Data processing apparatus, data processing method, and program

Abstract

To provide a data processing apparatus, a data processing method, and a program for reducing the workload of staff in a nursery facility.SOLUTION: A data processing apparatus includes: an input unit for receiving a user input; a processing unit which performs first specific processing using a text generation model that generates a text according to input data; and an output unit which outputs a result of the first specific processing. The first specific processing includes a process of generating a summary record formed by summarizing life records of preschool children. The processing unit includes inputting, to the text generation model, information obtained from the user input and the life records, as the input data.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present disclosure 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 a description and related instruction sentence regarding the 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. [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] In recent years, the labor shortage and increasing complexity of work in the childcare industry have led to an increase in the workload of childcare facility staff, such as childcare workers. In particular, in addition to childcare activities that directly involve children, the increase in administrative activities (i.e., clerical work), such as creating records summarizing the status of each child and formulating childcare plans, is one of the factors that contribute to the increase in the workload of childcare workers. On the other hand, while the use of AI models, such as chatbots as mentioned above, is spreading to various fields, there is room for consideration regarding the specific methods of use in the childcare industry. [Means for solving the problem]

[0005] A first aspect of the data processing device relating to the technology disclosed herein includes an input unit that accepts user input, a processing unit that performs a first specific processing using a sentence generation model that generates sentences according to the input data, and an output unit that outputs a result of the first specific processing, wherein the first specific processing includes a process of generating a summary that summarizes a daily life record of a preschool child, and the processing unit inputs information obtained from the user input and the life record as the input data into the sentence generation model.

[0006] A second aspect of the data processing device of the technology disclosed herein relates to the data processing device of the first aspect described above, and the life record is a record about the child created by the child's guardian and a caregiver who cares for or educates the child.

[0007] A third aspect of the data processing device of the technology disclosed herein relates to the data processing device of the first or second aspect described above, and the processing unit further performs a second identification process using the sentence generation model, the second identification process including a process of generating a childcare plan for a childcare facility that provides childcare or education for the child, and the processing unit inputs information obtained from the user input, information regarding the child's development, and arrangements regarding the education and childcare of preschool children as input data into the sentence generation model.

[0008] A fourth aspect of the data processing device according to the technology disclosed herein relates to the data processing device of the third aspect described above, and the input unit is capable of accepting childcare information regarding childcare of the child, and the processing unit includes inputting information obtained from the user input, information regarding the child's development, arrangements regarding the education and childcare of preschool children, and the childcare information as input data into the sentence generation model.

[0009] A data processing device of a fifth aspect according to the technique of the present disclosure relates to the data processing device of the third or fourth aspect described above, wherein the information regarding the child's development includes a result of the first specific processing.

[0010] A data processing device of a sixth aspect of the technology disclosed herein relates to a data processing device of any of the third to fifth aspects described above, wherein the agreements regarding the education and childcare of preschool children include at least one of nursery school childcare guidelines, kindergarten education guidelines, and education and childcare guidelines for a certified early childhood education and care center.

[0011] A seventh aspect of a data processing method according to the technology disclosed herein includes the steps of accepting user input, acquiring a daily life record of a preschool child, generating input data from information obtained from the user input and the life record to be input into a sentence generation model that generates sentences according to the input data, in order to execute a first specific process to generate a summary summarizing the life record, inputting the generated input data into the sentence generation model to execute the first specific process, and outputting a result of the first specific process.

[0012] A program of an eighth aspect relating to the technology of the present disclosure causes at least one processor of a computer constituting a data processing device to execute the following processes: accepting user input; acquiring a daily life record of a preschool child; generating input data to be input into a sentence generation model that generates sentences according to the input data from information obtained from the user input and the life record, in order to execute a first specific process of generating a summary summarizing the life record; inputting the generated input data into the sentence generation model to execute the first specific process; and outputting a result of the first specific process.

[0013] A ninth aspect of the data processing device related to the technology disclosed herein comprises an input unit that accepts user input, a processing unit that performs specific processing using a sentence generation model that generates sentences according to the input data, and an output unit that outputs the results of the specific processing, wherein the specific processing includes a process of generating a childcare plan for a childcare facility that provides childcare for preschool children, and the processing unit inputs information obtained from the user input, information regarding the child's development, and agreements regarding the education and childcare of the preschool child into the sentence generation model as the input data.

[0014] A data processing device of a tenth aspect of the technology disclosed herein relates to the data processing device of the ninth aspect described above, wherein the input unit is capable of accepting childcare information relating to the child, and the processing unit includes inputting information obtained from the user input, information relating to the child's development, arrangements regarding the education and childcare of preschool children, and the childcare information as input data into the sentence generation model.

