Data processing device, data processing method, and program

Abstract

To provide a data processing device capable of presenting the status of a managed person, a data processing method, and a program.SOLUTION: A data processing device includes an input unit which accepts a user input by a manager and a managed person having an education teaching relationship, a processing unit which performs specific processing using a sentence generation model for generating a sentence according to an input sentence, and an output unit which controls the behavior of an electronic device so as to output the results of specific processing. The processing unit regards the acceptance of a user input by the manager as a trigger condition. When the trigger condition is met, the processing unit performs processing for presenting the status of the managed person to the manager as specific processing using the sentence generation model where information of a submission recording the status of the managed person for submission serves as the input sentence.SELECTED DRAWING: Figure 3B

Description

[Technical field]

[0001] The technology disclosed herein relates to a data processing device, a data processing method, and a program. [Background technology]

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. Meanwhile, as the declining birthrate accelerates, the environment surrounding children is becoming very harsh, with bullying, abuse, young carer issues, etc. In addition, even in educational settings and government agencies that are responsible for improving these environments, it is difficult to accurately grasp the state of children, such as their living environment and mental state, due to busy schedules, working conditions, labor shortages, etc. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the conventional technology, the use of AI (Artificial Intelligence) technologies such as chatbots in educational settings has only just begun, and there is room for improvement in terms of teachers, who act as administrators, understanding the status of students, who are the subjects of their administration, for example in schools. [Means for solving the problem]

[0005] A data processing device according to a first aspect of the technology disclosed herein includes an input unit that accepts user input from a manager and a managed person who are in a teaching relationship, a processing unit that performs a specific processing using a sentence generation model that generates a sentence according to the input sentence, and an output unit that controls the behavior of an electronic device to output the result of the specific processing, wherein the processing unit uses the acceptance of user input from the manager as a trigger condition, and when the trigger condition is satisfied, performs the specific processing by using the output of the sentence generation model when the input sentence is information on a submission that records the status of the managed person and is submitted by the managed person as user input.

[0006] A data processing device according to a second aspect of the technology disclosed herein has the configuration of the first aspect, wherein the information is information acquired during a period designated by a user input by the administrator.

[0007] A data processing device relating to a third aspect of the technology disclosed herein has the configuration of the first aspect or the second aspect, wherein the input unit accepts user input from multiple managed persons, and the processing unit performs the identification processing for each managed person.

[0008] A data processing device according to a fourth aspect of the technology disclosed herein, in the configuration of the third aspect described above, has an input unit that accepts user input from a higher-level administrator who manages the administrator, and the processing unit uses the acceptance of user input from the higher-level administrator as a trigger condition, and when the trigger condition is satisfied, performs the specific process of presenting a comprehensive status of the multiple managed persons to the higher-level administrator using the output of the sentence generation model when the information as user input by the multiple managed persons managed by the administrator is used as input sentences.

[0009] A data processing method according to a fifth aspect of the technology disclosed herein accepts user input from a manager and a managed person who are in a teaching relationship, and when user input from the manager is accepted, performs a specific process of presenting the status of the managed person to the manager using the output of a sentence generation model that records the status of the managed person as user input by the managed person and generates a sentence corresponding to the input sentence when information on the submission to be submitted is used as the input sentence, and outputs the result of the specific process.

[0010] A program relating to a sixth aspect of the technology disclosed herein accepts user input from a manager and a managed person who are in a teaching relationship, and when user input from the manager is accepted, performs a specific process of presenting the status of the managed person to the manager using the output of a sentence generation model that records the status of the managed person as user input by the managed person and generates a sentence corresponding to the input sentence when information on the submission to be submitted is used as the input sentence, and causes a computer to execute a process including outputting a result of the specific process. [Brief description of the drawings]

[0011] [Figure 1] FIG. 1 is a conceptual diagram illustrating an example of a configuration of a data processing system. [Diagram 2] FIG. 2 is a conceptual diagram showing an example of main functions of a data processing device and a smart device. [Figure 3A] The outline of the specific process is shown below. [Figure 3B] 13 shows an example of a display on the manager's terminal. [Figure 3C] 13 shows an example of a display on the terminal of a higher-level administrator. [Figure 4] 2 shows a schematic functional configuration of a specific processing unit of the data processing device. [Diagram 5] 13 illustrates an example of an operational flow of a specific process performed by a data processing device. [Figure 6] 13 illustrates an example of an operational flow of a reception output process performed by a smart device of an administrator. [Figure 7]13 illustrates an example of an operational flow of a reception output process performed by a smart device of a higher-level administrator. [Figure 8A] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 8B] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Hereinafter, an example of an embodiment of a data processing device, a data processing method, and a program according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0013] First, the terms used in the following description will be explained.

