Data processing device, data processing method and data processing program

Abstract

To provide a data processing device, a data processing method and a program that allow a user to easily grasp multiple replies received from multiple terminals.SOLUTION: A data processing device includes: an input unit that accepts, from multiple terminals, replies to a certain question; a classification result obtaining unit which inputs, to a generative AI, instruction information including the received replies and instructing the classification of the reply, and which obtains the classification result of the reply from the output by the generative AI; and an output unit that outputs the classification result of the reply in a visualized manner for each of the multiple replies received from the multiple terminals.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a data processing device, a data processing method, and a data processing program. [Background technology]

[0002] Non-Patent Document 1 discloses a method for displaying notes from 4 to 6 students on one screen as an appropriate display method that is easy to read and understand when a teacher views students' notes during class. [Prior art documents] [Non-patent literature]

[0003] [Non-Patent Document 1] Hiroki Echigo and Yuki Igarashi, "SectionsNote: A digital notebook that can be laid out and viewed with sections in mind," WISS 2020 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the conventional technology leaves room for improvement in terms of allowing teachers to classify and understand answers from multiple students into answer patterns. [Means for solving the problem]

[0005] A first aspect of the technology disclosed herein is a data processing device that includes an input unit that accepts answers to a specific question from a plurality of terminals, a classification result acquisition unit that inputs instruction information that includes the accepted answers and instructs the classification of the answers into a generative AI model and acquires classification results of the answers from the output of the generative AI model, and an output unit that visualizes and outputs the classification results of the answers for the plurality of answers accepted from the plurality of terminals.

[0006] A second aspect of the technology disclosed herein is a data processing method in which a computer receives answers to a specific question from multiple terminals, inputs instruction information that includes the received answers and instructs how to classify the answers into a generative AI model, obtains classification results for the answers from the output of the generative AI model, and visualizes and outputs the classification results for the answers received from the multiple terminals.

[0007] A third aspect of the technology disclosed herein is a data processing program for causing a computer to execute a process of accepting answers to a specific question from multiple terminals, inputting instruction information including the accepted answers and instructing classification of the answers into a generative AI model, obtaining classification results of the answers from the output of the generative AI model, and visualizing and outputting the classification results of the answers for the multiple answers accepted from the multiple terminals. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a conceptual diagram illustrating an example of a configuration of a data processing system. [Figure 2] FIG. 2 is a conceptual diagram showing an example of main functions of a data processing device and a user terminal. [Figure 3] An overview of the specific processing is shown below. [Figure 4] 2 shows a schematic functional configuration of a specific processing unit of the data processing device. [Figure 5] This shows how to input answer patterns in advance. [Figure 6] The results of visualizing the answer are shown below. [Figure 7] 10 is a diagram illustrating an example of an operational flow of a specific process performed by the data processing device according to the first embodiment. [Figure 8] 10 is a diagram illustrating an example of an operational flow of a specific process performed by a data processing device according to a second embodiment. [Figure 9] 11 shows an example of an operational flow of a specific process by a data processing device according to a third embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, exemplary embodiments of a data processing device, a data processing method, and a data processing program according to the techniques of the present disclosure will be described with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), or an APU (Accelerated Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] FIG. 1 shows an example of the configuration of a data processing system 10 according to the embodiment.

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and user terminals 14A and 14B. An example of the data processing device 12 is a server. Examples of the user terminals 14A and 14B are a personal computer, a tablet, or a smartphone. The multiple user terminals 14A are used by multiple children, one each. The user terminal 14B is used by a teacher. In this embodiment, the data processing device 12 is an example of a "data processing device" according to the technology of the present disclosure.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The user terminals 14A and 14B each include a computer 36, a reception device 38, an output device 40, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38 and the output device 40 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a keyboard, a mouse, etc., and receives user input. The reception device 38 may also receive user input by touch of an indicator (for example, a pen or a finger) by detecting contact with the touch panel, or may receive user input by voice by detecting the user's voice by a microphone. The control unit 46A transmits data indicating the received user input to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to a person by outputting the data in a form of expression that can be perceived by the person (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the user terminals 14A and 14B.

[0024] As shown in FIG. 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "data processing program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a generative AI model 58. The generative AI model 58 is used by the specific processing unit 290.

[0026] The generative AI model 58 is a so-called generative AI (Artificial Intelligence). An example of the generative AI model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generative AI models. The generative AI model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the generative AI model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The generative AI model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0027] In the user terminals 14A and 14B, the processor 46 performs the reception output process. The storage 50 stores a reception output program 62. The reception output program 62 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 62 from the storage 50 and executes the read reception output program 62 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 62 executed on the RAM 48.