[0015] A data processing device of an eleventh aspect of the technology disclosed herein relates to the data processing device of the ninth or tenth aspect described above, wherein the agreements regarding the education and childcare of preschool children include at least one of nursery school childcare guidelines, kindergarten education guidelines, and education and childcare guidelines for a certified early childhood education and care center.

[0016] A twelfth aspect of the data processing device of the technology disclosed herein relates to any one of the ninth to eleventh aspects described above, wherein the information regarding the child's development includes at least one of a daily life record of the child and a summary summarizing the life record.

[0017] A data processing method of a thirteenth aspect relating to the technology of the present disclosure includes the steps of accepting user input, acquiring information regarding the development of a preschool child, generating input data to be input into a sentence generation model that generates sentences according to the input data from the information obtained from the user input, information regarding the development of the child, and agreements regarding the education and care of the preschool child, in order to execute a specific process of generating a childcare plan for a childcare facility that will care for the child, inputting the generated input data into the sentence generation model to execute the specific process, and outputting the results of the specific process.

[0018] A 14th aspect of the program relating to the technology of the present disclosure causes at least one processor of a computer constituting a data processing device to perform the following processes: accepting user input; acquiring information regarding the development of a preschool child; generating input data to be input into a sentence generation model that generates sentences according to the input data from the information obtained from the user input, information regarding the development of the preschool child, and agreements regarding the education and care of the preschool child, in order to execute a specific process of generating a childcare plan for a childcare facility that will care for the child; inputting the generated input data into the sentence generation model to execute the specific process; and outputting the results of the specific process. [Brief description of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram illustrating an example of a configuration of a data processing system including a data processing device according to a first embodiment of the present disclosure. [Diagram 2] FIG. 2 is a conceptual diagram showing an example of main functions of a data processing device and a smart device. [Diagram 3] 13 shows an overview of an example of a first identification process. [Figure 4] 2 shows a schematic functional configuration of a specific processing unit of the data processing device. [Diagram 5] 4 illustrates an example of an operational flow of the first identification process illustrated in FIG. 3. [Figure 6A] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 6B] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 7] 1 shows an example of a second specific process. [Figure 8] 7 illustrates an example of an operational flow of the second identification process illustrated in FIG. 6. [Figure 9] 13 shows an overview of an example of a specific process executed by a data processing device according to a second embodiment of the present disclosure. [Figure 10] 9 illustrates an example of an operational flow of the specific processing illustrated in FIG. 8. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] In the following embodiments, a coded random access memory (RAM) is a memory in which information is temporarily stored, and is mainly used as a working memory by the processor.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] <First embodiment> FIG. 1 shows an example of a configuration of a data processing system 10 according to a first embodiment of the present disclosure.

[0028] As shown in FIG. 1, a data processing system 10 may include a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server. An example of the smart device 14 is a smartphone, a tablet terminal, or a mobile PC. In this embodiment, the data processing device 12 is an example of a "data processing device" according to the technology of the present disclosure. Note that various components of the data processing device according to the technology of the present disclosure may be mounted on a device other than the data processing device 12 described below, such as the smart device 14.

[0029] The data processing device 12 may include 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 may include a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 may be connected to each other via a bus 34 so as to be able to communicate with each other. The database 24 and the communication I / F 26 may also be connected to each other via the bus 34 so as to be able to communicate with each other. The database 24 may store various information necessary for executing processes including specific processes described later. The database 24 may also be realized in the form of a cloud or the like. The communication I / F 26 may be connected to a network 54. Examples of the network 54 include a wide area network (WAN) and / or a local area network (LAN).

[0030] The smart device 14 may include a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 may include a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 may be connected to a bus 52. The reception device 38, the output device 40, and the camera 42 may also be connected to the bus 52.

[0031] The reception device 38 may include a touch panel 38A and a microphone 38B, and can receive user input. The touch panel 38A can receive user input by touching an indicator (e.g., a pen or a finger) by detecting the contact of the indicator. The microphone 38B can receive user input by voice by detecting the user's voice. The processor 46 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.

[0032] The output device 40 may include a display 40A and a speaker 40B, and presents data to the person 20 by outputting the data in a form of expression (e.g., voice and / or text) that can be perceived by the person 20. The display 40A displays visual 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.

[0033] Camera 42 is, for example, a camera built into a smartphone or tablet terminal, and can be composed of a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] 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.