[0014] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0015] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0016] 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.

[0017] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0018] 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[0019] FIG. 1 shows an example of the configuration of a data processing system 10 according to the embodiment.

[0020] As shown in Fig. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server such as a cloud server. An example of the smart device 14 is a smartphone, a tablet terminal, etc. In this embodiment, the data processing device 12 is an example of a "data processing device" according to the technology of the present disclosure.

[0021] 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 wide area network (WAN) and / or a local area network (LAN).

[0022] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, 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, the output device 40, and the camera 42 are also connected to the bus 52.

[0023] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0024] The output device 40 includes a display 40A and a speaker 40B, and presents data to the person 20 by outputting the data in a form of expression that the person 20 can perceive (e.g., voice and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs voice according to instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0025] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

[0026] FIG. 2 shows an example of main functions of the data processing device 12 and the smart device 14.

[0027] As shown in Fig. 2, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process program 56 executed on the RAM 30.

[0028] The storage 32 stores a data generation model 58 and an emotion identification model 60. The data generation model 58 and the emotion identification model 60 are used by the identification processing unit 290.

[0029] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 62. The reception output program 62 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads out 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.

[0030] Next, the process of the specific processing unit 290 when the data processing device 12 performs the specific process of presenting the status of the managed person to the manager will be described. In this embodiment, the manager and the managed person are in a relationship of teaching education. As an example, in an educational setting such as a school or a cram school, the manager is a teacher, professor, lecturer, etc. of the school or cram school who teaches education, and the managed person is a student or child who is taught education. The specific process according to this embodiment is a process of presenting the status of the managed person to the manager using the output of the data generation model 58 when the information of the submission that records the status of the managed person as a user input by the managed person and submits it is used as an input text.

[0031] In the specific process in this embodiment, as shown in FIG. 3A, a diary system installed in the data processing device 12 accepts user input from a student S1 and a teacher T1 of each school 15. Specifically, the student S1 writes a daily diary using, for example, a diary application installed in a smartphone serving as a smart device 14. In this embodiment, the diary written by the student S1 corresponds to information on an item submitted by recording the situation of the student S1 (subject to management), and the contents of the written diary are sent to the diary system (i.e., the data processing device 12) as information on the item submitted. In other words, the diary system accepts information on the item submitted as user input.

[0032] Also, the teacher T1 can read the contents of the diary written by the student S1 via the diary system, for example, using a tablet terminal as the smart device 14. Specifically, when the teacher T1 logs in to his / her account, as shown in Fig. 3B, the first information 14A, which is the name of the teacher T1 (XXXX Taro) and information on the date of login, is displayed in the upper left corner of the display 40A of the smart device 14, for example.

[0033] Furthermore, the name of each student S1 and the diary entry written by that student S1 are displayed as the second information 14B for each student S1. As an example, "I'm not feeling well today either. It's hard for me to go to school" is displayed as Taichi X's diary entry, and "Teacher, there was a basketball game today! I made a three-point shot and enjoyed lunch with my friends. I'll do my best tomorrow too!" is displayed as Mika X's diary entry.

[0034] In FIG. 3B, the diaries of two students are displayed as student S1, but it is possible to display the diary of student S1 that is not displayed, for example, by scrolling.

[0035] Also, on the right side of the second information 14B, "How are things going in the last month?" is displayed, and below "How are things going in the last month?", a "Listen" button is displayed for each student S1. As an example, when "How are things going in the last month?" is displayed by positioning an arrow cursor over "How are things going in the last month?" and clicking it, or by teacher T1 touching it with his / her finger, a slide bar appears, and by moving the slide bar that appears, "1 month" can be changed to a desired period such as "6 months" or "1 year."

