Information processing device, method, program and system

Abstract

Improve the efficiency of writing documents. [Solution] The program causes the processor to execute the following steps: receiving from a first user a designation of a child or a group to which the child belongs as a target for generating sentence suggestions; identifying one or more images from among images recording activities related to child welfare stored in a database as images related to the child or group designated as a target for generation; generating a prompt including instructions including reading the situation of the identified image and generating a sentence suggestion related to the child or group designated as a target for generation based on the read situation; inputting the prompt including information about the image into the large-scale language model to obtain sentence suggestions from the large-scale language model; and presenting the obtained sentence suggestions to the first user.

Description

[Technical field]

[0001] The present disclosure relates to an information processing device, a method, a program, and a system. [Background technology]

[0002] In addition to providing support for the daily lives and education of children, staff at child welfare facilities, such as childcare workers and early childhood educators, also perform paperwork tasks such as contacting parents, recording work content, and publicizing activities. Because paperwork is time-consuming and laborious, there is a demand for efficiency in this task.

[0003] Patent Document 1 describes an image utilization system 10. The image utilization system 10 in Patent Document 1 acquires an image including a child 80 captured by the image capture function of a childcare worker terminal 30 or a parent terminal 20, generates a processed image by performing a predetermined process on the acquired image, including adding data and / or deleting data and / or correcting data, and generates service data as data to be used for various services using the data incorporating the processed image, thereby creating a processed image suitable for each communication tool, and creating a communication tool to which a processed image suitable for the purpose of each communication tool is automatically selected and applied, thereby making it possible to appropriately apply images to communication tools created by a childcare center 110 or the like, thereby improving the efficiency of operations. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2022-071553 Summary of the Invention [Problem to be solved by the invention]

[0005] The image utilization system described in Patent Document 1 was insufficiently efficient in creating text to be written on documents.

[0006] An object of the present disclosure is to improve the efficiency of creating text to be written in documents. [Means for solving the problem]

[0007] The program causes the processor to execute the following steps: receiving from a first user a designation of a child or a group to which the child belongs as a target for generating sentence suggestions; identifying one or more images from among images recording activities related to child welfare stored in the database as images related to the child or group designated as the target for generation; generating a prompt including instructions including reading the situation of the identified image and generating a sentence suggestion related to the child or group designated as the target for generation based on the read situation; inputting the prompt including information about the image into the large-scale language model to obtain sentence suggestions from the large-scale language model; and presenting the obtained sentence suggestions to the first user. Effect of the Invention

[0008] According to the present disclosure, the creation of text to be written on a document can be made more efficient. [Brief description of the drawings]

[0009] [Figure 1] FIG. 2 is a block diagram showing the functional configuration of the system 1. [Diagram 2] 2 is a block diagram showing the functional configuration of the terminal device 10. FIG. [Diagram 3] FIG. 2 is a block diagram showing the functional configuration of the server 20. [Figure 4] FIG. 2 is a diagram showing an example of the configuration of a prompt P. [Diagram 5] FIG. 2 is a diagram showing the data structure of a user table 2021. [Figure 6] FIG. 2 shows the data structure of a child table 2022. [Figure 7] FIG. 2 shows the data structure of an image table 2023. [Figure 8] 2 shows the data structure of a document type table 2024. FIG. [Figure 9] 2 shows the data structure of an output format table 2025. FIG. [Figure 10] FIG. 23 is a diagram showing the data structure of a text table 2026. [Figure 11] FIG. 2 shows the data structure of a log management table 2027. [Figure 12] 4 is a flowchart of a document generation process according to the present embodiment. [Figure 13] FIG. 13 is a schematic diagram showing an example of an input screen D1. [Figure 14] FIG. 13 is a schematic diagram showing an example of a text proposal display screen D2. [Figure 15] 4 is a flowchart of an evaluation process according to the present embodiment. [Figure 16] FIG. 13 is a schematic diagram showing an example of a condition setting screen D3. [Figure 17] FIG. 13 is a schematic diagram showing an example of a result display screen D4. [Figure 18] FIG. 2 is a block diagram showing the basic hardware configuration of a computer 90. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, an embodiment of the present disclosure will be described with reference to the drawings. In all the drawings explaining the embodiment, the same reference numerals are given to common components, and repeated explanations are omitted. Note that the following embodiment does not unduly limit the contents of the present disclosure described in the claims. In addition, not all of the components shown in the embodiment are necessarily essential components of the present disclosure. In addition, each figure is a schematic diagram and is not necessarily illustrated strictly.

[0011] In the following description, a "processor" refers to one or more processors. The at least one processor is typically a microprocessor such as a CPU (Central Processing Unit), but may be another type of processor such as a GPU (Graphics Processing Unit). The at least one processor may be a single-core or multi-core.

[0012] Furthermore, the at least one processor may be a processor in the broad sense, such as a hardware circuit (for example, a field-programmable gate array (FPGA) or an application specific integrated circuit (ASIC)) that performs part or all of the processing.

[0013] In the following explanation, information that gives an output for an input may be described using an expression such as "xxx table", but this information may be data of any structure or a learning model such as a neural network that generates an output for an input. Therefore, the "xxx table" may be called "xxx information".

[0014] Furthermore, in the following description, the configuration of each table is an example, and one table may be divided into two or more tables, or all or part of two or more tables may be one table.

[0015] In addition, in the following explanation, the processing may be described with the "program" as the subject, but since the program is executed by a processor to perform a specified processing step by appropriately using a memory unit and / or an interface unit, etc., the subject of the processing may be the processor (or a device such as a controller having the processor).

[0016] The program may be installed in a device such as a computer, or may be, for example, in a program distribution server or a computer-readable (e.g., non-transitory) recording medium. In the following description, two or more programs may be realized as one program, or one program may be realized as two or more programs.

[0017] In the following description, identification numbers are used as identification information for various objects, but other types of identification information (for example, identifiers including alphabetic characters or symbols) may be used instead.

[0018] In addition, in the following description, when describing elements of the same type without distinguishing between them, reference signs (or common signs among the reference signs) may be used, and when describing elements of the same type with distinction between them, the identification numbers (or reference signs) of the elements may be used.

[0019] In the following description, the control lines and information lines are those that are considered necessary for the description, and not all control lines and information lines in the product are necessarily shown. All components may be connected to each other.

[0020] Each information processing device is configured by a computer equipped with a calculation device and a storage device. The basic hardware configuration of the computer and the basic functional configuration of the computer realized by the hardware configuration will be described later. For each of the terminal device 10 and the server 20, descriptions that overlap with the basic hardware configuration and basic functional configuration of the computer described later will be omitted.

[0021] <Definition> In this disclosure, documents are documents related to activities related to child welfare. Documents include, for example, documents (diaries, reports, business records, plans, etc.) used by people working at child welfare facilities (childcare workers, etc.) for recording, reporting, etc., and documents (communication books, letters, etc.) used to report to people (children, etc.) belonging to child welfare facilities and their guardians.

[0022] In this disclosure, a child is a child who belongs to (attends) a child welfare facility. A group to which a child belongs is a group that includes a child in a child welfare facility, and includes, for example, a child welfare facility, a year, a class, a group, etc. In the following description, "a child or a group to which a child belongs" will be simply referred to as "children, etc."

[0023] <Configuration> A description will be given of the configuration of an information processing system according to the first embodiment. Fig. 1 is a block diagram illustrating the configuration of an information processing system according to the first embodiment.

[0024] As shown in FIG. 1, the information processing system 1 includes a terminal device 10, a server 20, and a generating AI 40.

[0025] 1, the number of terminal devices 10 included in the system 1 is not limited to one. The number of terminal devices 10 included in the system 1 may be two or more.

[0026] 1 shows an example in which the system 1 includes one server 20, but the number of servers 20 included in the system 1 is not limited to one. The servers 20 may each be composed of a plurality of servers depending on the functions they have. Also, for example, each server 20 may be a collection of a plurality of devices as one server. The method of allocating a plurality of functions required to realize the server 20 according to this embodiment to one or a plurality of hardware devices can be appropriately determined in consideration of the processing capacity of each hardware device and / or the specifications required for the server 20.

[0027] 1 is realized by, for example, a desktop PC (Personal Computer) or a laptop PC. The terminal device 10 may also be realized by, for example, a mobile terminal such as a smartphone or tablet compatible with a mobile communication system. The terminal device 10 may also be realized by, for example, a wearable terminal such as an HMD (Head Mount Display).

[0028] The terminal device 10 includes a communication IF (Interface) 12, an input device 13, an output device 14, a memory 15, a storage 16, and a processor 19. The input device 13 is a device (e.g., a touch panel, a touch pad, etc.) for receiving an input operation from a user. The output device 14 is a device (a display, a speaker, etc.) for presenting information to a user.

[0029] The server 20 is realized, for example, by an information processing device connected to a network 80. As shown in Fig. 1, the server 20 includes a communication IF 22, an input / output IF 23, a memory 25, a storage 26, and a processor 29. The input / output IF 23 functions as an interface of an input device for receiving an input operation from a user and an output device for presenting information to the user.

