Display method and program

Abstract

To provide a user interface that makes it easier for users to understand the evaluation results of their answers. [Solution] A method for displaying the evaluation result of a user's answer on a display device, wherein, in response to the user's input of an answer, the first display control is performed to display a first image indicating the correct answer and a first evaluation in the first case where it is determined that the user's answer matches the model answer; the second display control is performed to display an identification display that identifies the parts that differ between the user's answer and the model answer, and a second image indicating the correct answer and a second evaluation lower than the first evaluation in the second case where the user's answer does not match the model answer but is evaluated as correct; and the third display control is performed to display an identification display and a third image indicating an incorrect answer in the third case where the user's answer, which includes parts that differ from the model answer, is evaluated as not correct.

Description

Technical Field

[0001] The present invention relates to a method and a program for causing a display device to display an evaluation result obtained by evaluating a user's translated answer sentence for a problem sentence.

Background Art

[0002] In recent years, software applications for English learning training have been provided to instantaneously translate Japanese presented as a problem sentence into English. By repeating this training, it is possible to increase the speed of drawing out English knowledge and efficiently improve the instant power of speaking.

[0003] Patent Document 1 discloses a method of evaluating the answers of learners to language problems by artificial intelligence, although it is not a training problem of translating Japanese sentences into English. The specific disclosure is as follows. The artificial intelligence determines the degree of approximation between the meaning of the learner's answer and the meanings of multiple model answers. After the learner answers, the learner's answer is judged by operating the "judgment" button. When it is judged that the answer is the most appropriate, all three star marks are displayed in a bright state. Next, when it is judged that the answer is appropriate, two star marks are displayed in a bright state. When it is judged that the answer is appropriate to some extent, one star mark is displayed in a bright state. When it is judged that the answer is inappropriate, all star marks are not displayed in a bright state. When the degree of approximation between the meaning of the learner's answer and the meaning of the model answer is 80%, all three star marks are displayed in a bright state. [[ID= seventeen]]

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] In the method described in Patent Document 1, if the student's answer and the model answer do not match, the difference between the student's answer and the model answer is not displayed, making it impossible to recognize the difference. Furthermore, the same three star symbols are displayed in a bright manner whether the student's answer and the model answer are perfectly identical or the degree of similarity between the meaning of the student's answer and the meaning of the model answer is 80%, making it impossible to recognize the difference between the two cases.

[0006] Because there are numerous English expressions, it is difficult to prepare all possible model answers for training exercises that require translating Japanese sentences into English, using an application designed for this purpose. Therefore, the system will compare the user's answer to a limited number of model answers. However, the challenge lies in how to evaluate the user's answer and what evaluation results to display when the answer is similar to the model answer, even if it does not exactly match it.

[0007] Therefore, the present invention aims to provide a user interface that allows users to more easily understand the evaluation results of their answers. [Means for solving the problem]

[0008] One aspect of the present invention for solving the above problems is a method for displaying an evaluation result obtained by an information processing device from an answer text translated into another language by a user in response to a problem text to be translated, the method comprising: first display control, in response to the input of the user's answer text to the problem text, in the first case in which the information processing device determines that the user's answer text matches the model answer text corresponding to the problem text, the display of a first image indicating the correct answer and the first evaluation; and second case in which the information processing device determines that the user's answer text does not match the model answer text and evaluates the user's answer text, which includes parts different from the model answer text, as correct, the user's answer text and the model answer text The information processing device performs one of the following: a second display control that causes the display device to perform an identification display that shows the parts of the user's answer that differ from the model answer in a different manner from the parts of the user's answer that are the same; and a second image that shows the correct answer and a second evaluation lower than the first evaluation when displaying the answer; and a third display control that causes the display device to perform the identification display and a third image that shows the incorrect answer when the information processing device evaluates that the user's answer, which includes parts that differ from the model answer, is not correct, wherein the first image that is displayed on the display device in the first case is not displayed on the display device in the second case, regardless of what the user's answer is. [Effects of the Invention]

[0009] According to the present invention, it is possible to provide a user interface that allows users to more easily understand the evaluation results of their answers. [Brief explanation of the drawing]

[0010] [Figure 1] A diagram showing the configuration of an information processing system. [Figure 2] A diagram showing the configuration of an information processing terminal. [Figure 3] A flowchart illustrating how to display the evaluation results of the user's answer on the display unit. [Figure 4]A flowchart illustrating the evaluation method for user responses. [Figure 5] A diagram showing the relationship between the transmission and reception of information between each information processing device. [Figure 6] A diagram showing the GUI of Example 1. [Figure 7] A diagram showing the GUI of Example 1. [Figure 8] A diagram showing the GUI of Example 1. [Figure 9] A diagram showing the GUI of Example 2. [Figure 10] A diagram showing the GUI of Example 2. [Figure 11] A diagram showing the GUI of Example 2. [Modes for carrying out the invention]

[0011] The embodiments of the present invention will be described by listing them. The present invention has, for example, the following configuration.