[0036] Teacher T1 checks the diary of student S1, and if there is a student S1 with a finding that concerns him / her, he / she selects "Listen" to the right of the student S1. Specifically, as an example, teacher T1 positions the arrow cursor and clicks, or teacher T1 touches with his / her finger to select "Listen."

[0037] When teacher T1 selects "listen", as shown in FIG. 3A, the diary system requests the data generation model 58 to analyze the contents of the diary of the selected student S1 for the specified period, i.e., the most recent month, and the state of student S1 is displayed on the display 40A as the analysis result of the data generation model 58, as shown in FIG. 3B. Specifically, "There are no particularly worrisome findings or changes in emotions. However, in the diary on May 23, it is written that "On the way home, someone put garbage in my bag. It's disgusting," so there is a possibility that she is being bullied, so attention should be paid. In addition, in the diary on May 30 and May 31, it is written that she is not feeling well, so attention should be paid to her health condition. " is displayed as the state of student S1.

[0038] Teacher T1 can visually check the state of student S1 and, if necessary, take action by going back to the diary of more than the past month. Specifically, teacher T1 changes "How is the past month going?" to a desired period such as "1 year" as described above, and then selects "listen" again.

[0039] In addition, the teacher T1 can write a diary reply to the student S1 in the diary system. The diary system accepts this diary reply as a user input from the teacher T1. In this embodiment, when a diary reply is written from the teacher T1, the diary reply is sent to the diary application of the smart device 14 operated by the student S1, and the student S1 can view the written diary reply.

[0040] In addition, below the displayed status of student S1, a push button "Close" is displayed, and when teacher T1 selects this "Close", the displayed status of student S1 is deleted from display 40A. Note that "Close" is selected, for example, by teacher T1 positioning the arrow cursor and clicking, or by teacher T1 touching with his / her finger.

[0041] Next, a description will be given of the processing of the specific processing unit 290 when the data processing device 12 performs specific processing to comprehensively present the statuses of multiple managed persons to the upper manager 16 who manages the manager. In this embodiment, the upper manager 16 is the one who has jurisdiction over the school or cram school to which the manager belongs, and specifically, when the manager is a teacher or lecturer at a school, it corresponds to the child welfare department or board of education of the local government or prefecture that has jurisdiction over the school to which the manager belongs, and when the manager is a lecturer at a cram school, it corresponds to the head office or headquarters that has jurisdiction over the cram school.

[0042] In the identification process of this embodiment, as shown in Fig. 3A, the diary system installed in the data processing device 12 accepts user input from a person in charge B1 belonging to the upper manager 16. Specifically, it accepts which school (cram school) each manager belongs to and for which the manager wishes to know the status of the student S1. The person in charge B1 can check the overall status of the multiple students S1 using a tablet terminal or the like as the smart device 14.

[0043] In other words, from the standpoint of the Personal Information Protection Act, filter 17 prevents the upper-level administrator from viewing the contents of the diary entries written by student S1, and the upper-level administrator can check the status of multiple students S1 belonging to the school (cram school) in terms of the number of items for each predetermined item.

[0044] Specifically, as shown in FIG. 3C, when person in charge B1 logs in to his / her account, third information 14D, which is information on the jurisdiction of the upper-level administrator 16 and the date of login, is displayed in the upper left corner of the display 40A of the smart device 14, as an example.

[0045] In addition, "School name" and "Symptoms of the past month" are displayed below the third information 14D, with the name of each school displayed below the "School name" and a "Confirm" button displayed for each school below the "Symptoms of the past month". As an example, when the user positions the arrow cursor on the "Symptoms of the past month" and clicks it, or touches it with his / her finger, a slide bar appears, and the user can move the slide bar to change "1 month" to a desired period such as "6 months" or "1 year".

[0046] Person in charge B1 selects "Confirm" to the right of the school he or she is interested in. Specifically, as one example, Person in charge B1 positions the arrow cursor and clicks, or Person in charge B1 touches it with his or her finger to select "Confirm."

