Display method and program

Abstract

To provide a user interface that enables a user to more easily understand the evaluation results of an answer. [Solution] A method for displaying the evaluation results of a user's answer sentence on a display device, which performs either a first display control in a first case in which it is determined that the user's answer sentence matches the model answer sentence, depending on the user's answer input, to display a first image indicating the correct answer and indicating a first evaluation; a second display control in a second case in which the user's answer sentence does not match the model answer sentence but is evaluated to be correct, to display an identification display that identifies the different parts of the user's answer sentence and the model answer sentence and a second image indicating the correct answer and a second evaluation that is lower than the first evaluation; or a third display control in a third case in which the user's answer sentence, which includes a part that differs from the model answer sentence, is evaluated to be incorrect, to display an identification display and a third image indicating an incorrect answer.

Description

[Technical field]

[0001] The present invention relates to a method and a program for displaying, on a display device, an evaluation result of an evaluation of a user's translated answer to a question. [Background technology]

[0002] In recent years, software applications have been provided that train students to instantly translate Japanese sentences into English. By repeatedly performing this training, students can increase the speed at which they can retrieve English knowledge and efficiently improve their speaking ability.

[0003] Patent Document 1 discloses a method for evaluating a student's answers to language questions using artificial intelligence, although the answers are not training questions for translating Japanese sentences into English. The specific disclosure is as follows: The artificial intelligence judges the degree of similarity between the meaning of the student's answer and the meaning of multiple model answers. After the student answers, the student's answer is judged by operating the "Judge" button. If the answer is judged to be the most appropriate, all three stars are displayed in a bright manner. Next, if the answer is judged to be appropriate, two stars are displayed in a bright manner. If the answer is judged to be somewhat appropriate, one star is displayed in a bright manner. If the answer is judged to be inappropriate, all stars are not displayed in a bright manner. If the degree of similarity between the meaning of the student's answer and the meaning of the model answer is 80%, all three stars are displayed in a bright manner. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 7067751 Summary of the Invention [Problem to be solved by the invention]

[0005] In the method described in Patent Document 1, when the student's answer does not match the model answer, the difference between the student's answer and the model answer is not displayed, and the difference from the model answer cannot be recognized. Also, the same three stars are displayed in a bright manner in both the case where the student's answer and the model answer match perfectly and the case where the degree of similarity between the meaning of the student's answer and the meaning of the model answer is 80%, so the difference between the two cases cannot be recognized.

[0006] Since there are many English expressions, it is difficult to prepare all possible model answers that users of an application for translating Japanese texts can give in training questions on translating Japanese texts into English. Therefore, the answer of the user is compared to a limited number of model answers. However, when the answer of the user is similar to the model answer even if it does not match the model answer, the issue is how to evaluate the answer of the user and what kind of evaluation result to output and display.

[0007] Therefore, an object of the present invention is to provide a user interface that enables a user to more easily understand the evaluation results of an answer. [Means for solving the problem]

[0008] A method according to one aspect of the present invention for solving the above problem is a method for displaying, on a display device, an evaluation result obtained by an information processing device evaluating an answer sentence that a user has translated into another language for a problem sentence to be translated, the method including the steps of: displaying, in a first case where the information processing device determines that the user's answer sentence matches a model answer sentence corresponding to the problem sentence in response to an input of the user's answer to the problem sentence, a correct answer; The answer to the above questiona first display control for causing the display device to display a first image indicating a first evaluation; and in a second case in which the information processing device determines that the answer sentence of the user does not match the model answer sentence and evaluates the user's answer sentence including a portion different from the model answer sentence to be correct, an identification display for showing the different portion of the user's answer sentence and the model answer sentence in a manner different from that of the same portion of the user's answer sentence and the model answer sentence when displaying the user's answer sentence and the model answer sentence; Unlike the first image, the answer text and a third display control for causing the display device to perform the identification display and display a third image indicating an incorrect answer in a third case in which the information processing device evaluates the user's answer sentence, which includes a portion different from the model answer sentence, as being incorrect. The first image to be displayed on the display device in the first case is displayed on the display device regardless of the type of the user's answer sentence in the second case. The color of the display area of ​​the first image is the same as the color of the display area of ​​the second image. It is characterized by: Effect of the Invention

[0009] According to the present invention, it is possible to provide a user interface that enables a user to more easily understand the evaluation results of an answer. [Brief description of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram showing a configuration of an information processing system. [Diagram 2] FIG. 2 is a diagram showing a configuration of an information processing terminal. [Diagram 3] FIG. 13 is a flowchart showing a method for displaying an evaluation result of a user's answer on a display unit. [Figure 4] FIG. 13 is a flowchart showing a method for evaluating a user's answer. [Diagram 5] FIG. 2 is a diagram showing the relationship of information transmission and reception between each information processing device. [Figure 6] FIG. 4 shows a GUI according to the first embodiment. [Figure 7] FIG. 4 shows a GUI according to the first embodiment. [Figure 8] FIG. 4 shows a GUI according to the first embodiment. [Figure 9] FIG. 11 is a diagram showing a GUI according to the second embodiment. [Figure 10] FIG. 11 is a diagram showing a GUI according to the second embodiment. [Figure 11] FIG. 11 is a diagram showing a GUI according to the second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] The present invention will be described below with reference to the preferred embodiments thereof.

[0012] [Item 1] A method for displaying on a display device an evaluation result of an answer sentence that a user has translated into another language for a question sentence to be translated, the method comprising: In response to the user's input of an answer to the question, a first display control that causes the display device to display a first image indicating a correct answer and a first evaluation in a first case in which the information processing device determines that the answer sentence of the user matches a model answer sentence corresponding to the question sentence; a second display control that causes the display device to perform, when displaying the user's answer sentence and the model answer sentence, a distinguishing display that shows the different part of the user's answer sentence and the model answer sentence in a manner different from that of the same part of the user's answer sentence and the model answer sentence, and a second image that indicates a correct answer and a second evaluation that is lower than the first evaluation, in a second case in which the information processing device determines that the user's answer sentence does not match the model answer sentence and evaluates the user's answer sentence including a part different from the model answer sentence to be correct; a third display control that causes the display device to perform the identification display and display a third image indicating an incorrect answer when the information processing device evaluates the user's answer sentence, which includes a portion different from the model answer sentence, as being incorrect; and Do one of the following: The method according to claim 1, wherein the first image to be displayed on the display device in the first case is not to be displayed on the display device in the second case regardless of the user's answer sentence. [Item 2] 2. The method according to item 1, characterized in that the identification display is performed so that words in the user's answer sentence that are not in the model answer sentence can be distinguished from words that are present in the model answer sentence. [Item 3] The method according to item 1 or 2, characterized in that when it is determined that the user's answer sentence does not match the model answer sentence, the information processing device outputs an evaluation result of the user's answer sentence based on information on the question sentence and information on the meaning of the user's answer sentence. [Item 4] 4. The method according to item 3, characterized in that the evaluation result is output based on information on the meaning of the user's answer sentence output by artificial intelligence. [Item 5] A program for causing a computer to execute the method according to any one of items 1 to 4.

