Information processing device, information processing system, information processing method, and program

Abstract

To heighten the effect of a user's learning effect of speaking.SOLUTION: A learning assistance system 1 comprises a server 10 as an information processing device, and an electronic dictionary device 20 as an electronic apparatus. The server 10 includes pronunciation evaluation means and teaching material creation means. The pronunciation evaluation means derives an evaluation result in which the pronunciation of a user voice regarding a phrase or an example sentence including the phrase is evaluated for each phoneme. The teaching material creation means creates an example sentence as a pronunciation learning material that includes phrases including a phoneme whose evaluation result is below or equal to a prescribed criterion, and displays the pronunciation learning material on the electronic dictionary device 20 for presentation to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Conventionally, electronic dictionaries with a foreign language speaking learning function are known. For example, a pronunciation learning support device is known that generates model speech data for a specified foreign language phrase to be learned and accepts input of user speech data pronounced by a user (see Patent Document 1). The pronunciation learning support device compares the user speech data with the model speech data and displays an evaluation score that is an average point weighted for each syllable. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2008-83446 Summary of the Invention [Problem to be solved by the invention]

[0004] However, although the above-mentioned pronunciation learning assistance device allows the user to check the evaluation score that takes syllables into account, it is not possible to suggest the next lesson according to the evaluation score.

[0005] An object of the present invention is to improve the effectiveness of a user's speaking learning. [Means for solving the problem]

[0006] In order to solve the above problem, the information processing device of the present invention is characterized by comprising: a pronunciation evaluation means for deriving an evaluation result by evaluating the pronunciation of a user's voice for a phrase or an example sentence containing the phrase for each phoneme; and a teaching material creation means for creating, as pronunciation learning teaching materials, sentences containing phrases that include phonemes whose evaluation results are below a predetermined standard, and presenting the sentences to the user. [Effects of the Invention]

[0007] The present invention can improve the effectiveness of a user's speaking learning. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a block diagram showing a learning support system according to an embodiment of the present invention; [Figure 2] FIG. 2 is a block diagram showing the functional configuration of a server. [Figure 3] FIG. 2 is a block diagram showing the functional configuration of the electronic dictionary device. [Figure 4] FIG. 10 is a diagram showing the configuration of a user information table. [Figure 5] 10 is a flowchart showing a pronunciation learning support providing process. [Figure 6] 10 is a flowchart showing a pronunciation learning support process. [Figure 7] FIG. 10 is a diagram showing an evaluation result screen. [Figure 8] FIG. 10 is a diagram showing a teaching material screen. DETAILED DESCRIPTION OF THE INVENTION

[0009] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below with reference to the accompanying drawings. However, the scope of the present invention is not limited to the illustrated examples.

[0010] 1, a learning support system 1 according to the present embodiment includes a server 10 as an information processing device and an electronic dictionary device 20 as an electronic device. The devices in the learning support system 1 are communicatively connected via a communication network N. The communication network N is, for example, the Internet, and may include a LAN (Local Area Network), a dedicated line, a virtual communication network, etc.

[0011] The server 10 is an information processing device that provides a foreign language learning support function to the electronic dictionary device 20. In this embodiment, the foreign language is English, but is not limited to this. The learning support function particularly includes a learning support function for speaking (pronunciation) of the foreign language (English). The electronic dictionary device 20 is an electronic dictionary device owned by a user who is a learner, such as a school student. The electronic dictionary device 20 provides the user with data on the contents of a foreign language (English) dictionary (encyclopedia), and has a learning support function for speaking the foreign language. As shown in FIG. 1, one electronic dictionary device 20 will be described as a representative example. In reality, the learning support system 1 includes multiple electronic dictionary devices 20 owned by different users.

[0012] As shown in FIG. 2, the server 10 includes a CPU (Central Processing Unit) 11, an operation unit 12, a RAM 13, a display unit 14, a storage unit 15, and a communication unit 16. The components of the server 10 are connected via a (system) bus 17. The CPU 11 controls the components of the server 10. The CPU 11 reads out a specified program from among the various programs stored in the storage unit 15, loads it into the RAM 13, and executes various processes in cooperation with the loaded program. The CPU 11 functions as a pronunciation evaluation unit, a teaching material creation unit, and a suggestion unit. The operation unit 12 includes a keyboard and a pointing device such as a mouse. The operation unit 12 receives key operations and position inputs from a user and outputs the operation information to the CPU 11. The RAM 13 is a volatile semiconductor memory and forms a work area for temporarily storing various data and programs. The display unit 14 includes a display panel such as an LCD (Liquid Crystal Display) or an EL (Electroluminescent) display. The display unit 14 displays various display information input from the CPU 11 and the like on a display panel.