[0028] Next, the processing of the specific processing unit 290 when the data processing device 12 performs specific processing for classifying and displaying answers to questions written by a plurality of children in a school class will be described.

[0029] In the identification process of this embodiment, as shown in Fig. 3, when each child handwrites an answer to a question in a school class into user terminal 14A, a list of answers from each child is displayed on user terminal 14B. At this time, the answers from each child are classified according to answer patterns prepared in advance, and the classification results are visualized to display a list of answers from each child.

[0030] As shown in FIG. 4, the identification processing unit 290 includes an input unit 291, a classification result acquisition unit 292, and an output unit 293.

[0031] The input unit 291 receives, from a plurality of user terminals 14A, image data representing handwritten characters or pictures as answers to questions presented to children in class at school. Note that the questions presented to children in class at school are an example of specific questions, and the answers are an example of responses to the specific questions.

[0032] Specifically, the input unit 291 randomly receives answers to questions presented to students in school classes from a plurality of user terminals 14A. The received answers may be text data.

[0033] The classification result acquisition unit 292 inputs instruction information, which includes the accepted answer and instructs the classification of the answer, to the generative AI model 58, and acquires the classification result of the answer from the output of the generative AI model 58.

[0034] Specifically, the instruction information includes image data representing handwritten characters or pictures indicating the accepted answer and a plurality of pre-prepared answer patterns, and instructs classification according to the plurality of answer patterns. For example, as shown in FIG. 5, the teacher pre-enters answer patterns in user terminal 14B, and the instruction information instructs classification according to the plurality of pre-entered answer patterns. The answer patterns are image data representing handwritten characters or pictures, or text data.

[0035] As an example, the instruction information "The first three image data to be input are handwritten images representing answer patterns to the question, 'If 5.4 L of juice is divided equally into three bottles, how many liters will each bottle contain?' The image data to be input subsequently are handwritten images representing answers to the question. Please classify the answers according to the answer patterns," along with the image data representing the answer patterns and the image data representing the answers, are input to the generative AI model 58.

[0036] Furthermore, each time the classification result acquisition unit 292 receives an answer randomly, it inputs instruction information including the answer to the generative AI model 58 and acquires the classification result of the answer from the output of the generative AI model 58.

[0037] The output unit 293 visualizes and outputs the classification results of the answers acquired from the multiple user terminals 14A.

[0038] Specifically, as shown in FIG. 6, the output unit 293 transmits data of a screen that displays multiple answers acquired from multiple user terminals 14A using colors according to the classification results of the answers to the user terminal 14B, and causes the user terminal 14B to display the screen.

[0039] At this time, each time the output unit 293 receives an answer from the user terminal 14A, it may visualize and output the classification result of the answer.

[0040] Next, the operation of the data processing system 10 will be described.

[0041] An example of the flow of the identification process by the data processing device 12 will be described with reference to FIG. 7. The flow of the identification process shown in FIG. 7 is an example of a "data processing method" according to the technology of the present disclosure. It is assumed that a set of a question sentence and image data representing multiple answer patterns for the question sentence has been received in advance from the user terminal 14B. Then, every time the data processing device 12 receives image data representing the answer to the question sentence from the user terminal 14A, it executes the identification process shown in FIG. 7.

[0042] In step S100, the input unit 291 receives image data representing a handwritten answer transmitted from the user terminal 14A.

[0043] In step S102, the classification result acquisition unit 292 creates instruction information that includes image data representing the accepted answer and image data representing a plurality of answer patterns, and instructs classification according to the plurality of answer patterns.

[0044] In step S104, the created instruction information is input to the generative AI model 58, and the classification result of the answer is obtained from the output of the generative AI model 58.

[0045] In step S106, the output unit 293 transmits image data representing the answer received in step S100 above, and a screen that visualizes and outputs the classification result of the answer, to the user terminal 14B, and ends the identification process.

[0046] Each time image data representing the answers to the question is received from each user terminal 14B, the data processing device 12 repeatedly executes the above-described identification process, and a screen that visualizes and outputs the classification results for the image data representing the multiple answers input by the multiple user terminals 14A is output to the user terminal 14B. This allows the teacher to easily understand the contents of the answers given by the multiple students.

[0047] As described above, the data processing system according to this embodiment accepts answers to a specific question from multiple user terminals, inputs instruction information including the accepted answers and instructing how to classify the answers into a generative AI model, obtains the classification results of the answers from the output of the generative AI model, and visualizes and outputs the classification results. This makes it easy to understand the contents of the multiple answers accepted from multiple user terminals.

[0048] [Second embodiment] Next, a data processing system according to a second embodiment will be described. Note that the configuration of the data processing system according to the second embodiment is the same as that of the first embodiment, so the same reference numerals are used and the description will be omitted.