[0013] <Details of the embodiment> A configuration diagram of an information processing system in this embodiment is shown in Figure 1. This system has an information processing terminal (information processing device) 1, an evaluation server (information processing device) 2, and an AI server (information processing device) 3. These are connected via a network 4.

[0014] Software and application programs are installed in the information processing terminal 1 for conducting learning training in which a sentence expressed in a predetermined language is presented to the user as a question, and the user looks at the question and translates it into another language. The programs are installed by downloading them from a server connected to the information processing terminal 1 via a network 4. The information processing terminal 1 obtains information on the answer translated by the user, and transmits the information to the evaluation server 2 via the network 4.

[0015] The evaluation server 2 is an information processing device (evaluation device) that performs information processing to evaluate an answer sentence that a user has translated into another language for a problem sentence to be translated. The evaluation server 2 receives information on the answer translated by the user, and evaluates the user's answer sentence based on that information. The AI ​​server 3 is a server equipped with artificial intelligence (AI). When the user's answer sentence should be evaluated by machine learning such as artificial intelligence (AI), the evaluation server 2 transmits information on the user's answer sentence to the AI ​​server 3 via the network 4.

[0016] The AI ​​server 3 inputs information about the user's answer into a machine learning model such as a trained large-scale language model, outputs information indicating the meaning of the user's answer and information about alternative expressions of the user's answer, and sends it to the evaluation server 2 via the network 4.

[0017] The evaluation server 2 receives the information output by the AI ​​server 3 and evaluates the user's answer sentence based on that information. The evaluation server 2 transmits the evaluation results of the user's answer sentence to the information processing terminal 1 via the network 4. Based on the evaluation results received from the evaluation server 2, the information processing terminal 1 performs display control to display the evaluation results of the user's answer sentence on the display device.

[0018] Next, a description will be given of the configuration of the information processing terminal 1. The information processing terminal 1 has a computer provided in a device such as a general-purpose computer such as a personal computer, a smartphone, or a tablet. The information processing terminal 1 can obtain information on a user's answer using installed software or applications (programs), and perform display control to display the evaluation results of the user's answer sentences on a display device.

[0019] 2 shows a configuration diagram of the information processing terminal 1. The information processing terminal 1 has a processing unit 11, a memory 12, a storage 13, a communication unit 14, an input unit 15, and a display unit 16. These are electrically connected to each other via a bus 17.

[0020] The processing unit 11 is an arithmetic device that controls the operation of the information processing terminal 1 as a whole, controls transmission and reception of data between each unit, and performs information processing necessary for program execution and authentication processing. The processing unit 11 includes an arithmetic processing device such as a processor such as a CPU, GPU, or FPGA, and is stored in the storage 13, and executes programs and the like deployed in the memory 12 to perform various information processing described below.

[0021] The memory 12 (storage unit) includes a main memory configured with a volatile storage device such as a DRAM, and an auxiliary memory configured with a non-volatile storage device such as a flash memory or a HDD. The memory 12 is used as a work area for the processing unit 11, and also stores a BIOS executed when the information processing terminal 1 is started up, various setting information, and the like.

[0022] The storage 13 (storage medium) stores various programs such as applications and programs. A database that stores data used for each process is constructed in the storage 13.

[0023] The communication unit 14 connects the information processing terminal 1 to the network 4. The communication unit 14 communicates with an external device directly or via a network access point, for example, by a method such as a wired LAN, a wireless LAN, Wi-Fi (Wireless Fidelity, registered trademark), infrared communication, Bluetooth (registered trademark), short-distance or non-contact communication, etc. The input unit 15 is an information input device, for example, a keyboard, a mouse, a touch panel, etc.

[0024] The display unit (display device) 16 includes a display that displays information obtained by calculations performed by the processing unit 11 or information received from the outside by the communication unit 14. The display unit 16 provides a graphical user interface (GUI) that displays various information on its screen. The display unit 16 is not limited to being provided integrally with the information processing terminal 1, and may be a display (display device) that is provided separately from the information processing terminal 1 and connected to the information processing terminal 1.

[0025] A bus 17 is commonly connected to all the above components, and transmits, for example, address signals, data signals and various control signals.

[0026] Next, the configuration of the assessment server 2 will be described. The assessment server 2 has a processing unit, a memory (storage unit), a storage (storage medium), and a communication unit. These are electrically connected to each other via a bus. The processing unit is a calculation device that controls the operation of the assessment server 2 as a whole, controls the transmission and reception of data between each unit, and performs information processing required for program execution and authentication processing. The processing unit includes a calculation processing device such as a processor such as a CPU, GPU, or FPGA, and is stored in the storage, and executes programs and the like deployed in the memory to perform various information processing described below.

[0027] The storage of the assessment server 2 stores various programs such as applications and programs. A database storing data used for each process is constructed in this storage. The communication unit of the assessment server 2 connects the assessment server 2 to the network 4. This communication unit receives information transmitted from the information processing terminal 1 or the AI ​​server 3 via the network 4. The received information is stored in the memory and used for information processing performed by the processing unit or stored in the storage.

[0028] Next, the configuration of the AI ​​server 3 will be described. The AI ​​server 3 has a processing unit, a memory (storage unit), a storage (storage medium), and a communication unit. These are electrically connected to each other via a bus. The processing unit is a calculation device that controls the operation of the entire AI server 3, controls the transmission and reception of data between each unit, and performs information processing necessary for program execution and authentication processing. The processing unit includes a calculation processing device such as a processor such as a CPU, GPU, or FPGA, and executes programs stored in the storage and expanded in the memory to perform various information processing described below.