[0035] FIG. 2 shows an example of main functions of the data processing device 12 and the smart device 14.

[0036] As shown in Fig. 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 may be stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 can read the specific processing program 56 from the storage 32 and execute the read specific processing program 56 on the RAM 30. The specific processing can be 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.

[0037] The storage 32 may store a data generation model 58 as an example of a sentence generation model and an emotion identification model 60. The data generation model 58 and the emotion identification model 60 may be used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 may store a reception output program 62. The reception output program 62 may be used together with the specific processing program 56 by the data processing system 10. The processor 46 may read out the reception output program 62 from the storage 50 and execute the read reception output program 62 on the RAM 48. The reception output process may be realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 62 executed on the RAM 48.

[0039] Next, the process of the specific processing unit 290 when the data processing device 12 performs specific processing for executing administrative tasks occurring in a childcare facility that cares for or educates children will be described.

[0040] The data processing system 10 including the data processing device 12 according to this embodiment performs part of the administrative work occurring in childcare facilities such as nursery teachers, etc., where preschool children (hereinafter simply referred to as "children") mainly attend, such as nursery schools, kindergartens, and certified childcare centers, on behalf of the staff of the childcare facilities. Specifically, the data processing device 12 according to this embodiment creates a summary that summarizes the daily life records of the preschool children, as a first specific process.

[0041] Here, the daily life record of a preschool child may be a record about the child made by the child's guardian (e.g., father or mother) and the caregiver who cares for or educates the child (e.g., the childcare worker who is in charge of the child at a childcare facility). More specifically, it may be a communication notebook in which the guardian and the caregiver write the child's daily condition, etc. every day. This communication notebook may be made of paper, or may be data provided in the form of an application or the like and written in. In addition, it is preferable that the contents of this communication notebook are written based on predetermined rules (specifically, a signature column for the writer and a column for writing about health conditions, etc.) so that the date of writing, the writer, the contents of the writing, etc. can be specified. Note that the record about the child is not limited to the communication notebook described above, and may be anything that allows the child's daily condition to be understood.

[0042] The summary may be a record prepared based on the child's behavior, characteristics, health condition, etc. for a specific period, for example, every month. This summary may be used to share information between childcare workers or to provide information to medical institutions or the elementary school the child will be attending in the future. Existing summaries are generally prepared by the childcare worker in charge based on the contents of the communication book, and summarize the child's behavior for a specific period in about several hundred characters.

[0043] FIG. 3 is an explanatory diagram showing an example of a situation in which the first specific processing is executed. The first specific processing in this embodiment can be executed for each child attending a childcare facility. Therefore, the data processing system 10 of this embodiment can be introduced, for example, on a childcare facility basis. In addition, in this embodiment, in order to execute the first specific processing, it is assumed that for each of a plurality of (for example, n (n=natural number)) children CH1, CH2, CH3, . . . , CHn attending a childcare facility, communication books CN1, CN2, CN3, . . . , CNn are entered in which the daily situation of the child is recorded between the guardian and the childcare worker.

[0044] When a specific period of time has elapsed while entries are continuously being made in the contact books CN1, CN2, CN3, ..., CNn, a user such as a staff member of the childcare facility (e.g., a childcare worker) inputs a user's name to create a summary via the reception device 38 of the smart device 14. When such a user's input is received, the specific processing unit 290 of the data processing device 12 executes a first specific process.

[0045] As shown in FIG. 4, the specific processing unit 290 includes an input unit 292, a processing unit 294, and an output unit 296.

[0046] The input unit 292 acquires a user input received by the smart device 14. Specifically, the input unit 292 can acquire, as the user input, a voice input of the user received by the microphone 38B of the smart device 14 or text information input via the touch panel 38A.

[0047] In addition to the user input, the input unit 292 can also acquire contact book data as an example of the daily life records of the children CH1, CH2, CH3, ..., CHn. The contact book data may be composed of text data of the contents of the contact books CN1, CN2, CN3, ..., CNn. If the contact books CN1, CN2, CN3, ..., CNn are made of paper, the contents may be converted into image data using the camera 42 of the smart device 14, for example, and the text data may be acquired by using a well-known OCR (Optical Character Recognition / Reader) function, or the image data may be input directly to the data generation model 58.

[0048] The processing unit 294 performs a specific process using the data generation model 58 as an example of a sentence generation model. Specifically, the processing unit 294 first determines whether a predetermined trigger condition is satisfied. More specifically, the trigger condition is that a voice or text question (e.g., "Please create a summary") is received from the user. Note that the processing unit 294 of this embodiment can execute a second specific process, which will be described later, in addition to the first specific process described above, but the following description will be mainly related to the first specific process.