[0030] The generation AI 40 is an artificial intelligence model executed by one or more information processing devices connected to the network 80. The generation AI 40 generates an output based on a user's input (prompt text, image, etc.) using a model previously trained. Examples of the generation AI 40 include GPT, Claude, LLaMA, BERT, and Gemini. The generation AI 40 may be a model capable of collectively processing multiple types of data such as text, image, audio, and video. In the present disclosure, a large-scale language model that mainly outputs text information as output information will be described as a type of the generation AI 40. The generation AI 40 may also be incorporated in the server 20.

[0031] Each information processing device is composed of a computer equipped with a calculation device and a storage device. The basic hardware configuration of the computer and the basic functional configuration of the computer realized by the hardware configuration will be described later. For each of the terminal device 10, the server 20, and the generation AI 40, the explanations that overlap with the basic hardware configuration and basic functional configuration of the computer described later will be omitted.

[0032] <Configuration of Terminal Device 10> Fig. 2 is a block diagram showing an example of the configuration of the terminal device 10 shown in Fig. 1. As shown in Fig. 2, the terminal device 10 includes a communication unit 120, an input device 13, an output device 14, an audio processing unit 17, a microphone 171, a speaker 172, a storage unit 180, and a control unit 190. The blocks included in the terminal device 10 are electrically connected to each other, for example, by a bus or the like.

[0033] The communication unit 120 performs processing such as modulation and demodulation processing for the terminal device 10 to communicate with other devices. The communication unit 120 performs transmission processing on a signal generated by the control unit 190 and transmits the signal to the outside (for example, the server 20). The communication unit 120 performs reception processing on a signal received from the outside and outputs the signal to the control unit 190.

[0034] The input device 13 is a device for inputting instructions or information by a user who operates the terminal device 10. The input device 13 is realized by a reader, a keyboard 131, a mouse 132, etc. The input device 13 may be realized by a touch-sensitive device in which an instruction is input by touching an operation surface. The input device 13 converts an instruction input by a user into an electrical signal, and outputs the electrical signal to the control unit 190. The input device 13 may include, for example, a receiving port that receives an electrical signal input from an external input device.

[0035] The output device 14 is a device for presenting information to a user who operates the terminal device 10. The output device 14 is realized, for example, by a display 141 or the like. The display 141 displays data according to the control of the control unit 190. The display 141 is realized, for example, by an LCD (Liquid Crystal Display) or an organic EL (Electro-Luminescence) display or the like.

[0036] The audio processing unit 17 performs, for example, digital-analog conversion processing of an audio signal. The audio processing unit 17 converts a signal provided from the microphone 171 into a digital signal and provides the converted signal to the control unit 190. The audio processing unit 17 also provides the audio signal to the speaker 172. The audio processing unit 17 is realized, for example, by a processor for audio processing. The microphone 171 accepts audio input and provides an audio signal corresponding to the audio input to the audio processing unit 17. The speaker 172 converts the audio signal provided from the audio processing unit 17 into audio and outputs the audio to the outside of the terminal device 10.

[0037] The storage unit 180 is realized by, for example, the memory 15, the storage 16, etc., and stores data and programs used by the terminal device 10. The storage unit 180 stores, for example, user information 181.

[0038] Information about the operating user is stored in the user information 181. The information about the user includes, for example, a user ID, a name, an age, an address, a date of birth, and a date of registration to the service.

[0039] The control unit 190 is realized by the processor 19 reading a program stored in the storage unit 180 and executing instructions included in the program. The control unit 190 controls the operation of the terminal device 10. The control unit 190 performs functions as an operation reception unit 191, a transmission / reception unit 192, and a presentation control unit 193 by operating according to the program.

[0040] The operation reception unit 191 performs processing for receiving instructions or information input from the input device 13. For example, the operation reception unit 191 receives instructions or information input from the input device 13 or the like.

[0041] Furthermore, the operation reception unit 191 receives audio information input from the microphone 171. Specifically, for example, the operation reception unit 191 receives audio data that is input from the microphone 171 and converted into digital data by the audio processing unit 17.

[0042] The transmitting / receiving unit 192 performs processing for the terminal device 10 to transmit and receive data to and from an external device such as the server 20 in accordance with a communication protocol. Specifically, for example, the transmitting / receiving unit 192 transmits an instruction input by a user to the server 20. The transmitting / receiving unit 192 receives information provided by the server 20.

[0043] The presentation control unit 193 controls the output device 14 and the like to present information such as information provided by the server 20 to the user.

[0044] <Functional configuration of server 20> 3 is a diagram showing an example of a functional configuration of the server 20. As shown in FIG. 3, the server 20 fulfills the functions of a communication unit 201, a storage unit 202, and a control unit 203.

[0045] The communication unit 201 performs processing for the server 20 to communicate with external devices.

[0046] The memory unit 202 includes, for example, a user table 2021, a child table 2022, an image table 2023, a document type table 2024, an output format table 2025, a text table 2026, a log management table 2027, and the like. The memory unit 202 may also store time period information that corresponds the start and end points of a specific time period with activities that take place during that time period (for example, 8:30-9:00: arriving at school, 9:00-10:00: morning meeting, 10:00-11:00: class activities, 11:00-11:30: preparing lunch, 11:30-13:00: lunch, 13:00-14:30: nap, 14:30-15:00: snack, 15:00-16:00: playing outside, 16:00-: leaving school).

[0047] The user table 2021 is a table that stores information about users who register with the service according to this embodiment. In this embodiment, the user is, for example, a person who performs the task of creating text related to the text proposal generated in this embodiment, and one example is a childcare worker.

[0048] The child table 2022 is a table that stores information about children.

[0049] The image table 2023 is a table that stores image information relating to children.

[0050] The document type table 2024 is a table for managing the types of documents created in child welfare facilities.

[0051] The output format table 2025 is a table that stores information regarding the format or output examples of text to be written on documents created in child welfare facilities.

[0052] The sentence table 2026 is a table that stores information related to sentences to be written on documents for recording activities related to child welfare. Specifically, the sentence table 2026 stores information used to generate a draft of a sentence to be written on a document for recording activities related to child welfare, information related to the draft, and information related to a sentence created based on the draft.

[0053] The log management table 2027 is a table that stores log information that associates the child's condition with the time (or date without time) when the condition was observed or recorded. The log information is, for example, the following information: Information regarding attendance at a child welfare facility (attending school, going to kindergarten, attending school, etc.) Information about leaving a child welfare facility (dropping off, leaving the facility, leaving the facility, etc.) Information on health status (temperature checks, excretion, etc.) Dietary information (food and fluid intake, etc.) -Information about sleep (falling asleep, waking up, sleep state, etc.)

[0054] The storage unit 202 may have different log management tables 2027 for each type of child's condition, such as sleep-related condition, diet-related condition, etc. For example, the storage unit 202 may store information on attendance at a child welfare facility and returning home, information on sleep, information on the child's health condition (temperature check, excretion, etc.), information on the child's diet, etc., in different log management tables 2027. Also, one or more time periods may be associated with a table for managing log information related to the time period. As an example, a log management table 2027A for managing log information related to meals associated with a time period of "11:30-13:00: lunch" and a log management table 2027B for managing log information related to sleep associated with a time period of "13:00-14:30: afternoon nap" may be defined.

[0055] The control unit 203 is realized by the processor 29 reading a program stored in the storage unit 202 and executing instructions included in the program. The control unit 203 operates in accordance with the program to fulfill functions as a reception control module 2031, a transmission control module 2032, a prompt generation module 2033, an evaluation module 2034, a log management module 2035, a presentation module 2036, and the like.

[0056] The reception control module 2031 controls the process in which the server 20 receives signals from external devices in accordance with a communication protocol. Specifically, for example, the reception control module 2031 receives signals transmitted from the terminal device 10 and the large-scale language model.

[0057] The transmission control module 2032 controls the process in which the server 20 transmits a signal to an external device in accordance with a communication protocol. For example, the transmission control module 2032 transmits information about various UIs (described later) to be displayed on the display 141 of the terminal device 10 to the terminal device 10. For example, the transmission control module 2032 transmits a request including a prompt to the large-scale language model.

[0058] The prompt generation module 2033 generates a prompt for input to the large-scale language model. The prompt is input data for instructing the generation of output data from the large-scale language model and for guiding the contents of the output data. The prompt may include various types of information including text data and image data (including still images and videos). The image data included in the prompt may be data in any image format such as JPEG, or may be encoded in text format or the like. The prompt may be in a format that causes the large-scale language model to read the image data by including a link such as a URL or a file path to a location where the image data is stored.

[0059] 4 is a diagram showing an example of the configuration of a prompt P generated by the prompt generation module 2033. The prompt P is text data, and includes text data of each portion exemplified by role instructions P1, document-specific instructions P2, child information P3, time period designation P4, image information P5, output format P6, and log information P7. The order in which role instructions P1 to log information P7 are written is not particularly limited. The prompt P does not need to include all of role instructions P1 to log information P7, and may include character strings other than role instructions P1 to log information P7.

[0060] (Role Instructions P1) The role instruction P1 includes a sentence that specifies the role (position) of the large-scale language model when generating a sentence proposal. The role instruction P1 includes a sentence that specifies the position of the large-scale language model when generating a sentence, such as "You are an excellent childcare worker." The prompt generation module 2033 generates a prompt P by combining the following document-specific instructions P2 through log information P7 with the role instructions P1.