[0029] The storage of the AI ​​server 3 stores various programs such as applications and programs. A database storing data used for each process is constructed in this storage. Machine learning models such as trained large-scale language models are stored in the storage or memory. The communication unit connects the AI ​​server 3 to the network 4. This communication unit receives information transmitted from the information processing terminal 1 or the evaluation server 2 via the network 4. The received information is stored in the memory and used for information processing performed by the processing unit, or stored in the storage.

[0030] Next, a method of using the above information processing system to display on a display device the evaluation result of the evaluation server 2 evaluating an answer sentence that a user has translated into another language for a question sentence to be translated, will be described.

[0031] The information processing terminal 1 executes a method for displaying on a display device an evaluation result of an answer sentence that a user has translated into another language for a question sentence to be translated, the evaluation server 2 having evaluated the answer. Specifically, the information processing terminal 1 performs one of the following three display controls on the display device in response to an input of an answer by the user for one question sentence. The display control includes a first display control for causing the display device to display a first image indicating a correct answer and indicating a first rating in a first case in which the evaluation server 2 determines that the user's answer sentence matches the model answer sentence corresponding to the question sentence; a second display control for causing the display device to display an identification display that shows the different parts of the user's answer sentence and the model answer sentence in a manner different from that of the same parts of the user's answer sentence and the model answer sentence when displaying the user's answer sentence and the model answer sentence, and a second image indicating the correct answer and indicating a second rating lower than the first rating in a third case in which the evaluation server 2 evaluates that the user's answer sentence including the part different from the model answer sentence is not correct. The first image displayed on the display device in the first case is not displayed on the display device in the second case, regardless of the user's answer sentence.

[0032] The information processing system as a whole performs an evaluation method in which an answer sentence that a user translates into another language for a question sentence to be translated is evaluated. Specifically, the method includes a step of displaying a question on a display screen of a terminal used by a user, a step of the terminal transmitting information on an answer to the question input by the user using the terminal and the question information to an information processing device, a step of the information processing device acquiring information on the question and information on the user's answer to the question, a step of the information processing device judging whether or not the user's answer matches a model answer sentence corresponding to the question, a step of the information processing device transmitting first information indicating that the user's answer sentence matches the model answer sentence to the terminal when the information processing device judges that the user's answer sentence matches the model answer sentence, a first display step of displaying the user's answer sentence and the model answer sentence, and displaying a first image indicating the highest evaluation among three images indicating the evaluation result, on the screen of the terminal when the information processing device judges that the user's answer sentence does not match the model answer sentence, the information processing device, when the evaluation result shows that the user's answer statement is correct, transmits to the terminal second information indicating that the user's answer statement does not match the model answer statement but is correct; if the terminal acquires the second information, a second display step of causing the terminal to display an identification display for allowing the user to identify a different portion between the user's answer statement and the model answer statement in the display of the user's answer statement and the model answer statement on the screen of the terminal, and a second image indicating the second evaluation of the three images indicating the evaluation result (indicating that the user's answer statement does not match the model answer statement but is correct); and a third display step of causing the terminal to display, when the evaluation result shows that the user's answer statement is incorrect, transmits third information to the terminal indicating that the user's answer statement is incorrect; and if the terminal acquires the third information, a third image indicating the lowest evaluation of the three images indicating the evaluation result (indicating that the user's answer statement is incorrect).

[0033] A specific method for displaying the evaluation results of a user's answer on a display device will now be described. Fig. 3 shows a flowchart of this method. Fig. 5 shows the relationship between the sending and receiving of information between each information processing device. The information processing described below is performed by executing programs implemented in the terminal 1, evaluation server 2, and AI server 3.

[0034] The predetermined language of the problem sentence to be translated may be any language such as Japanese, English, Chinese, Korean, German, French, etc., but in this embodiment, it is described as Japanese. The other language to be translated may be any language other than the predetermined language mentioned above, but in this embodiment, it is described as English. Below, a method, device, and program for a user who is a student of English language learning to translate a problem sentence to be translated expressed in Japanese into an English sentence will be described.

[0035] The information processing terminal 1 (hereinafter, terminal 1) launches an English learning application (software) in response to input operations from the user. After launching, the display unit 16 displays icon images indicating groups of questions, for example, by level. The user selects the desired question to study by clicking or tapping on one of the images displayed on the display unit 16. The processing unit 11 obtains information on the question selected by the user, for example, by a signal from the mouse of the input unit 15 or the touch panel of the display unit 16.

[0036] The processing unit 11 acquires information on the question selected by the user from the question sentence database stored in the storage 13, stores it in the memory 12, and displays the question sentence included in the acquired question information on the display screen of the display unit 16 (S1). The question sentence database may be stored in the evaluation server 2. In that case, the evaluation server 2 may transmit the information on the question sentence to the terminal 1 in response to a request from the terminal 1.

[0037] The user answers the question by looking at the Japanese problem sentence to be translated, displayed on the display unit 16, considering an appropriate translation into English, and inputting the translated English sentence into the terminal 1. The user may input the answer into the terminal 1 by speaking through a microphone, or may input characters through the touch panel or keyboard of the display unit 16. When the user inputs the answer by oral speech, a process is performed to convert the input voice information into character information. This conversion process may be performed by the processing unit 11, or may be performed by the evaluation server 2 other than the terminal 1 or another server (external information processing device) after acquiring the voice information from the terminal 1. When an information processing device other than the terminal 1 performs the above conversion process, the converted character information is transmitted to the terminal 1. In this way, the processing unit 11 acquires information on the English composition, which is the English sentence translated by the user, as the user's answer sentence (S2). The terminal 1 transmits information on the user's answer to the evaluation server 2, and requests the evaluation server 2 for an evaluation result of the user's answer.

[0038] The evaluation server 2 acquires information on the question selected by the user and information on the user's answer to that question via the network 4 (S3). Information on the question selected by the user is acquired by receiving it from the terminal 1. Information on the user's answer to the question may be acquired as text information acquired by the terminal 1 as described above, or may be acquired by receiving voice information from the terminal 1 and converting it into text information.