[0049] Then, when the trigger condition is satisfied, the processing unit 294 inputs an input sentence (an example of input data) expressing an instruction for obtaining data for the specific processing, more specifically, text data, to the data generation model 58, and acquires a processing result based on the output of the data generation model 58. More specifically, when the processing unit 294 executes the first specific processing, it generates text data to be input to the data generation model 58 from information obtained from the user input accepted by the input unit 292 and the life record, more specifically, the address book data. Then, it inputs the generated text data to the data generation model 58, and acquires the processing result as a result of the first specific processing.

[0050] The processing unit 294 may estimate the emotion of the user (for example, a child, a guardian of the child, or a childcare worker) using the emotion identification model 60, and perform identification processing using the emotion of the user and the data generation model 58. In this case, the text data generated by the processing unit 294 is generated by also using a prompt corresponding to the emotion of the user estimated by the emotion identification model 60. An example of a method of identifying the emotion of the user using the emotion identification model 60 will be described later.

[0051] The output unit 296 outputs the result of the specific processing acquired by the processing unit 294. Specific methods of output include, for example, transmitting the result of the first specific processing to the smart device 14, and notifying the user of the result of the first specific processing as a summary SR1, SR2, SR3, . . . , SRn in the smart device 14 via the output device 40 or the like, or storing the summary SR1, SR2, SR3, . . . , SRn in the database 24 or the storage 50 so that the user can view it at any time.

[0052] For example, when the result of the first identification process is notified to the user by the above-mentioned method, the user may further perform a user input in response to the result. For example, when the microphone 38B acquires a voice indicating a user input in response to the result of the first identification process, the control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. Then, in the data processing device 12, the identification processing unit 290 executes the identification process again (specifically, the first identification process or the second identification process described later).

[0053] The data generation model 58 may be 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 making a neural network perform deep learning. 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 may be input. The data generation model 58 performs inference on 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.

[0054] Next, an example of the operation of the data processing system 10 will be described with reference to Fig. 5. Here, an example of the flow of a first specific process will be described with reference to Fig. 5. The flow of the first specific process shown in Fig. 5 is an example of a "data processing method" according to the technology of the present disclosure. Furthermore, this flow of the first specific process can be performed by the processor 28 of the data processing device 12, and the processing by the processor can be realized by the processor executing the specific processing program 56.

[0055] 5, when the data processing system 10 starts to operate, the specific processing unit 290 first monitors whether the reception device 38 of the smart device 14 has received a user input that is a trigger condition for the first specific processing (step S101). Here, for example, when a user input that is a trigger condition for the first specific processing is made by a staff member of a childcare facility via the reception device 38, and this user input is transmitted to the data processing device 12 via the communication I / Fs 44 and 26 and acquired by the input unit 292 (Yes in step S101), the first specific processing by the specific processing unit 290 is started.

[0056] When the first identification process is started, first, the address book data of the child for which the summary is to be created is obtained (step S102). The address book data may be stored in the database 24 in advance, or may be collected by the user together with the user's input and transmitted to the data processing device 12. In Fig. 3, the paper address books CN1, CN2, CN3, ..., CNn of a plurality of (e.g., n (n = natural number)) children CH1, CH2, ..., CHn are read using the camera 42 of the smart device 14, and converted into text data to obtain the address book data.

[0057] When the input unit 292 acquires the user input and the address book data, the processing unit 294 then generates an input sentence to be input to the data generation model 58 from the information obtained from the user input and the address book data (step S103). The generated input sentence is input to the data generation model 58, and a sentence corresponding to the input sentence is generated in the data generation model 58 (step S104).

[0058] The sentences generated by the data generation model 58 are sent to, for example, the smart device 14 as a result of the first specific process, and are output as summaries SR1, SR2, SR3, ..., SRn by the output device 40 (step S105). In parallel with this, the summaries SR1, SR2, SR3, ..., SRn are preferably stored in the database 24 or storage 50 so that staff at the childcare facility, medical facilities, etc. can view them at any time.

[0059] In the above-mentioned series of first identification processes, the input sentences input to the data generation model 58 and the corresponding output results are exemplified below.