[0012] [Item 1] A method for displaying evaluation results on a display device, which is obtained by an information processing device from an evaluation of an answer text translated by a user into another language for a problem text to be translated, In response to the user's input of the answer to the aforementioned problem statement, In the first case where the information processing device determines that the user's answer matches the model answer corresponding to the problem statement, a first display control is performed to cause the display device to display a first image indicating the correct answer and a first evaluation. In the second case where the information processing device determines that the user's answer does not match the model answer and evaluates the user's answer, which includes parts that differ from the model answer, as correct, the second display control causes the display device to perform the following actions when displaying the user's answer and the model answer: an identification display that shows the parts that differ between the user's answer and the model answer in a manner different from the parts that are the same between the user's answer and the model answer; and a second image that indicates the correct answer and shows a second evaluation lower than the first evaluation. In a third case where the information processing device evaluates that the user's answer sentence including a part different from the model answer sentence is incorrect, a third display control for causing the display device to perform the identification display and display a third image indicating an incorrect answer. Perform any 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 user's answer sentence in the second case. A method characterized by this. [Item 2] The method according to item 1, characterized in that the identification display is performed so that a word not present in the model answer sentence in the user's answer sentence can be identified from a word present in the model answer sentence. [Item 3] 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 the information of the problem sentence and the semantic information of the user's answer sentence. The method according to item 1 or 2, characterized by this. [Item 4] The method according to item 3, characterized in that the evaluation result is output based on the semantic information of the user's answer sentence output by artificial intelligence. [Item 5]<照 A program for causing a computer to execute the method according to any one of items 1 to 4.

[0013] <Details of the embodiment> FIG. 1 shows a configuration diagram of an information processing system in the present embodiment. This system includes 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 by a network 4. <照

[0014] Information processing terminal 1 has software and applications installed that present the user with a text expressed in a predetermined language as a problem statement, and the user translates this problem statement into another language as part of a learning training program. This program is installed by downloading it from a server connected to information processing terminal 1 via network 4. Information processing terminal 1 obtains the user's translated answer information and transmits this information to evaluation server 2 via network 4.

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

[0016] AI Server 3 inputs information about the user's answer into a machine learning model, such as a pre-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 Evaluation Server 2 via Network 4.

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

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

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

[0020] The processing unit 11 is a computing device that controls the operation of the entire information processing terminal 1, controls the transmission and reception of data between each part, and performs information processing necessary for program execution and authentication processing. The processing unit 11 includes a computing device such as a CPU, GPU, or FPGA, and executes programs stored in the storage 13 and loaded into the memory 12 to perform various information processing described later.

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

[0022] Storage 13 (storage medium) stores various programs such as applications and other programs. A database containing data used for each process is built on storage 13.

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

[0024] The display unit (display device) 16 includes a display that shows information calculated by the processing unit 11 or information received from an external source 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 integrated with the information processing terminal 1, but may also be a display (display device) provided separately from the information processing terminal 1 and connected to the information processing terminal 1.

[0025] Bus 17 is connected in common to all of the above components and transmits, for example, address signals, data signals, and various control signals.

[0026] Next, the configuration of the evaluation server 2 will be described. The evaluation server 2 has a processing unit, memory (storage unit), storage (storage medium), and communication unit. These are electrically connected to each other via a bus. The processing unit is a computing device that controls the operation of the entire evaluation server 2, 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 computing device such as a CPU, GPU, or FPGA, and executes programs stored in storage and loaded into memory to perform various information processing described later.

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

[0028] Next, the configuration of AI Server 3 will be described. AI Server 3 has a processing unit, memory (storage unit), storage (storage medium), and communication unit. These are electrically connected to each other via a bus. The processing unit is a computing 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 computing device such as a CPU, GPU, or FPGA, and executes programs stored in storage and loaded into memory to perform various information processing described later.

[0029] The storage of AI Server 3 stores various programs such as applications and other programs. A database containing data used for each process is built in this storage. Machine learning models, such as trained large-scale language models, are stored and remembered in the storage or memory. The communication unit connects AI Server 3 to Network 4. This communication unit receives information transmitted from Information Processing Terminal 1 or Evaluation Server 2 via Network 4. The received information is stored in memory and used for information processing performed by the processing unit, or stored in storage.

[0030] Next, we will explain how to use the above-described information processing system to display the evaluation results on a display device, which are obtained by the evaluation server 2 from the user's translated answer text into another language for the question text to be translated.