[0039] The storage of the assessment server 2 stores a model answer database. The model answer is an answer that is set as the optimal answer for a corresponding question, and is prepared in advance. The processing unit of the assessment server 2 acquires information on the model answer corresponding to the question acquired from the terminal 1 from the model answer base stored in the storage (S4). The model answer database may have one or more model answer sentences registered as model answers for one question, but in this embodiment, an example in which one model answer sentence is registered for one question sentence will be described.

[0040] Next, the evaluation server 2 uses its processing unit to determine whether the user's answer matches the model answer (S5). The processing unit of the evaluation server 2 compares the user's answer translated into English with the model answer corresponding to the question text answered by the user based on the information on the user's answer text acquired from the terminal 1. In this comparison, for example, it determines whether the English words contained in the model answer are identical to the English words contained in the user's answer text, starting from the beginning. If the English words are completely the same from the beginning to the end of the English text, the processing unit determines that the user's answer matches the model answer. If different English words exist from the beginning to the end of the English text, or if the same English words exist but in a different order, it determines that the user's answer does not match the model answer. As described above, the processing unit of the evaluation server 2 determines whether the user's answer matches the model answer, and transmits information on the determination result to the terminal 1.

[0041] If the processing unit of the evaluation server 2 determines that the user's answer does not match the model answer, it evaluates whether the user's answer is correct or not (S6). In this evaluation, it evaluates whether the meaning of the user's answer matches the intent, gist or meaning of the question sentence.

[0042] For example, the evaluation server 2 sends the AI ​​server 3 a question asking about the meaning of the user's answer, which is input into a large-scale language model, which is the artificial intelligence of the AI ​​server 3, and the model outputs information on the meaning of the user's answer and sends it to the evaluation server 2, thereby the evaluation server 2 obtains information on the meaning of the user's answer. The information on the meaning of the user's answer output by the large-scale language model of the AI ​​server 3 can be output in any language, but can be information expressed in Japanese, for example.

[0043] Then, the processing unit of the evaluation server 2 judges whether or not the information on the meaning of the user's answer sentence that has been acquired contains information on the question sentence. For example, it judges whether or not the Japanese sentence expressing the meaning of the user's answer sentence contains a word from the Japanese question sentence. If it is judged that the Japanese sentence expressing the meaning of the user's answer sentence contains a word from the Japanese question sentence, the user's answer sentence matches the intention, gist or meaning of the question sentence, and the user's answer can be evaluated as a correct answer. If it is judged that the Japanese sentence expressing the meaning of the user's answer sentence does not contain a word from the Japanese question sentence, the user's answer sentence does not match the intention, gist or meaning of the question sentence, and the user's answer can be evaluated as an incorrect answer. Furthermore, the evaluation server 2 may send a question asking about the meaning of the question sentence to the AI ​​server 3, acquire information on the meaning of the question sentence, and compare the meaning of the question sentence with the meaning of the user's answer.

[0044] Another example of the evaluation of a user's answer is a method of translating the user's English answer into Japanese. In this method, information on the user's answer is sent from the evaluation server 2 to a translation server, and the translation server performs a process of translating the English sentence of the user's answer into Japanese. Then, information on the translated Japanese sentence is sent to the evaluation server 2, and the evaluation server 2 evaluates whether the meaning of the translated Japanese sentence of the user's answer matches the intention, main point, or meaning of the question sentence. For example, it is determined whether the Japanese sentence of the user's answer contains a word from the Japanese question sentence. If it is determined that the Japanese sentence of the user's answer contains a word from the Japanese question sentence, the user's answer matches the intention, main point, or meaning of the question sentence, and therefore the user's answer can be evaluated as correct. If it is determined that the Japanese sentence of the user's answer does not contain a word from the Japanese question sentence, the user's answer does not match the intention, main point, or meaning of the question sentence, and therefore the user's answer can be evaluated as incorrect.

[0045] Another example of the evaluation of a user's answer is to refer to a thesaurus database for mismatched English words in the user's answer and the model answer. In this method, a thesaurus database is used to determine whether the mismatched English words in the user's answer and the model answer are similar. If they are similar, the meaning of the user's answer can be evaluated as matching the meaning of the question, and the user's answer can be evaluated as correct. If they are not similar, the user's answer can be evaluated as incorrect.

[0046] Using the above method, the processing unit of the assessment server 2 evaluates whether the user's answer is correct or not, and transmits the evaluation result information to the terminal 1 (S7). The terminal 1 obtains from the assessment server 2 the determination result of whether the user's answer matches the model answer, and the evaluation result of the user's answer when the user's answer does not match the model answer.

[0047] FIG. 4 shows a flowchart of the rating processing method by the rating server 2 in steps S5 to S7.

[0048] In the first case where it is determined in S11 that the user's answer matches the model answer sentence corresponding to the question sentence, the evaluation server 2 transmits to the terminal 1 first information indicating that the user's answer matches the model answer sentence, and ends the process (S12). In the first case, the terminal 1 acquires the first information indicating that the user's answer matches the model answer sentence, and displays on the screen of the display unit an indication that the user's answer matches the model answer sentence (S9). Specifically, a first image, which is an image indicating the correct answer and indicates the highest evaluation (first evaluation), is displayed on the GUI of the display unit. The first image may be an image of ◎, which is the highest evaluation symbol among the symbols ◎, ○, and ×, or a text image such as "perfect" or "perfect match."

[0049] In this way, in the first case, the terminal 1 performs a first display control to cause the display unit to display a first image indicating the correct answer and the first evaluation. The user can recognize that the user's answer is correct by looking at the screen of the display unit.

[0050] Furthermore, in the first case, the terminal 1 can also display the model answer sentence for the question sentence and the user's answer sentence on the GUI of the display unit. This makes it possible to confirm that the user's answer sentence completely matches the model answer sentence. The user's answer sentence and the model answer sentence can also be displayed simultaneously on the same screen. It is not essential to display the user's answer sentence and the model answer sentence, and it is also possible to display only one of them.

[0051] In a second case where the evaluation server 2 determines in S11 that the user's answer does not match the model answer sentence and evaluates in S13 that the user's answer sentence, which includes a portion different from the model answer sentence, is correct, it transmits second information indicating that the user's answer sentence does not match the model answer sentence but is correct to the terminal 1 and ends the process (S14). The terminal 1 obtains the second information in the second case and displays on the screen of the display unit an indication that the user's answer sentence does not match the model answer sentence but is correct (S9).