[0013] The storage unit 15 is a storage unit capable of reading and writing various information and programs, such as a hard disk drive (HDD) or a solid state drive (SSD). The storage unit 15 stores programs such as a pronunciation learning support program P1, and various information such as a user information table 30, native speech data 50, recorded data 60, and evaluation result data 70. The pronunciation learning support program P1 is a program for executing a pronunciation learning support process, which will be described later. The user information table 30 is a table that stores information about each user, which will be described in detail later. The native speech data 50 is speech data of a specific English phrase spoken by a native English speaker in an English-speaking region or an example sentence containing the phrase. The native speech data 50 is used to evaluate the user's speech data (recorded data) of the phrase or an example sentence containing the phrase. The phrase includes at least one word. The recorded data 60 is speech data of a specific phrase spoken by a user or an example sentence containing the phrase. The evaluation result data 70 is data resulting from evaluating the audio recording data 60. The evaluation result data 70 includes, for example, a score out of 100 for each phonetic symbol as a phoneme of a phrase in the user's audio recording data 60 or an example sentence containing that phrase. The communication unit 16 is an interface such as a network card connected to the communication network N. The CPU 11 transmits and receives information to and from external devices such as the electronic dictionary device 20 on the communication network N via the communication unit 16.

[0014] As shown in FIG. 3, the electronic dictionary device 20 includes a CPU 21, an operation unit 22, a RAM 23, a display unit 24, a storage unit 25, a communication unit 26, an audio input unit 27, and an audio output unit 28. The various units of the electronic dictionary device 20 are connected via a (system) bus 29. The CPU 21, RAM 23, and display unit 24 have the same configurations as the CPU 11, RAM 13, and display unit 14 of the server 10, respectively, so the following mainly describes the differences. The CPU 21 controls the various units of the electronic dictionary device 20. The operation unit 22 accepts operation inputs from the user. The operation unit 22 has a key operation unit 221 and a touch panel 222. The key operation unit 221 has alphanumeric keys, a shift key, a cursor key, various function keys, etc., and accepts key operation inputs from the user and outputs the operation information to the CPU 21. The touch panel 222 is a capacitive or resistive touch panel that is integrally provided on the display screen of the display unit 24. The touch panel 222 receives touch input from the user and outputs the operation information to the CPU 21.

[0015] The memory unit 25 is a memory unit, such as a flash memory, that can read and write various information and programs. The memory unit 25 stores programs such as the pronunciation learning support program P2, as well as various information such as a dictionary database 80 and learning content data 90. The pronunciation learning support program P2 is a program for executing the pronunciation learning support process described below. The dictionary database 80 is a database containing data on the contents of a foreign language (English) dictionary. The learning content data 90 is data on the contents of multiple learning content items as learning units for speaking the foreign language (English). Each learning content item includes predetermined words or example sentences containing those words for learning to speak the foreign language (English). The learning content data 90 includes native speech data obtained from native speakers in each region corresponding to the predetermined words or example sentences containing those words in each learning content item. The communication unit 26 is a wireless LAN interface, such as WiFi (registered trademark), that includes an antenna, a modulation / demodulation unit, a signal processing unit, etc. The communication unit 26 communicates wirelessly with access points and base stations of the communication network N. The CPU 21 transmits and receives information to and from external devices such as the server 10 on the communication network N via the communication unit 26. The audio input unit 27 is composed of a microphone and the like, and records the user's pronunciation, generates recorded data as audio data, and outputs it to the CPU 21. The audio output unit 28 is composed of an amplifier, a speaker, and the like, and outputs audio based on the audio data input from the CPU 21.

[0016] As shown in FIG. 4, the user information table 30 has columns for user ID 31, password 32, learning content 33, details 33a, region 34, native speech data 35, recording data 36, ​​evaluation result 37, and number of results 38. The user ID 31 is identification information for the user of the electronic dictionary device 20 and is a login ID for the server 10. The user ID 31 is assigned to each user whose registration is approved by, for example, a company that provides a pronunciation learning support provision process via the server 10. The password 32 is a login password for the user corresponding to the user ID 31.