[0060] For example, as shown in FIG. 3, a case will be described in which a staff member of a childcare facility makes a voice input to the smart device 14 as a user input, "Please make a one-month summary of XX-kun" in order to make a summary SR1 of the child CH1 for the past month. When the voice input is acquired, the processing unit 294 of the data processing device 12 starts a first specific process using the voice input as a trigger. Specifically, first, contact book data is created from the contact book CN1 of the child CH1. At this time, among the contents of the contact book CN1 from which the contact book data is created, only the records for the past month may be created as the contact book data, or records for a period longer than the past month may be created as the contact book data.

[0061] Next, the processing unit 294 generates a prompt as an input sentence, for example, "'... (contents of the contact book data)...' This is a daily record of Mr. X. Please create a summary summarizing Mr. X.'s daily record for the past month," and inputs it to the data generation model 58. When the above-mentioned prompt is input, the data generation model 58 can output a summary SR1 composed of text data or the like. Note that the contact book data may be input to the data generation model 58 in a format that is attached to the input sentence.

[0062] Returning to the description of Fig. 2, 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. 6A), which is a specific mapping.

[0063] FIG. 6A 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.

[0064] These emotions are distributed in the 3 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.

[0065] 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).

[0066] 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.

[0067] 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."

[0068] 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. 6B. FIG. 6B shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0069] The emotion value identified by the emotion identification model 60 can be used in the input sentence. When used in the input sentence, the emotion value may be changed to a prompt and made a part of the input sentence. The emotion value identified here may be, for example, the emotion value of children CH1, CH2, CH3, ..., CHn attending a childcare facility. In order to collect the emotion values ​​of each child CH1, CH2, CH3, ..., CHn when using the childcare facility, a camera capable of capturing the facial expressions of the children CH1, CH2, CH3, ..., CHn and a temperature sensor capable of measuring the body temperature of the children CH1, CH2, CH3, ..., CHn may be installed at an appropriate location in the childcare facility. The emotion values ​​collected in this manner are accumulated for each child CH1, CH2, CH3, ..., CHn and may be referred to when the first identification process is executed.

[0070] As described above, the data processing device 12, data processing method, and program according to this embodiment make it possible to create a summary for each child attending a childcare facility by using the data generation model 58. This makes it possible to significantly reduce the administrative work of the staff at the childcare facility.

[0071] Meanwhile, childcare facilities perform various administrative tasks other than the preparation of the above-mentioned minutes. For example, childcare facilities may prepare childcare plans for each class for a specific period (e.g., one week). These childcare plans are generally created for one or more classes or age groups determined by the childcare facility. A childcare plan is a schedule of childcare activities implemented by the childcare facility, and may include specific details of education or childcare (lunch times, nap times, educational curriculum, etc.) and plans for whether or not to go out.

[0072] Childcare plans must be determined based on the situation of the children in each class, events scheduled by the childcare facility, the environment around the facility, and the arrangements for the education and care of preschool children. Therefore, childcare plans are often prepared by staff at the childcare facility who are familiar with various circumstances, such as the childcare worker in charge of the class. However, when there are children in the facility, childcare workers give priority to childcare activities that involve direct contact with the children, making it difficult for them to perform administrative tasks during these activities. For these reasons, administrative tasks are performed after the children return home, which can lead to longer working hours for childcare workers.

[0073] In the data processing device 12 of this embodiment, in consideration of the above points, in addition to the first specification process, a second specification process for creating a childcare plan 80 can also be executed. The second specification process will be described below.

[0074] 7 is an explanatory diagram showing an example of a situation in which the second identification process is executed. The second identification process executed by the data processing device 12 of this embodiment can be executed for a group to which multiple children belong, for example, for a class in a childcare facility. In this embodiment, in order to execute the second identification process, the first identification process is executed in advance to create a summary SR1, SR2, SR3, . . . , SRn of children CH1, CH2, CH3, . . . , CHn belonging to a specific class in a childcare facility.

[0075] When a user, such as a staff member of a childcare facility, performs user input for creating a childcare plan 80 via a reception device 38 of the smart device 14, the specific processing unit 290 of the data processing device 12 executes a second specific process.

[0076] The second specific process is executed by the above-mentioned specific processing unit 290. The specific processing unit 290 may determine whether the specific process to be executed is the first specific process or the second specific process based on the contents of the user input acquired by the input unit 292, etc. Specifically, for example, by setting different trigger conditions for the first specific process and the second specific process as predetermined trigger conditions set in the processing unit 294, the first specific process and the second specific process can be selectively executed.

[0077] When a trigger condition for executing the second specific processing, which is set in the processing unit 294 of the specific processing unit 290, is satisfied, the processing unit 294 collects some information to execute the second specific processing. Specifically, the processing unit 294 collects information on child development and the agreement 70 on education and childcare for preschool children. In this embodiment, the information on child development is exemplified as being the summary SR1, SR2, SR3, . . . , SRn of specific children CH1, CH2, CH3, . . . , CHn created in advance by executing the first specific processing.