[0052] Specifically, the model answer to the question and the user's answer are displayed on the GUI of the display unit. Also, a second image, which is an image showing the correct answer and indicates a rating (second rating) lower than the first rating, is displayed on the GUI of the display unit. The second image may be an image of the symbol ○, which indicates a middle rating out of the symbols ◎, ○, and ×, or a text image such as "This expression is OK" or "It looks good." Also, the symbol △ may be used as the second image.

[0053] In addition, in the second case, the terminal 1 displays the user's answer sentence and the model answer sentence on the screen of the display unit (S8). In the second case, when the terminal 1 displays the user's answer sentence and the model answer sentence, it performs identification display to display the different parts of the user's answer sentence and the model answer sentence in a different manner from the same parts of the user's answer sentence and the model answer sentence. As different manners, for example, different colors, different thickness of characters, underlining, etc., can be used. In addition, for example, it is also possible to perform identification display such as changing the color so that words in the user's answer sentence that are not in the model answer sentence can be distinguished from words that are present in the model answer sentence. With this identification display, the user can easily visually confirm where the user's answer sentence differs from the model answer. The terminal 1 can also perform identification display regardless of whether the user's answer is in the second case or the evaluated user's answer sentence.

[0054] As the second image, a text image may be displayed together with the model answer, indicating that there is another way to express the model answer, or a text image may be displayed together with the model answer, pointing out an error in the user's answer.

[0055] In this way, in the second case, when the terminal 1 displays the user's answer sentence and the model answer sentence, the terminal 1 performs a second display control which causes the display unit to perform an identification display which shows different parts of the user's answer sentence and the model answer sentence in a manner different from that of the same parts of the user's answer sentence and the model answer sentence, and to display a second image which indicates the correct answer and a second rating which is lower than the first rating.

[0056] In addition, in the second case, the evaluation server 2 does not display the first image to be displayed on the display unit in the first case in which the answer sentence of the user and the model answer sentence match on the display unit. Furthermore, as a result of the evaluation server 2 receiving various user's answer sentences, regardless of the answer sentence of the user that is determined to correspond to the second case, the evaluation server 2 does not display the first image to be displayed on the display unit in the first case on the display unit. In other words, the first image to be displayed on the display unit in the first case is not displayed on the display unit regardless of the answer sentence of the user in the second case. It can also be expressed that the second display control does not perform display control to display the first image on the screen of the terminal 1 regardless of the answer sentence of the user. In addition, in the second case, the evaluation server 2 may perform display control to not display the first image to be displayed on the display unit in the first case on the display unit. The display control on the display unit of the terminal 1 performed in the second display control may not include display control to display the second image without identifying it. It is also possible that the first image displayed when the user's answer is determined to match the model answer and the second image displayed when the user's answer is evaluated to be correct will not be the same regardless of the user's answer.

[0057] By doing so, the user can distinguish and recognize whether the user's answer matches the model answer or whether it does not match but is still within the range that can be considered correct.

[0058] Furthermore, in the first case, in the first display control, the second image that is displayed in the second display control in the case where the user's answer sentence is either one of the two may not be displayed on the display unit. Also, in the first case, the evaluation server 2 may perform display control not to display on the display unit the second image that is displayed on the display unit in the second case. In the first case, if the user's answer sentence and the model answer sentence are displayed on the screen, the user can visually confirm that the user's answer sentence and the model answer sentence match, so even if there is confusion between the first image and the second image as the image displayed in the first case, the impact is relatively small.

[0059] In the first case where the user's answer text and the model answer text match, and the second case where the user's answer text and the model answer text do not match but are evaluated as correct, if one or more common images are used as images showing the evaluation result of the user's answer text, confusion will arise between cases where the user's answer text and the model answer text match and cases where they do not match, making it difficult to easily confirm whether or not they match.

[0060] Since there are many possible English expressions, users may enter a variety of answers. Therefore, if there are only one or two model answers for a question, if the user's answer does not match the model answer, it may reduce the user's satisfaction. This is even more so if a process is set up to allow the user to redo the incorrect question.

[0061] Therefore, if the user's answer does not match the model answer but is similar to the model answer or matches the meaning, intent, or gist of the original question text, it can be output and displayed as the correct answer, thereby improving the user's sense of satisfaction. Furthermore, by displaying the difference between the model answer and the user's answer so that the user can visually recognize it, the user can learn the difference or learn a different way of expression from the user's answer, thereby improving the learning effect.

[0062] In a third case where the evaluation server 2 determines in S11 that the user's answer does not match the model answer sentence, and evaluates in S14 that the user's answer sentence, which includes a portion different from the model answer sentence, is not correct, i.e., is incorrect, it transmits third information indicating that the user's answer sentence does not match the model answer sentence and is incorrect to the terminal 1, and ends the process (S15). The terminal 1 obtains the third information in the third case, and displays on the screen of the display unit a message indicating that the user's answer sentence does not match the model answer sentence and is incorrect (S9).

[0063] Specifically, a third image, which is an image showing an incorrect answer and indicates the lowest evaluation (third evaluation), is displayed on the GUI of the display unit. The third image may be an image of the symbol ×, which is the lowest evaluation symbol among the symbols ◎○×, or a text image of “incorrect answer.”

[0064] Also in the third case, the evaluation server 2 displays the user's answer sentence and the model answer sentence on the GUI of the display unit on the screen of the display unit. When displaying the user's answer sentence and the model answer sentence, a distinguishing display can be performed to show the different parts of the user's answer sentence and the model answer sentence in a different manner from the same parts of the user's answer sentence and the model answer sentence. As a different manner, for example, a different color, a different thickness of the letters, or underlining can be used. This distinguishing display allows the user to easily visually confirm how the user's answer sentence differs from the model answer.

[0065] Thus, in the third case, the terminal 1 performs a third display control that causes the display unit to perform the above-mentioned identification display and display a third image indicating an incorrect answer. By visually displaying the difference between the model answer and the user's answer, the user can learn the difference and learn a different way of expressing the answer from the user's, thereby improving the learning effect. In addition, when the terminal 1 determines that the user's answer does not match the model answer (in the second and third cases), it can also not display the first image on the display device regardless of the user's answer.