[0017] Learning content 33 is the identification number of the learning content for the learning unit of the pronunciation of a foreign language (English). Content 33a is data of the content of learning content 33, including a predetermined phrase or example sentences containing that phrase, and its phonetic symbols. Region 34 is the region where the language used to evaluate the recording data 60 pronounced by the user with user ID 31 corresponding to the learning content of learning content 33 is used. When the foreign language to be learned is English, even the same phrase may have a different pronunciation depending on the region where it is used. The user selects a region depending on which region they would like their pronunciation to resemble. In this way, region 34 indicates a region where there are differences in pronunciation, such as the United Kingdom, the United States, and Australia.

[0018] Native voice data 35 is identification information for voice data (native voice data 50) of a predetermined phrase or example sentence containing that phrase from learning content 33 spoken by a native foreigner corresponding to region 34. Native voice data 35 may also include storage location information for native voice data 50 within storage unit 15. Recorded voice data 36 is identification information for voice data (recorded voice data 60) of a predetermined phrase or example sentence containing that phrase from learning content 33 spoken by a user with user ID 31 corresponding to region 34. Recorded voice data 36 may also include storage location information for recorded voice data 60 within storage unit 15.

[0019] The evaluation result 37 is identification information of the evaluation result (evaluation result data 70) of the audio recording data 60 of the audio recording data 36 of the user with the user ID 31, evaluated by comparing the native audio data 35 with the native audio data 50. The evaluation result 37 may also include information on the storage location of the evaluation result data 70 in the storage unit 15. The result count 38 is the number of evaluation results 37 (the number of stored evaluation result data 70) for each region 34 of the user with the user ID 31. The result count 38 is a number used to determine the timing to suggest the creation of teaching material data for speaking practice in the foreign language (English) to be presented to the user. For example, if the result count 38 is a predetermined number (e.g., 10) or more, the creation of teaching material data is suggested.

[0020] Next, a pronunciation learning support providing process executed by the server 10 will be described as an operation of the learning support system 1. The pronunciation learning support providing process provides foreign language speaking learning support by evaluating the pronunciation of a foreign language (English) spoken by a user using the electronic dictionary device 20 and generating learning material data. A user as a learner uses the electronic dictionary device 20 in advance. In the server 10, the CPU 11 starts receiving a user ID and password for logging in to the server 10 from the electronic dictionary device 20 via the communication unit 16. This user ID and password are information entered by the user in the electronic dictionary device 20, as will be described later. Triggered by the start of reception, the CPU 11 executes the pronunciation learning support providing process in accordance with the pronunciation learning support providing program P1 stored in the storage unit 15.

[0021] 5, the CPU 11 completes receiving the user ID and password from the electronic dictionary device 20 via the communication unit 16 (step S11). Then, the CPU 11 performs login authentication based on whether the user ID and password received in step S11 are included in the combination of user ID 31 and password 32 in the user information table 30, and determines whether the login authentication is successful (step S12). If it determines that the login authentication is not successful (step S12; NO), the process proceeds to step S11.

[0022] If it is determined that the login authentication is successful (step S12; YES), the CPU 11 generates authentication success information for the user's login authentication and transmits the authentication success information to the electronic dictionary device 20 via the communication unit 16 (step S13). Then, the CPU 11 determines whether or not it has received the designated study content, the designated area, and the recorded data from the electronic dictionary device 20 via the communication unit 16 (step S14). The designated study content is the name of the study content designated by the logged-in user. The designated area is the name of the area where the foreign language (English) designated by the logged-in user is used. The recorded data is the recorded data of a specific phrase from the designated study content or an example sentence containing that phrase, in which the pronunciation of the logged-in user is recorded for the designated area.

[0023] If it is determined that audio recording data or the like has been received (step S14; YES), the CPU 11 assigns identification information to the received audio recording data and stores it as audio recording data 60 in the storage unit 15. The CPU 11 also stores the assigned identification information in the audio recording data 36 corresponding to the learning content 33 of the designated learning content and the area 34 of the designated region for the user ID 31 of the logged-in user in the user information table 30. The CPU 11 then analyzes the audio recording data, reads out native voice data 50 from the storage unit 15, and compares the audio recording data with the read out native voice data 50 (step S15). The read out native voice data 50 is native voice data corresponding to the learning content 33 of the designated learning content and the area 34 of the designated region for the user ID 31 of the logged-in user. The analysis of the audio recording data is assumed to be amplitude analysis or frequency analysis. In this case, the amplitude or frequency pattern of the audio recording data is compared with the amplitude or frequency pattern of the native voice data. However, the method of analyzing the audio recording data is not limited to this. Furthermore, the analysis of the recorded data is performed for each phonetic symbol as a phoneme of a predetermined sentence or phrase using the details 33a of the designated content.