[0078] Here, the agreements on education and childcare for preschool children (hereinafter also referred to as "childcare guidance guidelines") 70 can be laws or agreements established by administrative agencies that have jurisdiction over childcare facilities. Specifically, the childcare guidance guidelines 70 may include at least one of the nursery school childcare guidelines, kindergarten education guidelines, and education and childcare guidelines for certified kindergarten-kindergarten ...

[0079] In addition, in the second identification process executed by the data processing device 12 of this embodiment, in addition to the above-mentioned two pieces of information, childcare information related to childcare may be further accepted. Childcare information related to childcare may include various information related to childcare, such as annual events determined for each childcare facility, facility information around the childcare facility (e.g., whether there is a park or a children's center, etc.), equipment information of the childcare facility itself, or requests from the childcare worker in charge. Such childcare information may be acquired by the input unit 292, for example, by a staff member of the childcare facility individually inputting it via the reception device 38 of the smart device 14. By using the childcare information in the second identification process, requests from the actual childcare site can be easily reflected in the childcare plan 80.

[0080] Next, the operation of the data processing system 10 will be described with reference to Fig. 8. Here, an example of the flow of the second specific process will be described with reference to Fig. 8. Note that this flow of the second specific process can be performed by the processor 28 of the data processing device 12, and the processing by the processor can be realized by the processor executing the specific processing program 56.

[0081] 8, when the data processing system 10 starts operating, the specific processing unit 290 first monitors whether the reception device 38 of the smart device 14 has received a user input that is a trigger condition for the second specific processing (step S111). Here, for example, when a user input that is a trigger condition for the second specific processing is made by a staff member of a childcare facility via the reception device 38, and this user input is transmitted to the data processing device 12 via the communication I / Fs 44 and 26 and acquired by the input unit 292 (Yes in step S111), the second specific processing by the specific processing unit 290 is started.

[0082] When the second identification process is started, first, the result of the first identification process acquired in advance is acquired (step S112). The result of the first identification process here may be data of the records SR1, SR2, SR3, ..., SRn of the children CH1, CH2, CH3, ..., CHn belonging to a specific class. The data of the records SR1, SR2, SR3, ..., SRn may be stored in the database 24 or the storage 50 in advance, or may be collected by executing the first identification process immediately before executing the second identification process.

[0083] In the second specific process, in parallel with obtaining data of the summaries SR1, SR2, SR3, ..., SRn, the childcare teaching guidelines 70 are obtained (step S113) and the childcare information 75 is received (step S114). The childcare teaching guidelines 70 may be obtained by previously storing them in the database 24. The childcare information 75 may be received by requesting it from the user when the trigger condition of the second specific process is satisfied, or by obtaining information that has been registered in advance. Note that steps S112 to S114 may be performed at least partially simultaneously, or may be performed in any order.

[0084] When the input unit 292 acquires the user input, the data of the summaries SR1, SR2, SR3, . . . , SRn, the childcare teaching guidelines 70, and the childcare information 75, the processing unit 294 then generates an input sentence to be input to the data generation model 58 from the information obtained from the user input, the data of the summaries SR1, SR2, SR3, . . . , SRn, the childcare teaching guidelines 70, and the childcare information 75 (step S115). The generated input sentence is input to the data generation model 58, and the data generation model 58 generates a sentence corresponding to the input sentence (step S116).

[0085] The text generated by the data generation model 58 is sent to, for example, the smart device 14 as a result of the second specific process, and is output as a childcare plan 80 by the output device 40 (step S105). In parallel with this, the childcare plan 80 is preferably stored in the database 24 or storage 50 so that staff at the childcare facility, medical facilities, etc. can view it at any time.

[0086] In the above-mentioned series of second identification processes, the input sentences input to the data generation model 58 and the corresponding output results are exemplified below.

[0087] For example, as shown in Fig. 7, a case will be described in which a staff member of a childcare facility makes a voice input to the smart device 14 as a user input, "Please make a childcare plan suitable for the children in class A" in order to make a childcare plan 80 for a specific class. When the voice input is acquired, the processing unit 294 of the data processing device 12 starts a second specific process using the voice input as a trigger. Specifically, first, the summary data of the children belonging to class A, the childcare teaching guidelines 70, and the childcare information 75 are collected.