[0066] In addition, in the above display control, it is preferable to simultaneously display the user's answer sentence and the model answer sentence. It is preferable to divide the screen of the display unit into an area for displaying the image of the user's answer sentence and an area for displaying the image of the model answer sentence, arrange them above and below, and display them simultaneously on the same screen. In addition, when displaying the image of the user's answer sentence and the image of the model answer sentence, displaying them on the same screen without user operation such as tapping or clicking reduces the user's effort and improves visibility and operability.

[0067] As described above, the terminal 1 transmits information about the user's answer to the assessment server 2 in response to the user's input of the answer to the question, and requests the assessment server 2 to provide the result of the judgment or evaluation of the user's answer. The terminal 1 obtains the judgment or evaluation result of the user's answer from the assessment server 2, and performs any one of the above-mentioned first display control, second display control, or third display control in response to the result of the judgment or evaluation. This makes it possible to provide a user interface that allows the user to more easily understand the evaluation result of the answer. Furthermore, it is possible to increase the user's sense of satisfaction with the evaluation result of the user's answer.

[0068] After the user has completed answering one question and confirmed the evaluation result on the display screen, the user selects the next question to solve. The question can be selected by clicking or tapping a button on the GUI of terminal 1. The user uses terminal 1 to write an English composition for the next question, and the information processing system evaluates the user's answer for the next question in the same manner as described above. After confirming the evaluation result of the answer, the user can further select and answer the next question. In this way, the user learns by solving multiple questions one after another, and terminal 1 can evaluate the user's multiple answers and display the evaluation result on the display unit.

[0069] The terminal 1 may evaluate the multiple answer sentences given by the user for a group of multiple problem sentences at a predetermined level, display each evaluation result on the display unit, and then compile all the evaluation results and display them as a summary display on the display unit. The terminal 1 displays a selection button on the display unit for the user to re-study the questions that the user got wrong, and, depending on the user's selection, displays the questions that the user got wrong again on the display unit to encourage the user to answer them. When re-studying the questions that the user got wrong, the terminal 1 presents the questions that the user evaluated as incorrect, excluding the questions that the user evaluated as correct as in the first and second cases above.

[0070] In other words, when a user answers a number of questions, terminal 1 sets the question for which the first image is displayed in response to the user's answer and the question for which the second image is displayed in response to the user's answer as the question that the user answered correctly, and when the user re-answers a question that he or she answered incorrectly, terminal 1 causes the display device to display the question for which the third image is displayed in response to the user's answer.

[0071] <Example 1> A specific example of the GUI displayed on the display unit of the terminal 1 will be described. Figures 6, 7, and 8 show diagrams of the GUI of the first embodiment. Figure 6 shows a screen display in the first case where the user's answer and the model answer match, Figure 7 shows a screen display in the second case where the user's answer and the model answer do not match but are evaluated as correct, and Figure 8 shows a screen display in the third case where the user's answer and the model answer do not match and are evaluated as incorrect.

[0072] In the display screen M of the display unit shown in FIG. 6, a question is displayed in Japanese in an area M1. In the example of FIG. 6, the question is "What time are you going to arrive?". The user sees the question and speaks in English to the terminal 1 to translate the question into English. The terminal 1 acquires the voice information of the user's speech and transmits the voice information to the evaluation server 2. The evaluation server 2 converts the user's voice information into English text information and transmits the English text information to the terminal 1. The terminal 1 displays the English sentence uttered by the user in an area M3. In the example of FIG. 6, the user's speech is "What time are you going to arrive?". The terminal 1 also acquires a model answer sentence for the question sentence from the evaluation server 2 and displays the model answer sentence in an area M2. In the example of FIG. 6, the model answer sentence is "What time are you going to arrive?". In the example of FIG. 6, the user's answer sentence and the model answer sentence are displayed simultaneously, vertically adjacent to each other, on the same screen.

[0073] The evaluation server 2 judges whether the answer sentence of the user and the model answer sentence match. In the example of FIG. 6, the answer sentence of the user and the model answer sentence match. The evaluation server 2 transmits to the terminal 1 first information indicating that the answer sentence of the user and the model answer sentence match. In response to receiving the first information, the terminal 1 displays on the screen a first image which is an image indicating a correct answer and indicates a first evaluation (highest evaluation) indicating that the answer sentence of the user and the model answer sentence match. The first image is displayed in the area M4. In the example of FIG. 6, the area M4 is shown in green. The terminal 1 displays an image showing the symbol ◎ in the area M5 within the range of the area M4 as the first image, and displays a text image saying "Perfect!! Amazing!" in the area M6 within the range of the area M4. The terminal 1 displays an icon image "Next" for selecting the next question in the area M4.

[0074] FIG. 7 shows an example in which the answer sentence of the user is different from the example of FIG. 6, and the question sentence and the model answer sentence are the same as the example of FIG. 6. The terminal 1 displays the English sentence uttered by the user in the area M3. The terminal 1 displays the English sentence uttered by the user in the area M3. In the example of FIG. 7, the user's utterance is "When will you arrive?". The terminal 1 also acquires the model answer sentence for the question sentence from the evaluation server 2 and displays the model answer sentence in the area M2. The evaluation server 2 judges whether the answer sentence of the user and the model answer sentence match. In the example of FIG. 7, the answer sentence of the user and the model answer sentence do not match. Therefore, the evaluation server 2 evaluates whether the answer sentence of the user is correct as described in the above embodiment. The example of FIG. 7 is an example in which the answer sentence of the user is evaluated as correct. The evaluation server 2 transmits second information to the terminal 1 indicating that the answer sentence of the user and the model answer sentence do not match but the answer sentence of the user is correct. In response to receiving the second information, terminal 1 displays on the screen a second image indicating the correct answer and indicating a second rating that is lower than the highest first rating. The second image is displayed in area M4. In the example of FIG. 7, area M4 is shown in green. Terminal 1 displays, as the second image, an image showing the symbol ○ in area M5 within area M4, and a text image saying "Correct! This expression is OK too!" in area M6 within area M4.

