target sentences included in the corresponding problem set is determined as a target sentence to be posed according to a predetermined order. Note that the target sentence to be posed may also be determined according to other rules. Furthermore, the determination of the target sentence may be based on the degree of memorization. For example, a target sentence whose degree of memorization does not exceed a set value may be determined as a target question to be posed.

[0069] Next, the learning assistance server 10 determines the difficulty level of the questions related to the target text to be posed (step S110). Specifically, the difficulty level of the questions is determined based on the learner's memory for the corresponding target text. In this example, the difficulty level has three levels: easy mode, normal mode, and difficult mode. For example, the difficulty level is determined to be easy mode when the learner's memory for the target text is less than a first threshold (e.g., 20 points), normal mode when the memory level is equal to or greater than the first threshold and less than a second threshold (e.g., 80 points), and difficult mode when the memory level is equal to or greater than the second threshold.

[0070] Next, the learning assistance server 10 transmits the question information to the learner terminal 30 (step S120). Specifically, the question information transmitted includes the target sentence in the target sentence information table 1515, the question content information, various information in the chunk information table 1516 (chunk information of the target sentence), and information including the determined difficulty level.

[0071] The learner user terminal 30 displays questions based on the received question information. Fig. 15 shows an example of a question screen 60 that is output on the learner user terminal 30 that has received the question information. As shown in the figure, the question screen 60 has a question statement display area 62 that displays the question statement, and an option display area 64 that displays answer options for the question.

[0072] The question sentence display area 62 displays the main text of the question sentence (in the example of FIG. 15, the sentence "What is memory?"), and has a target sentence display area 622 that displays the sentence to be memorized.

[0073] The question screen 60 shown in Fig. 15 corresponds to a case where the difficulty level of the question is set to easy mode, in which case the sentence to be memorized is displayed semi-transparently in the target sentence display area 622, and an underline object 6221 is placed in the part corresponding to the first chunk (in the example of Fig. 15, the sentence "Memory is the foundation of intellectual activity in humankind") of the multiple chunks contained in the sentence (chunks that have the sentence as their parent). The underline object 6221 indicates that the question requires the selection of the sentence corresponding to the first chunk of the sentence to be memorized.

[0074] The option display area 64 has four option areas 641 to 644, and when the difficulty level of the question is in easy mode, the horizontally long rectangular option areas 641 to 644 are arranged vertically. Of the four option areas 641 to 644, one corresponds to the correct option, and the remaining three correspond to the incorrect options. In easy mode, of the four option areas 641 to 644, the correct option displays a sentence corresponding to the target chunk, and the incorrect option displays another sentence. The sentence displayed in the incorrect option is set, for example, in the question content information in the target sentence information table 1515.

[0075] In the easy mode, the sentence to be memorized is displayed semi-transparently in the target sentence display area 622 of the question sentence display area 62, so the learning user can select the correct answer option (option area 644 in the example of Figure 15) in the option display area 64 while looking at the displayed sentence (the part where the underline object 6221 is located).

[0076] 16 illustrates the question screen 60 illustrated in FIG. 15 after the Confirm button 66 is selected with the correct answer option area 644 selected. In this state of the question screen 60, as illustrated, the underline object 6221 in the target sentence display area 622 of the question sentence display area 62 has moved from the portion corresponding to the first chunk to the portion corresponding to the next chunk. Furthermore, the sentence corresponding to the first chunk has been changed from a semi-transparent display to a normal display (opaque display). Each of the four option areas 641 to 644 in the option display area 64 displays either the correct sentence or the incorrect sentence corresponding to the new chunk.

[0077] 15, when the Confirm button 66 is selected with one of the incorrect answer option areas 641-643 selected, the sentence corresponding to the target chunk (the portion where the underlined object 6221 is located) is highlighted in the target sentence display area 622, guiding the user to the correct answer. If the Confirm button 66 is then selected with the correct answer option area 644 selected, the screen transitions to the question screen 60 shown in FIG. 16, but in this case, the answer status of the corresponding chunk becomes incorrect (the first answer takes priority).

[0078] Then, for multiple chunks contained in the text to be memorized, questions are presented and answers (selections from options) are accepted in sequence.