[0088] Next, the processing unit 294 generates a prompt as an input sentence, for example, "This is the summary, childcare guidance, and childcare information of the children in class A. Please create a childcare plan that suits these children." Then, the prompt is input to the data generation model 58 together with the summary data of all the children belonging to class A, the childcare guidance 70, and the childcare information 75. When the data generation model 58 receives the above-mentioned prompt and various data, it can output a childcare plan 80 composed of text data, etc.

[0089] As described above, the data processing device 12, data processing method, and program according to this embodiment can use the data generation model 58 to create a childcare plan in addition to creating a summary for each child attending the childcare facility. This can further significantly reduce the administrative work of the childcare facility staff. In addition, because the summary and childcare plan are created automatically, it can also suppress the variation in quality caused by the ability of the childcare worker who creates the summary and childcare plan, which occurred in the previous method.

[0090] <Second embodiment> In the above-mentioned first embodiment, when creating the childcare plan 80 by the second specification process, the summary created by the first specification process is used as part of the input text, but the method of creating the childcare plan 80 is not limited to this. Specifically, the data processing device, data processing method, and program disclosed herein can also create the childcare plan 80 based on information other than the summary created by the first specification process. Therefore, hereinafter, as the second embodiment of the present disclosure, a method of creating a childcare plan that is different from the above-mentioned second specification process will be described.

[0091] The data processing device, data processing method, and program according to the second embodiment are the same as the second specific process described in the first embodiment, except that the information used in the processing unit is different. Therefore, the following description will omit the description of the same points as in the first embodiment, and will focus on the points that are different from the first embodiment.

[0092] FIG. 8 is an explanatory diagram showing an example of a situation in which a specific process is executed in the data processing device of the second embodiment. The specific process executed by the data processing device 12A of this embodiment can be executed in units of a group to which a plurality of children belong. The data processing device 12A of this embodiment may be composed of the same components as the data processing device 12 of the first embodiment. The data processing device 12A can also operate on a system similar to the data processing system 10 described above. Therefore, the description of the configuration of the data processing device 12A is to be taken from that of the data processing device 12, and the description will be omitted here.

[0093] When a user such as a staff member of a childcare facility inputs a user's input for creating a childcare plan 80 via the reception device 38 of the smart device 14, the specific processing unit 290 of the data processing device 12A executes a specific process. The specific process in this embodiment may be executed with the user input acquired by the input unit 292 of the specific processing unit 290 as a trigger.

[0094] When the trigger condition set in the processing unit 294 of the specific processing unit 290 is satisfied, the processing unit 294 collects some information to execute the specific processing. Specifically, the processing unit 294 collects the information 90 about the child's development and the arrangements 70 about the education and care of the preschool child.

[0095] Here, the information on the development of the child (hereinafter also referred to as "child development information") 90 in this embodiment may include various information related to the child. Specifically, it may include a daily life record of a preschool child, as typified by the above-mentioned communication book, and a summary of the child's situation, etc., created by a childcare worker. This child development information 90 may be automatically created using an AI model, etc., or may be manually created by a childcare worker or a guardian and collected in the form of an image or text.

[0096] Also in the specific process executed by the data processing device 12A of this embodiment, childcare information 75 relating to childcare can be further used in the input text, similarly to the first embodiment.

[0097] Next, an example of the operation of a data processing system including the data processing device 12A will be described with reference to Fig. 10. Here, an example of the flow of a specific process in this embodiment will be described with reference to Fig. 10. Note that this flow of the specific process can be performed by the processor 28 of the data processing device 12, and the processing by the processor can be realized by the processor executing the specific processing program 56.

[0098] As can be seen from Fig. 10, the identification process executed by the data processing device 12A of this embodiment is similar to the flow of the second identification process shown in Fig. 8, except that after accepting a user input, instead of acquiring the result of the first identification process (step S112), child development information is acquired (step S112A). In relation to the above point, in step S115 of this embodiment, the processing unit 294 generates an input sentence to be input to the data generation model 58 from the information obtained from the user input, the child development information 90, the childcare teaching guidelines 70, and the childcare information 75.

[0099] As described above, the data processing device 12A, data processing method, and program according to the present embodiment make it possible to create a childcare plan using the data generation model 58. This allows the clerical work of the staff at the childcare facility to be significantly reduced. In addition, since the childcare plan is created automatically, it is also possible to suppress the variation in quality caused by the ability of the childcare worker who creates the childcare plan, which occurred in the previous method.

[0100] In each of the above embodiments, 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.

[0101] In each of the above embodiments, 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.

[0102] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing devices 12, 12A 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.