[0031] The information processing terminal 1 executes a method to display the evaluation results on the display device, which are obtained by the evaluation server 2 from the user's translated answer to the question text to be translated. Specifically, in response to the user's input of an answer to a question text, the information processing terminal 1 performs one of the following three display controls on the display device. The display control includes: a first display control that causes the display device to display a first image indicating the correct answer and a first evaluation when the evaluation server 2 determines that the user's answer matches the model answer corresponding to the question; a second display control that causes the display device to display an identification display that shows the differences between the user's answer and the model answer in a different manner from the same parts of the user's answer and the model answer when the evaluation server 2 determines that the user's answer does not match the model answer and evaluates the user's answer, which includes parts that differ from the model answer, as correct when the evaluation server 2 displays the user's answer and the model answer, as well as a second image indicating the correct answer and a second evaluation lower than the first evaluation when the evaluation server 2 evaluates the user's answer, which includes parts that differ from the model answer, as incorrect when the evaluation server 2 displays an identification display and a third image indicating an incorrect answer. In the first case, the first image displayed on the display device will not be displayed on the display device in the second case, regardless of the user's answer.

[0032] The information processing system as a whole employs an evaluation method that assesses the user's translated answer text into another language in response to the problem text to be translated. Specifically, the process involves the steps of: displaying the question on the user's device screen; the device transmitting information about the user's answer to the question and the question itself to the information processing device; the information processing device acquiring the information about the question and the user's answer to the question; the information processing device determining whether the user's answer matches the model answer corresponding to the question; if the information processing device determines that the user's answer matches the model answer, it transmits a first piece of information to the device indicating that the user's answer matches the model answer; if the device acquires the first piece of information, it performs a first display step, which involves displaying the user's answer and the model answer, as well as the first image showing the highest evaluation among three images indicating the evaluation results, on the device screen; and if the information processing device determines that the user's answer does not match the model answer, it evaluates the user's answer, including the parts that differ from the model answer. The steps to be performed include: if the evaluation result determines that the user's answer is correct, the information processing device sends second information to the terminal indicating that the user's answer does not match the model answer but is correct; if the terminal has received the second information, the terminal displays an identification display on the terminal screen to allow the user to identify the differences between the user's answer and the model answer, and a second image showing the second evaluation out of three images showing the evaluation results (indicating that the user's answer does not match the model answer but is correct); and if the evaluation result determines that the user's answer is incorrect, the information processing device sends third information to the terminal indicating that the user's answer is incorrect; and if the terminal has received the third information, the terminal displays an identification display and a third image showing the lowest evaluation out of three images showing the evaluation results (indicating that the user's answer is incorrect) on the terminal screen.

[0033] This section describes a specific method for displaying the evaluation results of the user's answers on a display device. Figure 3 shows a flowchart of this method. Figure 5 shows the relationship between the transmission and reception of information between each information processing device. The information processing described below is performed by executing programs implemented on terminal 1, evaluation server 2, and AI server 3.

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

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

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

[0037] The user views the Japanese problem statement to be translated displayed on the display unit 16, considers an appropriate English translation, and answers the problem statement by inputting the translated English sentence into terminal 1. The user may input the answer into terminal 1 by speaking into the microphone, or by typing on the touch panel or keyboard of the display unit 16. If the user inputs the answer by speaking, the input voice information is converted into text information. This conversion process may be performed by the processing unit 11, or by an evaluation server 2 or other server (external information processing device) other than terminal 1 after acquiring the voice information from terminal 1. If an information processing device other than terminal 1 performs the above conversion process, the converted text information is sent to terminal 1. In this way, the processing unit 11 acquires the English sentence translated by the user as the user's answer (S2). Terminal 1 sends the user's answer information to the evaluation server 2 and requests the evaluation server 2 to evaluate the user's answer.

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

[0039] The storage of evaluation server 2 stores a database of model answers. Model answers are pre-prepared answers that are set as the optimal answer for a corresponding problem. The processing unit of evaluation server 2 retrieves information on the model answer corresponding to the problem statement obtained from terminal 1 from the model answer database stored in storage (S4). The model answer database may have one or more model answer statements registered for a single problem, but in this embodiment, an example in which one model answer statement is registered for a single problem statement 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). Based on the information of the user's answer obtained from terminal 1, the processing unit of evaluation server 2 compares the user's answer, which has been translated into English, with the model answer corresponding to the question answered by the user. In this comparison, for example, it determines whether the English words in the English model answer are identical to the English words in the user's answer, starting from the beginning. If the English words are exactly the same from beginning to end, the processing unit determines that the user's answer and the model answer match. If there are different English words from beginning to end, or if there are the same English words but in a different order, the processing unit determines that the user's answer and the model answer do not match. As described above, the processing unit of evaluation server 2 determines whether the user's answer and the model answer match and sends the information of the determination result to terminal 1.

[0041] If the processing unit of 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 assesses whether the meaning of the user's answer is consistent with the intent, main point, or meaning of the question.