[0079] 17 illustrates a question screen 60 when the difficulty level of the question is normal mode. In this state of the question screen 60, as shown in the figure, the sentence corresponding to the first chunk of multiple chunks included in the sentence to be memorized is hidden in the target sentence display area 622, while the sentences corresponding to the other chunks are displayed. An underline object 6221 is also placed in the portion corresponding to the first chunk (i.e., the portion where the sentence is hidden). The underline object 6221 indicates that the question requires the user to select the sentence corresponding to the first chunk from the sentence to be memorized.

[0080] In the option display area 64, horizontally long rectangular option areas 641 to 644 are arranged vertically, just as when the difficulty level of the question is in easy mode. In normal mode, of the four option areas 641 to 644, the correct option displays a character string (phrase) corresponding to the first of multiple child chunks whose parent is the target chunk, while the incorrect options display other character strings. The character string displayed in the incorrect options is set, for example, in the question content information in the target sentence information table 1515.

[0081] In normal mode, the sentence corresponding to the target chunk among the sentences to be memorized is hidden in the target sentence display area 622 of the question sentence display area 62, so the learning user must rely on their own memory to select the correct answer option (option area 641 in the example of Figure 17) in the option display area 64.

[0082] Figure 18 illustrates an example of the question screen 60 after the Confirm button 66 is selected with the correct answer option area 641 selected on the question screen 60 illustrated in Figure 17. In this state of the question screen 60, as shown in the figure, a character string corresponding to the first child chunk (the phrase "memory is" in the example of Figure 18) of the sentence corresponding to the first chunk is displayed in the target sentence display area 622 of the question sentence display area 62.

[0083] In addition, each of the four option areas 641 to 644 in the option display area 64 displays a correct or incorrect string corresponding to the second child chunk among multiple child chunks that have the target chunk as their parent.

[0084] 17, if the Confirm button 66 is selected with one of the incorrect answer option areas 642 to 644 selected, the two option areas including the correct answer option area 641 are highlighted in the option display area 64, guiding the user to the correct answer. If the Confirm button 66 is then selected with the correct answer option area 641 selected, the screen transitions to the question screen 60 shown in FIG. 18, but in this case the answer status of the corresponding child chunk becomes incorrect (the first answer takes priority).

[0085] Then, for the multiple child chunks of the target chunk, questions are presented and answers (selections of options) are accepted in sequence.Furthermore, for the multiple chunks included in the sentence to be memorized, questions are presented and answers (selections of options) are accepted in sequence for the child chunks.

[0086] 19 shows an example of the question screen 60 when the difficulty level of the question is in the difficult mode. In this state of the question screen 60, as shown in the figure, the sentence to be memorized is hidden in the target sentence display area 622, and an underline object 6221 is placed in the part corresponding to the first chunk of the multiple chunks contained in the sentence. The underline object 6221 indicates that the question requires the user to select the sentence corresponding to the first chunk of the sentence to be memorized.

[0087] Furthermore, in the option display area 64, when the difficulty level of the question is in the difficult mode, approximately square option areas 641 to 644 are arranged side by side in the left-right direction. In the difficult mode, of the four option areas 641 to 644, the correct option displays the first character of the sentence corresponding to the target chunk, and the incorrect option displays one other character. The one character displayed in the incorrect option is set, for example, in the question content information in the target sentence information table 1515.

[0088] In the difficult mode, the sentence to be memorized is hidden in the target sentence display area 622 of the question sentence display area 62, so the learning user must rely on their own memory to select the correct answer option (option area 641 in the example of Figure 19) in the option display area 64.

[0089] 20 illustrates the question screen 60 illustrated in FIG. 19 after the Confirm button 66 is selected with the correct answer option area 641 selected. In this state of the question screen 60, as illustrated, the target sentence display area 622 of the question sentence display area 62 displays a sentence corresponding to the first chunk, and the underline object 6221 has moved to the portion corresponding to the chunk next to the first chunk. Each of the four option areas 641 to 644 in the option display area 64 displays one character of the correct answer or one character of the incorrect answer corresponding to the new chunk.

[0090] 19, if the Confirm button 66 is selected with one of the incorrect answer option areas 642 to 644 selected, the correct answer option area 641 is highlighted in the option display area 64, guiding the user to the correct answer. If the Confirm button 66 is then selected with the correct answer option area 641 selected, the screen transitions to the question screen 60 shown in FIG. 20, but in this case the answer status of the corresponding chunk becomes incorrect (the first answer takes priority).