[0047] When the person in charge B1 selects "Confirm", as shown in Fig. 3C, the diary system requests the data generation model 58 to analyze the contents of the diaries of multiple students S1 belonging to the selected school for the specified period, i.e., the most recent month, and the status of multiple students S1 is displayed on the display 40A as the analysis result of the data generation model 58, as shown in Fig. 3C. Specifically, "Total number of diary entries: 30, violence and harassment: 2, negative emotions: 0, poor health: 2" is displayed as the overall result of the status of multiple students S1, i.e., the status of the school.

[0048] The person in charge B1 can visually confirm the overall results of the state of the multiple students S1, i.e., the state of the school, and then, if necessary, can take action by going back to the diary from more than the past month. Specifically, the person in charge B1 changes the "signs of the past month" to a desired period such as "one year" as described above, and then selects "check" again.

[0049] In addition, below the displayed status of the multiple students S1, i.e., the overall result of the school's status, a push button "Close" is displayed, and when the person in charge B1 selects this "Close", the displayed status of the multiple students S1, i.e., the overall result of the school's status, is deleted from the display 40A. In addition, as one example, the selection of "Close" is performed by the person in charge B1 positioning the arrow cursor and clicking, or by touching with a finger.

[0050] Next, a description will be given of the configuration of the specific processing unit 290 that performs the above specific processing. The specific processing unit 290 includes an input unit 292, a processing unit 294, and an output unit 296, as shown in FIG.

[0051] The input unit 292 acquires user input received by the smart device 14. Specifically, the input unit 292 acquires at least one of a user's voice input and a character input received by the smart device 14. More specifically, the input unit 292 acquires information on a diary entered by the student S1 (subject to management) in which the situation of the student S1 is recorded. The input unit 292 also acquires information on a reply from the teacher T1 to the diary of the student S1.

[0052] The processing unit 294 performs a specific process using the data generation model 58. Specifically, the processing unit 294 determines whether or not a predetermined trigger condition is satisfied. More specifically, the first trigger condition is that the selection of "listen" by the teacher T1 as the administrator is accepted as a user input, and the second trigger condition is that the selection of "check" by the person in charge B1 is accepted as a user input.

[0053] Then, when the first trigger condition is satisfied, the processing unit 294 inputs text representing instructions for obtaining data for a specific process as a prompt to the data generation model 58, and acquires a processing result based on the output of the data generation model 58. More specifically, the processing unit 294 inputs, as prompts to the data generation model 58, text representing information on the diary of the specific student S1 for a predetermined period stored in the diary system database, text representing instructions for inquiring about the status of the specific student S1, and text expressing a desire to play the role of a psychological counselor knowledgeable about child welfare, and acquires information representing the status of the specific student S1 to be presented to the teacher T1 based on the output of the data generation model 58.

[0054] Furthermore, when the second trigger condition is satisfied, the processing unit 294 inputs text representing an instruction for obtaining data for a specific process as a prompt to the data generation model 58, and acquires a processing result based on the output of the data generation model 58. More specifically, the processing unit 294 inputs, as prompts, text representing diary information of multiple students S1 of a specific school for a predetermined period stored in the diary system database, text representing an instruction for inquiring about the status of the specific school, i.e., the multiple students S1, and text expressing a desire to play a role as a psychological counselor knowledgeable about child welfare, to the data generation model 58, and acquires information representing the status of the specific school (multiple students S1) to be presented comprehensively to the upper manager 16, i.e., the person in charge B1 belonging to the upper manager 16, based on the output of the data generation model 58.

[0055] The processing unit 294 may estimate the user's emotion using the emotion identification model 60 and perform identification processing using the user's emotion and the data generation model 58.

[0056] The output unit 296 transmits the result of the specific processing to the smart device 14. In this embodiment, the output unit 296 transmits to the smart device 14 information representing the state of a specific student S1 to be presented to the teacher T1 and information representing the state of a specific school (multiple students S1) to be comprehensively presented to the person in charge B1, which are acquired by the processing unit 294 from the data generation model 58. The output unit 296 transmits the result of the specific processing to the smart device 14 so that the information is displayed on the smart device 14 in a manner as shown in FIG. 3B or FIG. 3C. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. In this embodiment, the control unit 46A causes the display 40A to output the result of the specific processing, as an example. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0057] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 infers from the input inference data according to 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. The data generation model 58 corresponds to the sentence generation model of the present disclosure.