[0049] The second embodiment differs from the first embodiment in that an answer group made up of answers that do not belong to a classification according to a plurality of answer patterns input in advance is further classified.

[0050] The classification result acquisition unit 292 of the data processing device 12 according to the second embodiment inputs instruction information, including the received answer and instructing the classification of the answer, to the generative AI model 58, and acquires the classification result of the answer from the output of the generative AI model 58.

[0051] Specifically, the instruction information includes image data representing handwritten characters or pictures indicating the accepted answer and a plurality of pre-prepared answer patterns, and instructs classification according to the plurality of answer patterns.

[0052] Furthermore, each time the classification result acquisition unit 292 receives an answer randomly, it inputs instruction information including the answer to the generative AI model 58 and acquires the classification result of the answer from the output of the generative AI model 58.

[0053] Furthermore, after receiving multiple answers from multiple user terminals 14A, the classification result acquisition unit 292 inputs instruction information to the generation AI model 58 instructing it to further classify a group of answers consisting of answers that do not belong to a classification according to multiple answer patterns, and acquires the answer classification results from the output of the generation AI model 58.

[0054] As an example, the instruction information "Classify answers that are determined not to belong to the classification corresponding to the answer pattern into three categories and create a title that summarizes each classification" is input to the generative AI model 58.

[0055] The output unit 293 visualizes and outputs the classification results of the answers acquired from the multiple user terminals 14A.

[0056] Specifically, the output unit 293 transmits data of a screen that outputs a plurality of answers acquired from a plurality of user terminals 14A using colors according to the classification results of the answers to the user terminal 14B, and displays the screen on the user terminal 14B. At this time, the screen may display a title indicating an overview of each classification for the classification results for the answer group made up of answers that are determined not to belong to the classification according to the answer pattern.

[0057] Next, the operation of the data processing system 10 will be described.

[0058] An example of the flow of the identification process by the data processing device 12 will be described with reference to Figures 7 and 8. It is assumed that a set of a question sentence and image data representing a plurality of answer patterns for the question sentence has been received in advance from the user terminal 14B. Then, every time the data processing device 12 receives image data representing the answer to the question sentence from the user terminal 14A, it executes the identification process shown in Figure 7 above.

[0059] Then, after executing the identification process shown in FIG. 7 for the plurality of answers received from the plurality of user terminals 14A, the data processing device 12 executes a second identification process shown in FIG.

[0060] In step S200, the input unit 291 acquires a group of answers that are determined not to belong to a classification corresponding to the answer pattern in the identification process shown in FIG. 7, from among the answers sent from the multiple user terminals 14A.

[0061] In step S202, the classification result acquisition unit 292 creates instruction information that instructs further classification of an answer group made up of answers that do not belong to a classification according to a plurality of answer patterns.

[0062] In step S204, the created instruction information is input to the generative AI model 58, and the classification result of the answer group is obtained from the output of the generative AI model 58.

[0063] In step S206, the output unit 293 transmits image data representing the answer that has been determined not to belong to the classification corresponding to the answer pattern to the user terminal 14B, and a screen that visualizes and outputs the classification result of the answer, and then ends the second identification process.

[0064] As described above, the data processing system according to this embodiment accepts answers to a specific question from multiple user terminals, inputs instruction information into the generative AI model that instructs the classification of the answers, including the accepted answers, according to pre-prepared answer patterns, obtains the classification results of the answers from the output of the generative AI model, and visualizes and outputs the classification results. At this time, for answer groups that do not belong to the answer patterns, further instruction information instructing the classification of the answers is input into the generative AI model, obtains the classification results of the answer groups that do not belong to the answer patterns from the output of the generative AI model, and visualizes and outputs the classification results. This allows the contents of answer groups that do not belong to the pre-prepared answer patterns to be easily understood.

[0065] [Third embodiment] Next, a data processing system according to a third embodiment will be described. Note that the configuration of the data processing system according to the third embodiment is the same as that of the first embodiment, so the same reference numerals are used and the description will be omitted.

[0066] The third embodiment differs from the first embodiment in that answer groups made up of accepted answers are classified without using answer patterns input in advance.

[0067] The classification result acquisition unit 292 of the data processing device 12 according to the third embodiment includes an answer group consisting of accepted answers, inputs instruction information instructing the classification of the answer group to the generative AI model 58, and acquires the classification result of the answer group from the output of the generative AI model 58.

[0068] Specifically, the instruction information includes multiple image data representing handwritten characters or pictures indicating answers received from multiple user terminals 14A, and instructs the classification of the answers represented by the multiple image data as well as the output of titles outlining each classification.