[0103] 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, 12A 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.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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]

[0110] 10 Data Processing System 12, 12A Data Processing Unit 14 Smart Devices 58 Data generation model (an example of a text generation model) 70 Childcare Guidance Guidelines (Examples of arrangements concerning the education and care of preschool children) 75 Childcare Information 80 Childcare Plan 90 Child Development Information 290 Specific Processing Department 292 Input section 294 Processing section 296 Output section

Claims

1. an input unit for accepting user input; A processing unit that performs a first identification process using a sentence generation model that generates sentences according to input data; an output unit that outputs a result of the first identification process, The first specific process includes generating a summary of the preschool child's daily life record; The processing unit inputs information obtained from the user input and the life record as the input data to the sentence generation model. Data processing device.

2. The life record is a record about the child created by the child's guardian and a caregiver who cares for or educates the child.

2. A data processing apparatus according to claim 1.

3. The processing unit further performs a second identification process using the sentence generation model, The second identification process includes a process of generating a childcare plan for a childcare facility that provides childcare or education for the child, The processing unit inputs the information obtained from the user input, the information regarding the child's development, and the arrangement regarding the education and care of the preschool child as the input data into the sentence generation model.

2. A data processing apparatus according to claim 1.

4. The input unit is capable of receiving childcare information related to childcare of the child, The processing unit inputs the information obtained from the user input, the information regarding the child's development, the arrangement regarding the education and care of the preschool child, and the childcare information as the input data into the sentence generation model.

4. A data processing apparatus according to claim 3.

5. The information regarding the child's development includes a result of the first identification process.

4. A data processing apparatus according to claim 3.

6. The arrangements regarding education and childcare for preschool children include at least one of the following: nursery school childcare guidelines, kindergarten education guidelines, and kindergarten-nursery school education and childcare guidelines; 4. A data processing apparatus according to claim 3.

7. accepting user input; obtaining a daily life record of a preschool child; A step of generating input data to be input to a sentence generation model that generates sentences according to input data from information obtained from a user input and the life record, in order to execute a first specific process of generating a summary that summarizes the life record; inputting the generated input data into the sentence generation model and executing the first identification process; and outputting a result of the first identification process. Data processing methods.

8. At least one processor of a computer constituting a data processing device A process for accepting user input; A process of obtaining a daily life record of a preschool child; A process for generating input data to be input to a sentence generation model that generates sentences according to input data from information obtained from a user input and the life record in order to execute a first specific process for generating a summary that summarizes the life record; A process of inputting the generated input data into the sentence generation model and executing the first specific process; and outputting a result of the first specific process. program.

9. an input unit for accepting user input; A processing unit that performs a specific process using a sentence generation model that generates sentences according to input data; an output unit that outputs a result of the specific processing, The identification process includes a process of generating a child care plan for a child care facility that provides child care for preschool children; The processing unit inputs the information obtained from the user input, the information regarding the child's development, and the arrangement regarding the education and care of the preschool child as the input data into the sentence generation model. Data processing device.

10. The input unit is capable of receiving childcare information related to the child, The processing unit inputs the information obtained from the user input, the information regarding the child's development, the arrangement regarding the education and care of the preschool child, and the childcare information as the input data into the sentence generation model.

10. A data processing apparatus according to claim 9.

11. The arrangements regarding education and childcare for preschool children include at least one of the following: nursery school childcare guidelines, kindergarten education guidelines, and kindergarten-nursery school education and childcare guidelines; 10. A data processing apparatus according to claim 9.

12. The information regarding the child's development includes at least one of a daily life record of the child and a summary of the daily life record.

10. A data processing apparatus according to claim 9.

13. accepting user input; obtaining information regarding the development of a preschool child; generating input data from the information obtained from the user input, information about the development of the child, and the education and care arrangements for the preschool child to be input into a sentence generation model that generates sentences according to the input data, in order to execute a specific process of generating a childcare plan for the childcare facility that will care for the child; inputting the generated input data into the sentence generation model and executing the specific process; and outputting a result of the specific processing. Data processing methods.

14. At least one processor of a computer constituting a data processing device A process for accepting user input; Obtaining information about the development of preschool children; a process of generating input data to be input to a sentence generation model that generates sentences according to the input data from information obtained from the user input, information about the development of the child, and agreements regarding the education and care of the preschool child, in order to execute a specific process of generating a childcare plan for the childcare facility that will care for the child; A process of inputting the generated input data into the sentence generation model and executing the specific process; and outputting a result of the specific processing. program.

Images