[0061] (Document specific instructions P2) The document-specific instructions P2 include a sentence that indicates the type of document for which a text draft is to be generated. The document-specific instructions P2 also include instructions regarding the content to be included in the text draft, which differs depending on the type of document. For example, if the document type is a "communication notebook," the document-specific instructions P2 may include a sentence such as, "Please create a text draft to be written in the communication notebook used for communicating with parents. Please output the child's efforts, facial expressions, state, and special notes estimated from the image in accordance with the format below." The prompt generation module 2033 generates a prompt including different instructions according to the type of document specified by the user. For example, the prompt generation module 2033 searches the document type table 2024 (described later) based on the type of document specified by the user, obtains text data of the item "document-specific instructions" of the corresponding record, and combines it with the role instructions P1 as document-specific instructions P2.

[0062] (Children's Information P3) The child information P3 includes a sentence that specifies the child, etc. for which a sentence proposal is to be generated. Specifically, the child information P3 includes information that can identify the child, etc. (the child's ID, name, etc., or the ID, name, etc. of the group to which the child belongs). The prompt generation module 2033, for example, searches the child table 2022 described below based on information about a child or other person specified by the user, identifies the identification information of the child or other person specified by the user (child ID, facility ID, class ID, group ID, etc.), and combines a sentence containing the identified identification information with the role instruction P1 as child information P3.

[0063] (Time zone specification P4) The time period specification P4 includes an instruction for specifying a time period. Specifically, the time period specification P4 includes an instruction for including a description of the specified time period in the text proposal. The time period specification P4 may also include an instruction for specifying a plurality of time periods and generating text proposals divided for each of the specified time periods.

[0064] An example of a time period specification P4 is shown below. Note that the fields enclosed in curly brackets are dynamically filled in by the prompt generation module 2033. (Example of time zone specification P4) Below is the facility's daily schedule by time period. Please write the draft sentences about the children's behavior during {time period 1} and {time period 2}, and print them out separately for each time period. {Time Zone 1} corresponds to {Image 1}. {Time Zone 2} corresponds to {Image 2}. 8:30-9:00: Arrival 9:00-10:00: Morning meeting 10:00-11:00: Class activities 11:00-11:30: Lunch preparation (excretion, washing hands, gargling) 11:30-13:00: Lunch ·13:00-14:30: Nap 14:30-15:00: Snacks 15:00-16:00: Outdoor play 16:00- : Leave school

[0065] When the user specifies one or more images and one or more time periods, the prompt generation module 2033 refers to the one or more time periods and the shooting times of the one or more images to determine, from among the one or more images, an image that corresponds to the time period specified by the user. For example, the module 2033 determines, as the image that corresponds to the time period specified by the user, an image whose shooting time falls within the time period specified by the user.

[0066] It is not essential for the user to specify a time period. In that case, the prompt generation module 2033 may refer to the time period information stored in the storage unit 202, identify the time period that includes the shooting time of the image specified by the user among all the time periods, and associate the image with the time period.

[0067] Then, the prompt generation module 2033 generates text including instructions to generate sentence suggestions including sentences related to each time period, separated by time period, by reading the situation of the image corresponding to each time period from the large-scale language model, and combines it with the role instruction P1 as a time period specification P4.

[0068] (Image information P5) The image information P5 includes a sentence that specifies an image to be read by the large-scale language model. For example, the image information P5 includes image data converted into an arbitrary format and information that can identify the image (image identification information, image URL, etc.). The prompt generation module 2033, for example, searches the image table 2023 described below based on the information of the image specified by the user, identifies the destination information for the image specified by the user, and combines the text containing the destination information with the role instruction P1 as image information P5.

[0069] (Output format P6) The output format P6 includes information on the output format (template) of the text proposal and an example of generating the text proposal. In this embodiment, the content of the output format P6 corresponds to the document type. The prompt generation module 2033 generates a prompt including information on the output format of the text proposal, which varies depending on the type of document specified by the user. For example, the prompt generation module 2033 searches the output format table 2025 (described later) based on the type of document specified by the user, obtains text data of the item "output format" of the corresponding record, and combines it with the role instruction P1 as the output format P6.

[0070] (Log information P7) The log information P7 includes log information to be referred to by the large-scale language model when generating sentence suggestions. The prompt generation module 2033, for example, retrieves log information for a child specified by the user from the log management table 2027 on a date specified by the user, and combines it with the role instruction P1 as log information P7 along with an instruction to generate a sentence proposal by referring to the log information.

[0071] The prompt generation module 2033 may extract log information recorded for the child specified by the user at a time included in the time period associated with the image from the log management table 2027, and include it in the log information P7. Then, when generating a sentence proposal for the image specified by the user, an instruction to include the contents of the extracted log information may be included in the log information P7.

[0072] Alternatively, the prompt generation module 2033 may extract log information of the child specified by the user from the log management table 2027 of a type corresponding to the time period associated with the image (for example, the log management table 2027B that manages log information related to sleep corresponding to the time period "13:00-14:30: Nap"), and include it in the log information P7. Then, when generating a sentence proposal for the image specified by the user, an instruction to include the contents of the extracted log information may be included in the log information P7.

[0073] The following is an example of log information P7. In the following example, "13:00-14:30: Nap" is specified as time period 1, and an image of a sleeping child specified by the user is specified as image 1. (Example of log information P7) {Time period 1} corresponds to {Image 1}, so please include the contents of the log information recorded during {Time period 1} in your text for {Image 1}. #{Time period 1}Log information 13:05: Fall asleep 13:10: Lying on your back 13:15: Awakening 13:30: Fall asleep 13:35: Landscape 14:00: Awakening

[0074] When a large-scale language model receives a prompt with inserted log information, it can refer to the log information to include in the proposed sentences matters that could not be read from the image. Therefore, it becomes possible to output a more detailed description of the child at the child welfare facility as a proposed sentence. For example, in the above example, since image 1 is an image of a child sleeping, the large-scale language model cannot read from image 1 that the child woke up in the middle of his nap. On the other hand, the large-scale language model can refer to the log information to output a proposed sentence about the child waking up in the middle of his nap.

[0075] As described above, the prompt generation module 2033 generates the prompt P by combining the role instruction P1 through the log information P7.

[0076] The evaluation module 2034 performs evaluation of the child or children to be evaluated by analyzing text data (sentence proposals) generated by the large-scale language model regarding the child or children to be evaluated. Specifically, the evaluation module 2034 performs text mining on the text data using any text mining means, thereby evaluating the designated child, etc. For example, the evaluation module 2034 vectorizes the text data by any method. Then, the evaluation module 2034 extracts characteristic words related to any index (specifically, indexes related to the qualities and growth of children established in activities related to child welfare, for example, indexes of the so-called "five areas of childcare" represented by "health," "human relationships," "environment," "language," and "expression"). The evaluation module 2034 evaluates the degree of the child's nature in each index by counting the frequency of appearance of the extracted words or evaluating the importance of the words in the text data by a method such as TF-IDF. The evaluation module 2034 may also use any sentiment analysis to evaluate the tone of the entire text data.

[0077] The evaluation module 2034 may present the evaluation level of each index to the user as an evaluation result in the form of an image such as a radar chart or graph. The evaluation module 2034 may also present the evaluation level of each index to the user in the form of text. As an example, a text based on the importance of words extracted from the text data of the sentence proposal may be generated and presented to the user. As an example, if the score of the importance of words associated with "human relationships" is high, it may be determined that the child to be evaluated has strengths in human relationships, and a text of a comment on the evaluation result may be generated.

[0078] In addition, the evaluation module 2034 may input text data or text data that has been processed into any format, such as vectorized data, into the large-scale language model, and output the child's evaluation of any indicator to the large-scale language model as a numerical value or text indicating the degree of evaluation for each indicator, as described above.

[0079] The log management module 2035 stores the log information in the storage unit 202. Specifically, the log management module 2035 processes the information on the child's condition that the reception control module 2031 has received from an external device into an arbitrary format and stores it in the storage unit 202 (particularly, the log management table 2027). For example, the log management module 2035 stores the log information in the storage unit 202 as follows. Recording the child's condition Information regarding the child's condition is received from a terminal device operated by a user, processed into an arbitrary format, and stored in the storage unit 202 as log information. An information processing device (any device such as a camera, sensor, etc.) that monitors the child's condition takes an image at a predetermined timing (a timing arbitrarily set by the user, or at regular timing). The log management module 2035 processes the information on the child's condition that the server 20 receives from the information processing device into an arbitrary format, and stores it in the storage unit 202 as log information.

[0080] The presentation module 2036 generates a control signal for causing the output device 14 of the terminal device 10 to output predetermined information, and transmits the control signal to the terminal device 10. In particular, the presentation module 2036 causes the output device 14 of the terminal device 10 to output sentence suggestions obtained by the server 20 from the large-scale language model.

[0081] <Data Structure> The data structure used in this embodiment will be described.

[0082] 5 is a diagram showing the data structure of the user table 2021. The user table 2021 is a table having columns such as user name, class of responsibility, and the like, with the user ID as the primary key.