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

[0043] The processing unit of evaluation server 2 then determines whether or not information from the question text is present in the semantic information of the user's answer. For example, it determines whether or not there are words from the Japanese question text in the Japanese sentence that represents the meaning of the user's answer. If it determines that there are words from the Japanese question text in the Japanese sentence that represents the meaning of the user's answer, the user's answer can be evaluated as correct because it matches the intent, main point, or meaning of the question text. If it determines that there are no words from the Japanese question text in the Japanese sentence that represents the meaning of the user's answer, the user's answer can be evaluated as incorrect because it does not match the intent, main point, or meaning of the question text. Furthermore, evaluation server 2 may send a question to AI server 3 asking about the meaning of the question text, obtain semantic information of the question text, and compare the meaning of the question text with the meaning of the user's answer.

[0044] Another example of evaluating user responses is translating the user's English response into Japanese. In this method, the evaluation server 2 sends information about the user's response to the translation server, which then translates the English response into Japanese. The translated Japanese response is then sent back to the evaluation server 2, which evaluates whether the meaning of the translated Japanese response matches the intent, main point, or meaning of the question. For example, it determines whether the Japanese response contains words from the Japanese question. If it determines that the Japanese response contains words from the Japanese question, the response matches the intent, main point, or meaning of the question, and the user's response can be evaluated as correct. If it determines that the Japanese response does not contain words from the Japanese question, the response does not match the intent, main point, or meaning of the question, and the user's response can be evaluated as incorrect.

[0045] Another method for evaluating user responses involves referring to a thesaurus database for words in the user's response that do not match those in the model answer. This method uses the thesaurus database to determine if the mismatched words are similar. If they are similar, the meaning of the user's response is considered to match the meaning of the question, and the user's response can be evaluated as correct. If they are not similar, the user's response can be evaluated as incorrect.

[0046] Using the method described above, the processing unit of the evaluation server 2 evaluates whether the user's answer is correct or not, and sends the evaluation result information to terminal 1 (S7). Terminal 1 receives from the evaluation server 2 the result of determining whether the user's answer matches the model answer, and the evaluation result of the user's answer if it does not match the model answer.

[0047] Figure 4 shows a flowchart illustrating the evaluation process performed by the evaluation server 2 in S5-S7.

[0048] In S11, if the evaluation server 2 determines that the user's answer matches the model answer corresponding to the question (Case 1), it sends a first piece of information indicating that the user's answer matches the model answer to terminal 1 and terminates processing (S12). In Case 1, terminal 1 obtains the first piece of information indicating that the user's answer matches the model answer and displays on the display unit screen that the user's answer matches the model answer (S9). Specifically, it displays a first image on the GUI of the display unit that represents the correct answer and shows the highest evaluation (first evaluation). The first image may be an image of ◎, the symbol with the highest evaluation among the symbols ◎○×, or a text image such as "Perfect" or "Exact Match".

[0049] Thus, in the first case, terminal 1 performs a first display control that causes the display unit to display a first image indicating the correct answer and the first evaluation. The user can recognize that their answer is correct by looking at the screen of the display unit.

[0050] Furthermore, in the first case, terminal 1 can also display the model answer to the question and the user's answer on the GUI of the display unit. This allows the user to confirm that their answer perfectly matches the model answer. Note that the user's answer and the model answer can also be displayed simultaneously on the same screen. Displaying both the user's answer and the model answer is not mandatory; displaying only one of them is also acceptable.

[0051] In the second case, where in S11 the evaluation server 2 determines that the user's answer does not match the model answer and in S13 the evaluation server 2 evaluates the user's answer, which includes parts that differ from the model answer, as correct, it sends second information to terminal 1 indicating that although the user's answer does not match the model answer, the user's answer is correct, and terminates the process (S14). Terminal 1 receives the second information in the second case and displays on the display screen that the user's answer does not match the model answer, but the user's answer is correct (S9).

[0052] Specifically, the GUI displays both the model answer to the problem statement and the user's answer. Additionally, a second image representing a correct answer, but with a lower rating than the first rating (second rating), is displayed on the GUI. This second image could be the symbol ○ (representing a medium rating) from the symbols ◎○×, or it could be a text image such as "This expression is OK" or "Looks good." Alternatively, the symbol △ could be used as the second image.

[0053] Furthermore, in the second case, terminal 1 displays the user's answer and the model answer on the display screen (S8). In the second case, when terminal 1 displays the user's answer and the model answer, it provides identification markings to indicate the differences between the user's answer and the model answer in a different manner than the similar parts of the user's answer and the model answer. Different mannerings include, for example, using different colors, changing the font weight, or adding underlines. Also, for example, it is possible to provide identification markings such as changing the color of words in the user's answer that are not present in the model answer so that they can be distinguished from words that are present in the model answer. This identification marking allows the user to easily visually confirm where their answer differs from the model answer. Terminal 1 can also be configured to provide identification markings regardless of whether the user's answer is in the second case or the user's answer has been evaluated as such.

[0054] The second image may include a text image showing the model answer along with an alternative expression for the model answer, or a text image showing the model answer along with an indication of flaws in the user's answer.