[0024] Then, CPU 11 calculates a score for each phonetic symbol in the recorded data based on the comparison result of step S15 (step S16). For example, the closer the amplitude or frequency pattern of the phonetic symbols in the recorded data is to the amplitude or frequency pattern of the phonetic symbols in the native speech data, the higher the score for that phonetic symbol is calculated. The score for each phonetic symbol in the recorded data is calculated, for example, on a scale of 100 points. CPU 11 then generates evaluation result data from the scores for each phonetic symbol corresponding to the designated study content and the designated region, assigns identification information to the generated evaluation result data, and stores the evaluation result data 70 in storage unit 15 (step S17). The evaluation result data includes content 33a. In step S17, CPU 11 stores the identification information assigned to the evaluation result data in evaluation result 37 corresponding to the study content 33 of the designated study content and the region 34 of the designated region for user ID 31 of the logged-in user. CPU 11 also increments by +1 the result number 38 corresponding to region 34 of the designated region for user ID 31 of the logged-in user.

[0025] Then, CPU 11 transmits the evaluation result data and the number of results generated in step S17 to electronic dictionary device 20 via communication unit 16 (step S18). Then, CPU 11 determines whether or not a teaching material creation instruction for pronunciation learning materials has been received from electronic dictionary device 20 via communication unit 16 (step S19). Also, if it determines that the designated learning content, designated area, and recording data have not been received (step S14; NO), the process proceeds to step S19.

[0026] If it is determined that a teaching material creation instruction has been received (step S19; YES), the CPU 11 creates teaching material data based on the evaluation result data 70 corresponding to the evaluation result 37 for the region 34 designated by the user ID 31 of the logged-in user (step S20). In step S20, all evaluation result data 70 stored in the storage unit 15 corresponding to the logged-in user and the designated region are read and used. In step S20, for example, the CPU 11 calculates the average score for each phonetic symbol in the read evaluation result data 70 and creates one or more example sentences containing phrases containing phonetic symbols whose average score is below a predetermined standard. The CPU 11 creates teaching material data including the created example sentences. The created example sentences are example sentences that focus on practicing pronunciation of phonetic symbols that the logged-in user has difficulty with. The predetermined standard is, for example, information that is input in advance by the user via the operation unit 22 of the electronic dictionary device 20 and transmitted to the server 10 and set. Specifically, the predetermined standard is a predetermined threshold score (e.g., 50) of the average score. The predetermined standard may be the ranking of the average score (for example, the lowest), etc. Furthermore, the learning material data may include native speech data of the included example sentences.

[0027] Then, the CPU 11 transmits the teaching material data created in step S20 to the electronic dictionary device 20 via the communication unit 16 (step S21). The CPU 11 then determines whether to terminate the pronunciation learning support providing process by determining whether a logoff instruction has been received from the electronic dictionary device 20 via the communication unit 16 (step S22). If it determines that it should be terminated (step S22; YES), the pronunciation learning support providing process ends. If it determines that it should not be terminated (step S22; NO), the process proceeds to step S14.

[0028] As shown in Fig. 6, the electronic dictionary device 20 executes a pronunciation learning support process corresponding to the pronunciation learning support providing process of Fig. 5. In the electronic dictionary device 20, the CPU 21 receives an input of an instruction to execute the pronunciation learning support process from the user via the operation unit 22. Triggered by this execution instruction, the CPU 21 executes the pronunciation learning support process in accordance with the pronunciation learning support program P2 stored in the storage unit 25.

[0029] First, the CPU 21 accepts input of a user ID and a password from the user via the operation unit 22. The CPU 21 transmits the input user ID and password to the server 10 via the communication unit 26 (step S31). Step S31 corresponds to step S11 of the pronunciation learning support suggestion process in FIG. 5. Then, the CPU 21 receives authentication success information from the server 10 via the communication unit 26 and determines whether the login authentication has been successful (step S32). Step S32 corresponds to step S13 in FIG. 5. If it is determined that the login authentication has not been successful (step S32; NO), the process proceeds to step S31.