[0058] For example, when the first trigger condition is satisfied, the processing unit 294 generates a prompt saying, "Summarize the diaries of student S2 for the past month and present the state of student S2" when the specific student corresponding to the selected "listen" is student S2, and inputs the prompt to the data generation model 58. Also, when the second trigger condition is satisfied, the processing unit 294 generates a prompt saying, "Summarize the diaries of all students S1 attending school SC for the past month and present the total number of diary entries, the number of cases of violence or harassment, the number of cases of negative emotions, and the number of cases of poor health without referring to the specific diary contents" when the specific school and school SC corresponding to the selected "confirm" are student S2, and inputs the prompt to the data generation model 58. The data generation model 58 generates data according to the prompt generated by the processing unit 294 and outputs the generated data.

[0059] In this embodiment, when the second trigger condition is satisfied, the processing unit 294 acquires information indicating the state of a specific school (multiple students S1) to be presented comprehensively to the person in charge B1 belonging to the upper-level administrator 16, but the technology disclosed herein is not limited to this. For example, the total number of diary entries, the number of cases of violence or harassment, the number of cases of negative emotions, the number of cases where poor health was mentioned, etc., for all schools under the jurisdiction of the upper-level administrator 16 may be acquired by a daily batch update function, and the list may be stored in the database 24.

[0060] Next, the operation of the data processing system 10 will be described with reference to FIGS.

[0061] First, an example of the flow of the specific process by the data processing device 12 will be described with reference to Fig. 5. The flow of the specific process shown in Fig. 5 is an example of a "data processing method" according to the technology of the present disclosure. In this embodiment, the flow of the specific process shown in Fig. 5 is automatically and repeatedly executed, for example, every time a certain period of time has elapsed.

[0062] 5, first, in step S100, the processing unit 294 determines whether or not a predetermined first trigger condition is satisfied. For example, in the case where the first trigger condition is that the input unit 292 has accepted the selection of "listen" by the teacher T1 as a user input, the processing unit 294 determines whether or not the input unit 292 has accepted the selection of "listen" as a user input.

[0063] If the first trigger condition is satisfied, the process proceeds to step S101. In step S101, the processing unit 294 generates a prompt based on the user input by adding an instruction sentence for obtaining the result of a specific process to the text representing the input. For example, as shown in FIG. 3B, when "How is it going in the last month?" is displayed above "listen" and the name of a specific student S2 is displayed to the left of "listen", information representing "present the state of student S2 in the last month" is transmitted from the smart device 14 operated by the teacher T1. Therefore, along with information showing the diary of the specific student S2 in the last month, a prompt is generated that reads "Please answer as a psychological counselor who is knowledgeable about child welfare" and "Please summarize the diary of student S2 in the last month and present the state of student S2."

[0064] On the other hand, if the first trigger condition is not satisfied in step S100, the process proceeds to step S102. In step S102, the processing unit 294 determines whether or not a predetermined second trigger condition is satisfied. For example, if the second trigger condition is that the input unit 292 has accepted the selection of "confirm" by the person in charge B1 who belongs to the upper manager B1 as a user input, the processing unit 294 determines whether or not the input unit 292 has accepted the selection of "confirm" as a user input. If the second trigger condition is not satisfied, the identification process is terminated.

[0065] If the second trigger condition is satisfied, the process proceeds to step S101. In step S101, the processing unit 294 generates a prompt based on the user input by adding an instruction for obtaining the result of the specific process to the text representing the input. For example, as shown in FIG. 3C, when "symptoms in the past month" is displayed above "Confirm" and the name of a specific school SC is displayed to the left of "Confirm", information representing "presentation of the past month's status of all students S1 attending the school SC" is transmitted from the smart device 14 operated by the person in charge B1. Therefore, along with information showing the past month's diaries of all students S1 attending the specific school SC, a prompt is generated that reads "Please answer as a psychological counselor familiar with child welfare" and "Please summarize the past month's diaries of all students S1 attending the school SC and present the total number of diary entries, the number of violence and harassment entries, the number of negative emotions, and the number of entries describing poor health, without referring to the specific contents of the diary entries."