[0055] Thus, in the second case, terminal 1 performs a second display control that causes the display unit to perform an identification display that shows the differences between the user's answer and the model answer in a manner different from the similar parts of the user's answer and the model answer, and a second image that shows the correct answer and a second evaluation lower than the first evaluation.

[0056] Furthermore, in the second case, evaluation server 2 does not display the first image on the display unit that would be displayed in the first case where the user's answer matches the model answer. In addition, if evaluation server 2 receives various user answers and determines that a user's answer falls under the second case, evaluation server 2 does not display the first image that would be displayed on the display unit in the first case, regardless of the user's answer. In other words, the first image that would be displayed on the display unit in the first case is not displayed on the display unit in the second case, regardless of the user's answer. This can also be expressed as: in the second display control, no display control is performed to display the first image on the screen of terminal 1, regardless of the user's answer. Also, evaluation server 2 may perform display control in the second case that does not display the first image that would be displayed on the display unit in the first case. The display control performed on the display unit of terminal 1 in the second display control may also not include display control that displays the second image without identification display. It is also possible to ensure 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 as correct, are never the same, regardless of the user's answer.

[0057] By doing so, users can distinguish and recognize whether their answer matches the model answer, or whether it does not match but falls within the range that can be considered correct.

[0058] Furthermore, in the first case, the first display control may choose not to display the second image on the display unit, which in the second case, the second display control would display if the user's answer is correct. Also, the evaluation server 2 may perform display control in the first case that prevents the display unit from displaying the second image that would be displayed in the second case. In the first case, if the user's answer and the model answer are displayed on the screen, the user can visually confirm that their answer and the model answer match, so even if there is confusion between the first image and the second image as the images displayed in the first case, the impact is relatively small.

[0059] If the same one or more images are used to represent the evaluation result of the user's answer in both the first case, where the user's answer matches the model answer, and the second case, where the user's answer does not match the model answer but is still evaluated as correct, confusion will arise between cases where the user's answer matches the model answer and cases where it does not, making it difficult to easily verify whether or not they match.

[0060] Since there can be numerous English expressions, users may submit a variety of answers. Therefore, if there are only one or two model answers set for a single question, marking every user's answer that does not match the model answer as incorrect may reduce user satisfaction. This is especially true if a process is set up to allow users to retry incorrect answers.

[0061] Therefore, by outputting and displaying a user's answer as correct if it does not exactly match the model answer but is similar to the model answer or matches the meaning, intent, or main point of the original question, it is possible to improve user satisfaction. Furthermore, by displaying the differences between the model answer and the user's answer in a way that allows users to visually recognize the differences and learn alternative ways of expressing their answers, the learning effect can be enhanced.

[0062] In the third case, where the evaluation server 2 determines in S11 that the user's answer does not match the model answer and evaluates in S14 that the user's answer, which contains parts that differ from the model answer, is not correct, i.e., incorrect, it sends third information to terminal 1 indicating that the user's answer does not match the model answer and that the user's answer is incorrect, and terminates processing (S15). Terminal 1 receives the third information in the third case and displays on the display screen that the user's answer does not match the model answer and that the user's answer is incorrect (S9).

[0063] Specifically, the GUI of the display unit will show a third image that represents an incorrect answer and indicates the lowest evaluation (third evaluation). The third image may be an image of the symbol ×, which has the lowest evaluation among the symbols ◎○×, or an image of the text "Incorrect".

[0064] Furthermore, in the third case as well, the evaluation server 2 displays the user's answer and the model answer on the display unit's screen using the display unit's GUI. When displaying the user's answer and the model answer, the server can provide identification markings to highlight the differences between the user's answer and the model answer in a different manner than the similar parts of the user's answer and the model answer. These different manners could include, for example, using different colors, changing the font weight, or adding underlines. This identification marking allows the user to easily visually confirm where their answer differs from the model answer.

[0065] Thus, in the third case, terminal 1 performs a third display control that causes the display unit to display the identification display described above and the 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 or learn alternative ways of expressing the answer, thereby enhancing the learning effect. Furthermore, if terminal 1 determines that the user's answer does not match the model answer (in the second and third cases), it can also choose not to display the first image on the display device, regardless of which answer the user has submitted.

[0066] Furthermore, in the display control described above, it is preferable to display the user's answer and the model answer simultaneously. Within the screen area of ​​the display unit, it is preferable to divide the area for displaying the user's answer image and the area for displaying the model answer image, arrange them vertically, and display them simultaneously on the same screen. Also, when displaying the user's answer image and the model answer image, displaying them on the same screen without any user operation such as tapping or clicking reduces the effort required from the user and improves visibility and ease of use.

[0067] As described above, terminal 1 transmits information of the user's answer to the problem statement to evaluation server 2 and requests evaluation results of the user's answer from evaluation server 2. Terminal 1 obtains the evaluation results of the user's answer from evaluation server 2 and performs one of the first, second, or third display controls described above according to the evaluation results. This provides a user interface that makes it easier for the user to understand the evaluation results of their answer. Furthermore, it can increase the user's satisfaction with the evaluation results of their answer.