[0030] If it is determined that the login authentication is successful (step S32; YES), CPU 21 accepts an input specifying the study content to be studied from the user via operation unit 22. CPU 21 launches the specified study content based on the input study content data 90 of the specified study content (step S33). Then, CPU 21 accepts an input specifying the region where the language to be studied is used from the user via operation unit 22 (step S34).

[0031] Then, based on the learning content data 90 of the designated learning content, CPU 21 displays the predetermined phrases pronounced in the designated learning content or example sentences containing those phrases on display unit 24. Furthermore, based on the native voice data in learning content data 90, CPU 21 outputs the displayed phrases or sentences in native voice via audio output unit 28 (step S35). Then, CPU 21 receives audio input of the predetermined phrases in the designated learning content pronounced by the user or example sentences containing those phrases via audio input unit 27, and generates recording data (step S36). In step S36, for example, CPU 21 starts recording when a recording instruction is input from the user via operation unit 22.

[0032] CPU 21 then determines whether or not a command to send the recorded data has been received from the user via operation unit 22 (step S37). If it determines that the command to send the recorded data has not been received (step S37; NO), the process proceeds to step S36. If it determines that the command to send the recorded data has been received (step S37; YES), CPU 21 transmits the recorded data of step S36 to server 10 via communication unit 26, together with the designated study content of step S33 and the designated area of ​​step S34 (step S38). Step S38 corresponds to step S14 in FIG. 5.

[0033] Then, CPU 21 receives the evaluation result data and the number of results from server 10 via communication unit 26 and displays them on display unit 24 (step S39). Step S39 corresponds to step S18 in FIG. 5. In step S39, for example, evaluation result screen 100 of FIG. 7 is displayed. Evaluation result screen 100 has a phrase / example sentence area 101, a score field 102, an evaluation result field 103, and a message 104. Note that the number of results is information used for determination in step 40, which will be described later, and therefore does not need to be displayed on display unit 24 or presented to the user.

[0034] The phrase and example sentence area 101 is an area displaying the spelling and phonetic symbols (and language) of a predetermined phrase to be evaluated or an example sentence containing that phrase. The phrase and example sentence area 101 has, for example, the phrase "water" and its phonetic symbols in British English. The score column 102 is a display column for the score of each phonetic symbol of the phrase in the phrase and example sentence area 101 or an example sentence containing that phrase. The score column 102 has, for example, the score of each phonetic symbol in British English for the phrase "water." For example, the score of the phonetic symbol for the long vowel in the symbol name "open O" is assumed to be relatively low. The evaluation result column 103 is a display column for the evaluation result of the pronunciation of the phrase in the phrase and example sentence area 101 or an example sentence containing that phrase, and the specified region that was compared (evaluated). The evaluation result score in the evaluation result column 103 is the average score of each phonetic symbol of the phrase in the score column 102 or an example sentence containing that phrase. The evaluation result column 103 includes the region (language) to which the recording data is compared. The message 104 is a message related to the evaluation result. For example, the message 104 is a message encouraging pronunciation practice of the phonetic symbol for the long vowel of the symbol name "open O" with a low score.

[0035] Then, the CPU 21 determines whether the number of results received in step S39 is equal to or greater than a predetermined number (10) (step S40). If it is determined that the number of results is equal to or greater than 10 (step S40; YES), the CPU 21 creates learning material creation suggestion screen information and displays it on the display unit 24 (step S41). The learning material creation suggestion screen information is screen information that suggests the login user to create learning material data for practicing appropriate phonetic symbols. The learning material data is, for example, data on pronunciation learning materials for mainly practicing the pronunciation of phonetic symbols for which the login user's average score is low in the evaluation result data stored in the server 10. Here, in the pronunciation learning support providing process, once learning material creation is executed (e.g., in step S20 or S21), the CPU 11 resets the number of results 38 stored in the user information table 30, which corresponds to the user ID 31 of the login user and the region 34 of the created learning material data. The CPU 21 determines whether a learning material creation instruction input instructing the creation of learning material data has been received from the user via the operation unit 22 (step S42). If the input of the instruction to create the learning material is accepted (step S42; YES), the CPU 21 transmits the instruction to create the learning material to the server 10 via the communication unit 26 (step S43). Step S43 corresponds to step S19 in FIG.