[0083] The item "user ID" is an item for storing a user ID for identifying a user.

[0084] The item "user name" is an item for storing the name of the user. The user name may be set to any character string such as the user's name or nickname.

[0085] The item "class of responsibility" is an item that stores information about the work that the user is in charge of at the child welfare facility. Specifically, the item "class of responsibility" stores identification information of the group that the user is in charge of at the child welfare facility.

[0086] 6 is a diagram showing the data structure of the child table 2022. The child table 2022 is a table having a child ID as a primary key and columns such as name, facility ID, class ID, and group ID.

[0087] The item "child ID" is an item for storing a child ID for identifying a child.

[0088] The item "name" is an item for storing the name of the child. The item "name" may be set to any character string, such as the child's first and last name.

[0089] The item "facility ID" is an item for storing identification information of a child welfare facility to which a child belongs. Note that the storage unit 202 may store information about the facility (such as the name) in association with each facility ID.

[0090] The item "class ID" is an item for storing identification information of a class to which a child belongs in a child welfare facility to which the child belongs. Note that the storage unit 202 may store information about the class (such as the class name and the childcare worker in charge) in association with each class ID.

[0091] The item "Group ID" is an item for storing identification information of the group to which the child belongs in the class of the child welfare facility to which the child belongs. Note that the storage unit 202 may store information related to the group (group name, etc.) in association with each group ID.

[0092] The child welfare facility, class, and group are examples of groups to which the child belongs. In addition to the child welfare facility, class, and group, the child table 2022 may store identification information of any group according to the group to which the child belongs.

[0093] 7 is a diagram showing the data structure of the image table 2023. The image table 2023 is a table having an image ID as a primary key and columns such as storage destination and shooting time.

[0094] The item "image ID" is an item for storing an image ID for identifying an image.

[0095] The item "save destination" is an item for storing save destination information regarding the save destination of the image related to the image ID. The save destination information may be, for example, address information in the storage unit 202 or a URL (Uniform Resource Locator) for referencing the image.

[0096] The item "photographed time" is an item for storing information about the photographed time of the image associated with the image ID. For example, the item "photographed time" stores timestamp information of the time when the image was photographed.

[0097] 8 is a diagram showing the data structure of the document type table 2024. The document type table 2024 is a table having a document type ID as a primary key and columns such as document type and document-specific instructions.

[0098] The item "document type ID" is an item for storing a document type ID that identifies the type of document.

[0099] The item "document type" is an item for storing the name of a document type. For example, the item "document type" stores character strings such as "childcare journal," "communication book," and "letter."

[0100] The item "document-specific instructions" is an item for storing information on the part of the prompt that is input to the large-scale language model, which differs for each document type. Specifically, the item "document-specific instructions" stores text data related to instructions for generating a sentence proposal, which differ depending on the type of document. For example, the item "Document-specific instructions" stores text data of instructions for document types for which text suggestions are to be generated, and instructions on the structure, writing style, etc. of text suggestions corresponding to the document types.

[0101] 9 is a diagram showing the data structure of the output format table 2025. The output format table 2025 is a table having an output format ID as a primary key and columns such as document type ID and output format.

[0102] The item "output format ID" is an item for storing an output format ID for identifying an output format.

[0103] The item "document type ID" is an item for storing the document type ID of the document type corresponding to the output format ID.

[0104] The item "output format" is an item for storing information about the format (template) used when generating a draft sentence. Specifically, the item "output format" stores information about rules and description formats for arranging a draft sentence into a certain form. For example, the item "output format" stores text data with dynamic parts indicated by blank fields. An example of the text data is shown below. Note that the fields enclosed in curly brackets are dynamically populated by the prompt generation module 2033. Also, the fields enclosed in square brackets are populated by the large-scale language model. (Output format) Today, {children etc.} will be [describe what they did today]. The answer was [describe the progress toward the initiatives] in response to [initiatives]. Also, [Special Notes].

[0105] The item "output format" may store text data of specific example sentences, or may store text data in which the contents to be written in the draft sentence are specified in bullet points or the like.

[0106] 10 is a diagram showing the data structure of the sentence table 2026. The sentence table 2026 is a table having a sentence ID as a primary key and columns such as a user ID, a child ID, a document type ID, a creation time, an image ID, a prompt, a sentence proposal, and a finalized sentence.

[0107] The item "text ID" is an item for storing a text ID for identifying a text.

[0108] The item "user ID" is an item for storing a user ID for identifying a user.

[0109] The item "child ID" is an item for storing a child ID for identifying a child. In addition to the child ID, the sentence table 2026 may store group identification information (facility ID, class ID, group ID, etc.). This makes it possible to store information on sentences generated for a specific group in addition to sentences generated for a specific child.

[0110] The item "document type ID" is an item for storing a document type ID that identifies a document type.

[0111] The item "creation time" is an item for storing the time when the text related to the text ID was created. Specifically, for example, the item "creation time" stores the time when the content of the text was finalized.

[0112] The item "image ID" is an item for storing an image ID for identifying an image.

[0113] The item "sentence proposal" is an item for storing text data of a sentence proposal generated by a large-scale language model in a sentence proposal generation process, which will be described later, for a sentence associated with a sentence ID.

[0114] The item "prompt" is an item for storing text data of a prompt used when the sentence plan stored in the item "sentence plan" is generated in the large-scale language model in the sentence plan generation process described later.

[0115] The item "confirmed text" is an item that stores text data of a confirmed text related to a text ID, the content of which has been confirmed by a user. Specifically, for example, the item "confirmed text" stores text data of a text that has been confirmed by a user after the user has confirmed the text data of the item "sentence proposal" and made appropriate corrections.

[0116] 11 is a diagram showing the data structure of the log management table 2027. The log management table 2027 is a table having a log ID as a primary key and columns such as a child ID, time information, and log information.

[0117] The item "log ID" is an item for storing a log ID for identifying log information.

[0118] The item "child ID" is an item for storing a child ID for identifying a child. In addition to the child ID, the log management table 2027 may store group identification information (facility ID, class ID, group ID, etc.). This makes it possible to store log information related to a specific group in addition to log information related to a specific child.

[0119] The item "time information" is an item for storing information about the time when the log was recorded. Specifically, for example, the item "time information" stores timestamp information when the log was recorded.

[0120] The item "log information" is an item for storing log information relating to the record of the child's condition that was recorded at the time specified in the item "time information". Specifically, the item "log information" stores identification information, character strings, etc., that indicate the child's condition. For example, when storing information regarding a child's sleeping state as log information in the "log information" item, as an example, a character string that can identify the child's sleeping state, such as "falling asleep" or "lying on one's back", is stored.

[0121] <Operation> (Text Proposal Generation Process) The operation of the system 1 of this embodiment will be described below. Fig. 12 is a flowchart of the sentence suggestion generation process of this embodiment.

[0122] First, the terminal device 10 executes an application for generating a writing draft. Note that the creation of a document may be performed via a web browser. For example, a user operates the terminal device 10 to select an application for generating a writing draft and causes the terminal device 10 to execute the application. When the terminal device 10 executes the application, the control unit 190 causes the display 141 to display a login screen for authenticating the user.

[0123] The user inputs, for example, a login ID and a password on the login screen. When the control unit 190 completes the authentication of the user, it accesses the server 20 in association with the user ID.

[0124] When the server 20 accepts access from the terminal device 10, the server 20 generates an input UI for inputting information required to generate a draft text based on the information on the child, etc. stored in the child table 2022, the information on the document type stored in the document type table 2024, etc., and presents the input UI to the user via the terminal device 10. For example, the server 20 causes an information input screen to be displayed on the display 141 of the terminal device 10.

[0125] In step S11, the terminal device 10 displays an input screen D1 for inputting information for generating a sentence plan on the display 141. Fig. 13 is a schematic diagram showing an example of the input screen D1. The input screen D1 includes operation objects D11, D12, D13, D14, D15, and D16.

[0126] The operation object D11 accepts an operation to specify a date for which a sentence draft is to be generated. For example, when an operation to the operation object D11 is accepted, the terminal device 10 displays a list of dates in a selectable manner. Then, the terminal device 10 accepts a date specification from the user.

[0127] The operation object D12 accepts an operation to specify a document type. For example, when an operation to the operation object D12 is accepted, the terminal device 10 displays a list of document types accepted from the server 20 in a selectable manner. Then, the terminal device 10 accepts the specification of the document type from the user.

[0128] The operation object D13 accepts an operation to specify a child for which a sentence draft is to be generated. For example, when an operation to the operation object D13 is accepted, the terminal device 10 displays a list of children accepted from the server 20 in a selectable manner. Then, the terminal device 10 accepts the specification of a child from the user. Note that the operation object D13 may be an object that allows a child to be specified by free input to an input form.

[0129] Furthermore, the operation object D13 may be capable of specifying a group (facility, class, group, etc.) in addition to or instead of being capable of specifying a child. For example, when the operation object D13 receives an operation from the user, it may display a list of groups received from the server 20 in a selectable manner and receive the specification of a group for which a sentence proposal is to be generated.