[0068] After completing an answer to one problem statement and checking the evaluation result on the display screen, the user selects the next problem to solve. Problem selection can be done by clicking or tapping a button on the GUI of terminal 1. The user uses terminal 1 to compose an English sentence for the next problem statement, and the information processing system evaluates the user's answer statement in the same manner as described above. After checking the evaluation result of the answer, the user can select and answer yet another problem. In this way, the user learns by solving multiple problems in succession, and terminal 1 can evaluate the user's multiple answers and display the evaluation results on the display unit.

[0069] Terminal 1 evaluates multiple user answers to a set of multiple questions at a predetermined level, displays the individual evaluation results on the display unit, and may then display all evaluation results together as a summary on the display unit. Terminal 1 displays a selection button on the display unit for the user to relearn the questions they answered incorrectly, and, based on the user's selection, displays the incorrectly answered questions again on the display unit and prompts the user to answer them. When the user relearns the questions they answered incorrectly, as in the first and second cases described above, questions that the user's answer was evaluated as correct are excluded, and only questions that were evaluated as incorrect are presented.

[0070] In other words, terminal 1 sets the question sentences for which the user displayed the first image and the second image in response to the user's answer as the question sentences the user answered correctly, and when the user answers an incorrect question sentence again, it displays the question sentence for which the user displayed the third image in response to the user's answer on the display device.

[0071] <Example 1> This section describes specific examples of GUIs displayed on the display unit of terminal 1. Figures 6, 7, and 8 show diagrams of the GUI for Example 1. Figure 6 shows the screen display for the first case where the user's answer and the model answer match, Figure 7 shows the screen display for the second case where the user's answer and the model answer do not match, but the answer is evaluated as correct, and Figure 8 shows the screen display for the third case where the user's answer and the model answer do not match and the answer is evaluated as incorrect.

[0072] In the display screen M of the display unit shown in Figure 6, the question is displayed in Japanese in area M1. In the example in Figure 6, the question is, "What time are you planning to arrive?" The user sees this question and speaks to terminal 1 in English to have it translated into English. Terminal 1 acquires the audio information of the user's speech and sends it to evaluation server 2. Evaluation server 2 converts the user's audio information into English text and sends the English text to terminal 1. Terminal 1 displays the English sentence spoken by the user in area M3. In the example in Figure 6, the user's speech is, "What time are you going to arrive?" Terminal 1 also acquires a model answer to the question from evaluation server 2 and displays the model answer in area M2. In the example in Figure 6, the model answer is, "What time are you going to arrive?" In the example in Figure 6, the user's answer and the model answer are displayed simultaneously, side by side, one above the other, on the same screen.

[0073] The evaluation server 2 determines whether the user's answer matches the model answer. In the example in Figure 6, the user's answer matches the model answer. The evaluation server 2 sends first information to terminal 1 indicating that the user's answer matches the model answer. Upon receiving the first information, terminal 1 displays a first image on its screen, which is an image representing the correct answer and indicates the first evaluation (highest evaluation) that the user's answer matches the model answer. The first image is displayed in area M4. In the example in Figure 6, area M4 is shown in green. As the first image, terminal 1 displays an image showing the symbol ◎ in area M5 within the range of area M4, and displays the text image "Perfect!! Amazing!" in area M6 within the range of area M4. Terminal 1 displays the icon image "Next" in area M4 for selecting the next question.

[0074] Figure 7 shows an example where the user's answer differs from the example in Figure 6, although the question and model answer are the same as in Figure 6. Terminal 1 displays the English sentence spoken by the user in area M3. In the example in Figure 7, the user's utterance is "When will you arrive?". Terminal 1 also obtains the model answer for the question from evaluation server 2 and displays the model answer in area M2. Evaluation server 2 determines whether the user's answer and the model answer match. In the example in Figure 7, the user's answer and the model answer do not match. Therefore, evaluation server 2 evaluates whether the user's answer is correct, as explained in the above embodiment. In the example in Figure 7, the evaluation server 2 evaluates whether the user's answer is correct. In response to receiving the second information, terminal 1 displays a second image on its screen that represents the correct answer and has a second evaluation lower than the highest first evaluation. The second image is displayed in region M4. In the example in Figure 7, region M4 is shown in green. As the second image, terminal 1 displays an image representing the symbol ○ in region M5, which is within the range of region M4, and displays a text image that says "Correct! This expression is also OK!" in region M6, which is within the range of region M4.

[0075] In the example in Figure 7, since the user's answer and the model answer do not match, when displaying the user's answer and the model answer, the differing part of the user's answer and the model answer, namely "When you" in the user's answer, is highlighted in a different way than the identical part of the user's answer and the model answer. In the example in Figure 7, "When you" is displayed in gray, making it visually distinguishable from the other words displayed in black.