[0036] The CPU 21 then receives the learning material data from the server 10 via the communication unit 26, displays it on the display unit 24, and stores it in the storage unit 25 (step S44). The learning material data is, for example, content data for displaying the learning material screen 110 shown in FIG. 8. The learning material screen 110 has a word / example sentence area 111 and a highlighting area 112. The word / example sentence area 111 is a display area for example sentences including words containing phonetic symbols whose average score in the evaluation result data of the logged-in user is below a predetermined standard. The word / example sentence area 111 displays, for example, a list of example sentences including words containing the phonetic symbol of the long vowel of the symbol name "open O," which had a low average score for the logged-in user. The highlighting area 112 is an area in the word / example sentence area 111 that highlights the selected and input word or example sentence containing that word and its Japanese translation. In addition, when the teaching material data includes native audio data for multiple example sentences, the CPU 21 can output the native audio data of the selected example sentence via the audio output unit 28 in response to an instruction to select an example sentence from the logged-in user via the operation unit 22.

[0037] Like other existing learning content data 90, the stored learning material data can be displayed on the display unit 24 based on user operation via the operation unit 22 even when the pronunciation learning support process is not being executed. Therefore, like the learning content data 90, pronunciation practice of the learning material data can be performed at any time. Note that the CPU 11 of the server 10 may be configured to create learning material data in response to a creation request input from the user via the operation unit 22 at any time even when the pronunciation learning support process is not being executed. The learning material data is transmitted from the server 10 to the electronic dictionary device 20 and stored in the memory unit 25.

[0038] Then, CPU 21 determines whether or not there is a logoff input from the user via operation unit 22 (step S45). If it is determined that there is no logoff input (step S45; NO), the process proceeds to step S33. If there is a logoff input (step S45; NO), CPU 21 transmits a logoff instruction to server 10 via communication unit 26 (step S46), and ends the pronunciation learning assistance process. Step S46 corresponds to step S22 in FIG. 5.

[0039] As described above, according to this embodiment, the server 10 as an information processing device includes a CPU 11. The CPU 11 derives evaluation result data by evaluating the pronunciation of a user's voice for each phoneme (phonetic symbol) of a phrase or an example sentence containing the phrase. The CPU 11 creates one or more example sentences containing phrases containing phonetic symbols whose evaluation results (scores) are equal to or less than a predetermined standard (e.g., 50) as teaching material data for pronunciation learning materials, and displays the teaching material data on the electronic dictionary device 20 to present to the user. Therefore, the teaching material data allows the user to focus on practicing pronunciation of example sentences containing phonetic symbols that are poorly rated by the user, thereby improving the effectiveness of the user's speaking learning. Furthermore, using teaching material data dedicated to the user allows for efficient learning.

[0040] Furthermore, CPU 11 stores the evaluation result data in storage unit 15. When a predetermined number (e.g., 10) or more pieces of evaluation result data have been stored, CPU 11 creates teaching material data for pronunciation learning materials. Therefore, it is possible to appropriately extract pronunciation symbols that are poorly used by the user and have received low ratings from the predetermined number or more pieces of evaluation result data.

[0041] Furthermore, the CPU 11 creates teaching material data for pronunciation learning materials based on the evaluation result data accumulated in the storage unit 15 at the time of the user's operation to instruct the creation of teaching materials in the electronic dictionary device 20. Therefore, at any time, it is possible to appropriately extract pronunciation symbols that the user is not good at and that have received low evaluations from the accumulated evaluation result data.

[0042] Furthermore, when a predetermined number (e.g., 10) or more pieces of evaluation result data have been accumulated, the CPU 11 displays on the electronic dictionary device 20 screen information for suggesting the creation of teaching material data for pronunciation learning materials to the user. The CPU 11 creates teaching material data based on user operations in response to the creation suggestions on the electronic dictionary device 20. This allows the user to recognize the appropriate timing for creating teaching material data, and allows the user to create teaching material data at any timing of their choice.

[0043] Furthermore, once the creation of teaching material data has been executed, the CPU 11 resets the number of results stored in the user information table 30. This makes it possible to prevent the user from being repeatedly prompted to create teaching material data.