[0130] The operation object D14 receives an operation for designating a time period for which a sentence suggestion is to be generated. For example, when an operation on the operation object D14 is accepted, the terminal device 10 refers to the time period information and displays a list of time periods on the display 141 so that the user can select the time period.

[0131] The terminal device 10 accepts from the user the designation of one or more time periods for which text suggestions are to be generated. Note that the user does not have to designate a time period.

[0132] The operation object D15 accepts an operation to specify an image for which a text draft is to be generated. For example, when an operation to the operation object D15 is accepted, the terminal device 10 accesses a database in which images are stored, which is provided in the storage unit 202 of the server 20, and displays a list of images in which activities related to child welfare are recorded on the display 141. Then, the terminal device 10 accepts, from the user, specification of one or more images for which a text draft is to be generated. Note that the specified image does not have to show the child specified in the operation object D13 (for example, it may be an image of a pool, a tree, or the like, in which no person is shown).

[0133] The operation object D16 accepts an operation for inputting an instruction to generate a text draft. For example, when the terminal device 10 accepts an operation on the operation object D16, the terminal device 10 transmits an instruction to generate a text draft to the server 20 together with each piece of information based on the operation input to the operation objects D11 to D15 on the input screen D1. The information transmitted by the terminal device 10 to the server 20 includes, for example, the following information: Date information regarding the date specified by the user - Document type identification information specified by the user (e.g. document type ID) Identification information of children, etc. specified by the user (for example, child ID, facility ID, class ID, group ID) - Information that can identify the time period specified by the user (for example, a character string that can identify the start and end points of a time period) - Image identification information specified by the user (e.g. image ID)

[0134] In the following description, as an example, a case where a specific child is designated as the designation of a child, etc., will be described. Note that, if a specific group other than a child is designated, in the following description, "child" may be appropriately read as "group."

[0135] In step S12, the server 20 accepts a date specification from the user. Specifically, the server 20 accepts date information transmitted from the terminal device 10, for example.

[0136] The server 20 also accepts a document type designation. Specifically, the server 20 accepts a document type ID transmitted from the terminal device 10, for example.

[0137] In addition, the server 20 accepts, from the user, a designation of a child or the like as a target for generating a sentence plan. Specifically, for example, the server 20 accepts a child ID transmitted from the terminal device 10.

[0138] Furthermore, the server 20 identifies one or more images among the images recording the state of activities related to child welfare stored in the database as images related to the child, etc., designated as the target of generation. Specifically, for example, the server 20 searches the image table 2023 based on the image ID transmitted from the terminal device 10, thereby identifying the image designated by the user as an image related to the child, etc., designated as the target of generation. The server 20 acquires information on the items "save destination" and "photographed time" of the identified image.

[0139] Furthermore, the server 20 accepts designation of one or more time periods from the user. Specifically, for example, the server 20 accepts information capable of identifying the time period transmitted from the terminal device 10.

[0140] Furthermore, the server 20 determines an image corresponding to the time period specified by the user, based on the time period specified by the user and the time information associated with the identified image. For example, the server 20 determines that the images whose shooting times fall within the time period specified by the user are images corresponding to the time period specified by the user. The user may operate the terminal device 10 to specify, from among a plurality of images specified by the user, images corresponding to a time period specified by the user.

[0141] In step S13, information regarding instructions for the large-scale language model, which differ depending on the document type, is obtained. Specifically, for example, the server 20 searches the document type table 2024 based on the document type ID received in step S12, and obtains the text data stored in the item "document-specific instructions" of the corresponding record.

[0142] The server 20 also obtains information regarding the output format of the sentence proposal. Specifically, for example, the server 20 searches the output format table 2025 based on the document type ID received in step S12, and obtains the text data stored in the item "output format" of the corresponding record.

[0143] The server 20 also obtains information about the child specified by the user. Specifically, for example, the server 20 searches the child table 2022 based on the child ID received in step S12, and acquires the information stored in the item "name."

[0144] The server 20 also acquires log information about the child specified by the user. Specifically, for example, when the server 20 receives date information and a child ID, it searches the log management table 2027 based on the date related to the date information and the child ID, and extracts a corresponding record. At this time, if there are multiple log management tables 2027 according to the type of log information, records may be extracted from all types of log management tables 2027, or records may be extracted from any type of log management table 2027 based on the type of log information designated by the user, etc.

[0145] In step S14, the server 20 generates a prompt including reading the situation of the image identified in step S12 and generating a sentence proposal related to the child, etc., designated as the generation target, based on the read situation. Specifically, for example, the server 20 generates a prompt to be input to the large-scale language model based on the information acquired in steps S12 and S13. The server 20 may also include in the prompt an instruction to select and present an appropriate image to attach to the generated draft sentence from the images identified in step S12.

[0146] In step S15, the server 20 inputs a prompt including information about the image determined in step S12 to the large-scale language model. Specifically, for example, the server 20 transmits a prompt including the image data determined in step S12 or information for the large-scale language model to access the image to the API of the large-scale language model. The large-scale language model generates a response including a sentence proposal based on the received prompt and transmits the response to the server 20.

[0147] In step S16, the server 20 obtains a response to the prompt from the large-scale language model, obtains a sentence plan included in the response, and obtains information (e.g., storage destination information) regarding an image attached to the sentence plan included in the response.

[0148] In step S17, the server 20 generates a display UI for displaying the writing plan extracted in step S16, and presents it to the user via the terminal device 10. Specifically, for example, the server 20 causes the display 141 of the terminal device 10 to display a display screen of the writing plan.

[0149] In step S18, the terminal device 10 displays on the display 141 a writing suggestion display screen D2 that displays the writing suggestion, thereby presenting the writing suggestion to the user.

[0150] 14 is a schematic diagram showing an example of a sentence suggestion display screen D2. The sentence suggestion display screen D2 includes a display object D21, a display object D22, a display object D23, an operation object D24, and an operation object D25.

[0151] The display object D21 displays information about the draft sentences and documents to be generated. For example, the display object D21 displays the name of the child, the date, etc., designated by the server 20 in step S12. The display object D21 may also display the child's sleeping, eating, excretion, etc. status in association with the time when the status was recorded, based on the log information acquired by the server 20 in step S13.

[0152] The display object D22 is an object that displays a sentence proposal output by the large-scale language model in response to the input of a prompt.

[0153] Display object D23 displays an image attached to a proposed sentence output by the large-scale language model in response to an input of a prompt.

[0154] The operation object D24 accepts an operation requesting a correction of the proposed sentence displayed on the display object D22. For example, when an operation on the operation object D24 is accepted, the terminal device 10 enables editing of the text of the proposed sentence displayed on the display object D22. The user operates the input device 13 to edit the text of the proposed sentence displayed on the display object D22. Note that the proposed sentence displayed on the display object D22 may be edited regardless of an operation on the operation object D24.

[0155] The operation object D25 accepts an operation for confirming the content of the sentence. For example, when an operation is accepted by the operation object D25, the proposed sentence displayed on the display object D22 at the time of accepting the operation is confirmed as an official confirmed sentence, and text data of the confirmed sentence is transmitted to the server 20.

[0156] In step S19, the server 20 accepts the text data of the confirmed sentence transmitted from the terminal device 10. The server 20 stores the user ID of the user, the child ID of the child whose designation was accepted from the user in step S12, the document type ID of the document type whose designation was accepted from the user in step S12, the image ID of the image identified in step S12, the text data of the prompt generated in step S14, the text data of the sentence proposal acquired in step S16, the text data of the confirmed sentence, and the creation time of the record in the items of sentence ID, user ID, child ID, document type ID, image ID, prompt, sentence proposal, confirmed sentence, and creation time of the record, respectively, in the items of sentence ID, user ID, child ID, document type ID, image ID, prompt, sentence proposal, confirmed sentence, and creation time of the new record in the sentence table 2026.

[0157] The server 20 creates document data of the document type designated in step S12, including the text data of the finalized sentence, the information displayed in the display object D21 of the sentence proposal display screen D2, and the attached image displayed in the display object D23, and stores the document data in the storage unit 202. The server 20 may transmit the created document data to any predetermined destination (for example, a contact address associated with a child identified by a child ID).

[0158] (Child Evaluation Processing) FIG. 15 is a flowchart of the evaluation process of this embodiment.

[0159] First, the terminal device 10 executes an application for evaluating a child or the like. The evaluation of a child may be performed via a web browser. For example, a user operates the terminal device 10, selects an application for evaluating a child or the like, and causes the terminal device 10 to execute the application. When the terminal device 10 executes the application, the control unit 190 causes the display 141 to display a login screen for authenticating the user.

[0160] The user inputs, for example, a login ID and a password on the login screen. When the control unit 190 completes the authentication of the user, it accesses the server 20 in association with the user ID.

[0161] When the server 20 accepts access from the terminal device 10, it generates an input UI for inputting information necessary for evaluating children, etc., and presents it to the user via the terminal device 10. For example, the server 20 causes the display 141 of the terminal device 10 to display a screen for setting conditions for evaluating children, etc.

[0162] In step S21, the terminal device 10 displays a condition setting screen D3, which is a setting screen for evaluating children, on the display 141. Fig. 16 is a schematic diagram showing an example of the condition setting screen D3. It includes an operation object D31, an operation object D32, an operation object D33, and an operation object D34.