[0066] Next, in step S103, the processing unit 294 inputs the generated prompt to the data generation model 58, and acquires the result of the specific processing based on the output of the data generation model 58. Then, in step S104, the output unit 296 controls the behavior of the smart device 14 so as to output the result of the specific processing, and ends the specific processing.

[0067] Specifically, when the first trigger condition is satisfied, the processing unit 294 acquires the state of the specific student S2 from the data generation model 58 as a result of the identification process. More specifically, the processing unit 294 acquires text data from the data generation model 58 that reads, "There are no particularly worrisome findings or changes in emotions. However, in the diary on May 23, it is written that 'On my way home, someone put trash in my bag. I feel sick.' So, caution is required as she may be being bullied. In addition, in the diary on May 30 and May 31, it is written that she is not feeling well, so caution is required regarding her health condition."

[0068] When the first trigger condition is satisfied, the output unit 296 transmits the above text data to the computer 36 of the smart device 14 operated by the teacher T1 via the communication I / F 44, and displays on the display 40A the following: "There are no particularly worrisome findings or changes in emotions. However, in the diary entry for May 23rd it is written, 'On my way home, someone put trash in my bag. I feel sick,' so caution is required as this may be a case of bullying. In addition, in the diary entries for May 30th and May 31st it is written that she is feeling unwell, so caution is required regarding her health condition."

[0069] On the other hand, when the second trigger condition is satisfied, the processing unit 294 acquires the overall state of all students S1 attending the specific school SC as a result of the identification process from the data generation model 58. Specifically, the processing unit 294 acquires text data with the content "Total number of diary entries: 30, violence and harassment: 2, negative emotions: 0, poor health: 2" from the data generation model 58.

[0070] When the second trigger condition is satisfied, the output unit 296 transmits the above text data via the communication I / F 44 to the computer 36 of the smart device 14 operated by the person in charge B1, and displays on the display 40A "Total number of diary entries: 30, violence and harassment: 2, negative emotions: 0, poor health: 2."

[0071] Next, an example of the flow of a reception output process by the smart device 14 operated by the teacher T1 will be described with reference to FIG.

[0072] In the reception output process shown in FIG. 6, first, in step S200, the processor 46 determines whether or not "listen" has been selected by the reception device 38. If "listen" has not been selected, the processor 46 repeats the process of step S200 until "listen" is selected. On the other hand, if "listen" has been selected, the process proceeds to step S201. In step S201, the processor 46 transmits an instruction to the data processing device 12 via the communication I / F 44 to request a summary of the diary of a specific student S2 for the most recent month. Specifically, the processor 46 transmits information indicating "present the status of student S2 for the most recent month."

[0073] Next, in step S202, the processor 46 determines whether or not a specific processing result has been received from the data processing device 12. If the specific processing result has not been received, the processor 46 repeats the process of step S202 until the specific processing result is received.

[0074] On the other hand, if the result is received in step S202, the processor 46 displays the result of the received specific processing on the display 40A and ends the acceptance output process. Specifically, as shown in FIG. 3B, the processor 46 displays on the display 40A the following: "There are no particularly worrisome findings or changes in emotions. However, in the diary on May 23, it is written that "On the way home, someone put garbage in my bag. It's disgusting.", so there is a possibility that the subject is being bullied, so caution is required. In addition, in the diary on May 30 and May 31, it is written that the subject is not feeling well, so caution is required regarding the state of health." In this embodiment, the result is displayed on the display 40A, but the technology of the present disclosure is not limited to this, and the result may be output by voice from the speaker 40B.

[0075] Next, an example of the flow of a reception output process by the smart device 14 operated by the person in charge B1 will be described with reference to FIG.

[0076] In the reception output process shown in FIG. 6, first, in step S300, the processor 46 determines whether or not "Confirm" has been selected by the reception device 38. If "Confirm" has not been selected, the processor 46 repeats the process of step S300 until "Confirm" is selected. On the other hand, if "Confirm" has been selected, the process proceeds to step S301. In step S301, the processor 46 transmits an instruction to the data processing device 12 via the communication I / F 44 to request an analysis of the diaries of all students S1 attending a specific school SC for the most recent month. Specifically, the processor 46 transmits information indicating "presenting the status of all students S1 attending the school SC for the most recent month."