[0044] After evaluating the user's voice recording data, the CPU 11 displays the evaluation result data on the electronic dictionary device 20 for the user to see. This allows the user to recognize the evaluation result data for the most recent recording data. The evaluation result data quantifies the differences between the user's own pronunciation and that of native speakers of foreign languages, making it possible to objectively understand the differences. This allows the user to accurately grasp their own level and improve the effectiveness of their learning.

[0045] Furthermore, the predetermined standard for the evaluation results is the user's arbitrary evaluation score or the ranking of the evaluation scores of each phoneme (phonetic symbol). This allows for more appropriate extraction of phonetic symbols that are poorly rated by the user.

[0046] Furthermore, the CPU 11 derives evaluation result data for the user's voice (recorded data) based on the pronunciation corresponding to the region selected by the user (native voice data for the specified region). Therefore, for languages ​​whose pronunciation varies depending on the region, the user's recorded data can be appropriately evaluated in the language of the region desired by the user.

[0047] In the above description, an example has been disclosed in which storage units 15 and 25 such as flash memory are used as computer-readable media for the program according to the present invention, but this is not limiting. Other computer-readable media include portable recording media such as ROM (Read Only Memory) and CD-ROM. Furthermore, a carrier wave is also applicable to the present invention as a medium for providing data for the program according to the present invention via a communication line.

[0048] The description in the above embodiment is merely an example of the information processing device, information processing system, information processing method and program according to the present invention, and the present invention is not limited to this.

[0049] For example, in the above embodiment, the learning assistance system 1 is configured to include a server 10 as an information processing device and an electronic dictionary device 20 as an electronic device. The server 10 manages information about users, stores recorded data, creates learning material data, and so on. However, this configuration is not limited to this. The learning assistance system 1 may also be configured to include only the electronic dictionary device 20 as an information processing device. In this configuration, the CPU 21 of the electronic dictionary device 20 performs the same processes as the pronunciation learning assistance providing system and pronunciation learning assistance processing, such as managing information about users, storing recorded data, and creating learning material data, all in one device.

[0050] In the above embodiment, the electronic dictionary device 20 is used as the information processing device connected to the server 10 and performing the pronunciation learning support process, but the present invention is not limited to this. The information processing device connected to the server 10 may be any other type of information processing device, such as a smartphone, a desktop PC (Personal Computer), a palmtop PC, or a tablet PC.

[0051] In the above embodiment, the comparison of the recorded data of a predetermined phrase or example sentence containing that phrase with native speech data in the designated study content of the logged-in user is configured to be performed for each phoneme, but this is not limited to this. The comparison may also be performed for each consecutive phonetic symbol. For example, a comparison may be performed for each sequence of phonetic symbols before and after a predetermined phonetic symbol (a sequence pattern of two or three consecutive phonetic symbols), and a score may be calculated for each of the two or three phonetic symbols. Furthermore, the comparison may also be performed for each consecutive phonetic symbol spanning the first and second phrases in a predetermined example sentence of the designated study content.

[0052] That is, CPU 11 associates the order of phonemes (phonetic symbols) of a phrase or an example sentence containing the phrase with an evaluation for each phonetic symbol and stores the associated data in storage unit 15 as evaluation result data. If the evaluation result data, in which phonemes are arranged according to a predetermined rule, is below a predetermined standard (e.g., a score of 50), CPU 11 creates one or more example sentences containing phonetic symbols arranged according to the predetermined rule or example sentences containing phrases containing phonetic symbols arranged according to the predetermined rule as teaching material data for pronunciation learning materials. With this configuration, for phonetic symbols with poor evaluations, it is possible to extract multiple patterns of phonetic symbol arrangements that are particularly difficult, or patterns in which phonetic symbols arranged according to a specific rule are difficult to pronounce even if they are not evaluated poorly as individual phonetic symbols, and these can be reflected in the teaching material data. In particular, by creating multiple example sentences as learning materials that include various phonetic symbol arrangement patterns, it becomes easier to accumulate evaluation data for multiple consecutive phonetic symbols.

[0053] Furthermore, in the above embodiment, the CPU 11 presents the evaluation results of the transmitted recording data to the user by displaying them on the electronic dictionary device 20. However, the evaluation result data for each phoneme (phonetic symbol) based on the evaluation result data stored in the storage unit 15 may be presented to the user by displaying them on the electronic dictionary device 20. In this case, the evaluation result data allows the user to recognize the evaluation results of the recording data for each phonetic symbol, further improving the learning effect.