[0075] In the example of Fig. 7, since the user's answer sentence and the model answer sentence do not match, when the user's answer sentence and the model answer sentence are displayed, the different part of the user's answer sentence and the model answer sentence, i.e., "When you" in the user's answer sentence, is displayed in a different manner from the same part of the user's answer sentence and the model answer sentence. In the example of Fig. 7, "When you" is displayed in gray and can be visually distinguished from other words displayed in black.

[0076] In the first embodiment, as in the screen of the example of Fig. 7, the image showing the symbol ◎, which is the first image shown in the example of Fig. 6, and the text image "Perfect!! Amazing!" are not displayed. In other words, these first images displayed on the screen in the above-mentioned first case are not displayed on the display unit regardless of the user's answer sentence in the second case. Furthermore, in the first display control in the first case, it is also possible not to display on the display unit the second image that is displayed in the second display control in the second case when the user's answer sentence is either one.

[0077] FIG. 8 shows an example in which the user's answer sentence is different from the examples in FIGS. 6 and 7, and the question sentence and the model answer sentence are the same as the examples in FIGS. 6 and 7. The terminal 1 displays the English sentence uttered by the user in the area M3. The terminal 1 displays the English sentence uttered by the user in the area M3. In the example in FIG. 8, the user's utterance is "When do you arrive?". The terminal 1 also acquires the model answer sentence for the question sentence from the evaluation server 2 and displays the model answer sentence in the area M2. The evaluation server 2 judges whether the user's answer sentence and the model answer sentence match. In the example in FIG. 8, the user's answer sentence and the model answer sentence do not match. Therefore, the evaluation server 2 evaluates whether the user's answer sentence is correct or not, as described in the above embodiment. The example in FIG. 8 is an example in which the user's answer sentence is evaluated as being incorrect. The evaluation server 2 transmits to the terminal 1 third information indicating that the user's answer sentence does not match the model answer sentence and that the user's answer sentence is incorrect. In response to receiving the third information, the terminal 1 displays on the screen a third image indicating an incorrect answer and indicating the lowest third evaluation. The third image is displayed in the area M4. In the example of FIG. 8, the area M4 is shown in red. The terminal 1 displays an image indicating a symbol × in the area M5 within the area M4 as the third image, and displays a text image saying "incorrect" in the area M6 within the area M4. In the example of FIG. 8, the terminal 1 performs an identification display to identify the difference between the user's answer sentence and the model answer sentence, as in the example of FIG. 7. In the example of FIG. 8, "When do" is displayed in gray and can be visually distinguished from other words displayed in black.

[0078] <Example 2> Next, Figures 9, 10, and 11 show diagrams of the GUI of Example 2. Figure 9 shows a screen display in the first case where the user's answer and the model answer match, Figure 10 shows a screen display in the second case where the user's answer and the model answer do not match but are evaluated as correct, and Figure 11 shows a screen display in the third case where the user's answer and the model answer do not match and are evaluated as incorrect.

[0079] In the display screen N of the display unit shown in FIG. 9, an assignment is displayed in an area N1, and a question sentence is displayed in Japanese in an area N2. In the example of FIG. 9, the question sentence is "Is that your phone?". The user sees the question sentence and speaks in English to the terminal 1 to translate the question sentence into English. The terminal 1 acquires voice information of the user's speech and transmits the voice information to the evaluation server 2. The evaluation server 2 converts the user's voice information into English text information and transmits the English text information to the terminal 1. The terminal 1 displays the English sentence spoken by the user in an area N3. In the example of FIG. 9, the user's speech is "Is that your phone". The evaluation server 2 judges whether the answer sentence of the user and the model answer sentence match. In the example of FIG. 9, the model answer sentence is "Is that your phone?", and it is an example in which it is judged that the answer sentence of the user and the model answer sentence match. The evaluation server 2 transmits to the terminal 1 first information indicating that the answer sentence of the user and the model answer sentence match. In response to receiving the first information, terminal 1 displays on the screen a first image which is an image indicating the correct answer and which indicates a first evaluation (highest evaluation) which indicates that the user's answer sentence matches the model answer sentence. The first image is displayed in area N4. In the example of FIG. 9, area N4 is shown in green. Terminal 1 displays, as the first image, an image indicating a check symbol in area N5 within area N4, and displays a text image saying "Perfect" in area N4. Terminal 1 displays an icon image "Next" for selecting the next question in area N4.

[0080] The terminal 1 also obtains model answers to the questions from the evaluation server 2. An area N6 in the area N4 shows icon images that the user can select, and when the user selects one, another screen N' is displayed, and the model answer is displayed in an area N7 of the other screen N'. The model answer and the question are also displayed in the area N7.

[0081] FIG. 10 shows an example in which the answer sentence of the user is different from the example in FIG. 9, and the question sentence and the model answer sentence are the same as the example in FIG. 9. The terminal 1 displays an English sentence uttered by the user in the area N3. In the example in FIG. 10, the user's utterance is "Is that your telephone". The evaluation server 2 judges whether the answer sentence of the user matches the model answer sentence. In the example in FIG. 10, the answer sentence of the user does not match the model answer sentence. Therefore, as described in the above embodiment, the evaluation server 2 evaluates whether the answer sentence of the user is correct or not. The example in FIG. 10 is an example in which the answer sentence of the user is evaluated as correct. The evaluation server 2 transmits second information to the terminal 1, which indicates that the answer sentence of the user does not match the model answer sentence, but the answer sentence of the user is correct. In response to receiving the second information, the terminal 1 displays on the screen a second image, which is an image indicating the correct answer and indicates a second evaluation lower than the highest first evaluation. The second image is displayed in the area N4. 10, region N4 is shown in green. Terminal 1 displays, as the second image, an image showing a check symbol in region N5 within the range of region N4, and displays a text image saying "Good job!" in region N4. Furthermore, when the user selects an icon image in area N6, terminal 1 displays another screen N' and displays the model answer sentence in area N7 of screen N'. In the example of FIG. 10, since the user's answer sentence and the model answer sentence do not match, when the user's answer sentence and the model answer sentence are displayed, a different part of the user's answer sentence and the model answer sentence, that is, the model answer "phone", is displayed in a different manner from the same part of the user's answer sentence and the model answer sentence. In the example of FIG. 10, the part "phone" is underlined, making it visually distinguishable from other words.