[0076] In Example 1, as shown in the example screen in Figure 7, the first image shown in the example in Figure 6, which is the image showing the symbol ◎ and the text image "Perfect!! Amazing!", is not displayed. In other words, these first images, which are displayed on the screen in the first case described above, are not displayed on the display unit in the second case, regardless of the user's answer. Furthermore, in the first case, the first display control can also prevent the display unit from showing the second image, which is displayed in the second display control in the second case depending on the user's answer.

[0077] Figure 8 shows an example where the user's response differs from the examples in Figures 6 and 7, although the question and model answer are the same as in Figures 6 and 7. Terminal 1 displays the English sentence spoken by the user in area M3. In the example in Figure 8, the user's utterance is "When do you arrive?". Terminal 1 also obtains the model answer for the question from evaluation server 2 and displays the model answer in area M2. Evaluation server 2 determines whether the user's response matches the model answer. In the example in Figure 8, the user's response does not match the model answer. Therefore, as explained in the above embodiment, evaluation server 2 evaluates whether the user's response is correct or not. Figure 8 is an example where the user's response is evaluated as incorrect. The evaluation server 2 sends third information to terminal 1 indicating that the user's answer does not match the model answer and that the user's answer is incorrect. Upon receiving the third information, terminal 1 displays a third image on its screen that indicates an incorrect answer and represents the lowest possible third evaluation. The third image is displayed in area M4. In the example in Figure 8, area M4 is shown in red. As the third image, terminal 1 displays an image showing the symbol × in area M5 within the range of area M4, and displays the text image "Incorrect" in area M6 within the range of area M4. In the example in Figure 8, as in the example in Figure 7, terminal 1 also performs identification displays to identify the difference between the user's answer and the model answer. In the example in Figure 8, "When do" is displayed in gray, making it visually distinguishable from the other words displayed in black.

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

[0079] In the display screen N of the display unit shown in Figure 9, the task is displayed in area N1, and the problem statement is displayed in Japanese in area N2. In the example in Figure 9, the problem statement is, "Is that your phone?" The user sees this problem statement and speaks to terminal 1 in English to have the problem statement translated into English. Terminal 1 acquires the audio information of the user's speech and sends the audio information to evaluation server 2. Evaluation server 2 converts the user's audio information into English text information and sends the English text information to terminal 1. Terminal 1 displays the English sentence spoken by the user in area N3. In the example in Figure 9, the user's speech is, "Is that your phone." Evaluation server 2 determines whether the user's answer matches the model answer. In the example in Figure 9, the model answer is "Is that your phone?", and it is determined that the user's answer matches the model answer. Evaluation server 2 sends first information to terminal 1 indicating that the user's answer matches the model answer. In response to receiving the first information, terminal 1 displays a first image on its screen that represents the correct answer and indicates the first evaluation (highest evaluation) that the user's answer matches the model answer. The first image is displayed in region N4. In the example in Figure 9, region N4 is shown in green. As the first image, terminal 1 displays an image showing a check mark in region N5, which is within the range of region N4, and displays the text image "Perfect" in region N4. Terminal 1 also displays the icon image "Next" in region N4 for selecting the next question.

[0080] Terminal 1 also obtains model answers to the questions from evaluation server 2. Area N6 within area N4 displays icon images that the user can select. When the user selects an icon, another screen N' is displayed, and the model answer is displayed in area N7 of that other screen N'. In addition, the question is displayed simultaneously in area N7 along with the model answer.

[0081] Figure 10 shows an example where the user's answer differs from the example in Figure 9, although the question and model answer are the same as in Figure 9. Terminal 1 displays the English sentence spoken by the user in area N3. In the example in Figure 10, the user's utterance is "Is that your telephone." Evaluation server 2 determines whether the user's answer matches the model answer. In the example in Figure 10, the user's answer does not match the model answer. Therefore, as explained in the above embodiment, evaluation server 2 evaluates whether the user's answer is correct. In the example in Figure 10, evaluation server 2 evaluates whether the user's answer is correct. Evaluation server 2 sends second information to terminal 1 indicating that the user's answer is correct, even though the user's answer does not match the model answer. In response to receiving the second information, terminal 1 displays a second image on the screen, which is an image indicating the correct answer and has a second evaluation lower than the highest first evaluation. The second image is displayed in area N4. In the example in Figure 10, region N4 is shown in green. Terminal 1 displays an image showing a check symbol in region N5, which is within the range of region N4, as a second image, and displays the text image "You did it!" in region N4. Furthermore, terminal 1 displays another screen N' when the user selects an icon image in area N6, and displays a model answer in area N7 of screen N'. In the example in Figure 10, since the user's answer and the model answer do not match, when displaying the user's answer and the model answer, the differing parts of the user's answer and the model answer, namely "phone" in the model answer, are indicated in a different manner from the identical parts of the user's answer and the model answer. In the example in Figure 10, the "phone" part is underlined, making it visually distinguishable from other words.