[0163] The operation object D31 accepts an operation to specify a child or the like to be evaluated. For example, when an operation to the operation object D31 is accepted, the terminal device 10 displays a list of the children or the like accepted from the server 20 in a selectable manner. Then, the terminal device 10 accepts the specification of the child or the like from the user. Note that the operation object D31 may be an object that allows the child or the like to be specified by free input to an input form.

[0164] In this embodiment, a case where a specific child is specified as the designation of a child, etc. will be described. When a specific group other than children is specified, in the following description, "child" may be appropriately read as "group."

[0165] The operation object D32 accepts an operation to specify a document type to be analyzed. For example, when an operation to the operation object D32 is accepted, the terminal device 10 displays a list of document types accepted from the server 20 in a selectable manner. Then, the terminal device 10 accepts the specification of one or more document types from the user.

[0166] The operation object D33 accepts an operation to specify a period for which text is to be searched. For example, when an operation to the operation object D33 is accepted, the terminal device 10 displays a list of dates so that the start and end points of the period can be selected. The terminal device 10 then accepts the specification of the period by accepting the specification of the start date and end date of the period.

[0167] The operation object D34 accepts an operation for inputting an instruction to evaluate the child. For example, when the terminal device 10 accepts an operation on the operation object D34, the terminal device 10 transmits an instruction to evaluate the child to the server 20 together with each piece of information based on the operation input to the operation objects D31 to D33 on the condition setting screen D3. The information transmitted by the terminal device 10 to the server 20 includes, for example, the following information: Identification information of children, etc. specified by the user (for example, child ID, facility ID, class ID, group ID) - Document type identification information specified by the user (e.g. document type ID) - Period information regarding the period specified by the user (for example, information on the start date and end date)

[0168] In step S22, the server 20 accepts a designation of a child or the like as an evaluation target from the user. Specifically, the server 20 accepts a child ID transmitted from the terminal device 10, for example.

[0169] The server 20 also accepts a designation of a document type and a designation of a period. Specifically, for example, the server 20 accepts a document type ID and period information transmitted from the terminal device 10.

[0170] Furthermore, the server 20 extracts a sentence plan associated with the child, etc., designated as the evaluation target, from the sentence plans stored in the database. Specifically, for example, the server 20 searches the items "child ID", "document type ID", and "creation time" of the sentence table 2026 based on the child ID, document type ID, and period information received from the terminal device 10, and acquires information stored in the item "sentence plan" of the corresponding record. Note that this information is information stored by the server 20 in step S19 of the sentence plan generation process. This makes it possible to acquire sentence plans related to the designated document type, generated by the large-scale language model for the designated child during the period from the start point to the end point of the designated period.

[0171] In step S23, the server 20 analyzes the text data of the extracted sentence plans to evaluate the children, etc., designated as the evaluation targets.

[0172] In step S24, the server 20 generates a result display UI for displaying the analysis result, and presents it to the user via the terminal device 10. Specifically, for example, the server 20 causes the display 141 of the terminal device 10 to display a display screen of the analysis results.

[0173] In step S25, the terminal device 10 displays a result display screen D4 on the display 141, which displays the analysis result, thereby presenting the analysis result to the user.

[0174] 17 is a schematic diagram showing an example of the result display screen D4. The result display screen D4 includes a display object D41.

[0175] The display object D41 displays the evaluation result output by the server 20 in step S23. Specifically, for example, the display object D41 displays the degree of evaluation for each index quantified in step S23 in a comparable manner. As an example, the display object D41 displays the degree of evaluation for each index in a radar chart as shown in Fig. 17. The display object D41 also displays text indicating comments regarding the child's evaluation result.

[0176] <Modification> The steps of the sentence plan generation process and the child evaluation process described above can be executed by either the terminal device 10 or the server 20. In the above description, an example has been given in which each step in each process is executed in a specific order, but the execution order of each step is not limited to the example described above as long as there is no dependency between the steps.

[0177] In the above embodiment, one output format is set for one document type in the output format table 2025. However, multiple output formats may be set for one document type. In this case, a designation of an output format from a user may be accepted in steps S11 and S12, and the output format P6 may be generated based on the designation.

[0178] In the above embodiment, in step S12, the server 20 accepts the designation of an image and the designation of a child. However, the server 20 may accept only the designation of either an image or a child. When the designation of only an image is accepted, the server 20 may identify the child from the face of the child included in the image by any face recognition technology, and may regard the identified child as the one designated by the user. When the designation of only a child is accepted, the server 20 may regard all images taken on a date designated by the user, to which the identification information of the child has been added by any face recognition technology, as the one designated by the user.

[0179] In the above embodiment, in step S12, the server 20 accepts a time period designation from the user. However, the server 20 may accept a time designation instead of or in addition to the time period. In this case, the server 20 may determine, as the image corresponding to the designated time, an image whose shooting time falls within a predetermined time range before and after the designated time. The server 20 may also include, in the log information P7 of the prompt P, an instruction to generate a sentence regarding the child's condition at the designated time, by referring to log information whose recorded time falls within a predetermined time range before and after the designated time.

[0180] In the above embodiment, in step S12, the server 20 accepts the designation of a time period from the user. However, the server 20 may accept the designation of one or more scenes instead of or in addition to the time period. The scene refers to any scene in a child welfare activity, such as going to kindergarten, morning meeting, class activity, etc. Then, the server 20 may determine an image corresponding to the scene designated by the user from images related to the child or the like designated by the user, read the situation of the image corresponding to the scene, and generate an instruction to generate a sentence proposal including a sentence related to the scene, and configure the instruction as a part of the prompt P. Alternatively, the server 20 may use any image recognition technology to associate a specific image among images related to a child or the like specified by the user with an image recording the scene specified by the user. The server 20 may then refer to the specific image to generate an instruction to generate a text proposal including a sentence related to the scene specified by the user, and configure the instruction as part of the prompt P.

[0181] In the above embodiment, the prompt generation module 2033 of the server 20 generates a prompt into which log information is inserted. However, the server 20 may receive a request for necessary log information from the large-scale language model after inputting a prompt including an instruction to read an image to the large-scale language model. Then, the server 20 may extract log information from the log management table 2027 in response to the request from the large-scale language model and provide it to the large-scale language model.

[0182] Specifically, first, the server 20 generates a prompt including an instruction to generate a sentence proposal about a child based on a specific image, as in the above embodiment, and inputs the generated prompt to the large-scale language model. At that time, for example, the server 20 inputs information about a function for searching the log management table 2027, which the large-scale language model can call for the server 20, to the large-scale language model.

[0183] The large-scale language model reads the content of the image based on the input prompt, determines which log information should be requested from the server 20, and sends the request to the server 20. As an example, if the large-scale language model reads that the input image is an image of a sleeping child, it determines that sleep log information should be requested from the server 20. The large-scale language model then requests the server 20 to call a function that acquires sleep log information for the child specified in the prompt.

[0184] The server 20 searches the log management table 2027 based on a request received from the large-scale language model, and provides the required log information to the large-scale language model. As an example, the server 20 executes a function received from the large-scale language model to search the log management table 2027B that stores log information related to sleep based on the child ID of the child specified in the prompt, extracts the relevant log information, and provides it to the large-scale language model.

[0185] The large-scale language model outputs a sentence proposal for the image input in the prompt while referring to the contents of the received log information. This allows the large-scale language model to include in the sentence proposal matters that could not be read from the image by referring to the log information. Therefore, it becomes possible to output a sentence proposal that provides more detailed information about the children in the child welfare facility.

[0186] <Summary>

[0187] As described above, the server 20 accepts a designation of a child or a group to which the child belongs from the first user as a target for generating a sentence proposal, and specifies one or more images among images in which the state of activities related to child welfare is recorded and stored in the database as images related to the child or group designated as the target for generation. The server 20 generates a prompt including instructions including an instruction to read the situation of the specified image and an instruction to generate a sentence proposal related to the child or group designated as the target for generation based on the read situation. The server 20 inputs the prompt including information about the image into the large-scale language model, thereby acquiring a sentence proposal from the large-scale language model and presenting it to the first user. This allows the user to create a sentence to be written in the document by referring to the sentence proposal output from the large-scale language model. Therefore, it is possible to efficiently create a sentence to be written in the document.

[0188] The draft text is a draft of text to be written in a document for recording activities related to child welfare. This makes it possible to efficiently create text to be written in a document for recording activities related to child welfare.

[0189] The server 20 also receives a specification of the type of document and generates a prompt including different instructions according to the specified type, thereby making it possible to present different writing suggestions according to the type of document specified by the user.

[0190] The server 20 also generates a prompt including information on the output format of the text proposal, which varies depending on the specified type, so that text proposals in different output formats can be presented depending on the type of document specified by the user.

[0191] The server 20 also accepts the designation of one or more time periods, and determines an image corresponding to the time period based on the designated time period and time information associated with the identified image. The server 20 generates a prompt including an instruction to generate a text suggestion including a sentence related to the time period by reading the status of the image corresponding to the time period. This makes it possible to present a text suggestion according to the time period designated by the user.