[0091] Then, for multiple chunks contained in the text to be memorized, questions are presented and answers (selections from options) are accepted in sequence.

[0092] 14, after transmitting the question information, the learning assistance server 10 then receives answer information from the learner terminal 30 (step S130). Specifically, the answer information includes the answer status (correct or incorrect) of each of the multiple chunks when the difficulty level of the question is easy mode or difficult mode, and includes the answer status (correct or incorrect) of each of the multiple child chunks when the difficulty level of the question is normal mode.

[0093] Next, the learning assistance server 10 updates the learning user's memory level based on the received answer information (step S140). Specifically, the memory level of each chunk is updated based on the answer status of the question corresponding to that chunk. For example, 20 points are added to the memory level of a chunk that was answered correctly, and 5 points are subtracted from the memory level of a chunk that was answered incorrectly.

[0094] When the memorability of a chunk is updated, the memorability of the parent sentence of the chunk is also updated. For example, when 20 points are added to the memorability of a chunk, 10 points are added to the memorability of the parent sentence.

[0095] Similarly, the memorability of each child chunk is updated based on the answer status of the question corresponding to that child chunk. When the memorability of a child chunk is updated, the memorability of the parent chunk of that child chunk is also updated.

[0096] In another example of this embodiment, the memory level is updated based on the answer status of the question corresponding to the chunk as well as the difficulty of the question. For example, the higher the difficulty of the question, the larger the amount of points added to the memory level and the smaller the amount of points subtracted.

[0097] Next, the learning assistance server 10 determines whether the degree of memory for the presented target sentence exceeds a set value (threshold value) (step S150). If the degree of memory exceeds the set value (YES in step S150), it is determined that the learner has memorized the presented target sentence, and the presentation of questions for the corresponding target sentence is terminated. After termination, another target sentence in the target question set that includes the presented target sentence may be determined as the target sentence to be presented, or the user may be allowed to select the target sentence to be presented. On the other hand, if the degree of memory does not exceed the set value (NO in step S150), the process returns to step S110, and steps S110 to S150 are repeated until the degree of memory exceeds the set value or the user is finished. Note that in determining the degree of memory in step S150, the degree of memory to be determined may be the degree of memory for the target sentence or the degree of memory for each of the divided sentences. For example, if the memory level of one divided sentence exceeds a set value, but the memory levels of other divided sentences do not exceed the set value, the process may return to step S110 and ask questions corresponding to the divided sentences that do not exceed the set value.

[0098] Returning to the learning top screen 50 in Fig. 13, the memory level button 526 is an object for displaying information about the memory level of the corresponding problem set. When the memory level button 526 is selected, a memory level display screen 70, as shown in Fig. 21, is output. As shown in the figure, the memory level display screen 70 has a first display area 72 that displays the memory level status of the target sentences included in the target problem set, and a second display area 74 that displays the target sentences.

[0099] The first display area 72 displays a pie chart showing the memory status of the target sentences included in the target question set. Specifically, the pie chart graphically depicts the frequency distribution (relative frequency (proportion)) of the number of chunks by memory category for multiple chunks that have the target sentence as a parent. The memory categories are specifically "Memorized" (memory level: 100 points), "Memorizing" (memory level: 20-99 points), "Weakness" (memory level: 0-19 points), and "Unknown" (memory level not set). The first display area 72 is configured so that the displayed target sentences can be switched by flicking left or right or sliding. The number of times each question has been studied may be counted, and a question with a study count greater than a predetermined value but a memory level lower than a predetermined value may be considered a weak point.

[0100] The second display area 74 displays the text of the questions related to the target text displayed in the first display area 72, and also includes a text display area 742 that displays the target text. The text displayed in the text display area 742 is highlighted for each chunk in a color corresponding to its memory level category (the same color as the pie chart in the first display area 72). This allows the user to intuitively understand the memorization status of the target text. When the questions displayed in the first display area 72 are switched, the displayed text in the second display area 74 changes accordingly. As another example of the memory level display screen 70, the first display area may display a graphic indicating the progress of studying the target text problem set (e.g., a pie chart showing the proportions of each target text classified as "memorized," "memorizing in progress," "weak point," and "not studied" based on the memory level and the number of times each target text has been studied), and the second display area may further display the selected target text and a graphic indicating the memory level of the selected target text.