[0069] As an example, the instruction information "The multiple image data to be input are handwritten images representing answers to the question, 'If 5.4 L of juice is divided equally into three bottles, how many liters will each bottle contain?' Please classify them into three categories and create a title that summarizes each category," along with multiple image data representing handwritten characters or pictures indicating answers received from multiple user terminals 14A, are input to the generative AI model 58.

[0070] Next, the operation of the data processing system 10 will be described.

[0071] An example of the flow of the identification process by the data processing device 12 will be described with reference to Fig. 9. When image data representing answers to questions is received from a plurality of user terminals 14A, the data processing device 12 executes the identification process shown in Fig. 9.

[0072] In step S300, the input unit 291 acquires an answer group consisting of answers transmitted from a plurality of user terminals 14A.

[0073] In step S302, the classification result acquisition unit 292 creates instruction information that instructs classification of an answer group made up of answers transmitted from a plurality of user terminals 14A.

[0074] In step S304, the created instruction information is input to the generative AI model 58, and the classification result of the answer group is obtained from the output of the generative AI model 58.

[0075] In step S306, the output unit 293 transmits to the user terminal 14B a screen that visualizes and outputs the classification results of the answers, along with image data representing the answers transmitted from the multiple user terminals 14A, and terminates the identification process.

[0076] As described above, the data processing system according to this embodiment accepts answers to a specific question from multiple user terminals, inputs instruction information including an answer group consisting of the accepted answers and instructing how to classify the answer group into a generative AI model, obtains the classification results of the answer group from the output of the generative AI model, and visualizes and outputs the classification results. This makes it easy to understand the contents of the answer group accepted from multiple user terminals.

[0077] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[0078] In the above embodiment, the problem sentences presented to students in school classes are specific questions, but the present invention is not limited to this. Questions other than problem sentences (for example, general questionnaires) may also be used. In this case, answers to the questions may be received from a user terminal, or may be classified according to a plurality of answer patterns prepared in advance.

[0079] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0080] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0081] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0082] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0083] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0084] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[0085] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0086] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0087] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0088] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0089] 10 Data Processing System 12 Data Processing Device 14A, 14B User terminal 22 Computer 24 databases 28 processors 32 Storage 56 Specific Processing Program 58 Generative AI Models 290 Special Processing Department 291 Input section 292 Classification result acquisition unit 293 Output Section< / url:>

Claims

1. an input unit that accepts answers to specific questions from multiple terminals; a classification result acquisition unit that inputs instruction information, including the received answer and instructing classification of the answer, into a generative AI model and acquires a classification result of the answer from the output of the generative AI model; an output unit that visualizes and outputs classification results of the answers received from the terminals; 2. A data processing device comprising:

2. 2. The data processing device according to claim 1, wherein the instruction information includes a plurality of response patterns prepared in advance and instructs classification according to the plurality of response patterns.

3. the input unit randomly accepts the answers from the plurality of terminals; The classification result acquisition unit inputs the instruction information including the answer into the generative AI model each time the answer is received, and acquires a classification result of the answer from an output of the generative AI model; The data processing device according to claim 2 , wherein the output unit visualizes and outputs a classification result of the answer for each answer received.

4. 2. The data processing device according to claim 1, wherein the answer is image data representing handwritten characters or pictures, or text data.

5. The data processing device according to claim 1 , wherein the output unit outputs the answers acquired from the plurality of terminals using colors corresponding to the classification results of the answers.

6. 2. The data processing device according to claim 1, wherein the instruction information includes a plurality of pre-prepared answer patterns, instruction information instructing classification according to the plurality of answer patterns, and instruction information instructing further classification of a group of answers consisting of answers that do not belong to a classification according to the plurality of answer patterns.

7. 2. The data processing device according to claim 1, wherein the instruction information includes a group of answers made up of answers received from the plurality of terminals, and instructs that the group of answers be classified.

8. 2. The data processing device according to claim 1, wherein the instruction information includes a group of answers made up of answers received from the plurality of terminals, and instructs to classify the group of answers and output a title indicating an outline of each classification.

9. The question is a problem statement presented to a learner in a school lesson, 2. The data processing device according to claim 1, wherein the answer is a solution given by the learner to the question.

10. The computer Accept answers to specific questions from multiple devices, Inputting instruction information including the received answer and instructing the classification of the answer into a generative AI model, and obtaining a classification result of the answer from the output of the generative AI model; Visualizing and outputting classification results of the answers received from the plurality of terminals. The data processing method that performs the processing.

11. On the computer, Accept answers to specific questions from multiple devices, Inputting instruction information including the received answer and instructing the classification of the answer into a generative AI model, and obtaining a classification result of the answer from the output of the generative AI model; Visualizing and outputting classification results of the answers received from the plurality of terminals. A data processing program for executing processing.

Images