[0192] The server 20 also identifies a plurality of images as images related to children, accepts the designation of a plurality of time periods, and determines a plurality of images corresponding to each of the designated plurality of time periods. The server 20 generates a prompt including an instruction to generate a sentence divided into a plurality of time periods by reading the situation of each of the plurality of images corresponding to the plurality of time periods. This makes it possible to present the user with a proposal of sentences divided into a plurality of time periods, and the user can create a sentence that clearly shows the state of the children, etc., in each time period.

[0193] The server 20 also receives the designation of one or more scenes, determines an image corresponding to the scene from images identified as images related to children, etc., and generates prompts including interpreting the situation of the image corresponding to the scene and generating a sentence proposal including a sentence related to the scene. In this way, it is possible to present a sentence proposal according to the scene designated by the user.

[0194] The server 20 also acquires log information in which information on the specified child's condition is recorded in association with time information, and generates a prompt including an instruction to generate a sentence proposal by referring to the log information. This allows the large-scale language model to refer to information other than images, making it possible to present a sentence proposal that refers to the child's condition in more detail.

[0195] The server 20 also receives the designation of one or more time periods, and generates a prompt including an instruction to generate a sentence proposal including a sentence regarding the child's condition corresponding to the time period by referring to the designated time period and the time information included in the log information. This makes it possible to present a sentence proposal that refers in more detail to the child's condition during the time period designated by the user.

[0196] The server 20 also generates a prompt including an instruction to select an image to be attached to the generated draft sentence from the images identified as images related to children, etc. The server 20 obtains information about the attached image from the large-scale language model and presents the attached image to the user. This reduces the effort required for the user to select an image by himself, and makes document creation more efficient.

[0197] The server 20 also stores the sentence plan acquired from the large-scale language model in the database in association with the child or group designated as the generation target. The server 20 accepts the designation of a child, etc., as the evaluation target from the user. The server 20 extracts a sentence plan associated with the child, etc., designated as the evaluation target from one or more sentence plans stored in the database. The server 20 evaluates the child, etc., designated as the evaluation target, or the group to which the child belongs, by analyzing the text data of the extracted sentence plan, and presents the evaluation result to the user. The server 20 also performs text mining on the text data of the extracted sentence plan, and evaluates the child, etc., designated as the evaluation target, by extracting features of the extracted sentence plan. This makes it possible to evaluate the child based on the sentence plan generated by the server 20. The sentence plan is an image of the child's situation in a child welfare facility, so that the state and behavior of the child in the child welfare facility can be appropriately evaluated. Furthermore, the sentence plan is an objective output by the large-scale language model by reading the situation in the image, and is not a sentence created or corrected by a childcare worker, etc. Therefore, the draft text does not include the subjective viewpoint of the childcare worker, etc., toward the child. Therefore, by analyzing the text data of the draft text, it is possible to make a more objective evaluation than if the childcare worker, etc., were to subjectively evaluate the child.

[0198] <4 Basic hardware configuration of computer> 18 is a block diagram showing the basic hardware configuration of a computer 90. The computer 90 includes at least a processor 94, a main storage device 95, an auxiliary storage device 96, and a communication IF (interface) 99. These are electrically connected to each other by a bus.

[0199] The processor 94 is hardware for executing an instruction set written in a program, and is composed of an arithmetic unit, a register, a peripheral circuit, and the like.

[0200] The main storage device 95 is for temporarily storing programs, data to be processed by the programs, etc. For example, it is a volatile memory such as a DRAM (Dynamic Random Access Memory).

[0201] The auxiliary storage device 96 is a storage device for saving data and programs, such as a flash memory, a hard disk drive (HDD), a magneto-optical disk, a CD-ROM, a DVD-ROM, or a semiconductor memory.

[0202] The communication IF 99 is an interface for inputting and outputting signals for communicating with other computers via a network using a wired or wireless communication standard.

[0203] The network is composed of the Internet, a LAN, various mobile communication systems constructed by wireless base stations, etc. For example, the network includes 3G, 4G, 5G mobile communication systems, LTE (Long Term Evolution), wireless networks that can connect to the Internet via a specified access point (e.g., Wi-Fi (registered trademark)), etc. In the case of wireless connection, communication protocols include, for example, Z-Wave (registered trademark), ZigBee (registered trademark), Bluetooth (registered trademark), etc. In the case of wired connection, the network also includes a network that is directly connected by a USB (Universal Serial Bus) cable or the like.

[0204] It should be noted that the computer 90 can be virtually realized by distributing all or part of each hardware configuration among multiple computers 90 and connecting them together via a network. In this way, the computer 90 is a concept that includes not only a computer 90 housed in a single housing or case, but also a virtualized computer system.

[0205] <Basic functional configuration of computer 90> A description will now be given of the functional configuration of a computer realized by the basic hardware configuration of a computer 90 shown in Fig. 18. The computer includes at least the functional units of a control unit, a storage unit, and a communication unit.

[0206] The functional units of the computer 90 can also be realized by distributing all or part of the functional units among multiple computers 90 connected to each other via a network. The computer 90 is a concept that includes not only a single computer 90 but also a virtualized computer system.

[0207] The control unit is realized by the processor 94 reading out various programs stored in the auxiliary storage device 96, expanding the programs in the main storage device 95, and executing processes according to the programs. The control unit can realize functional units that perform various information processing depending on the type of program. In this way, the computer is realized as an information processing device that performs information processing.

[0208] The storage unit is realized by a main storage device 95 and an auxiliary storage device 96. The storage unit stores data, various programs, and various databases. Furthermore, the processor 94 can secure a storage area corresponding to the storage unit in the main storage device 95 or the auxiliary storage device 96 in accordance with a program. Furthermore, the control unit can cause the processor 94 to execute processes of adding, updating, and deleting data stored in the storage unit in accordance with the various programs.

[0209] A database refers to a relational database, which is used to manage data sets called tables, which are structured according to rows and columns, by relating them to each other. In a database, a table is called a table, a column in a table is called a column, and a row in a table is called a record. In a relational database, it is possible to set relationships between tables and associate them.

[0210] Usually, a column is set in each table as a key for uniquely identifying a record, but setting a key in the column is not essential. The control unit can cause the processor 94 to add, delete, or update records in a specific table stored in the storage unit according to various programs.

[0211] The communication unit is realized by the communication IF 99. The communication unit realizes a function of communicating with other computers 90 via a network. The communication unit can receive information transmitted from other computers 90 and input the information to the control unit. The control unit can cause the processor 94 to execute information processing on the received information in accordance with various programs. In addition, the communication unit can transmit information output from the control unit to other computers 90.

[0212] The functions performed by the components described herein may be implemented in circuitry or processing circuitry, including general purpose processors, application specific processors, integrated circuits, ASICs (Application Specific Integrated Circuits), a CPU (a Central Processing Unit), conventional circuits, and / or combinations thereof, programmed to perform the functions described. Processors include transistors and other circuits and are considered to be circuitry or processing circuitry. A processor may be a programmed processor that executes a program stored in a memory. In this specification, a circuitry, unit, or means is hardware that is programmed to realize or performs the described functions, which may be any hardware disclosed in this specification or any hardware known to be programmed to realize or perform the described functions. If the hardware is a processor considered to be a type of circuitry, the circuitry, means, or unit is a combination of the hardware and software used to configure the hardware and / or processor.

[0213] Although several embodiments of the present disclosure have been described above, these embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and modifications are within the scope of the invention and its equivalents as described in the claims, as well as the scope and spirit of the invention.