[0101] In the above example, the difficulty level is determined for each question, but it may also be determined for each chunk. In this case, for example, the difficulty level is determined to be easy mode when the learning user's memory for the chunk is less than a first threshold, normal mode when the memory level is equal to or greater than the first threshold and less than a second threshold, and difficult mode when the memory level is equal to or greater than the second threshold.

[0102] In the above example, questions are presented and answers are received sequentially for multiple chunks included in the text to be memorized, but questions may be presented and answers received for only some of these multiple chunks. In this case, the frequency of questions may be determined based on the memorability of the chunks (e.g., the lower the memorability of a chunk, the more frequently questions are presented).

[0103] In the above example, when updating the memorability of a chunk, the memorability of the target chunk may be corrected based on the memorability of a similar chunk (e.g., a chunk whose cosine similarity of the sentence is equal to or greater than a threshold value). For example, if the memorability of a similar chunk is equal to or greater than a threshold value (e.g., 90 points), 5 points are added to the memorability of the target chunk.

[0104] In the above example, the division of the sentence into chunks and child chunks is performed by the operator of the learning assistance service, but such division may also be performed by the learning assistance server 10. For example, when a sentence to be memorized is input, a prompt including instructions for dividing the sentence into a predetermined number of chunks may be automatically generated and input to a large-scale language model, and multiple chunks may be obtained based on information output from the large-scale language model.

[0105] The learning assistance server 10 according to the present embodiment described above presents the learner with questions corresponding to the segments (e.g., chunks) obtained by dividing a target sentence into segments, and determines the learner's level of memory for the segments based on the learner's answers to the questions. This allows the learner to manage the degree to which each segment has been memorized, thereby supporting the learner's memorization of the target sentence. In other words, the learning assistance server 10 supports efficient memorization of the entire sentence.

[0106] In other embodiments of the present invention, some or all of the functions of the learning assistance server 10 in the above-described embodiments may be realized by cooperation between the learning assistance server 10 and the instructor user terminal 20 or the learner user terminal 30, or may be realized by the instructor user terminal 20 or the learner user terminal 30. For example, some or all of the functions of the learning management unit 114 of the learning assistance server 10 may be realized by the learner user terminal 30, and, for example, the target sentences to be quizzed and their difficulty levels may also be determined by the learner user terminal 30. In other words, the system of the present invention may be constituted not only by the learning assistance server 10, but also by the learning assistance server 10 and the instructor user terminal 20 or the learner user terminal 30, or by the instructor user terminal 20 or the learner user terminal 30.

[0107] The processes and procedures described herein, other than those explicitly described, may be implemented by software, hardware, or any combination thereof. For example, the processes and procedures described herein may be implemented by implementing logic corresponding to the processes and procedures in a medium such as an integrated circuit, volatile memory, non-volatile memory, or magnetic disk. Furthermore, the processes and procedures described herein may be implemented as a computer program corresponding to the processes and procedures and executed by various computers.

[0108] Although processes and procedures described herein are described as being performed by a single device, software, component, or module, such processes or procedures may be performed by multiple devices, software, components, and / or modules. Also, the software and hardware elements described herein may be implemented by combining them into fewer components or breaking them down into more components.

Claims

1. A program for assisting in the memorization of a sentence, the program causing one or more computers to execute the following steps: presenting a learning user with a question corresponding to a first divided sentence contained in multiple divided sentences obtained by dividing a target sentence to be memorized; acquiring answer information of the learning user to the question corresponding to the first divided sentence; and determining the learning user's degree of memory for the first divided sentence based on the answer information to the question corresponding to the first divided sentence.

2. The program of claim 1, further causing said one or more computers to execute a step of determining the learning user's degree of memory for said target sentence based on the learning user's degree of memory for each of said plurality of segmented sentences.

3. The program of claim 1, further causing the one or more computers to execute the following steps: posing to the learning user a question corresponding to a first subdivision element contained in multiple subdivision elements into which the first subdivision sentence is further divided; acquiring answer information of the learning user to the question corresponding to the first subdivision element; determining the learning user's degree of memory for the first subdivision element based on the answer information to the question corresponding to the first subdivision element; and determining the learning user's degree of memory for the first subdivision sentence based on the learning user's degree of memory for each of the multiple subdivision elements.