[0054] Furthermore, in the above embodiment, the evaluation result data is created by directly comparing the user's recording data with native speech data, but this is not limited to this. The evaluation result data may also be created using AI (Artificial Intelligence). For example, a trained model may be created by learning the region, phonemes (phonetic symbols), recording data, native speech data, and scores for each phonetic symbol corresponding to a predetermined phrase or an example sentence containing the phrase as training data. When the region, phonetic symbols, and recording data corresponding to a predetermined phrase or an example sentence containing the phrase are input, the trained model is trained to output evaluation data having a score for each phonetic symbol for the region corresponding to the predetermined phrase or an example sentence containing the phrase, based on the native speech data. When creating the evaluation result data, the designated region, phonetic symbols, and recording data corresponding to the logged-in user's predetermined phrase or an example sentence containing the phrase are input to the trained model, and the evaluation result data is output.

[0055] 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. [Explanation of symbols]

[0056] 10 servers, 11 CPUs

Claims

1. a pronunciation evaluation means for evaluating pronunciation of a user's voice for each phoneme of a phrase or an example sentence including the phrase, and deriving an evaluation result; a teaching material creation means for creating, as pronunciation learning teaching materials, example sentences including phrases containing phonemes determined to be below a predetermined standard as the evaluation results, and presenting the example sentences to a user; An information processing device comprising:

2. The pronunciation evaluation means accumulates the evaluation results, 2. The information processing apparatus according to claim 1, wherein said teaching material creating means creates said pronunciation learning teaching material when it determines that a predetermined number of said evaluation results have been accumulated.

3. the pronunciation evaluation means associates the order of phonemes of the phrase or the example sentence containing the phrase with an evaluation for each phoneme, and stores the evaluation results; The information processing device according to claim 1, characterized in that, when the teaching material creation means determines that the phonemes are arranged according to a predetermined rule and that the evaluation result is below the predetermined standard, it creates, as the pronunciation learning teaching material, example sentences containing phonemes arranged according to the predetermined rule or example sentences containing phrases containing phonemes arranged according to the predetermined rule.

4. 4. The information processing apparatus according to claim 2, wherein the teaching material creating means creates the pronunciation learning teaching material based on the evaluation results accumulated at the time the user operates, in response to the user operation.

5. and a suggestion unit that suggests to the user to create the pronunciation learning material when it is determined that the number of evaluation results accumulated is equal to or greater than a predetermined number.

4. The information processing apparatus according to claim 2, wherein the teaching material creating means creates the pronunciation learning teaching material based on a user operation in response to the creation suggestion.

6. 2. The information processing apparatus according to claim 1, wherein the pronunciation evaluation means, after evaluating the user's voice, presents the evaluation result to the user.

7. The information processing apparatus according to claim 1 or 3, wherein the predetermined criterion for the evaluation result is a user-selected evaluation score or a ranking of the evaluation scores of each phoneme.

8. 2. The information processing apparatus according to claim 1, wherein the pronunciation evaluation means derives an evaluation result of the user's voice based on pronunciation corresponding to a region selected by the user.

9. 4. The information processing apparatus according to claim 2, wherein the pronunciation evaluation means presents to the user an evaluation result for each phoneme based on the accumulated evaluation results.

10. An information processing device and an electronic device are provided, The information processing device includes: a pronunciation evaluation means for evaluating pronunciation of a user's voice for each phoneme of a phrase or an example sentence including the phrase, and deriving an evaluation result; a teaching material creation means for creating, as pronunciation learning teaching materials, example sentences including phrases including phonemes whose evaluation results are below a predetermined standard, and displaying the pronunciation learning teaching materials on the electronic device to present to the user; An information processing system comprising:

11. a pronunciation evaluation step of deriving an evaluation result by evaluating the pronunciation of a user's voice for each phoneme of a phrase or an example sentence including the phrase; a teaching material creation step of creating example sentences containing phrases including phonemes whose evaluation results are below a predetermined standard as pronunciation learning teaching materials and presenting the example sentences to a user; An information processing method comprising:

12. Computer, a pronunciation evaluation means for evaluating pronunciation of a user's voice for each phoneme of a phrase or an example sentence including the phrase, and deriving an evaluation result; a teaching material creation means for creating, as pronunciation learning teaching materials, example sentences including phrases including phonemes whose evaluation results are below a predetermined standard, and presenting the example sentences to a user; A program to function as a

Images