[0082] In the second embodiment, the character image "Perfect" shown in the example of Fig. 9, which is the first image, is not displayed as in the screen of the example of Fig. 10. In other words, the first image displayed on the screen in the above-mentioned first case is not displayed on the display unit regardless of the user's answer sentence in the second case. Furthermore, in the first display control in the first case, it is also possible not to display the second image displayed in the second display control in the second case when the user's answer sentence is either one.

[0083] FIG. 11 shows an example in which the answer sentence of the user is different from the examples of FIGS. 9 and 10, and the question sentence and the model answer sentence are the same as the examples of FIGS. 9 and 10. The terminal 1 displays an English sentence uttered by the user in the area N3. In the example of FIG. 11, the user's utterance is "Is this your phone". The evaluation server 2 judges whether the answer sentence of the user and the model answer sentence match. In the example of FIG. 11, the answer sentence of the user and the model answer sentence do not match. Therefore, as described in the above embodiment, the evaluation server 2 evaluates whether the answer sentence of the user is correct or not. The example of FIG. 11 is an example in which the answer sentence of the user is evaluated as being incorrect. The evaluation server 2 transmits third information indicating that the answer sentence of the user is incorrect to the terminal 1. In response to receiving the third information, the terminal 1 displays a third image on the screen, which is an image indicating an incorrect answer and indicates the lowest third evaluation. The third image is displayed in the area N4. In the example of FIG. 11, the area N4 is displayed in a red color. The terminal 1 displays an image showing a symbol × in the area N5 within the range of the area N4 as the third image, and displays a text image saying "incorrect" in the area N4. The terminal 1 also displays a model answer sentence in the area N4. In the example of FIG. 11, since the user's answer sentence and the model answer sentence do not match, when the user's answer sentence and the model answer sentence are displayed, a different part of the user's answer sentence and the model answer sentence, that is, "that" in the model answer, is displayed in a different manner from the same part of the user's answer sentence and the model answer sentence. In the example of FIG. 11, the part "that" is underlined and displayed in bold, so that it can be visually distinguished from other words. The terminal 1 can also display the model answer sentence in the area N7 of another screen N' by the user selecting the icon image in the area N6.

[0084] Although the preferred embodiments of the present disclosure have been described in detail above with reference to the accompanying drawings, the technical scope of the present disclosure is not limited to such examples. Furthermore, not all of the components shown in the embodiments are necessarily essential components of the present disclosure. Furthermore, the features shown in each embodiment can be applied to other embodiments as long as they are not mutually inconsistent.

[0085] The display control of the display unit described above can be performed by the terminal 1 in which a program is installed, or by transmitting and receiving information to and from other information processing devices via a network or cable. In addition, various information processes other than the display control, such as cloud services and distributed computers, can also be performed by one or more information processing devices in which a program is installed. In addition, the evaluation server 2 may be equipped with the function of an AI server.

[0086] The terminal 1 can also measure the time from when the question sentence is displayed on the display unit to when the user finishes speaking the answer. The terminal 1 may also display the evaluation result of the user's answer sentence on the display unit and the measured time on the display unit.

[0087] For example, when an image in which the user's answer is evaluated as correct or incorrect is displayed, there is a possibility that some users will think that the evaluation result is incorrect. Therefore, the terminal 1 may display the evaluation result of the user's answer on the display unit, and may also display a selection button for changing the evaluation result. In response to the selection button being selected by the user, the terminal 1 transmits information indicating that the evaluation result of the user's answer has been changed to the evaluation server 2, and the evaluation server 2 can store the information in memory or storage. The evaluation server 2 can also modify the model answer sentence stored in the model answer database based on the changed information.

Claims

1. A method for displaying on a display device an evaluation result of an answer sentence that a user has translated into another language for a question sentence to be translated, the method comprising: In response to the user's input of an answer to the question, a first display control that causes the display device to display a first image indicating a correct answer and a first evaluation of the answer sentence in a first case in which the information processing device determines that the answer sentence of the user matches a model answer sentence corresponding to the question sentence; a second display control that causes the display device to perform, when displaying the user's answer sentence and the model answer sentence, a distinguishing display that shows the different part of the user's answer sentence and the model answer sentence in a manner different from that of the same part of the user's answer sentence and the model answer sentence, and a second image that indicates a correct answer, is different from the first image, and shows a second evaluation of the answer sentence, in a second case in which the information processing device determines that the user's answer sentence does not match the model answer sentence and evaluates the user's answer sentence including a part different from the model answer sentence as being correct; a third display control that causes the display device to perform the identification display and display a third image indicating an incorrect answer when the information processing device evaluates the user's answer sentence, which includes a portion different from the model answer sentence, as being incorrect; and Do one of the following: The first image to be displayed on the display device in the first case is not displayed on the display device regardless of the answer sentence of the user in the second case, A method according to any one of claims 1 to 4, characterized in that the color of the display area of ​​the first image and the color of the display area of ​​the second image are the same.

2. The method described in claim 1, characterized in that the identification display includes a display in which, in displaying the user's answer sentence and the model answer sentence, the same parts of the user's answer sentence and the model answer sentence are shown in the same manner, and the different parts of the user's answer sentence and the model answer sentence are shown in different manners.

3. The method according to claim 1, characterized in that when it is determined that the user's answer sentence does not match the model answer sentence, the information processing device outputs an evaluation result of the user's answer sentence by comparing information of the question sentence with information on the meaning of the user's answer sentence.

4. The method according to claim 3, characterized in that the evaluation result is output based on information on the meaning of the user's answer sentence output by artificial intelligence.

5. The information on the meaning of the user's answer includes information translating the user's answer into a language of the question, 4. The method according to claim 3, wherein the evaluation result is output by comparing information on the question sentence with information obtained by translating the user's answer sentence into a language of the question sentence.

6. Each of the first image, the second image and the third image includes a symbol or a character; The method of claim 1 , wherein the two images include symbols or characters that are different from the symbols or characters of the first image.

7. The method of claim 1, characterized in that the second image includes the words "correct answer."

8. The method according to claim 1, characterized in that the identification display includes a display in which the parts of the user's answer sentence and the model answer sentence where they differ are displayed in different colors, or a display in which the parts of the user's answer sentence and the model answer sentence where they differ are underlined.

9. A program for causing a computer to execute the method according to any one of claims 1 to 8.

Images