4. The program of claim 1, wherein the step of determining the degree of memory of the first segmented sentence further determines the learning user's degree of memory of the first segmented sentence based on the learning user's degree of memory of sentences similar to the first segmented sentence.

5. The program of claim 1, further causing the one or more computers to execute a step of determining the difficulty level of the questions corresponding to the first segmented sentence to be posed to the learning user based on the learning user's degree of memory for the first segmented sentence.

6. The program of claim 1, further causing the one or more computers to execute the steps of: determining the learning user's degree of memory for the target sentence based on the learning user's degree of memory for each of the plurality of divided sentences; and determining the difficulty level of questions corresponding to the first divided sentence to be given to the learning user based on the learning user's degree of memory for the target sentence.

7. The program of claim 1, further causing the one or more computers to execute a step of determining a frequency of questions to be given to the learning user corresponding to the first segmented sentence based on the learning user's memory for the first segmented sentence.

8. The program of claim 1, further causing the one or more computers to execute a step of determining, based on the learning user's memory of the first divided sentence, whether or not it is necessary to give the learning user questions corresponding to each of the multiple sub-segment elements into which the first divided sentence is further divided.

9. The program of claim 1, further causing the one or more computers to execute a step of presenting to the learning user a specified screen displaying the target sentence by displaying the plurality of divided sentences in a manner based on the memorability of each of the plurality of divided sentences.

10. The program of claim 9, wherein the predetermined screen displays the target sentence by displaying the divided sentences in a color corresponding to the memorability of each of the divided sentences in accordance with the order in the target sentence.

11. The program according to claim 9, wherein the predetermined screen displays the target sentence in association with a graphic indicating the memorability of the target sentence based on the memorability of each of the plurality of divided sentences in the target sentence.

12. The program of claim 1, further causing the one or more computers to execute a step of presenting to the learning user a question corresponding to a second divided sentence included in the plurality of divided sentences, the second divided sentence being the next in order to the first divided sentence in the target sentence, as a question following the question corresponding to the first divided sentence.

13. The program of claim 1, wherein the question corresponding to the first divided sentence includes a question sentence that prompts the user to select the first divided sentence in accordance with the order of the multiple divided sentences in the target sentence, a correct answer choice that displays the first divided sentence, and an incorrect answer choice that displays a sentence different from the first divided sentence.

14. The program of claim 1, wherein the question corresponding to the first divided sentence includes a question sentence that prompts the user to select the first divided sentence in accordance with the order of the multiple divided sentences in the target sentence, a correct answer choice that displays a first sub-segmented element included in multiple sub-segmented elements into which the first divided sentence is further divided, and an incorrect answer choice that displays an element other than the first sub-segmented element.

15. The program of claim 1, wherein the question corresponding to the first divided sentence includes a question sentence that prompts the user to select the first character or character string of the first divided sentence in accordance with the order of the divided sentences in the target sentence, a correct answer option that displays the first character or character string, and an incorrect answer option that displays a character or character string different from the first character or character string.

16. The program of claim 1, further causing the one or more computers to execute a step of dividing the target sentence into the plurality of divided sentences through a predetermined natural language processing.

17. The program of claim 16, wherein the step of dividing the target sentence includes inputting information including instructions for dividing the target sentence into the plurality of divided sentences to a large-scale language model, and obtaining the plurality of divided sentences from information output by the large-scale language model.

18. A system for assisting in memorization of a sentence, comprising one or more computer processors, the one or more computer processors executing the steps of: presenting a learning user with a question corresponding to a first divided sentence contained in a plurality of divided sentences into which a target sentence to be memorized is divided; acquiring answer information of the learning user to the question corresponding to the first divided sentence; and determining the learning user's degree of memory for the first divided sentence based on the answer information to the question corresponding to the first divided sentence.

19. A method for assisting in memorization of a sentence, executed by one or more computers, comprising the steps of: presenting a learning user with a question corresponding to a first divided sentence contained in a plurality of divided sentences into which a target sentence to be memorized is divided; acquiring answer information of the learning user to the question corresponding to the first divided sentence; and determining the learning user's degree of memory for the first divided sentence based on the answer information to the question corresponding to the first divided sentence.

Images