[0077] Next, in step S302, the processor 46 determines whether or not a specific processing result has been received from the data processing device 12. If the specific processing result has not been received, the processor 46 repeats the process of step S302 until the specific processing result is received.

[0078] On the other hand, if the result of the specific process is received in step S302, the processor 46 displays the received result of the specific process on the display 40A and ends the acceptance output process. Specifically, the processor 46 displays "Total number of diary entries: 30, violence and harassment: 2, negative emotions: 0, poor health: 2" on the display 40A as shown in Fig. 3C. Note that, although the display is displayed on the display 40A in this embodiment, the technology of the present disclosure is not limited to this, and the result may be output by voice from the speaker 40B.

[0079] As explained above, the data processing device 12 allows the teacher T1 to efficiently investigate the past diaries of the student S1, and further allows the teacher T1 to obtain indications from perspectives that he or she would not have noticed. Also, the data processing device 12 allows the upper manager B1 to judge whether or not a problem is occurring at the school from the transition in the number of cases presented for each item while maintaining the privacy of each student S1, and can call out to the school as necessary or carry out the appropriate procedures to investigate in detail.

[0080] The emotion identification model 60 may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 60 may determine the emotion of the user according to an emotion map (see FIG. 8A), which is a specific mapping.

[0081] FIG. 8A is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0082] These emotions are distributed in the three o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0083] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0084] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0085] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0086] The emotion identification model 60 inputs user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. In addition, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 8B. FIG. 8B shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0087] 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.

[0088] 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 Universal Serial Bus (USB) 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.

[0089] In addition, 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 upon request from the data processing device 12.

[0090] 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.

[0091] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing the specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0092] The hardware resource that executes the specific process may be one of these various processors, or may be 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 process may be a single processor.

[0093] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0094] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0095] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 description and illustrations, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above description and illustrations omit explanations of technical common sense that do not require explanation in order to enable the implementation of the technology of the present disclosure.

[0096] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0097] 10 Data Processing System 12 Data Processing Device 14 Smart Devices

Claims

1. an input unit that receives user input from a manager and a person being managed who are in a teaching relationship; A processing unit that performs a specific process using a sentence generation model that generates a sentence according to an input sentence; an output unit that controls an action of the electronic device so as to output a result of the specific processing; The processing unit includes: A data processing device that uses the acceptance of user input by the administrator as a trigger condition, and when the trigger condition is satisfied, performs a specific process of presenting the status of the managed person to the administrator using the output of the sentence generation model when the input sentence is information on the submission that records the status of the managed person as user input by the managed person.

2. The data processing apparatus according to claim 1 , wherein the information is information acquired during a period designated by a user input by the administrator.

3. The input unit accepts user inputs from a plurality of managed persons, The data processing device according to claim 1 , wherein the processing unit performs the specific process for each of the managed persons.

4. The input unit accepts user input from a higher-level administrator who manages the administrator; The data processing device of claim 3, wherein the processing unit uses the acceptance of user input by the upper-level administrator as a trigger condition, and when the trigger condition is satisfied, performs the specific processing of presenting a comprehensive status of the multiple managed persons to the upper-level administrator using the output of the sentence generation model when the information as user input by the multiple managed persons is used as an input sentence.

5. accepting user input from an administrator and an administrator who are in a teaching relationship; When a user input by the manager is accepted, a process is performed as a specific process to present the status of the managed person to the manager using the output of a sentence generation model that records the status of the managed person as user input by the managed person and generates a sentence corresponding to the input sentence when information on the submission to be submitted is used as the input sentence; A data processing method for outputting a result of the specific processing.

6. accepting user input from an administrator and an administrator who are in a teaching relationship; When a user input by the manager is accepted, a process is performed as a specific process to present the status of the managed person to the manager using the output of a sentence generation model that records the status of the managed person as user input by the managed person and generates a sentence corresponding to the input sentence when information on the submission to be submitted is used as the input sentence; A program for causing a computer to execute processing including outputting the results of the specific processing.

Images