[0082] In Example 2, the first image shown in the example in Figure 9, which is the text image "Perfect," is not displayed, as shown in the example screen in Figure 10. In other words, the first image, which is displayed on the screen in the first case described above, is not displayed on the display unit in the second case, regardless of the user's answer. Furthermore, in the first case, the first display control can also prevent the display unit from showing the second image, which is displayed in the second display control in the second case depending on the user's answer.

[0083] Figure 11 shows an example where the user's answer differs from the examples in Figures 9 and 10, although the question and model answer are the same as in Figures 9 and 10. Terminal 1 displays the English sentence spoken by the user in area N3. In the example in Figure 11, the user's utterance is "Is this your phone." Evaluation server 2 determines whether the user's answer matches the model answer. In the example in Figure 11, the user's answer does not match the model answer. Therefore, as explained in the above embodiment, evaluation server 2 evaluates whether the user's answer is correct or not. Figure 11 is an example where the user's answer is evaluated as incorrect. Evaluation server 2 sends third information indicating that the user's answer is incorrect to terminal 1. In response to receiving the third information, terminal 1 displays the third image on the screen, which is an image indicating an incorrect answer and represents the lowest third evaluation. The third image is displayed in area N4. In the example in Figure 11, area N4 is shown in a reddish color. Terminal 1 displays an image showing the symbol × in area N5 within the range of area N4 as a third image, and displays the text image "Incorrect" in area N4. It also displays the model answer in area N4. In the example in Figure 11, since the user's answer and the model answer do not match, when displaying the user's answer and the model answer, it provides an identification display that shows the difference between the user's answer and the model answer, namely "that" in the model answer, in a different manner than the same part of the user's answer and the model answer. In the example in Figure 11, the "that" is underlined and displayed in bold, making it visually distinguishable from other words. Terminal 1 can also display the model answer in area N7 of another screen N' when the user selects an icon image in area N6.

[0084] Preferred embodiments of this disclosure have been described in detail above with reference to the attached drawings, but the technical scope of this disclosure is not limited to these examples. Furthermore, not all components shown in the embodiments are essential components of this disclosure. Also, features shown in each embodiment are applicable to other embodiments insofar as they do not contradict each other.

[0085] The display control of the display unit described above can also be performed by terminal 1 on which the program is installed, or by sending and receiving information via a network or cable with other information processing devices. In addition, various information processing other than display control, such as cloud services and distributed computing, can also be performed by one or more information processing devices on which the program is installed. Furthermore, the AI ​​server function may be incorporated into evaluation server 2.

[0086] Terminal 1 can also measure the time from when it displays the question to when the user finishes speaking their answer. Terminal 1 may display the evaluation result for the user's answer on its display, as well as the measured time.

[0087] For example, if an image is displayed that evaluates a user's answer as correct or incorrect, some users may think that the evaluation result is wrong. Therefore, terminal 1 may display the evaluation result of the user's answer on its display unit, as well as display a selection button to change the evaluation result. When the selection button is selected by the user, terminal 1 sends information to evaluation server 2 indicating that the evaluation result of the user's answer has been changed, and evaluation server 2 can store this information in memory or storage. Based on the changed information, evaluation server 2 can also modify the model answer text stored in the model answer database.

Claims

1. A method for displaying evaluation results on a display device, which is obtained by an information processing device from an evaluation of an answer text translated by a user into another language for a problem text to be translated, In response to the user's input of the answer to the aforementioned problem statement, In the first case where the information processing device determines that the user's answer matches the model answer corresponding to the problem statement, a first display control is performed to cause the display device to display a first image indicating the correct answer and a first evaluation. In the second case where the information processing device determines that the user's answer does not match the model answer and evaluates the user's answer, which includes parts that differ from the model answer, as correct, the second display control causes the display device to perform the following actions when displaying the user's answer and the model answer: an identification display that shows the parts that differ between the user's answer and the model answer in a manner different from the parts that are the same between the user's answer and the model answer; and a second image that shows the correct answer and a second evaluation lower than the first evaluation. In the third case in which the information processing device evaluates that the user's answer, which includes a part that differs from the model answer, is not correct, the third display control causes the display device to perform the identification display and the display of a third image indicating an incorrect answer. Do one of the following: A method characterized in that, in the first case, the first image to be displayed on the display device is not displayed on the display device regardless of the user's answer in the second case.

2. The method according to claim 1, characterized in that the identification display is performed so that words in the user's answer that are not in the model answer can be distinguished from words that are present in the model answer.

3. The method according to claim 1, characterized in that, if the information processing device determines that the user's answer does not match the model answer, it outputs an evaluation result of the user's answer based on the information in the question and the semantic information of the user's answer.

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

5. A program for causing a computer to perform the method according to any one of claims 1 to 4.

Images