[0214] <Additional Notes> The matters described in the above embodiments will be supplemented below. (Appendix 1) A program for operating a computer having a processor and a memory, the program causing the processor to execute the following steps: receiving from a first user a designation of a child or a group to which the child belongs as a target for generating sentence suggestions; identifying one or more images from among images recording activities related to child welfare stored in a database as images related to the child or group designated as the target for generation; generating a prompt that includes reading the situation of the identified image and generating a sentence suggestion related to the child or group designated as the target for generation based on the read situation; inputting a prompt including information about the image into a large-scale language model to obtain sentence suggestions from the large-scale language model; and presenting the obtained sentence suggestions to the first user. (Appendix 2) The proposed text is a proposed text to be included in a document for recording child welfare activities, as described in Appendix 1 of the program. (Appendix 3) A program as described in Appendix 1 or Appendix 2, which in the step of accepting a specification of a document type to be generated, accepts a specification of a document type, and in the step of generating a prompt, generates a prompt including different instructions depending on the specified type. (Appendix 4) The program according to claim 3, wherein in the step of generating a prompt, a prompt including information regarding an output format of the text proposal is generated, the information differing depending on the specified type. (Appendix 5) A program as described in any of Appendix 1 to Appendix 4, wherein in the step of accepting the specification of an object to be generated, the specification of one or more time periods is accepted, and the program causes the processor to execute a step of determining an image corresponding to the time period based on the specified time period and time information associated with the identified image, and in the step of generating a prompt, a prompt including an instruction to generate a sentence proposal including a sentence related to the time period is generated by reading the status of the image corresponding to the time period. (Appendix 6) The program described in Appendix 5, wherein in the identifying step, a plurality of images are identified; in the step of accepting the specification of the target to be generated, the specification of a plurality of time periods is accepted; in the step of determining images corresponding to the time periods, a plurality of images corresponding to each of the specified plurality of time periods are determined; and in the step of generating a prompt, a prompt including instructions for generating sentences separated by a plurality of time periods is generated by reading the status of each of the plurality of images corresponding to the plurality of time periods. (Appendix 7) A program described in any one of Appendix 1 to Appendix 6, which generates a prompt including, in a step of accepting designation of a generation target, accepting designation of one or more scenes, and in a step of generating a prompt, determining an image corresponding to the scene from identified images, reading a situation of the image corresponding to the scene, and generating a sentence proposal including a sentence related to the scene. (Appendix 8) The program is a program described in any one of Appendix 1 to Appendix 7, which causes a processor to execute a step of acquiring log information in which information regarding the status of a specified child or children belonging to a group is recorded in association with time information, and in a step of generating a prompt, generates a prompt including an instruction to generate a sentence proposal by referring to the log information. (Appendix 9) The program described in Appendix 8, wherein in the step of accepting the specification of the target to be generated, the specification of one or more time periods is accepted, and in the step of generating a prompt, a prompt including an instruction to generate a sentence proposal including a sentence regarding the child's condition corresponding to the time period is generated by referring to the specified time period and time information included in the log information. (Appendix 10) A program described in any of Appendix 1 to Appendix 9, wherein in the prompt generating step, a prompt including an instruction to select an attached image for the generated text suggestion from the identified image is generated, in the text suggestion obtaining step, information related to the attached image is obtained, and in the text suggestion presenting step, the obtained attached image is presented. (Appendix 11) The program described in any of Appendix 1 to Appendix 10, which causes a processor to execute the steps of: storing sentence plans obtained from the large-scale language model in a database in association with the child or group designated as the target of generation; accepting from a second user a designation of the child or the group to which the child belongs as the target of evaluation; extracting sentence plans associated with the child or the group to which the child belongs designated as the target of evaluation from one or more sentence plans stored in the database; evaluating the child or the group to which the child belongs designated as the target of evaluation by analyzing text data of the extracted sentence plans; and presenting the results of the evaluation to the second user. (Appendix 12) The program described in Appendix 11, in which, in the evaluating step, text mining is performed on the text data of the extracted sentence plans and features of the extracted sentence plans are extracted to evaluate the child or group to which the child designated as the evaluation subject belongs. (Appendix 13) A method executed by a computer having a processor, the method comprising the steps of: receiving from a first user a designation of a child or a group to which the child belongs as a target for generating sentence suggestions; identifying one or more images from among images recording activities related to child welfare stored in a database as images related to the child or group designated as the target for generation; generating a prompt including reading a situation of the identified image and generating a sentence suggestion related to the child or group designated as the target for generation based on the read situation; obtaining sentence suggestions from the large-scale language model by inputting a prompt including information about the image into the large-scale language model; and presenting the obtained sentence suggestions to the first user. (Appendix 14) An information processing device having a control unit, wherein the control unit executes the following steps: receiving from a first user a designation of a child or a group to which the child belongs as a target for generating sentence suggestions; identifying one or more images from among images recording activities related to child welfare stored in a database as images related to the child or group designated as the target for generation; generating a prompt that includes reading the situation of the identified image and generating a sentence suggestion related to the child or group designated as the target for generation based on the read situation; acquiring sentence suggestions from a large-scale language model by inputting a prompt including information related to the image into the large-scale language model; and presenting the acquired sentence suggestions to the first user. (Appendix 15) A system comprising: means for receiving, from a first user, a designation of a child or a group to which the child belongs as a target for generating sentence suggestions; means for identifying one or more images from among images recording activities related to child welfare stored in a database as images related to the child or group designated as the target for generation; means for generating a prompt that includes reading the situation of the identified image and generating a sentence suggestion related to the child or group designated as the target for generation based on the read situation; means for acquiring sentence suggestions from a large-scale language model by inputting a prompt including information related to the image into the large-scale language model; and means for presenting the acquired sentence suggestions to the first user. [Explanation of symbols]

[0215] 1... system 10... terminal device 12... communication IF 120... communication unit 13... input device 14... output device 141... display 15... memory 16... storage 17... voice processing unit 180... storage unit 19... processor 190... control unit 20... server

Claims

1. A program for operating a computer having a processor and a memory, the program causing the processor to: receiving, from a first user, a designation of a child or a group to which the child belongs as a target for generating a sentence plan; Identifying one or more images from among images of activities related to child welfare stored in a database as images related to the child or group designated as the subject of the generation; generating a prompt including reading a context of the identified image and generating a sentence suggestion for the child or group designated for generation based on the read context; obtaining the sentence suggestions from a large scale language model by inputting the prompt, including information about the image, into the large scale language model; presenting the obtained writing suggestions to the first user; A program to execute.

2. The program according to claim 1 , wherein the proposed text is a proposed text to be included in a document for recording activities related to child welfare.

3. In the step of accepting the specification of the generation target, a specification of a document type is accepted; In the step of generating the prompt, a prompt including different instructions is generated depending on the specified type. The program according to claim 1.

4. generating a prompt including information on an output format of the sentence plan, the information being different depending on the specified type; The program according to claim 3.

5. In the step of accepting the designation of the generation target, the designation of one or more time periods is accepted; The program causes the processor to execute a step of determining an image corresponding to the time period based on the specified time period and time information associated with the identified image; In the step of generating a prompt, a prompt including an instruction to generate a sentence proposal including a sentence related to the time period by reading a situation of an image corresponding to the time period is generated. The program according to claim 1.

6. In the step of identifying, a plurality of images are identified; In the step of accepting the designation of the generation target, a designation of a plurality of time periods is accepted; In the step of determining an image corresponding to the time period, a plurality of images corresponding to the designated plurality of time periods are determined, In the step of generating the prompt, a prompt including an instruction to generate a sentence divided for each of the plurality of time periods is generated by reading the situations of the plurality of images corresponding to the plurality of time periods. The program according to claim 5.

7. In the step of accepting a designation of a scene to be generated, a designation of one or more scenes is accepted; In the step of generating the prompt, the prompt is generated by determining an image corresponding to the scene from the identified images, reading a context of the image corresponding to the scene, and generating a sentence proposal including a sentence related to the scene. The program according to claim 1.

8. The program causes the processor to: acquiring log information in which information on the status of the designated child or children belonging to the group is associated with time information; generating a prompt including an instruction to generate the sentence proposal by referring to the log information; The program according to claim 1.

9. In the step of accepting the designation of the generation target, the designation of one or more time periods is accepted; In the step of generating the prompt, a prompt including an instruction to generate a sentence proposal including a sentence related to the condition of the child corresponding to the time period is generated by referring to the specified time period and the time information included in the log information. The program according to claim 8.

10. generating a prompt including instructions to select an attachment image for the generated text suggestion from the identified images; obtaining information about the attached image in the step of obtaining a text proposal; presenting the obtained attached image in the step of presenting the sentence proposal; The program according to claim 1.

11. The program causes the processor to: storing the sentence suggestions obtained from the large-scale language model in a database in association with the child or group designated for generation; receiving, from a second user, a designation of a child or a group to which the child belongs as a target for evaluation; extracting a sentence plan associated with the child or group to which the child designated as the evaluation subject belongs from the one or more sentence plans stored in a database; evaluating the child or group to which the child designated as the evaluation subject belongs by analyzing the extracted text data of the sentence plan; presenting a result of the evaluation to the second user; The program according to claim 1 .

12. In the evaluating step, text data of the extracted sentence plans is subjected to text mining, and features of the extracted sentence plans are extracted to evaluate the child or a group to which the child designated as an evaluation target belongs. The program according to claim 11.

13. 1. A computer-implemented method comprising: receiving, from a first user, a designation of a child or a group to which the child belongs as a target for generating a sentence plan; Identifying one or more images from among images of activities related to child welfare stored in a database as images related to the child or group designated as the subject of the generation; generating a prompt including reading a context of the identified image and generating a sentence suggestion for the child or group designated for generation based on the read context; obtaining the sentence suggestions from a large scale language model by inputting the prompt, including information about the image, into the large scale language model; presenting the obtained writing suggestions to the first user; How to do it.

14. An information processing device including a control unit, receiving, from a first user, a designation of a child or a group to which the child belongs as a target for generating a sentence plan; Identifying one or more images from among images of activities related to child welfare stored in a database as images related to the child or group designated as the subject of the generation; generating a prompt including reading a context of the identified image and generating a sentence suggestion for the child or group designated for generation based on the read context; obtaining the sentence suggestions from a large scale language model by inputting the prompt, including information about the image, into the large scale language model; presenting the obtained writing suggestions to the first user; An information processing device that executes the above.

15. A means for receiving, from a first user, a designation of a child or a group to which the child belongs as a target for generating a sentence proposal; A means for identifying one or more images among images of activities related to child welfare stored in a database as images related to the child or group designated as the subject of the generation; a prompt generating means for generating a prompt including reading a context of the identified image and generating a sentence proposal for the child or group designated for the generation based on the read context; means for inputting the prompt, including information about the image, into a large scale language model to obtain the sentence suggestions from the large scale language model; means for presenting the obtained writing suggestions to the first user; A system comprising:

Images